From da142f3d373a6ddaca0119615a8db2175ddc4121 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 5 Dec 2025 15:26:55 -0800
Subject: [PATCH 0001/1303] KVM: Remove subtle "struct kvm_stats_desc"
 pseudo-overlay

Remove KVM's internal pseudo-overlay of kvm_stats_desc, which subtly
aliases the flexible name[] in the uAPI definition with a fixed-size array
of the same name.  The unusual embedded structure results in compiler
warnings due to -Wflex-array-member-not-at-end, and also necessitates an
extra level of dereferencing in KVM.  To avoid the "overlay", define the
uAPI structure to have a fixed-size name when building for the kernel.

Opportunistically clean up the indentation for the stats macros, and
replace spaces with tabs.

No functional change intended.

Reported-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Closes: https://lore.kernel.org/all/aPfNKRpLfhmhYqfP@kspp
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
[..]
Acked-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Bibo Mao <maobibo@loongson.cn>
Acked-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/20251205232655.445294-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/guest.c    |  4 +-
 arch/loongarch/kvm/vcpu.c |  2 +-
 arch/loongarch/kvm/vm.c   |  2 +-
 arch/mips/kvm/mips.c      |  4 +-
 arch/powerpc/kvm/book3s.c |  4 +-
 arch/powerpc/kvm/booke.c  |  4 +-
 arch/riscv/kvm/vcpu.c     |  2 +-
 arch/riscv/kvm/vm.c       |  2 +-
 arch/s390/kvm/kvm-s390.c  |  4 +-
 arch/x86/kvm/x86.c        |  4 +-
 include/linux/kvm_host.h  | 83 +++++++++++++++++----------------------
 include/uapi/linux/kvm.h  |  8 ++++
 virt/kvm/binary_stats.c   |  2 +-
 virt/kvm/kvm_main.c       | 20 +++++-----
 14 files changed, 70 insertions(+), 75 deletions(-)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 1c87699fd886..332c453b87cf 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -29,7 +29,7 @@
 
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 
@@ -42,7 +42,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, hvc_exit_stat),
 	STATS_DESC_COUNTER(VCPU, wfe_exit_stat),
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 656b954c1134..b3547bd41d21 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -14,7 +14,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, int_exits),
 	STATS_DESC_COUNTER(VCPU, idle_exits),
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 194ccbcdc3b3..7deff56e0e1a 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -10,7 +10,7 @@
 #include <asm/kvm_eiointc.h>
 #include <asm/kvm_pch_pic.h>
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, pages),
 	STATS_DESC_ICOUNTER(VM, hugepages),
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index b0fb92fda4d4..23e69baad453 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -38,7 +38,7 @@
 #define VECTORSPACING 0x100	/* for EI/VI mode */
 #endif
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 
@@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, wait_exits),
 	STATS_DESC_COUNTER(VCPU, cache_exits),
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d79c5d1098c0..2efbe05caed7 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -38,7 +38,7 @@
 
 /* #define EXIT_DEBUG */
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, num_2M_pages),
 	STATS_DESC_ICOUNTER(VM, num_1G_pages)
@@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, sum_exits),
 	STATS_DESC_COUNTER(VCPU, mmio_exits),
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 3401b96be475..f3ddb24ece74 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -36,7 +36,7 @@
 
 unsigned long kvmppc_booke_handlers;
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, num_2M_pages),
 	STATS_DESC_ICOUNTER(VM, num_1G_pages)
@@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, sum_exits),
 	STATS_DESC_COUNTER(VCPU, mmio_exits),
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index a55a95da54d0..fdd99ac1e714 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -24,7 +24,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, ecall_exit_stat),
 	STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 66d91ae6e9b2..715a06ae8c13 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -13,7 +13,7 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_mmu.h>
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 56a50524b3ee..495141bf0398 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -64,7 +64,7 @@
 #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
 			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, inject_io),
 	STATS_DESC_COUNTER(VM, inject_float_mchk),
@@ -90,7 +90,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, exit_userspace),
 	STATS_DESC_COUNTER(VCPU, exit_null),
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ff8812f3a129..69e0a033e4ac 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -237,7 +237,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv);
 bool __read_mostly enable_device_posted_irqs = true;
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs);
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
 	STATS_DESC_COUNTER(VM, mmu_pte_write),
@@ -263,7 +263,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, pf_taken),
 	STATS_DESC_COUNTER(VCPU, pf_fixed),
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d93f75b05ae2..7428d9949382 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1927,56 +1927,43 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	struct kvm *kvm;
-	const struct _kvm_stats_desc *desc;
+	const struct kvm_stats_desc *desc;
 	enum kvm_stat_kind kind;
 };
 
-struct _kvm_stats_desc {
-	struct kvm_stats_desc desc;
-	char name[KVM_STATS_NAME_SIZE];
-};
-
-#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		       \
-	.flags = type | unit | base |					       \
-		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	       \
-	.exponent = exp,						       \
-	.size = sz,							       \
+#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		\
+	.flags = type | unit | base |					\
+		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |       \
+		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	\
+		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	\
+	.exponent = exp,						\
+	.size = sz,							\
 	.bucket_size = bsz
 
-#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, generic.stat)   \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
+#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, stat),			\
+	.name = #stat,							\
+}
+#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, stat),			\
+	.name = #stat,							\
+}
 /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
 #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz)		       \
 	SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
@@ -2053,7 +2040,7 @@ struct _kvm_stats_desc {
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
-		       const struct _kvm_stats_desc *desc,
+		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset);
 
@@ -2098,9 +2085,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
 
 
 extern const struct kvm_stats_header kvm_vm_stats_header;
-extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
+extern const struct kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
-extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
+extern const struct kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index dddb781b0507..76bd54848b11 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -14,6 +14,10 @@
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
+#ifdef __KERNEL__
+#include <linux/kvm_types.h>
+#endif
+
 #define KVM_API_VERSION 12
 
 /*
@@ -1579,7 +1583,11 @@ struct kvm_stats_desc {
 	__u16 size;
 	__u32 offset;
 	__u32 bucket_size;
+#ifdef __KERNEL__
+	char name[KVM_STATS_NAME_SIZE];
+#else
 	char name[];
+#endif
 };
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c
index eefca6c69f51..76ce697c773b 100644
--- a/virt/kvm/binary_stats.c
+++ b/virt/kvm/binary_stats.c
@@ -50,7 +50,7 @@
  * Return: the number of bytes that has been successfully read
  */
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
-		       const struct _kvm_stats_desc *desc,
+		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5b5b69c97665..cf65fd82d36d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -983,9 +983,9 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
 		kvm_free_memslot(kvm, memslot);
 }
 
-static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
+static umode_t kvm_stats_debugfs_mode(const struct kvm_stats_desc *desc)
 {
-	switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
+	switch (desc->flags & KVM_STATS_TYPE_MASK) {
 	case KVM_STATS_TYPE_INSTANT:
 		return 0444;
 	case KVM_STATS_TYPE_CUMULATIVE:
@@ -1020,7 +1020,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 	struct dentry *dent;
 	char dir_name[ITOA_MAX_LEN * 2];
 	struct kvm_stat_data *stat_data;
-	const struct _kvm_stats_desc *pdesc;
+	const struct kvm_stats_desc *pdesc;
 	int i, ret = -ENOMEM;
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
@@ -6186,11 +6186,11 @@ static int kvm_stat_data_get(void *data, u64 *val)
 	switch (stat_data->kind) {
 	case KVM_STAT_VM:
 		r = kvm_get_stat_per_vm(stat_data->kvm,
-					stat_data->desc->desc.offset, val);
+					stat_data->desc->offset, val);
 		break;
 	case KVM_STAT_VCPU:
 		r = kvm_get_stat_per_vcpu(stat_data->kvm,
-					  stat_data->desc->desc.offset, val);
+					  stat_data->desc->offset, val);
 		break;
 	}
 
@@ -6208,11 +6208,11 @@ static int kvm_stat_data_clear(void *data, u64 val)
 	switch (stat_data->kind) {
 	case KVM_STAT_VM:
 		r = kvm_clear_stat_per_vm(stat_data->kvm,
-					  stat_data->desc->desc.offset);
+					  stat_data->desc->offset);
 		break;
 	case KVM_STAT_VCPU:
 		r = kvm_clear_stat_per_vcpu(stat_data->kvm,
-					    stat_data->desc->desc.offset);
+					    stat_data->desc->offset);
 		break;
 	}
 
@@ -6360,7 +6360,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 static void kvm_init_debug(void)
 {
 	const struct file_operations *fops;
-	const struct _kvm_stats_desc *pdesc;
+	const struct kvm_stats_desc *pdesc;
 	int i;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
@@ -6373,7 +6373,7 @@ static void kvm_init_debug(void)
 			fops = &vm_stat_readonly_fops;
 		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
 				kvm_debugfs_dir,
-				(void *)(long)pdesc->desc.offset, fops);
+				(void *)(long)pdesc->offset, fops);
 	}
 
 	for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
@@ -6384,7 +6384,7 @@ static void kvm_init_debug(void)
 			fops = &vcpu_stat_readonly_fops;
 		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
 				kvm_debugfs_dir,
-				(void *)(long)pdesc->desc.offset, fops);
+				(void *)(long)pdesc->offset, fops);
 	}
 }
 

From f947d9e77b26238b821b5227afb4fee8c7ea0d5a Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Mon, 12 Jan 2026 09:39:03 +1000
Subject: [PATCH 0002/1303] nvme/host: fixup some typos

Fix up some minor typos in the nvme host driver and a comment
style to conform to the standard kernel style.

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 69cb04406b47..74cbbf48a981 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -25,7 +25,8 @@
 
 struct nvme_tcp_queue;
 
-/* Define the socket priority to use for connections were it is desirable
+/*
+ * Define the socket priority to use for connections where it is desirable
  * that the NIC consider performing optimized packet processing or filtering.
  * A non-zero value being sufficient to indicate general consideration of any
  * possible optimization.  Making it a module param allows for alternative
@@ -926,7 +927,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 			req->curr_bio = req->curr_bio->bi_next;
 
 			/*
-			 * If we don`t have any bios it means that controller
+			 * If we don't have any bios it means the controller
 			 * sent more data than we requested, hence error
 			 */
 			if (!req->curr_bio) {

From ddfb8b322bbd8ae996f4ac0192f0190feb0a01ce Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 3 Nov 2025 15:44:06 +0100
Subject: [PATCH 0003/1303] nvme: expose active quirks in sysfs

Currently, there is no straightforward way for a user to inspect
which quirks are active for a given device from userspace.

Add a new "quirks" sysfs attribute to the nvme controller device.

Reading this file will display a human-readable list
of all active quirks, with each quirk name on a new line.
If no quirks are active, it will display "none".

Tested-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/nvme.h  | 54 +++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/sysfs.c | 23 +++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9a5f28c5103c..523015ae2add 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -180,6 +180,60 @@ enum nvme_quirks {
 	NVME_QUIRK_DMAPOOL_ALIGN_512		= (1 << 22),
 };
 
+static inline char *nvme_quirk_name(enum nvme_quirks q)
+{
+	switch (q) {
+	case NVME_QUIRK_STRIPE_SIZE:
+		return "stripe_size";
+	case NVME_QUIRK_IDENTIFY_CNS:
+		return "identify_cns";
+	case NVME_QUIRK_DEALLOCATE_ZEROES:
+		return "deallocate_zeroes";
+	case NVME_QUIRK_DELAY_BEFORE_CHK_RDY:
+		return "delay_before_chk_rdy";
+	case NVME_QUIRK_NO_APST:
+		return "no_apst";
+	case NVME_QUIRK_NO_DEEPEST_PS:
+		return "no_deepest_ps";
+	case NVME_QUIRK_QDEPTH_ONE:
+		return "qdepth_one";
+	case NVME_QUIRK_MEDIUM_PRIO_SQ:
+		return "medium_prio_sq";
+	case NVME_QUIRK_IGNORE_DEV_SUBNQN:
+		return "ignore_dev_subnqn";
+	case NVME_QUIRK_DISABLE_WRITE_ZEROES:
+		return "disable_write_zeroes";
+	case NVME_QUIRK_SIMPLE_SUSPEND:
+		return "simple_suspend";
+	case NVME_QUIRK_SINGLE_VECTOR:
+		return "single_vector";
+	case NVME_QUIRK_128_BYTES_SQES:
+		return "128_bytes_sqes";
+	case NVME_QUIRK_SHARED_TAGS:
+		return "shared_tags";
+	case NVME_QUIRK_NO_TEMP_THRESH_CHANGE:
+		return "no_temp_thresh_change";
+	case NVME_QUIRK_NO_NS_DESC_LIST:
+		return "no_ns_desc_list";
+	case NVME_QUIRK_DMA_ADDRESS_BITS_48:
+		return "dma_address_bits_48";
+	case NVME_QUIRK_SKIP_CID_GEN:
+		return "skip_cid_gen";
+	case NVME_QUIRK_BOGUS_NID:
+		return "bogus_nid";
+	case NVME_QUIRK_NO_SECONDARY_TEMP_THRESH:
+		return "no_secondary_temp_thresh";
+	case NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND:
+		return "force_no_simple_suspend";
+	case NVME_QUIRK_BROKEN_MSI:
+		return "broken_msi";
+	case NVME_QUIRK_DMAPOOL_ALIGN_512:
+		return "dmapool_align_512";
+	}
+
+	return "unknown";
+}
+
 /*
  * Common request structure for NVMe passthrough.  All drivers must have
  * this structure as the first member of their request-private data.
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 29430949ce2f..16c6fea4b2db 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -601,6 +601,28 @@ static ssize_t dctype_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(dctype);
 
+static ssize_t quirks_show(struct device *dev, struct device_attribute *attr,
+                char *buf)
+{
+	int count = 0, i;
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned long quirks = ctrl->quirks;
+
+	if (!quirks)
+		return sysfs_emit(buf, "none\n");
+
+	for (i = 0; quirks; ++i) {
+		if (quirks & 1) {
+			count += sysfs_emit_at(buf, count, "%s\n",
+					nvme_quirk_name(BIT(i)));
+		}
+		quirks >>= 1;
+	}
+
+	return count;
+}
+static DEVICE_ATTR_RO(quirks);
+
 #ifdef CONFIG_NVME_HOST_AUTH
 static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -742,6 +764,7 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_kato.attr,
 	&dev_attr_cntrltype.attr,
 	&dev_attr_dctype.attr,
+	&dev_attr_quirks.attr,
 #ifdef CONFIG_NVME_HOST_AUTH
 	&dev_attr_dhchap_secret.attr,
 	&dev_attr_dhchap_ctrl_secret.attr,

From ac30cd304347f2daeece6998bb5f0ae2db64e397 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Wed, 28 Jan 2026 08:26:23 +0000
Subject: [PATCH 0004/1303] nvme: stop using AWUPF

As described at [0], much of the atomic write parts of the specification
are lacking.

For now, there is nothing which we can do in software about the lack of
a dedicated NVMe write atomic command.

As for reading the atomic write limits, it is felt that the per-namespace
values are mostly properly specified and it is assumed that they are
properly implemented.

The specification of NAWUPF is quite clear. However the specification of
NABSPF is less clear. The lack of clarity in NABSPF comes from deciding
whether NABSPF applies when NSABP is 0 - it is assumed that NSABPF does
not apply when NSABP is 0.

As for the per-controller AWUPF, how this value applies to shared
namespaces is missing in the specification. Furthermore, the value is in
terms of logical blocks, which is an NS entity.

Since AWUPF is so poorly defined, stop using it already together.
Hopefully this will force vendors to implement NAWUPF support always.

Note that AWUPF not only effects atomic write support, but also the
physical block size reported for the device.

To help users know this restriction, log an info message per NS.

[0] https://lore.kernel.org/linux-nvme/20250707141834.GA30198@lst.de/

Tested-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 14 +++++---------
 drivers/nvme/host/nvme.h |  3 ++-
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7bf228df6001..83efc88ac0f9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2045,14 +2045,10 @@ static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
 		if (id->nabspf)
 			boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
 	} else {
-		/*
-		 * Use the controller wide atomic write unit.  This sucks
-		 * because the limit is defined in terms of logical blocks while
-		 * namespaces can have different formats, and because there is
-		 * no clear language in the specification prohibiting different
-		 * values for different controllers in the subsystem.
-		 */
-		atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+		if (ns->ctrl->awupf)
+			dev_info_once(ns->ctrl->device,
+				"AWUPF ignored, only NAWUPF accepted\n");
+		atomic_bs = bs;
 	}
 
 	lim->atomic_write_hw_max = atomic_bs;
@@ -3221,7 +3217,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
-	subsys->awupf = le16_to_cpu(id->awupf);
 
 	/* Versions prior to 1.4 don't necessarily report a valid type */
 	if (id->cntrltype == NVME_CTRL_DISC ||
@@ -3654,6 +3649,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
+	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 523015ae2add..9971045dbc05 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -464,6 +464,8 @@ struct nvme_ctrl {
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
+
+	u16			awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -496,7 +498,6 @@ struct nvme_subsystem {
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
-	u16			awupf; /* 0's based value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;

From 1799d8abeabc68ec05679292aaf6cba93b343c05 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Tue, 27 Jan 2026 19:38:44 +0800
Subject: [PATCH 0005/1303] xfrm6: fix uninitialized saddr in xfrm6_get_saddr()

xfrm6_get_saddr() does not check the return value of
ipv6_dev_get_saddr(). When ipv6_dev_get_saddr() fails to find a suitable
source address (returns -EADDRNOTAVAIL), saddr->in6 is left
uninitialized, but xfrm6_get_saddr() still returns 0 (success).

This causes the caller xfrm_tmpl_resolve_one() to use the uninitialized
address in xfrm_state_find(), triggering KMSAN warning:

=====================================================
BUG: KMSAN: uninit-value in xfrm_state_find+0x2424/0xa940
 xfrm_state_find+0x2424/0xa940
 xfrm_resolve_and_create_bundle+0x906/0x5a20
 xfrm_lookup_with_ifid+0xcc0/0x3770
 xfrm_lookup_route+0x63/0x2b0
 ip_route_output_flow+0x1ce/0x270
 udp_sendmsg+0x2ce1/0x3400
 inet_sendmsg+0x1ef/0x2a0
 __sock_sendmsg+0x278/0x3d0
 __sys_sendto+0x593/0x720
 __x64_sys_sendto+0x130/0x200
 x64_sys_call+0x332b/0x3e70
 do_syscall_64+0xd3/0xf80
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable tmp.i.i created at:
 xfrm_resolve_and_create_bundle+0x3e3/0x5a20
 xfrm_lookup_with_ifid+0xcc0/0x3770
=====================================================

Fix by checking the return value of ipv6_dev_get_saddr() and propagating
the error.

Fixes: a1e59abf8249 ("[XFRM]: Fix wildcard as tunnel source")
Reported-by: syzbot+e136d86d34b42399a8b1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68bf1024.a70a0220.7a912.02c2.GAE@google.com/T/
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv6/xfrm6_policy.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 1f19b6f14484..125ea9a5b8a0 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -57,6 +57,7 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr,
 	struct dst_entry *dst;
 	struct net_device *dev;
 	struct inet6_dev *idev;
+	int err;
 
 	dst = xfrm6_dst_lookup(params);
 	if (IS_ERR(dst))
@@ -68,9 +69,11 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr,
 		return -EHOSTUNREACH;
 	}
 	dev = idev->dev;
-	ipv6_dev_get_saddr(dev_net(dev), dev, &params->daddr->in6, 0,
-			   &saddr->in6);
+	err = ipv6_dev_get_saddr(dev_net(dev), dev, &params->daddr->in6, 0,
+				 &saddr->in6);
 	dst_release(dst);
+	if (err)
+		return -EHOSTUNREACH;
 	return 0;
 }
 

From 0a4524bc69882a4ddb235bb6b279597721bda197 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 27 Jan 2026 14:49:23 +0200
Subject: [PATCH 0006/1303] xfrm: skip templates check for packet offload
 tunnel mode

In packet offload, hardware is responsible to check templates. The
result of its operation is forwarded through secpath by relevant
drivers. That secpath is actually removed in __xfrm_policy_check2().

In case packet is forwarded, this secpath is reset in RX, but pushed
again to TX where policy is rechecked again against dummy secpath
in xfrm_policy_ok().

Such situation causes to unexpected XfrmInTmplMismatch increase.

As a solution, simply skip template mismatch check.

Fixes: 600258d555f0 ("xfrm: delete intermediate secpath entry in packet offload mode")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 62486f866975..5428185196a1 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3801,8 +3801,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl **tpp = tp;
+		int i, k = 0;
 		int ti = 0;
-		int i, k;
 
 		sp = skb_sec_path(skb);
 		if (!sp)
@@ -3828,6 +3828,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			tpp = stp;
 		}
 
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET && sp == &dummy)
+			/* This policy template was already checked by HW
+			 * and secpath was removed in __xfrm_policy_check2.
+			 */
+			goto out;
+
 		/* For each tunnel xfrm, find the first matching tmpl.
 		 * For each tmpl before that, find corresponding xfrm.
 		 * Order is _important_. Later we will implement
@@ -3837,7 +3843,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		 * verified to allow them to be skipped in future policy
 		 * checks (e.g. nested tunnels).
 		 */
-		for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
+		for (i = xfrm_nr - 1; i >= 0; i--) {
 			k = xfrm_policy_ok(tpp[i], sp, k, family, if_id);
 			if (k < 0) {
 				if (k < -1)
@@ -3853,6 +3859,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			goto reject;
 		}
 
+out:
 		xfrm_pols_put(pols, npols);
 		sp->verified_cnt = k;
 

From 0a1fc2f301529ac75aec0ce80d5ab9d9e4dc4b16 Mon Sep 17 00:00:00 2001
From: Daniel Hodges <hodgesd@meta.com>
Date: Sat, 31 Jan 2026 19:08:40 -0800
Subject: [PATCH 0007/1303] nvme-fabrics: use kfree_sensitive() for DHCHAP
 secrets

The DHCHAP secrets (dhchap_secret and dhchap_ctrl_secret) contain
authentication key material for NVMe-oF. Use kfree_sensitive() instead
of kfree() in nvmf_free_options() to ensure secrets are zeroed before
the memory is freed, preventing recovery from freed pages.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Hodges <hodgesd@meta.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fabrics.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 55a8afd2efd5..d37cb140d832 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -1290,8 +1290,8 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts)
 	kfree(opts->subsysnqn);
 	kfree(opts->host_traddr);
 	kfree(opts->host_iface);
-	kfree(opts->dhchap_secret);
-	kfree(opts->dhchap_ctrl_secret);
+	kfree_sensitive(opts->dhchap_secret);
+	kfree_sensitive(opts->dhchap_ctrl_secret);
 	kfree(opts);
 }
 EXPORT_SYMBOL_GPL(nvmf_free_options);

From b84bb7bd913d8ca2f976ee6faf4a174f91c02b8d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 31 Jan 2026 22:48:08 +0800
Subject: [PATCH 0008/1303] nvme: fix admin queue leak on controller reset

When nvme_alloc_admin_tag_set() is called during a controller reset,
a previous admin queue may still exist. Release it properly before
allocating a new one to avoid orphaning the old queue.

This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix
admin request_queue lifetime").

Cc: Keith Busch <kbusch@kernel.org>
Fixes: 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").
Reported-and-tested-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs9wv3SdPo+N01Fw2SHBYDs9tj2M_e1-GdQOkRy=DsBB1w@mail.gmail.com/
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 83efc88ac0f9..c12986495e71 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4860,6 +4860,13 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ret)
 		return ret;
 
+	/*
+	 * If a previous admin queue exists (e.g., from before a reset),
+	 * put it now before allocating a new one to avoid orphaning it.
+	 */
+	if (ctrl->admin_q)
+		blk_put_queue(ctrl->admin_q);
+
 	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);

From 594c11d0e1d445f580898a2b8c850f2e3f099368 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Tue, 27 Jan 2026 07:22:35 -0600
Subject: [PATCH 0009/1303] ipmi: Fix use-after-free and list corruption on
 sender error

The analysis from Breno:

When the SMI sender returns an error, smi_work() delivers an error
response but then jumps back to restart without cleaning up properly:

1. intf->curr_msg is not cleared, so no new message is pulled
2. newmsg still points to the message, causing sender() to be called
   again with the same message
3. If sender() fails again, deliver_err_response() is called with
   the same recv_msg that was already queued for delivery

This causes list_add corruption ("list_add double add") because the
recv_msg is added to the user_msgs list twice. Subsequently, the
corrupted list leads to use-after-free when the memory is freed and
reused, and eventually a NULL pointer dereference when accessing
recv_msg->done.

The buggy sequence:

  sender() fails
    -> deliver_err_response(recv_msg)  // recv_msg queued for delivery
    -> goto restart                    // curr_msg not cleared!
  sender() fails again (same message!)
    -> deliver_err_response(recv_msg)  // tries to queue same recv_msg
    -> LIST CORRUPTION

Fix this by freeing the message and setting it to NULL on a send error.
Also, always free the newmsg on a send error, otherwise it will leak.

Reported-by: Breno Leitao <leitao@debian.org>
Closes: https://lore.kernel.org/lkml/20260127-ipmi-v1-0-ba5cc90f516f@debian.org/
Fixes: 9cf93a8fa9513 ("ipmi: Allow an SMI sender to return an error")
Cc: stable@vger.kernel.org # 4.18
Reviewed-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_msghandler.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 3f48fc6ab596..a590a67294e2 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -4852,8 +4852,15 @@ static void smi_work(struct work_struct *t)
 			if (newmsg->recv_msg)
 				deliver_err_response(intf,
 						     newmsg->recv_msg, cc);
-			else
-				ipmi_free_smi_msg(newmsg);
+			if (!run_to_completion)
+				spin_lock_irqsave(&intf->xmit_msgs_lock,
+						  flags);
+			intf->curr_msg = NULL;
+			if (!run_to_completion)
+				spin_unlock_irqrestore(&intf->xmit_msgs_lock,
+						       flags);
+			ipmi_free_smi_msg(newmsg);
+			newmsg = NULL;
 			goto restart;
 		}
 	}

From 1d90e6c1a56f6ab83e5c9d30ded19e7ac8155713 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Tue, 27 Jan 2026 07:35:02 -0600
Subject: [PATCH 0010/1303] ipmi: Consolidate the run to completion checking
 for xmit msgs lock

It made things hard to read, move the check to a function.

Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Breno Leitao <leitao@debian.org>
---
 drivers/char/ipmi/ipmi_msghandler.c | 42 ++++++++++++++++-------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a590a67294e2..a042b1596933 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -602,6 +602,22 @@ static int __ipmi_bmc_register(struct ipmi_smi *intf,
 static int __scan_channels(struct ipmi_smi *intf,
 				struct ipmi_device_id *id, bool rescan);
 
+static void ipmi_lock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion,
+				unsigned long *flags)
+{
+	if (run_to_completion)
+		return;
+	spin_lock_irqsave(&intf->xmit_msgs_lock, *flags);
+}
+
+static void ipmi_unlock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion,
+				  unsigned long *flags)
+{
+	if (run_to_completion)
+		return;
+	spin_unlock_irqrestore(&intf->xmit_msgs_lock, *flags);
+}
+
 static void free_ipmi_user(struct kref *ref)
 {
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
@@ -1878,11 +1894,9 @@ static void smi_send(struct ipmi_smi *intf,
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	unsigned long flags = 0;
 
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	smi_msg = smi_add_send_msg(intf, smi_msg, priority);
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (smi_msg)
 		handlers->sender(intf->send_info, smi_msg);
@@ -4826,8 +4840,7 @@ static void smi_work(struct work_struct *t)
 	 * message delivery.
 	 */
 restart:
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	if (intf->curr_msg == NULL && !intf->in_shutdown) {
 		struct list_head *entry = NULL;
 
@@ -4843,8 +4856,7 @@ static void smi_work(struct work_struct *t)
 			intf->curr_msg = newmsg;
 		}
 	}
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (newmsg) {
 		cc = intf->handlers->sender(intf->send_info, newmsg);
@@ -4852,13 +4864,9 @@ static void smi_work(struct work_struct *t)
 			if (newmsg->recv_msg)
 				deliver_err_response(intf,
 						     newmsg->recv_msg, cc);
-			if (!run_to_completion)
-				spin_lock_irqsave(&intf->xmit_msgs_lock,
-						  flags);
+			ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 			intf->curr_msg = NULL;
-			if (!run_to_completion)
-				spin_unlock_irqrestore(&intf->xmit_msgs_lock,
-						       flags);
+			ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 			ipmi_free_smi_msg(newmsg);
 			newmsg = NULL;
 			goto restart;
@@ -4928,16 +4936,14 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf,
 		spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
 				       flags);
 
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	/*
 	 * We can get an asynchronous event or receive message in addition
 	 * to commands we send.
 	 */
 	if (msg == intf->curr_msg)
 		intf->curr_msg = NULL;
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (run_to_completion)
 		smi_work(&intf->smi_work);

From 9f235ccecd03c436cb1683eac16b12f119e54aa9 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Tue, 13 Jan 2026 17:41:34 +0800
Subject: [PATCH 0011/1303] ipmi: ipmb: initialise event handler read bytes

IPMB doesn't use i2c reads, but the handler needs to set a value.
Otherwise an i2c read will return an uninitialised value from the bus
driver.

Fixes: 63c4eb347164 ("ipmi:ipmb: Add initial support for IPMI over IPMB")
Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Message-ID: <20260113-ipmb-read-init-v1-1-a9cbce7b94e3@codeconstruct.com.au>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_ipmb.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/char/ipmi/ipmi_ipmb.c b/drivers/char/ipmi/ipmi_ipmb.c
index 3a51e58b2487..28818952a7a4 100644
--- a/drivers/char/ipmi/ipmi_ipmb.c
+++ b/drivers/char/ipmi/ipmi_ipmb.c
@@ -202,11 +202,16 @@ static int ipmi_ipmb_slave_cb(struct i2c_client *client,
 		break;
 
 	case I2C_SLAVE_READ_REQUESTED:
+		*val = 0xff;
+		ipmi_ipmb_check_msg_done(iidev);
+		break;
+
 	case I2C_SLAVE_STOP:
 		ipmi_ipmb_check_msg_done(iidev);
 		break;
 
 	case I2C_SLAVE_READ_PROCESSED:
+		*val = 0xff;
 		break;
 	}
 

From 6b157b408d0c7d125e4d7c62e11e7d9376a5d150 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 16 Jan 2026 17:22:01 -0600
Subject: [PATCH 0012/1303] ipmi:ls2k: Make ipmi_ls2k_platform_driver static

No need for it to be global.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601170753.3zDBerGP-lkp@intel.com/
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_ls2k.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_ls2k.c b/drivers/char/ipmi/ipmi_si_ls2k.c
index 45442c257efd..4c1da80f256c 100644
--- a/drivers/char/ipmi/ipmi_si_ls2k.c
+++ b/drivers/char/ipmi/ipmi_si_ls2k.c
@@ -168,7 +168,7 @@ static void ipmi_ls2k_remove(struct platform_device *pdev)
 	ipmi_si_remove_by_dev(&pdev->dev);
 }
 
-struct platform_driver ipmi_ls2k_platform_driver = {
+static struct platform_driver ipmi_ls2k_platform_driver = {
 	.driver = {
 		.name = "ls2k-ipmi-si",
 	},

From 7bb8c40f5ad88392bbabb719ebfd5e3354ce0428 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 4 Feb 2026 11:55:55 +0100
Subject: [PATCH 0013/1303] nvme: add support for dynamic quirk configuration
 via module parameter

Introduce support for enabling or disabling specific NVMe quirks at module
load time through the `quirks` module parameter.
This mechanism allows users to apply known quirks dynamically based on the
device's PCI vendor and device IDs, without requiring to add hardcoded
entries in the driver and recompiling the kernel.

While the generic PCI new_id sysfs interface exists for dynamic
configuration, it is insufficient for scenarios where the system fails
to boot (for example, this has been reported to happen because of the
bogus_nid quirk). The new_id attribute is writable only after the system
has booted and sysfs is mounted.

The `quirks` parameter accepts a list of quirk specifications separated by
a '-' character in the following format:

<VID>:<DID>:<quirk_names>[-<VID>:<DID>:<quirk_names>-..]

Each quirk is represented by its name and can be prefixed with `^` to
indicate that the quirk should be disabled; quirk names are separated by
a ',' character.

Example: enable BOGUS_NID and BROKEN_MSI, disable DEALLOCATE_ZEROES:

   $ modprobe nvme quirks=7170:2210:bogus_nid,broken_msi,^deallocate_zeroes

Tested-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 .../admin-guide/kernel-parameters.txt         |  13 ++
 drivers/nvme/host/pci.c                       | 162 ++++++++++++++++++
 2 files changed, 175 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a8d0afde7f85..f0b286c2dfc1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -74,6 +74,7 @@
 	TPM	TPM drivers are enabled.
 	UMS	USB Mass Storage support is enabled.
 	USB	USB support is enabled.
+	NVME	NVMe support is enabled
 	USBHID	USB Human Interface Device support is enabled.
 	V4L	Video For Linux support is enabled.
 	VGA	The VGA console has been enabled.
@@ -4671,6 +4672,18 @@ Kernel parameters
 			This can be set from sysctl after boot.
 			See Documentation/admin-guide/sysctl/vm.rst for details.
 
+	nvme.quirks=    [NVME] A list of quirk entries to augment the built-in
+			nvme quirk list. List entries are separated by a
+			'-' character.
+			Each entry has the form VendorID:ProductID:quirk_names.
+			The IDs are 4-digits hex numbers and quirk_names is a
+			list of quirk names separated by commas. A quirk name
+			can be prefixed by '^', meaning that the specified
+			quirk must be disabled.
+
+			Example:
+			nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi
+
 	ohci1394_dma=early	[HW,EARLY] enable debugging via the ohci1394 driver.
 			See Documentation/core-api/debugging-via-ohci1394.rst for more
 			info.
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9fc4a60280a0..bd884e294600 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -72,6 +72,13 @@
 static_assert(MAX_PRP_RANGE / NVME_CTRL_PAGE_SIZE <=
 	(1 /* prp1 */ + NVME_MAX_NR_DESCRIPTORS * PRPS_PER_PAGE));
 
+struct quirk_entry {
+	u16 vendor_id;
+	u16 dev_id;
+	u32 enabled_quirks;
+	u32 disabled_quirks;
+};
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0444);
 
@@ -102,6 +109,142 @@ static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096");
 
+static struct quirk_entry *nvme_pci_quirk_list;
+static unsigned int nvme_pci_quirk_count;
+
+/* Helper to parse individual quirk names */
+static int nvme_parse_quirk_names(char *quirk_str, struct quirk_entry *entry)
+{
+	int i;
+	size_t field_len;
+	bool disabled, found;
+	char *p = quirk_str, *field;
+
+	while ((field = strsep(&p, ",")) && *field) {
+		disabled = false;
+		found = false;
+
+		if (*field == '^') {
+			/* Skip the '^' character */
+			disabled = true;
+			field++;
+		}
+
+		field_len = strlen(field);
+		for (i = 0; i < 32; i++) {
+			unsigned int bit = 1U << i;
+			char *q_name = nvme_quirk_name(bit);
+			size_t q_len = strlen(q_name);
+
+			if (!strcmp(q_name, "unknown"))
+				break;
+
+			if (!strcmp(q_name, field) &&
+				    q_len == field_len) {
+				if (disabled)
+					entry->disabled_quirks |= bit;
+				else
+					entry->enabled_quirks |= bit;
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			pr_err("nvme: unrecognized quirk %s\n", field);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+/* Helper to parse a single VID:DID:quirk_names entry */
+static int nvme_parse_quirk_entry(char *s, struct quirk_entry *entry)
+{
+	char *field;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->vendor_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->dev_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field)
+		return -EINVAL;
+
+	return nvme_parse_quirk_names(field, entry);
+}
+
+static int quirks_param_set(const char *value, const struct kernel_param *kp)
+{
+	int count, err, i;
+	struct quirk_entry *qlist;
+	char *field, *val, *sep_ptr;
+
+	err = param_set_copystring(value, kp);
+	if (err)
+		return err;
+
+	val = kstrdup(value, GFP_KERNEL);
+	if (!val)
+		return -ENOMEM;
+
+	if (!*val)
+		goto out_free_val;
+
+	count = 1;
+	for (i = 0; val[i]; i++) {
+		if (val[i] == '-')
+			count++;
+	}
+
+	qlist = kcalloc(count, sizeof(*qlist), GFP_KERNEL);
+	if (!qlist) {
+		err = -ENOMEM;
+		goto out_free_val;
+	}
+
+	i = 0;
+	sep_ptr = val;
+	while ((field = strsep(&sep_ptr, "-"))) {
+		if (nvme_parse_quirk_entry(field, &qlist[i])) {
+			pr_err("nvme: failed to parse quirk string %s\n",
+				value);
+			goto out_free_qlist;
+		}
+
+		i++;
+	}
+
+	nvme_pci_quirk_count = count;
+	nvme_pci_quirk_list  = qlist;
+	goto out_free_val;
+
+out_free_qlist:
+	kfree(qlist);
+out_free_val:
+	kfree(val);
+	return err;
+}
+
+static char quirks_param[128];
+static const struct kernel_param_ops quirks_param_ops = {
+	.set = quirks_param_set,
+	.get = param_get_string,
+};
+
+static struct kparam_string quirks_param_string = {
+	.maxlen = sizeof(quirks_param),
+	.string = quirks_param,
+};
+
+module_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0444);
+MODULE_PARM_DESC(quirks, "Enable/disable NVMe quirks by specifying "
+						"quirks=VID:DID:quirk_names");
+
 static int io_queue_count_set(const char *val, const struct kernel_param *kp)
 {
 	unsigned int n;
@@ -3439,12 +3582,25 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 	return 0;
 }
 
+static struct quirk_entry *detect_dynamic_quirks(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < nvme_pci_quirk_count; i++)
+		if (pdev->vendor == nvme_pci_quirk_list[i].vendor_id &&
+		    pdev->device == nvme_pci_quirk_list[i].dev_id)
+			return &nvme_pci_quirk_list[i];
+
+	return NULL;
+}
+
 static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 		const struct pci_device_id *id)
 {
 	unsigned long quirks = id->driver_data;
 	int node = dev_to_node(&pdev->dev);
 	struct nvme_dev *dev;
+	struct quirk_entry *qentry;
 	int ret = -ENOMEM;
 
 	dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids),
@@ -3476,6 +3632,11 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 			 "platform quirk: setting simple suspend\n");
 		quirks |= NVME_QUIRK_SIMPLE_SUSPEND;
 	}
+	qentry = detect_dynamic_quirks(pdev);
+	if (qentry) {
+		quirks |= qentry->enabled_quirks;
+		quirks &= ~qentry->disabled_quirks;
+	}
 	ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
 			     quirks);
 	if (ret)
@@ -4074,6 +4235,7 @@ static int __init nvme_init(void)
 
 static void __exit nvme_exit(void)
 {
+	kfree(nvme_pci_quirk_list);
 	pci_unregister_driver(&nvme_driver);
 	flush_workqueue(nvme_wq);
 }

From 211ecfaaef186ee5230a77d054cdec7fbfc6724a Mon Sep 17 00:00:00 2001
From: Brad Spengler <brad.spengler@opensrcsec.com>
Date: Wed, 7 Jan 2026 12:12:36 -0500
Subject: [PATCH 0014/1303] drm/vmwgfx: Fix invalid kref_put callback in
 vmw_bo_dirty_release

The kref_put() call uses (void *)kvfree as the release callback, which
is incorrect. kref_put() expects a function with signature
void (*release)(struct kref *), but kvfree has signature
void (*)(const void *). Calling through an incompatible function pointer
is undefined behavior.

The code only worked by accident because ref_count is the first member
of vmw_bo_dirty, making the kref pointer equal to the struct pointer.

Fix this by adding a proper release callback that uses container_of()
to retrieve the containing structure before freeing.

Fixes: c1962742ffff ("drm/vmwgfx: Use kref in vmw_bo_dirty")
Signed-off-by: Brad Spengler <brad.spengler@opensrcsec.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Cc: Ian Forbes <ian.forbes@broadcom.com>
Link: https://patch.msgid.link/20260107171236.3573118-1-zack.rusin@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index fd4e76486f2d..45561bc1c9ef 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -260,6 +260,13 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo)
 	return ret;
 }
 
+static void vmw_bo_dirty_free(struct kref *kref)
+{
+	struct vmw_bo_dirty *dirty = container_of(kref, struct vmw_bo_dirty, ref_count);
+
+	kvfree(dirty);
+}
+
 /**
  * vmw_bo_dirty_release - Release a dirty-tracking user from a buffer object
  * @vbo: The buffer object
@@ -274,7 +281,7 @@ void vmw_bo_dirty_release(struct vmw_bo *vbo)
 {
 	struct vmw_bo_dirty *dirty = vbo->dirty;
 
-	if (dirty && kref_put(&dirty->ref_count, (void *)kvfree))
+	if (dirty && kref_put(&dirty->ref_count, vmw_bo_dirty_free))
 		vbo->dirty = NULL;
 }
 

From 922f9dec5d19df4cfbb7070275e5c131d10c80f3 Mon Sep 17 00:00:00 2001
From: Ian Forbes <ian.forbes@broadcom.com>
Date: Fri, 9 Jan 2026 09:51:39 -0600
Subject: [PATCH 0015/1303] drm/vmwgfx: Set a unique ID for each submitted
 command buffer

These IDs are logged by the Hypervisor when debug logging is enabled.
Having the IDs in the log makes it much easier to see when command
buffers start and finish. They can also be used by logging/tracing
in the Guest to help correlate between Guest and Hypervisor logs.

Signed-off-by: Ian Forbes <ian.forbes@broadcom.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://patch.msgid.link/20260109155139.3259493-1-ian.forbes@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 94e8982f5616..1ee37690b940 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -105,6 +105,7 @@ struct vmw_cmdbuf_context {
  * @handle: DMA address handle for the command buffer space if @using_mob is
  * false. Immutable.
  * @size: The size of the command buffer space. Immutable.
+ * @id: Monotonically increasing ID of the last cmdbuf submitted.
  * @num_contexts: Number of contexts actually enabled.
  */
 struct vmw_cmdbuf_man {
@@ -132,6 +133,7 @@ struct vmw_cmdbuf_man {
 	bool has_pool;
 	dma_addr_t handle;
 	size_t size;
+	u64 id;
 	u32 num_contexts;
 };
 
@@ -303,6 +305,8 @@ static int vmw_cmdbuf_header_submit(struct vmw_cmdbuf_header *header)
 	struct vmw_cmdbuf_man *man = header->man;
 	u32 val;
 
+	header->cb_header->id = man->id++;
+
 	val = upper_32_bits(header->handle);
 	vmw_write(man->dev_priv, SVGA_REG_COMMAND_HIGH, val);
 

From 5023ca80f9589295cb60735016e39fc5cc714243 Mon Sep 17 00:00:00 2001
From: Ian Forbes <ian.forbes@broadcom.com>
Date: Tue, 13 Jan 2026 11:53:57 -0600
Subject: [PATCH 0016/1303] drm/vmwgfx: Return the correct value in
 vmw_translate_ptr functions

Before the referenced fixes these functions used a lookup function that
returned a pointer. This was changed to another lookup function that
returned an error code with the pointer becoming an out parameter.

The error path when the lookup failed was not changed to reflect this
change and the code continued to return the PTR_ERR of the now
uninitialized pointer. This could cause the vmw_translate_ptr functions
to return success when they actually failed causing further uninitialized
and OOB accesses.

Reported-by: Kuzey Arda Bulut <kuzeyardabulut@gmail.com>
Fixes: a309c7194e8a ("drm/vmwgfx: Remove rcu locks from user resources")
Signed-off-by: Ian Forbes <ian.forbes@broadcom.com>
Reviewed-by: Zack Rusin <zack.rusin@broadcom.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Link: https://patch.msgid.link/20260113175357.129285-1-ian.forbes@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 3057f8baa7d2..e1f18020170a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1143,7 +1143,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
 	if (ret != 0) {
 		drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n");
-		return PTR_ERR(vmw_bo);
+		return ret;
 	}
 	vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_MOB, VMW_BO_DOMAIN_MOB);
 	ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo);
@@ -1199,7 +1199,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
 	if (ret != 0) {
 		drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n");
-		return PTR_ERR(vmw_bo);
+		return ret;
 	}
 	vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM,
 			     VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM);

From 63059500b124254c2630b2f8c46cb3555e726f52 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 5 Feb 2026 17:11:15 +0000
Subject: [PATCH 0017/1303] nvme: stop setting namespace gendisk device driver
 data

Since commit 1f4137e882c6 ("nvme: move passthrough logging attribute to
head"), we stopped using the namespace to hold the passthrough logging
enabled attribute. There is now nowhere now which looks up the gendisk dev
driver data, so stop setting it.

Incidentally, it would have been better to set this before adding the
disk.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c12986495e71..3a2126584a23 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4181,13 +4181,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
-	/*
-	 * Set ns->disk->device->driver_data to ns so we can access
-	 * ns->head->passthru_err_log_enabled in
-	 * nvme_io_passthru_err_log_enabled_[store | show]().
-	 */
-	dev_set_drvdata(disk_to_dev(ns->disk), ns);
-
 	return;
 
  out_cleanup_ns_from_list:

From 3ddfbfbc78ac1d3d9e95098fb6a32b57b8a0dcae Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 5 Feb 2026 17:11:14 +0000
Subject: [PATCH 0018/1303] nvme: correct comment about nvme_ns_remove()

The comment in nvme_mpath_remove_disk() references nvme_remove_ns(), which
should be nvme_ns_remove().

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/multipath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 174027d1cc19..bfcc5904e6a2 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1300,7 +1300,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	mutex_lock(&head->subsys->lock);
 	/*
 	 * We are called when all paths have been removed, and at that point
-	 * head->list is expected to be empty. However, nvme_remove_ns() and
+	 * head->list is expected to be empty. However, nvme_ns_remove() and
 	 * nvme_init_ns_head() can run concurrently and so if head->delayed_
 	 * removal_secs is configured, it is possible that by the time we reach
 	 * this point, head->list may no longer be empty. Therefore, we recheck

From 52c9ee202edd21d0599ac3b5a6fe1da2a2f053e5 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 6 Feb 2026 09:59:32 -0600
Subject: [PATCH 0019/1303] ipmi:si: Handle waiting messages when BMC failure
 detected

If a BMC failure is detected, the current message is returned with an
error.  However, if there was a waiting message, it would not be
handled.

Add a check for the waiting message after handling the current message.

Suggested-by: Guenter Roeck <linux@roeck-us.net>
Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Closes: https://lore.kernel.org/linux-acpi/CAK8fFZ58fidGUCHi5WFX0uoTPzveUUDzT=k=AAm4yWo3bAuCFg@mail.gmail.com/
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_intf.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 5459ffdde8dc..ff159b1162b9 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -809,6 +809,12 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 			 */
 			return_hosed_msg(smi_info, IPMI_BUS_ERR);
 		}
+		if (smi_info->waiting_msg != NULL) {
+			/* Also handle if there was a message waiting. */
+			smi_info->curr_msg = smi_info->waiting_msg;
+			smi_info->waiting_msg = NULL;
+			return_hosed_msg(smi_info, IPMI_BUS_ERR);
+		}
 		smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_HOSED);
 		goto out;
 	}

From c3bb3295637cc9bf514f690941ca9a385bf30113 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 6 Feb 2026 10:33:52 -0600
Subject: [PATCH 0020/1303] ipmi:si: Use a long timeout when the BMC is
 misbehaving

If the driver goes into HOSED state, don't reset the timeout to the
short timeout in the timeout handler.

Reported-by: Igor Raits <igor@gooddata.com>
Closes: https://lore.kernel.org/linux-acpi/CAK8fFZ58fidGUCHi5WFX0uoTPzveUUDzT=k=AAm4yWo3bAuCFg@mail.gmail.com/
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_intf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index ff159b1162b9..0049e3792ba1 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1119,7 +1119,9 @@ static void smi_timeout(struct timer_list *t)
 		     * SI_USEC_PER_JIFFY);
 	smi_result = smi_event_handler(smi_info, time_diff);
 
-	if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
+	if (smi_info->si_state == SI_HOSED) {
+		timeout = jiffies + SI_TIMEOUT_HOSED;
+	} else if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
 		/* Running with interrupts, only do long timeouts. */
 		timeout = jiffies + SI_TIMEOUT_JIFFIES;
 		smi_inc_stat(smi_info, long_timeouts);

From 4efa91a28576054aae0e6dad9cba8fed8293aef8 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Fri, 30 Jan 2026 19:42:47 +0900
Subject: [PATCH 0021/1303] xfrm: always flush state and policy upon
 NETDEV_UNREGISTER event

syzbot is reporting that "struct xfrm_state" refcount is leaking.

  unregister_netdevice: waiting for netdevsim0 to become free. Usage count = 2
  ref_tracker: netdev@ffff888052f24618 has 1/1 users at
       __netdev_tracker_alloc include/linux/netdevice.h:4400 [inline]
       netdev_tracker_alloc include/linux/netdevice.h:4412 [inline]
       xfrm_dev_state_add+0x3a5/0x1080 net/xfrm/xfrm_device.c:316
       xfrm_state_construct net/xfrm/xfrm_user.c:986 [inline]
       xfrm_add_sa+0x34ff/0x5fa0 net/xfrm/xfrm_user.c:1022
       xfrm_user_rcv_msg+0x58e/0xc00 net/xfrm/xfrm_user.c:3507
       netlink_rcv_skb+0x158/0x420 net/netlink/af_netlink.c:2550
       xfrm_netlink_rcv+0x71/0x90 net/xfrm/xfrm_user.c:3529
       netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
       netlink_unicast+0x5aa/0x870 net/netlink/af_netlink.c:1344
       netlink_sendmsg+0x8c8/0xdd0 net/netlink/af_netlink.c:1894
       sock_sendmsg_nosec net/socket.c:727 [inline]
       __sock_sendmsg net/socket.c:742 [inline]
       ____sys_sendmsg+0xa5d/0xc30 net/socket.c:2592
       ___sys_sendmsg+0x134/0x1d0 net/socket.c:2646
       __sys_sendmsg+0x16d/0x220 net/socket.c:2678
       do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
       do_syscall_64+0xcd/0xf80 arch/x86/entry/syscall_64.c:94
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

This is because commit d77e38e612a0 ("xfrm: Add an IPsec hardware
offloading API") implemented xfrm_dev_unregister() as no-op despite
xfrm_dev_state_add() from xfrm_state_construct() acquires a reference
to "struct net_device".
I guess that that commit expected that NETDEV_DOWN event is fired before
NETDEV_UNREGISTER event fires, and also assumed that xfrm_dev_state_add()
is called only if (dev->features & NETIF_F_HW_ESP) != 0.

Sabrina Dubroca identified steps to reproduce the same symptoms as below.

  echo 0 > /sys/bus/netdevsim/new_device
  dev=$(ls -1 /sys/bus/netdevsim/devices/netdevsim0/net/)
  ip xfrm state add src 192.168.13.1 dst 192.168.13.2 proto esp \
     spi 0x1000 mode tunnel aead 'rfc4106(gcm(aes))' $key 128   \
     offload crypto dev $dev dir out
  ethtool -K $dev esp-hw-offload off
  echo 0 > /sys/bus/netdevsim/del_device

Like these steps indicate, the NETIF_F_HW_ESP bit can be cleared after
xfrm_dev_state_add() acquired a reference to "struct net_device".
Also, xfrm_dev_state_add() does not check for the NETIF_F_HW_ESP bit
when acquiring a reference to "struct net_device".

Commit 03891f820c21 ("xfrm: handle NETDEV_UNREGISTER for xfrm device")
re-introduced the NETDEV_UNREGISTER event to xfrm_dev_event(), but that
commit for unknown reason chose to share xfrm_dev_down() between the
NETDEV_DOWN event and the NETDEV_UNREGISTER event.
I guess that that commit missed the behavior in the previous paragraph.

Therefore, we need to re-introduce xfrm_dev_unregister() in order to
release the reference to "struct net_device" by unconditionally flushing
state and policy.

Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API")
Cc: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_device.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 52ae0e034d29..550457e4c4f0 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -544,6 +544,14 @@ static int xfrm_dev_down(struct net_device *dev)
 	return NOTIFY_DONE;
 }
 
+static int xfrm_dev_unregister(struct net_device *dev)
+{
+	xfrm_dev_state_flush(dev_net(dev), dev, true);
+	xfrm_dev_policy_flush(dev_net(dev), dev, true);
+
+	return NOTIFY_DONE;
+}
+
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -556,8 +564,10 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 		return xfrm_api_check(dev);
 
 	case NETDEV_DOWN:
-	case NETDEV_UNREGISTER:
 		return xfrm_dev_down(dev);
+
+	case NETDEV_UNREGISTER:
+		return xfrm_dev_unregister(dev);
 	}
 	return NOTIFY_DONE;
 }

From fd3634312a04f336dcbfb481060219f0cd320738 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Sat, 7 Feb 2026 14:27:05 +0100
Subject: [PATCH 0022/1303] debugobject: Make it work with deferred page
 initialization - again

debugobjects uses __GFP_HIGH for allocations as it might be invoked
within locked regions. That worked perfectly fine until v6.18. It still
works correctly when deferred page initialization is disabled and works
by chance when no page allocation is required before deferred page
initialization has completed.

Since v6.18 allocations w/o a reclaim flag cause new_slab() to end up in
alloc_frozen_pages_nolock_noprof(), which returns early when deferred
page initialization has not yet completed. As the deferred page
initialization takes quite a while the debugobject pool is depleted and
debugobjects are disabled.

This can be worked around when PREEMPT_COUNT is enabled as that allows
debugobjects to add __GFP_KSWAPD_RECLAIM to the GFP flags when the context
is preemtible. When PREEMPT_COUNT is disabled the context is unknown and
the reclaim bit can't be set because the caller might hold locks which
might deadlock in the allocator.

In preemptible context the reclaim bit is harmless and not a performance
issue as that's usually invoked from slow path initialization context.

That makes debugobjects depend on PREEMPT_COUNT || !DEFERRED_STRUCT_PAGE_INIT.

Fixes: af92793e52c3 ("slab: Introduce kmalloc_nolock() and kfree_nolock().")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://patch.msgid.link/87pl6gznti.ffs@tglx
---
 lib/Kconfig.debug  |  1 +
 lib/debugobjects.c | 19 ++++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba36939fda79..a874146ad828 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -723,6 +723,7 @@ source "mm/Kconfig.debug"
 
 config DEBUG_OBJECTS
 	bool "Debug object operations"
+	depends on PREEMPT_COUNT || !DEFERRED_STRUCT_PAGE_INIT
 	depends on DEBUG_KERNEL
 	help
 	  If you say Y here, additional code will be inserted into the
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 89a1d6745dc2..12f50de85b62 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -398,9 +398,26 @@ static void fill_pool(void)
 
 	atomic_inc(&cpus_allocating);
 	while (pool_should_refill(&pool_global)) {
+		gfp_t gfp = __GFP_HIGH | __GFP_NOWARN;
 		HLIST_HEAD(head);
 
-		if (!kmem_alloc_batch(&head, obj_cache, __GFP_HIGH | __GFP_NOWARN))
+		/*
+		 * Allow reclaim only in preemptible context and during
+		 * early boot. If not preemptible, the caller might hold
+		 * locks causing a deadlock in the allocator.
+		 *
+		 * If the reclaim flag is not set during early boot then
+		 * allocations, which happen before deferred page
+		 * initialization has completed, will fail.
+		 *
+		 * In preemptible context the flag is harmless and not a
+		 * performance issue as that's usually invoked from slow
+		 * path initialization context.
+		 */
+		if (preemptible() || system_state < SYSTEM_SCHEDULING)
+			gfp |= __GFP_KSWAPD_RECLAIM;
+
+		if (!kmem_alloc_batch(&head, obj_cache, gfp))
 			break;
 
 		guard(raw_spinlock_irqsave)(&pool_lock);

From fef0e649f8b42bdffe4a916dd46e1b1e9ad2f207 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Fri, 30 Jan 2026 00:21:19 +0800
Subject: [PATCH 0023/1303] drm/logicvc: Fix device node reference leak in
 logicvc_drm_config_parse()

The logicvc_drm_config_parse() function calls of_get_child_by_name() to
find the "layers" node but fails to release the reference, leading to a
device node reference leak.

Fix this by using the __free(device_node) cleanup attribute to automatic
release the reference when the variable goes out of scope.

Fixes: efeeaefe9be5 ("drm: Add support for the LogiCVC display controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20260130-logicvc_drm-v1-1-04366463750c@gmail.com
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/logicvc/logicvc_drm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/logicvc/logicvc_drm.c b/drivers/gpu/drm/logicvc/logicvc_drm.c
index 204b0fee55d0..bbebf4fc7f51 100644
--- a/drivers/gpu/drm/logicvc/logicvc_drm.c
+++ b/drivers/gpu/drm/logicvc/logicvc_drm.c
@@ -92,7 +92,6 @@ static int logicvc_drm_config_parse(struct logicvc_drm *logicvc)
 	struct device *dev = drm_dev->dev;
 	struct device_node *of_node = dev->of_node;
 	struct logicvc_drm_config *config = &logicvc->config;
-	struct device_node *layers_node;
 	int ret;
 
 	logicvc_of_property_parse_bool(of_node, LOGICVC_OF_PROPERTY_DITHERING,
@@ -128,7 +127,8 @@ static int logicvc_drm_config_parse(struct logicvc_drm *logicvc)
 	if (ret)
 		return ret;
 
-	layers_node = of_get_child_by_name(of_node, "layers");
+	struct device_node *layers_node __free(device_node) =
+		of_get_child_by_name(of_node, "layers");
 	if (!layers_node) {
 		drm_err(drm_dev, "Missing non-optional layers node\n");
 		return -EINVAL;

From b777b5e09eabeefc6ba80f4296366a4742701103 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Feb 2026 17:02:25 +0000
Subject: [PATCH 0024/1303] time/jiffies: Inline jiffies_to_msecs() and
 jiffies_to_usecs()

For common cases (HZ=100, 250 or 1000), these helpers are at most one
multiply, so there is no point calling a tiny function.

Keep them out of line for HZ=300 and others.

This saves cycles in TCP fast path, among other things.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/8 grow/shrink: 25/89 up/down: 530/-3474 (-2944)
...
nla_put_msecs                                193       -    -193
message_stats_print                         2131     920   -1211
Total: Before=25365208, After=25362264, chg -0.01%

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260210170226.57209-1-edumazet@google.com
---
 include/linux/jiffies.h | 40 ++++++++++++++++++++++++++++++++++++++--
 kernel/time/time.c      | 19 +++++++------------
 2 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fdef2c155c27..d1c3d4941854 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -434,8 +434,44 @@ extern unsigned long preset_lpj;
 /*
  * Convert various time units to each other:
  */
-extern unsigned int jiffies_to_msecs(const unsigned long j);
-extern unsigned int jiffies_to_usecs(const unsigned long j);
+
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+/**
+ * jiffies_to_msecs - Convert jiffies to milliseconds
+ * @j: jiffies value
+ *
+ * This inline version takes care of HZ in {100,250,1000}.
+ *
+ * Return: milliseconds value
+ */
+static inline unsigned int jiffies_to_msecs(const unsigned long j)
+{
+	return (MSEC_PER_SEC / HZ) * j;
+}
+#else
+unsigned int jiffies_to_msecs(const unsigned long j);
+#endif
+
+#if !(USEC_PER_SEC % HZ)
+/**
+ * jiffies_to_usecs - Convert jiffies to microseconds
+ * @j: jiffies value
+ *
+ * Return: microseconds value
+ */
+static inline unsigned int jiffies_to_usecs(const unsigned long j)
+{
+	/*
+	 * Hz usually doesn't go much further MSEC_PER_SEC.
+	 * jiffies_to_usecs() and usecs_to_jiffies() depend on that.
+	 */
+	BUILD_BUG_ON(HZ > USEC_PER_SEC);
+
+	return (USEC_PER_SEC / HZ) * j;
+}
+#else
+unsigned int jiffies_to_usecs(const unsigned long j);
+#endif
 
 /**
  * jiffies_to_nsecs - Convert jiffies to nanoseconds
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 0ba8e3c50d62..36fd2313ae7e 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -365,20 +365,16 @@ SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp)
 }
 #endif
 
+#if HZ > MSEC_PER_SEC || (MSEC_PER_SEC % HZ)
 /**
  * jiffies_to_msecs - Convert jiffies to milliseconds
  * @j: jiffies value
  *
- * Avoid unnecessary multiplications/divisions in the
- * two most common HZ cases.
- *
  * Return: milliseconds value
  */
 unsigned int jiffies_to_msecs(const unsigned long j)
 {
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
-	return (MSEC_PER_SEC / HZ) * j;
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+#if HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
 	return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
 #else
 # if BITS_PER_LONG == 32
@@ -390,7 +386,9 @@ unsigned int jiffies_to_msecs(const unsigned long j)
 #endif
 }
 EXPORT_SYMBOL(jiffies_to_msecs);
+#endif
 
+#if (USEC_PER_SEC % HZ)
 /**
  * jiffies_to_usecs - Convert jiffies to microseconds
  * @j: jiffies value
@@ -405,17 +403,14 @@ unsigned int jiffies_to_usecs(const unsigned long j)
 	 */
 	BUILD_BUG_ON(HZ > USEC_PER_SEC);
 
-#if !(USEC_PER_SEC % HZ)
-	return (USEC_PER_SEC / HZ) * j;
-#else
-# if BITS_PER_LONG == 32
+#if BITS_PER_LONG == 32
 	return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
-# else
+#else
 	return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
-# endif
 #endif
 }
 EXPORT_SYMBOL(jiffies_to_usecs);
+#endif
 
 /**
  * mktime64 - Converts date to seconds.

From bbdaa8c17cae18b977f4509911d7a390aa8a6597 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 11 Feb 2026 17:30:28 +0100
Subject: [PATCH 0025/1303] nvme: fix memory leak in quirks_param_set()

When loading the nvme module, if the 'quirks' parameter is specified
via both the kernel command line (e.g., nvme.quirks=...) and the
modprobe command line (e.g., modprobe nvme quirks=...), the
quirks_param_set() callback is invoked twice.

Currently, in the double-invocation scenario, the second call
overwrites the nvme_pci_quirk_list pointer, causing the memory
allocated in the first call to leak.

Fix this by freeing the existing list before assigning the new one.

Fixes: b4247c8317c5 ("nvme: add support for dynamic quirk configuration via module parameter")
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bd884e294600..c0f2104326ab 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -219,6 +219,7 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 		i++;
 	}
 
+	kfree(nvme_pci_quirk_list);
 	nvme_pci_quirk_count = count;
 	nvme_pci_quirk_list  = qlist;
 	goto out_free_val;

From 5ee01f1a7343d6a3547b6802ca2d4cdce0edacb1 Mon Sep 17 00:00:00 2001
From: Qingye Zhao <zhaoqingye@honor.com>
Date: Wed, 11 Feb 2026 09:24:04 +0000
Subject: [PATCH 0026/1303] cgroup: fix race between task migration and
 iteration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a task is migrated out of a css_set, cgroup_migrate_add_task()
first moves it from cset->tasks to cset->mg_tasks via:

    list_move_tail(&task->cg_list, &cset->mg_tasks);

If a css_task_iter currently has it->task_pos pointing to this task,
css_set_move_task() calls css_task_iter_skip() to keep the iterator
valid. However, since the task has already been moved to ->mg_tasks,
the iterator is advanced relative to the mg_tasks list instead of the
original tasks list. As a result, remaining tasks on cset->tasks, as
well as tasks queued on cset->mg_tasks, can be skipped by iteration.

Fix this by calling css_set_skip_task_iters() before unlinking
task->cg_list from cset->tasks. This advances all active iterators to
the next task on cset->tasks, so iteration continues correctly even
when a task is concurrently being migrated.

This race is hard to hit in practice without instrumentation, but it
can be reproduced by artificially slowing down cgroup_procs_show().
For example, on an Android device a temporary
/sys/kernel/cgroup/cgroup_test knob can be added to inject a delay
into cgroup_procs_show(), and then:

  1) Spawn three long-running tasks (PIDs 101, 102, 103).
  2) Create a test cgroup and move the tasks into it.
  3) Enable a large delay via /sys/kernel/cgroup/cgroup_test.
  4) In one shell, read cgroup.procs from the test cgroup.
  5) Within the delay window, in another shell migrate PID 102 by
     writing it to a different cgroup.procs file.

Under this setup, cgroup.procs can intermittently show only PID 101
while skipping PID 103. Once the migration completes, reading the
file again shows all tasks as expected.

Note that this change does not allow removing the existing
css_set_skip_task_iters() call in css_set_move_task(). The new call
in cgroup_migrate_add_task() only handles iterators that are racing
with migration while the task is still on cset->tasks. Iterators may
also start after the task has been moved to cset->mg_tasks. If we
dropped css_set_skip_task_iters() from css_set_move_task(), such
iterators could keep task_pos pointing to a migrating task, causing
css_task_iter_advance() to malfunction on the destination css_set,
up to and including crashes or infinite loops.

The race window between migration and iteration is very small, and
css_task_iter is not on a hot path. In the worst case, when an
iterator is positioned on the first thread of the migrating process,
cgroup_migrate_add_task() may have to skip multiple tasks via
css_set_skip_task_iters(). However, this only happens when migration
and iteration actually race, so the performance impact is negligible
compared to the correctness fix provided here.

Fixes: b636fd38dc40 ("cgroup: Implement css_task_iter_skip()")
Cc: stable@vger.kernel.org # v5.2+
Signed-off-by: Qingye Zhao <zhaoqingye@honor.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cgroup.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8af4351536cf..49da0874a023 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 
 	mgctx->tset.nr_tasks++;
 
+	css_set_skip_task_iters(cset, task);
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,

From 166e31d7dbf6aa44829b98aa446bda5c9580f12a Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 09:26:54 -0800
Subject: [PATCH 0027/1303] nvme-pci: ensure we're polling a polled queue

A user can change the polled queue count at run time. There's a brief
window during a reset where a hipri task may try to poll that queue
before the block layer has updated the queue maps, which would race with
the now interrupt driven queue and may cause double completions.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0f2104326ab..4ee4d7ead5a9 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1627,7 +1627,8 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	struct nvme_queue *nvmeq = hctx->driver_data;
 	bool found;
 
-	if (!nvme_cqe_pending(nvmeq))
+	if (!test_bit(NVMEQ_POLLED, &nvmeq->flags) ||
+	    !nvme_cqe_pending(nvmeq))
 		return 0;
 
 	spin_lock(&nvmeq->cq_poll_lock);

From 4735b510a00fb2d4ac9e8d21a8c9552cb281f585 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 11:00:12 -0800
Subject: [PATCH 0028/1303] nvme-pci: cap queue creation to used queues

If the user reduces the special queue count at runtime and resets the
controller, we need to reduce the number of queues and interrupts
requested accordingly rather than start with the pre-allocated queue
count.

Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4ee4d7ead5a9..c63efa49132f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2902,7 +2902,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->nr_write_queues = write_queues;
 	dev->nr_poll_queues = poll_queues;
 
-	nr_io_queues = dev->nr_allocated_queues - 1;
+	/*
+	 * The initial number of allocated queue slots may be too large if the
+	 * user reduced the special queue parameters. Cap the value to the
+	 * number we need for this round.
+	 */
+	nr_io_queues = min(nvme_max_io_queues(dev),
+			   dev->nr_allocated_queues - 1);
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
 		return result;

From baa47c4f89eb2e7614e6a06dd5957632e38c4e74 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 10:38:09 -0800
Subject: [PATCH 0029/1303] nvme-pci: do not try to add queue maps at runtime

The block layer allocates the set's maps once. We can't add special
purpose queues at runtime if they weren't allocated at initialization
time.

Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c63efa49132f..0c1a8d7aa1c0 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2902,6 +2902,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->nr_write_queues = write_queues;
 	dev->nr_poll_queues = poll_queues;
 
+	if (dev->ctrl.tagset) {
+		/*
+		 * The set's maps are allocated only once at initialization
+		 * time. We can't add special queues later if their mq_map
+		 * wasn't preallocated.
+		 */
+		if (dev->ctrl.tagset->nr_maps < 3)
+			dev->nr_poll_queues = 0;
+		if (dev->ctrl.tagset->nr_maps < 2)
+			dev->nr_write_queues = 0;
+	}
+
 	/*
 	 * The initial number of allocated queue slots may be too large if the
 	 * user reduced the special queue parameters. Cap the value to the

From f66857bafd4f151c5cc6856e47be2e12c1721e43 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:12 +0000
Subject: [PATCH 0030/1303] KVM: arm64: Hide S1POE from guests when not
 supported by the host

When CONFIG_ARM64_POE is disabled, KVM does not save/restore POR_EL1.
However, ID_AA64MMFR3_EL1 sanitisation currently exposes the feature to
guests whenever the hardware supports it, ignoring the host kernel
configuration.

If a guest detects this feature and attempts to use it, the host will
fail to context-switch POR_EL1, potentially leading to state corruption.

Fix this by masking ID_AA64MMFR3_EL1.S1POE in the sanitised system
registers, preventing KVM from advertising the feature when the host
does not support it (i.e. system_supports_poe() is false).

Fixes: 70ed7238297f ("KVM: arm64: Sanitise ID_AA64MMFR3_EL1")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-2-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a7cd0badc20c..1b4cacb6e918 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1816,6 +1816,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		       ID_AA64MMFR3_EL1_SCTLRX |
 		       ID_AA64MMFR3_EL1_S1POE |
 		       ID_AA64MMFR3_EL1_S1PIE;
+
+		if (!system_supports_poe())
+			val &= ~ID_AA64MMFR3_EL1_S1POE;
 		break;
 	case SYS_ID_MMFR4_EL1:
 		val &= ~ID_MMFR4_EL1_CCIDX;

From 9cb0468d0b335ccf769bd8e161cc96195e82d8b1 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:13 +0000
Subject: [PATCH 0031/1303] KVM: arm64: Optimise away S1POE handling when not
 supported by host

Although ID register sanitisation prevents guests from seeing the
feature, adding this check to the helper allows the compiler to entirely
eliminate S1POE-specific code paths (such as context switching POR_EL1)
when the host kernel is compiled without support (CONFIG_ARM64_POE is
disabled).

This aligns with the pattern used for other optional features like SVE
(kvm_has_sve()) and FPMR (kvm_has_fpmr()), ensuring no POE logic if the
host lacks support, regardless of the guest configuration state.

Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-3-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5d5a3bbdb95e..2ca264b3db5f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1616,7 +1616,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP))
 
 #define kvm_has_s1poe(k)				\
-	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+	(system_supports_poe() &&			\
+	 kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
 #define kvm_has_ras(k)					\
 	(kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP))

From 7e7c2cf0024d89443a7af52e09e47b1fe634ab17 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:14 +0000
Subject: [PATCH 0032/1303] KVM: arm64: Fix ID register initialization for
 non-protected pKVM guests

In protected mode, the hypervisor maintains a separate instance of
the `kvm` structure for each VM. For non-protected VMs, this structure is
initialized from the host's `kvm` state.

Currently, `pkvm_init_features_from_host()` copies the
`KVM_ARCH_FLAG_ID_REGS_INITIALIZED` flag from the host without the
underlying `id_regs` data being initialized. This results in the
hypervisor seeing the flag as set while the ID registers remain zeroed.

Consequently, `kvm_has_feat()` checks at EL2 fail (return 0) for
non-protected VMs. This breaks logic that relies on feature detection,
such as `ctxt_has_tcrx()` for TCR2_EL1 support. As a result, certain
system registers (e.g., TCR2_EL1, PIR_EL1, POR_EL1) are not
saved/restored during the world switch, which could lead to state
corruption.

Fix this by explicitly copying the ID registers from the host `kvm` to
the hypervisor `kvm` for non-protected VMs during initialization, since
we trust the host with its non-protected guests' features. Also ensure
`KVM_ARCH_FLAG_ID_REGS_INITIALIZED` is cleared initially in
`pkvm_init_features_from_host` so that `vm_copy_id_regs` can properly
initialize them and set the flag once done.

Fixes: 41d6028e28bd ("KVM: arm64: Convert the SVE guest vcpu flag to a vm flag")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-4-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/pkvm.c | 35 ++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 8e29d7734a15..f3c1c6955163 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -342,6 +342,7 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	/* No restrictions for non-protected VMs. */
 	if (!kvm_vm_is_protected(kvm)) {
 		hyp_vm->kvm.arch.flags = host_arch_flags;
+		hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED);
 
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
@@ -471,6 +472,35 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h
 	return ret;
 }
 
+static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
+	const struct kvm *host_kvm = hyp_vm->host_kvm;
+	struct kvm *kvm = &hyp_vm->kvm;
+
+	if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags))
+		return -EINVAL;
+
+	if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))
+		return 0;
+
+	memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs));
+
+	return 0;
+}
+
+static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	int ret = 0;
+
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	else
+		ret = vm_copy_id_regs(hyp_vcpu);
+
+	return ret;
+}
+
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 			      struct pkvm_hyp_vm *hyp_vm,
 			      struct kvm_vcpu *host_vcpu)
@@ -490,8 +520,9 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
 	hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 
-	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
-		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	ret = pkvm_vcpu_init_sysregs(hyp_vcpu);
+	if (ret)
+		goto done;
 
 	ret = pkvm_vcpu_init_traps(hyp_vcpu);
 	if (ret)

From 02471a78a052b631204aed051ab718e4d14ae687 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:15 +0000
Subject: [PATCH 0033/1303] KVM: arm64: Remove redundant kern_hyp_va() in
 unpin_host_sve_state()

The `sve_state` pointer in `hyp_vcpu->vcpu.arch` is initialized as a
hypervisor virtual address during vCPU initialization in
`pkvm_vcpu_init_sve()`.

`unpin_host_sve_state()` calls `kern_hyp_va()` on this address. Since
`kern_hyp_va()` is idempotent, it's not a bug. However, it is
unnecessary and potentially confusing. Remove the redundant conversion.

Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-5-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/pkvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index f3c1c6955163..2f029bfe4755 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -392,7 +392,7 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 	if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE))
 		return;
 
-	sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state);
+	sve_state = hyp_vcpu->vcpu.arch.sve_state;
 	hyp_unpin_shared_mem(sve_state,
 			     sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu));
 }

From ee5c38a8d31e5dea52299c43c2ec3213351ab6e1 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 6 Feb 2026 14:30:23 -0800
Subject: [PATCH 0034/1303] KVM: arm64: vgic: Handle const qualifier from
 gic_kvm_info allocation type

In preparation for making the kmalloc family of allocators type aware,
we need to make sure that the returned type from the allocation matches
the type of the variable being assigned. (Before, the allocator would
always return "void *", which can be implicitly cast to any pointer type.)

The assigned type is "struct gic_kvm_info", but the returned type,
while matching, is const qualified. To get them exactly matching, just
use the dereferenced pointer for the sizeof().

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20260206223022.it.052-kees@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 86c149537493..a53f93546aa0 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -654,7 +654,7 @@ static struct gic_kvm_info *gic_kvm_info;
 void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
 {
 	BUG_ON(gic_kvm_info != NULL);
-	gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL);
+	gic_kvm_info = kmalloc(sizeof(*gic_kvm_info), GFP_KERNEL);
 	if (gic_kvm_info)
 		*gic_kvm_info = *info;
 }

From 0b87d51690dd5131cbe9fbd23746b037aab89815 Mon Sep 17 00:00:00 2001
From: Franz Schnyder <franz.schnyder@toradex.com>
Date: Fri, 6 Feb 2026 13:37:36 +0100
Subject: [PATCH 0035/1303] drm/bridge: ti-sn65dsi86: Enable HPD polling if IRQ
 is not used

Fallback to polling to detect hotplug events on systems without
interrupts.

On systems where the interrupt line of the bridge is not connected,
the bridge cannot notify hotplug events. Only add the
DRM_BRIDGE_OP_HPD flag if an interrupt has been registered
otherwise remain in polling mode.

Fixes: 55e8ff842051 ("drm/bridge: ti-sn65dsi86: Add HPD for DisplayPort connector type")
Cc: stable@vger.kernel.org # 6.16: 9133bc3f0564: drm/bridge: ti-sn65dsi86: Add
Signed-off-by: Franz Schnyder <franz.schnyder@toradex.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
[dianders: Adjusted Fixes/stable line based on discussion]
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patch.msgid.link/20260206123758.374555-1-fra.schnyder@gmail.com
---
 drivers/gpu/drm/bridge/ti-sn65dsi86.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 276d05d25ad8..98d64ad791d0 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -1415,6 +1415,7 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev,
 {
 	struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent);
 	struct device_node *np = pdata->dev->of_node;
+	const struct i2c_client *client = to_i2c_client(pdata->dev);
 	int ret;
 
 	pdata->next_bridge = devm_drm_of_get_bridge(&adev->dev, np, 1, 0);
@@ -1433,8 +1434,9 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev,
 			   ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP;
 
 	if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) {
-		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT |
-				    DRM_BRIDGE_OP_HPD;
+		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT;
+		if (client->irq)
+			pdata->bridge.ops |= DRM_BRIDGE_OP_HPD;
 		/*
 		 * If comms were already enabled they would have been enabled
 		 * with the wrong value of HPD_DISABLE. Update it now. Comms

From e9e0b48cd15b46dcb2bbc165f6b0fee698b855d6 Mon Sep 17 00:00:00 2001
From: Simon Ser <contact@emersion.fr>
Date: Sun, 8 Feb 2026 22:47:26 +0000
Subject: [PATCH 0036/1303] drm/fourcc: fix plane order for 10/12/16-bit YCbCr
 formats

The short comments had the correct order, but the long comments
had the planes reversed.

Fixes: 2271e0a20ef7 ("drm: drm_fourcc: add 10/12/16bit software decoder YCbCr formats")
Signed-off-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Robert Mader <robert.mader@collabora.com>
Link: https://patch.msgid.link/20260208224718.57199-1-contact@emersion.fr
---
 include/uapi/drm/drm_fourcc.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e527b24bd824..c89aede3cb12 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -401,8 +401,8 @@ extern "C" {
  * implementation can multiply the values by 2^6=64. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [6:10] little endian
- * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
- * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian
  */
 #define DRM_FORMAT_S010	fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
 #define DRM_FORMAT_S210	fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
@@ -414,8 +414,8 @@ extern "C" {
  * implementation can multiply the values by 2^4=16. For that reason the padding
  * must only contain zeros.
  * index 0 = Y plane, [15:0] z:Y [4:12] little endian
- * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
- * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian
  */
 #define DRM_FORMAT_S012	fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
 #define DRM_FORMAT_S212	fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
@@ -424,8 +424,8 @@ extern "C" {
 /*
  * 3 plane YCbCr
  * index 0 = Y plane, [15:0] Y little endian
- * index 1 = Cr plane, [15:0] Cr little endian
- * index 2 = Cb plane, [15:0] Cb little endian
+ * index 1 = Cb plane, [15:0] Cb little endian
+ * index 2 = Cr plane, [15:0] Cr little endian
  */
 #define DRM_FORMAT_S016	fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
 #define DRM_FORMAT_S216	fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */

From cb184dd19154fc486fa3d9e02afe70a97e54e055 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Fri, 6 Feb 2026 14:20:28 +0800
Subject: [PATCH 0037/1303] fs: init flags_valid before calling
 vfs_fileattr_get

syzbot reported a uninit-value bug in [1].

Similar to the "*get" context where the kernel's internal file_kattr
structure is initialized before calling vfs_fileattr_get(), we should
use the same mechanism when using fa.

[1]
BUG: KMSAN: uninit-value in fuse_fileattr_get+0xeb4/0x1450 fs/fuse/ioctl.c:517
 fuse_fileattr_get+0xeb4/0x1450 fs/fuse/ioctl.c:517
 vfs_fileattr_get fs/file_attr.c:94 [inline]
 __do_sys_file_getattr fs/file_attr.c:416 [inline]

Local variable fa.i created at:
 __do_sys_file_getattr fs/file_attr.c:380 [inline]
 __se_sys_file_getattr+0x8c/0xbd0 fs/file_attr.c:372

Reported-by: syzbot+7c31755f2cea07838b0c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7c31755f2cea07838b0c
Tested-by: syzbot+7c31755f2cea07838b0c@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Link: https://patch.msgid.link/tencent_B6C4583771D76766D71362A368696EC3B605@qq.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/file_attr.c b/fs/file_attr.c
index 42721427245a..0e9b4f737546 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -376,7 +376,7 @@ SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
 	struct path filepath __free(path_put) = {};
 	unsigned int lookup_flags = 0;
 	struct file_attr fattr;
-	struct file_kattr fa;
+	struct file_kattr fa = { .flags_valid = true }; /* hint only */
 	int error;
 
 	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);

From 9eed043d10f17301c1b5141e16bb98a85a8fd07e Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 3 Feb 2026 17:40:14 +0800
Subject: [PATCH 0038/1303] writeback: Fix wakeup and logging timeouts for
 !DETECT_HUNG_TASK

Recent changes of fs-writeback cause such warnings if DETECT_HUNG_TASK
is not enabled:

INFO: The task sync:1342 has been waiting for writeback completion for more than 1 seconds.

The reason is sysctl_hung_task_timeout_secs is 0 when DETECT_HUNG_TASK
is not enabled, then it causes the warning message even if the writeback
lasts for only one second.

Guard the wakeup and logging with "#ifdef CONFIG_DETECT_HUNG_TASK" can
eliminate the warning messages. But on the other hand, it is possible
that sysctl_hung_task_timeout_secs be also 0 when DETECT_HUNG_TASK is
enabled. So let's just check the value of sysctl_hung_task_timeout_secs
to decide whether do wakeup and logging.

Fixes: 1888635532fb ("writeback: Wake up waiting tasks when finishing the writeback of a chunk.")
Fixes: d6e621590764 ("writeback: Add logging for slow writeback (exceeds sysctl_hung_task_timeout_secs)")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://patch.msgid.link/20260203094014.2273240-1-chenhuacai@loongson.cn
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs-writeback.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 68228bf89b82..eb1ca86bf30a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -198,10 +198,11 @@ static void wb_queue_work(struct bdi_writeback *wb,
 
 static bool wb_wait_for_completion_cb(struct wb_completion *done)
 {
+	unsigned long timeout = sysctl_hung_task_timeout_secs;
 	unsigned long waited_secs = (jiffies - done->wait_start) / HZ;
 
 	done->progress_stamp = jiffies;
-	if (waited_secs > sysctl_hung_task_timeout_secs)
+	if (timeout && (waited_secs > timeout))
 		pr_info("INFO: The task %s:%d has been waiting for writeback "
 			"completion for more than %lu seconds.",
 			current->comm, current->pid, waited_secs);
@@ -1955,6 +1956,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		.range_end		= LLONG_MAX,
 	};
 	unsigned long start_time = jiffies;
+	unsigned long timeout = sysctl_hung_task_timeout_secs;
 	long write_chunk;
 	long total_wrote = 0;  /* count both pages and inodes */
 	unsigned long dirtied_before = jiffies;
@@ -2041,9 +2043,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		__writeback_single_inode(inode, &wbc);
 
 		/* Report progress to inform the hung task detector of the progress. */
-		if (work->done && work->done->progress_stamp &&
-		   (jiffies - work->done->progress_stamp) > HZ *
-		   sysctl_hung_task_timeout_secs / 2)
+		if (work->done && work->done->progress_stamp && timeout &&
+		   (jiffies - work->done->progress_stamp) > HZ * timeout / 2)
 			wake_up_all(work->done->waitq);
 
 		wbc_detach_inode(&wbc);

From 81f16c9778d730f573d0d565706bb7227e2405f4 Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Fri, 13 Feb 2026 18:30:06 +0800
Subject: [PATCH 0039/1303] statmount: Fix the null-ptr-deref in do_statmount()

If the mount is internal, it's mnt_ns will be MNT_NS_INTERNAL, which is
defined as ERR_PTR(-EINVAL). So, in the do_statmount(), need to check ns
of mount by IS_ERR() and return.

Fixes: 0e5032237ee5 ("statmount: accept fd as a parameter")
Reported-by: syzbot+9e03a9535ea65f687a44@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698e287a.a70a0220.2c38d7.009e.GAE@google.com/
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Link: https://patch.msgid.link/20260213103006.2472569-1-wangqing7171@gmail.com
Reviewed-by: Bhavik Sachdev <b.sachdev1904@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/namespace.c b/fs/namespace.c
index a67cbe42746d..90700df65f0d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5678,6 +5678,8 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 
 		s->mnt = mnt_file->f_path.mnt;
 		ns = real_mount(s->mnt)->mnt_ns;
+		if (IS_ERR(ns))
+			return PTR_ERR(ns);
 		if (!ns)
 			/*
 			 * We can't set mount point and mnt_ns_id since we don't have a

From ac83896172798cf82ebc643cf555aa4cdd3a07da Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Fri, 13 Feb 2026 02:28:12 +0000
Subject: [PATCH 0040/1303] iomap: Describe @private in iomap_readahead()

The kernel test rebot reports the kernel-doc warning:

```
Warning: fs/iomap/buffered-io.c:624 function parameter 'private'
 not described in 'iomap_readahead'
```

The former commit in "iomap: stash iomap read ctx in the private
field of iomap_iter" has added a new parameter @private to
iomap_readahead(), so let's describe the parameter.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601261111.vIL9rhgD-lkp@intel.com/
Fixes: 8806f279244b ("iomap: stash iomap read ctx in the private field of iomap_iter")
Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20260213022812.766187-1-lihongbo22@huawei.com
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1fe19b4ee2f4..58887513b894 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -625,6 +625,7 @@ static int iomap_readahead_iter(struct iomap_iter *iter,
  * iomap_readahead - Attempt to read pages from a file.
  * @ops: The operations vector for the filesystem.
  * @ctx: The ctx used for issuing readahead.
+ * @private: The filesystem-specific information for issuing iomap_iter.
  *
  * This function is for filesystems to call to implement their readahead
  * address_space operation.

From 1cb968a2013ffa8112d52ebe605009ea1c6a582c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Sat, 24 Jan 2026 04:18:40 +0000
Subject: [PATCH 0041/1303] nfsd: Fix cred ref leak in
 nfsd_nl_threads_set_doit().

syzbot reported memory leak of struct cred. [0]

nfsd_nl_threads_set_doit() passes get_current_cred() to
nfsd_svc(), but put_cred() is not called after that.

The cred is finally passed down to _svc_xprt_create(),
which calls get_cred() with the cred for struct svc_xprt.

The ownership of the refcount by get_current_cred() is not
transferred to anywhere and is just leaked.

nfsd_svc() is also called from write_threads(), but it does
not bump file->f_cred there.

nfsd_nl_threads_set_doit() is called from sendmsg() and
current->cred does not go away.

Let's use current_cred() in nfsd_nl_threads_set_doit().

[0]:
BUG: memory leak
unreferenced object 0xffff888108b89480 (size 184):
  comm "syz-executor", pid 5994, jiffies 4294943386
  hex dump (first 32 bytes):
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 369454a7):
    kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline]
    slab_post_alloc_hook mm/slub.c:4958 [inline]
    slab_alloc_node mm/slub.c:5263 [inline]
    kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270
    prepare_creds+0x22/0x600 kernel/cred.c:185
    copy_creds+0x44/0x290 kernel/cred.c:286
    copy_process+0x7a7/0x2870 kernel/fork.c:2086
    kernel_clone+0xac/0x6e0 kernel/fork.c:2651
    __do_sys_clone+0x7f/0xb0 kernel/fork.c:2792
    do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
    do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94
    entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 924f4fb003ba ("NFSD: convert write_threads to netlink command")
Cc: stable@vger.kernel.org
Reported-by: syzbot+dd3b43aa0204089217ee@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69744674.a00a0220.33ccc7.0000.GAE@google.com/
Tested-by: syzbot+dd3b43aa0204089217ee@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 89fe2c0e8d44..43ced6b0e197 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1647,7 +1647,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 	if (attr)
 		nn->min_threads = nla_get_u32(attr);
 
-	ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope);
+	ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope);
 	if (ret > 0)
 		ret = 0;
 out_unlock:

From 92978c83bb4eef55d02a6c990c01c423131eefa7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Sat, 24 Jan 2026 04:18:41 +0000
Subject: [PATCH 0042/1303] nfsd: Fix cred ref leak in
 nfsd_nl_listener_set_doit().

nfsd_nl_listener_set_doit() uses get_current_cred() without
put_cred().

As we can see from other callers, svc_xprt_create_from_sa()
does not require the extra refcount.

nfsd_nl_listener_set_doit() is always in the process context,
sendmsg(), and current->cred does not go away.

Let's use current_cred() in nfsd_nl_listener_set_doit().

Fixes: 16a471177496 ("NFSD: add listener-{set,get} netlink command")
Cc: stable@vger.kernel.org
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 43ced6b0e197..b06adb5d5a2e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2000,7 +2000,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
-					      get_current_cred());
+					      current_cred());
 		/* always save the latest error */
 		if (ret < 0)
 			err = ret;

From 9478c166c46934160135e197b049b5a05753f2ad Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 21 Nov 2024 11:46:01 +1000
Subject: [PATCH 0043/1303] nouveau/gsp: drop WARN_ON in ACPI probes

These WARN_ONs seem to trigger a lot, and we don't seem to have a
plan to fix them, so just drop them, as they are most likely
harmless.

Cc: stable@vger.kernel.org
Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patch.msgid.link/20241121014601.229391-1-airlied@gmail.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 .../gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c    | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
index 7fb13434c051..a575a8dbf727 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
@@ -737,8 +737,8 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	if (!obj)
 		goto done;
 
-	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
-	    WARN_ON(obj->buffer.length != 4))
+	if (obj->type != ACPI_TYPE_BUFFER ||
+	    obj->buffer.length != 4)
 		goto done;
 
 	caps->status = 0;
@@ -773,8 +773,8 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	if (!obj)
 		goto done;
 
-	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
-	    WARN_ON(obj->buffer.length != 4))
+	if (obj->type != ACPI_TYPE_BUFFER ||
+	    obj->buffer.length != 4)
 		goto done;
 
 	jt->status = 0;
@@ -861,8 +861,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod)
 
 	_DOD = output.pointer;
 
-	if (WARN_ON(_DOD->type != ACPI_TYPE_PACKAGE) ||
-	    WARN_ON(_DOD->package.count > ARRAY_SIZE(dod->acpiIdList)))
+	if (_DOD->type != ACPI_TYPE_PACKAGE ||
+	    _DOD->package.count > ARRAY_SIZE(dod->acpiIdList))
 		return;
 
 	for (int i = 0; i < _DOD->package.count; i++) {

From 46120745bb4e7e1f09959624716b4c5d6e2c2e9e Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Sun, 15 Feb 2026 22:04:38 -0600
Subject: [PATCH 0044/1303] drm/tiny: sharp-memory: fix pointer error
 dereference

The function devm_drm_dev_alloc() returns a pointer error upon failure
not NULL. Change null check to pointer error check.

Detected by Smatch:
drivers/gpu/drm/tiny/sharp-memory.c:549 sharp_memory_probe() error:
'smd' dereferencing possible ERR_PTR()

Fixes: b8f9f21716fec ("drm/tiny: Add driver for Sharp Memory LCD")
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patch.msgid.link/20260216040438.43702-1-ethantidmore06@gmail.com
---
 drivers/gpu/drm/tiny/sharp-memory.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/tiny/sharp-memory.c b/drivers/gpu/drm/tiny/sharp-memory.c
index 64272cd0f6e2..cbf69460ebf3 100644
--- a/drivers/gpu/drm/tiny/sharp-memory.c
+++ b/drivers/gpu/drm/tiny/sharp-memory.c
@@ -541,8 +541,8 @@ static int sharp_memory_probe(struct spi_device *spi)
 
 	smd = devm_drm_dev_alloc(dev, &sharp_memory_drm_driver,
 				 struct sharp_memory_device, drm);
-	if (!smd)
-		return -ENOMEM;
+	if (IS_ERR(smd))
+		return PTR_ERR(smd);
 
 	spi_set_drvdata(spi, smd);
 

From 1072020685f4b81f6efad3b412cdae0bd62bb043 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 12 Feb 2026 12:41:25 +0100
Subject: [PATCH 0045/1303] irqchip/sifive-plic: Fix frozen interrupt due to
 affinity setting

PLIC ignores interrupt completion message for disabled interrupt, explained
by the specification:

    The PLIC signals it has completed executing an interrupt handler by
    writing the interrupt ID it received from the claim to the
    claim/complete register. The PLIC does not check whether the completion
    ID is the same as the last claim ID for that target. If the completion
    ID does not match an interrupt source that is currently enabled for
    the target, the completion is silently ignored.

This caused problems in the past, because an interrupt can be disabled
while still being handled and plic_irq_eoi() had no effect. That was fixed
by checking if the interrupt is disabled, and if so enable it, before
sending the completion message. That check is done with irqd_irq_disabled().

However, that is not sufficient because the enable bit for the handling
hart can be zero despite irqd_irq_disabled(d) being false. This can happen
when affinity setting is changed while a hart is still handling the
interrupt.

This problem is easily reproducible by dumping a large file to uart (which
generates lots of interrupts) and at the same time keep changing the uart
interrupt's affinity setting. The uart port becomes frozen almost
instantaneously.

Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().

Fixes: cc9f04f9a84f ("irqchip/sifive-plic: Implement irq_set_affinity() for SMP host")
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260212114125.3148067-1-namcao@linutronix.de
---
 drivers/irqchip/irq-sifive-plic.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 60fd8f91762b..70058871d2fb 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -172,8 +172,13 @@ static void plic_irq_disable(struct irq_data *d)
 static void plic_irq_eoi(struct irq_data *d)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+	u32 __iomem *reg;
+	bool enabled;
 
-	if (unlikely(irqd_irq_disabled(d))) {
+	reg = handler->enable_base + (d->hwirq / 32) * sizeof(u32);
+	enabled = readl(reg) & BIT(d->hwirq % 32);
+
+	if (unlikely(!enabled)) {
 		plic_toggle(handler, d->hwirq, 1);
 		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
 		plic_toggle(handler, d->hwirq, 0);

From ce9e40a9a5e5cff0b1b0d2fa582b3d71a8ce68e8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 6 Feb 2026 15:48:16 +0000
Subject: [PATCH 0046/1303] irqchip/gic-v3-its: Limit number of per-device MSIs
 to the range the ITS supports

The ITS driver blindly assumes that EventIDs are in abundant supply, to the
point where it never checks how many the hardware actually supports.

It turns out that some pretty esoteric integrations make it so that only a
few bits are available, all the way down to a single bit.

Enforce the advertised limitation at the point of allocating the device
structure, and hope that the endpoint driver can deal with such limitation.

Fixes: 84a6a2e7fc18d ("irqchip: GICv3: ITS: device allocation and configuration")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Zenghui Yu <zenghui.yu@linux.dev>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260206154816.3582887-1-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 4 ++++
 include/linux/irqchip/arm-gic-v3.h | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2988def30972..a51e8e6a8181 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3475,6 +3475,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	int lpi_base;
 	int nr_lpis;
 	int nr_ites;
+	int id_bits;
 	int sz;
 
 	if (!its_alloc_device_table(its, dev_id))
@@ -3486,7 +3487,10 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	/*
 	 * Even if the device wants a single LPI, the ITT must be
 	 * sized as a power of two (and you need at least one bit...).
+	 * Also honor the ITS's own EID limit.
 	 */
+	id_bits = FIELD_GET(GITS_TYPER_IDBITS, its->typer) + 1;
+	nvecs = min_t(unsigned int, nvecs, BIT(id_bits));
 	nr_ites = max(2, nvecs);
 	sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
 	sz = max(sz, ITS_ITT_ALIGN);
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 70c0948f978e..0225121f3013 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -394,6 +394,7 @@
 #define GITS_TYPER_VLPIS		(1UL << 1)
 #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT	4
 #define GITS_TYPER_ITT_ENTRY_SIZE	GENMASK_ULL(7, 4)
+#define GITS_TYPER_IDBITS		GENMASK_ULL(12, 8)
 #define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS		GENMASK_ULL(17, 13)

From f0617176be5e497b67b3c87bac35b26ebccac499 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 12:04:50 +0100
Subject: [PATCH 0047/1303] irqchip/mmp: Make icu_irq_chip variable static
 const

File-scope 'icu_irq_chip' is not used outside of this unit and is not
modified anywhere, so make it static const to silence sparse warning:

  irq-mmp.c:139:17: warning: symbol 'icu_irq_chip' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260216110449.160277-2-krzysztof.kozlowski@oss.qualcomm.com
---
 drivers/irqchip/irq-mmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 09e640430208..8e210cb451be 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -136,7 +136,7 @@ static void icu_unmask_irq(struct irq_data *d)
 	}
 }
 
-struct irq_chip icu_irq_chip = {
+static const struct irq_chip icu_irq_chip = {
 	.name		= "icu_irq",
 	.irq_mask	= icu_mask_irq,
 	.irq_mask_ack	= icu_mask_ack_irq,

From bffda93a51b40afd67c11bf558dc5aae83ca0943 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Thu, 12 Feb 2026 11:23:27 -0800
Subject: [PATCH 0048/1303] scsi: lpfc: Properly set WC for DPP mapping

Using set_memory_wc() to enable write-combining for the DPP portion of
the MMIO mapping is wrong as set_memory_*() is meant to operate on RAM
only, not MMIO mappings. In fact, as used currently triggers a BUG_ON()
with enabled CONFIG_DEBUG_VIRTUAL.

Simply map the DPP region separately and in addition to the already
existing mappings, avoiding any possible negative side effects for
these.

Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4")
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Reviewed-by: Mathias Krause <minipli@grsecurity.net>
Link: https://patch.msgid.link/20260212192327.141104-1-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_init.c |  2 ++
 drivers/scsi/lpfc/lpfc_sli.c  | 36 +++++++++++++++++++++++++++++------
 drivers/scsi/lpfc/lpfc_sli4.h |  3 +++
 3 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index a116a16c4a6f..b5e53c7d33e7 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -12039,6 +12039,8 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba)
 		iounmap(phba->sli4_hba.conf_regs_memmap_p);
 		if (phba->sli4_hba.dpp_regs_memmap_p)
 			iounmap(phba->sli4_hba.dpp_regs_memmap_p);
+		if (phba->sli4_hba.dpp_regs_memmap_wc_p)
+			iounmap(phba->sli4_hba.dpp_regs_memmap_wc_p);
 		break;
 	case LPFC_SLI_INTF_IF_TYPE_1:
 		break;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 734af3d039f8..690763e0aa55 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -15981,6 +15981,32 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
 	return NULL;
 }
 
+static __maybe_unused void __iomem *
+lpfc_dpp_wc_map(struct lpfc_hba *phba, uint8_t dpp_barset)
+{
+
+	/* DPP region is supposed to cover 64-bit BAR2 */
+	if (dpp_barset != WQ_PCI_BAR_4_AND_5) {
+		lpfc_log_msg(phba, KERN_WARNING, LOG_INIT,
+			     "3273 dpp_barset x%x != WQ_PCI_BAR_4_AND_5\n",
+			     dpp_barset);
+		return NULL;
+	}
+
+	if (!phba->sli4_hba.dpp_regs_memmap_wc_p) {
+		void __iomem *dpp_map;
+
+		dpp_map = ioremap_wc(phba->pci_bar2_map,
+				     pci_resource_len(phba->pcidev,
+						      PCI_64BIT_BAR4));
+
+		if (dpp_map)
+			phba->sli4_hba.dpp_regs_memmap_wc_p = dpp_map;
+	}
+
+	return phba->sli4_hba.dpp_regs_memmap_wc_p;
+}
+
 /**
  * lpfc_modify_hba_eq_delay - Modify Delay Multiplier on EQs
  * @phba: HBA structure that EQs are on.
@@ -16944,9 +16970,6 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 	uint8_t dpp_barset;
 	uint32_t dpp_offset;
 	uint8_t wq_create_version;
-#ifdef CONFIG_X86
-	unsigned long pg_addr;
-#endif
 
 	/* sanity check on queue memory */
 	if (!wq || !cq)
@@ -17132,14 +17155,15 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 
 #ifdef CONFIG_X86
 			/* Enable combined writes for DPP aperture */
-			pg_addr = (unsigned long)(wq->dpp_regaddr) & PAGE_MASK;
-			rc = set_memory_wc(pg_addr, 1);
-			if (rc) {
+			bar_memmap_p = lpfc_dpp_wc_map(phba, dpp_barset);
+			if (!bar_memmap_p) {
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"3272 Cannot setup Combined "
 					"Write on WQ[%d] - disable DPP\n",
 					wq->queue_id);
 				phba->cfg_enable_dpp = 0;
+			} else {
+				wq->dpp_regaddr = bar_memmap_p + dpp_offset;
 			}
 #else
 			phba->cfg_enable_dpp = 0;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index ee58383492b2..b6d90604bb61 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -785,6 +785,9 @@ struct lpfc_sli4_hba {
 	void __iomem *dpp_regs_memmap_p;  /* Kernel memory mapped address for
 					   * dpp registers
 					   */
+	void __iomem *dpp_regs_memmap_wc_p;/* Kernel memory mapped address for
+					    * dpp registers with write combining
+					    */
 	union {
 		struct {
 			/* IF Type 0, BAR 0 PCI cfg space reg mem map */

From 57297736c08233987e5d29ce6584c6ca2a831b12 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Thu, 29 Jan 2026 15:30:39 +0100
Subject: [PATCH 0049/1303] scsi: storvsc: Fix scheduling while atomic on
 PREEMPT_RT

This resolves the follow splat and lock-up when running with PREEMPT_RT
enabled on Hyper-V:

[  415.140818] BUG: scheduling while atomic: stress-ng-iomix/1048/0x00000002
[  415.140822] INFO: lockdep is turned off.
[  415.140823] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec ghash_clmulni_intel aesni_intel rapl binfmt_misc nls_ascii nls_cp437 vfat fat snd_pcm hyperv_drm snd_timer drm_client_lib drm_shmem_helper snd sg soundcore drm_kms_helper pcspkr hv_balloon hv_utils evdev joydev drm configfs efi_pstore nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vsock vmw_vmci efivarfs autofs4 ext4 crc16 mbcache jbd2 sr_mod sd_mod cdrom hv_storvsc serio_raw hid_generic scsi_transport_fc hid_hyperv scsi_mod hid hv_netvsc hyperv_keyboard scsi_common
[  415.140846] Preemption disabled at:
[  415.140847] [<ffffffffc0656171>] storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[  415.140854] CPU: 8 UID: 0 PID: 1048 Comm: stress-ng-iomix Not tainted 6.19.0-rc7 #30 PREEMPT_{RT,(full)}
[  415.140856] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/04/2024
[  415.140857] Call Trace:
[  415.140861]  <TASK>
[  415.140861]  ? storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[  415.140863]  dump_stack_lvl+0x91/0xb0
[  415.140870]  __schedule_bug+0x9c/0xc0
[  415.140875]  __schedule+0xdf6/0x1300
[  415.140877]  ? rtlock_slowlock_locked+0x56c/0x1980
[  415.140879]  ? rcu_is_watching+0x12/0x60
[  415.140883]  schedule_rtlock+0x21/0x40
[  415.140885]  rtlock_slowlock_locked+0x502/0x1980
[  415.140891]  rt_spin_lock+0x89/0x1e0
[  415.140893]  hv_ringbuffer_write+0x87/0x2a0
[  415.140899]  vmbus_sendpacket_mpb_desc+0xb6/0xe0
[  415.140900]  ? rcu_is_watching+0x12/0x60
[  415.140902]  storvsc_queuecommand+0x669/0xbe0 [hv_storvsc]
[  415.140904]  ? HARDIRQ_verbose+0x10/0x10
[  415.140908]  ? __rq_qos_issue+0x28/0x40
[  415.140911]  scsi_queue_rq+0x760/0xd80 [scsi_mod]
[  415.140926]  __blk_mq_issue_directly+0x4a/0xc0
[  415.140928]  blk_mq_issue_direct+0x87/0x2b0
[  415.140931]  blk_mq_dispatch_queue_requests+0x120/0x440
[  415.140933]  blk_mq_flush_plug_list+0x7a/0x1a0
[  415.140935]  __blk_flush_plug+0xf4/0x150
[  415.140940]  __submit_bio+0x2b2/0x5c0
[  415.140944]  ? submit_bio_noacct_nocheck+0x272/0x360
[  415.140946]  submit_bio_noacct_nocheck+0x272/0x360
[  415.140951]  ext4_read_bh_lock+0x3e/0x60 [ext4]
[  415.140995]  ext4_block_write_begin+0x396/0x650 [ext4]
[  415.141018]  ? __pfx_ext4_da_get_block_prep+0x10/0x10 [ext4]
[  415.141038]  ext4_da_write_begin+0x1c4/0x350 [ext4]
[  415.141060]  generic_perform_write+0x14e/0x2c0
[  415.141065]  ext4_buffered_write_iter+0x6b/0x120 [ext4]
[  415.141083]  vfs_write+0x2ca/0x570
[  415.141087]  ksys_write+0x76/0xf0
[  415.141089]  do_syscall_64+0x99/0x1490
[  415.141093]  ? rcu_is_watching+0x12/0x60
[  415.141095]  ? finish_task_switch.isra.0+0xdf/0x3d0
[  415.141097]  ? rcu_is_watching+0x12/0x60
[  415.141098]  ? lock_release+0x1f0/0x2a0
[  415.141100]  ? rcu_is_watching+0x12/0x60
[  415.141101]  ? finish_task_switch.isra.0+0xe4/0x3d0
[  415.141103]  ? rcu_is_watching+0x12/0x60
[  415.141104]  ? __schedule+0xb34/0x1300
[  415.141106]  ? hrtimer_try_to_cancel+0x1d/0x170
[  415.141109]  ? do_nanosleep+0x8b/0x160
[  415.141111]  ? hrtimer_nanosleep+0x89/0x100
[  415.141114]  ? __pfx_hrtimer_wakeup+0x10/0x10
[  415.141116]  ? xfd_validate_state+0x26/0x90
[  415.141118]  ? rcu_is_watching+0x12/0x60
[  415.141120]  ? do_syscall_64+0x1e0/0x1490
[  415.141121]  ? do_syscall_64+0x1e0/0x1490
[  415.141123]  ? rcu_is_watching+0x12/0x60
[  415.141124]  ? do_syscall_64+0x1e0/0x1490
[  415.141125]  ? do_syscall_64+0x1e0/0x1490
[  415.141127]  ? irqentry_exit+0x140/0x7e0
[  415.141129]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

get_cpu() disables preemption while the spinlock hv_ringbuffer_write is
using is converted to an rt-mutex under PREEMPT_RT.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-by: Florian Bezdeka <florian.bezdeka@siemens.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://patch.msgid.link/0c7fb5cd-fb21-4760-8593-e04bade84744@siemens.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/storvsc_drv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 19e18939d3a5..19ff0004e259 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1855,8 +1855,9 @@ static enum scsi_qc_status storvsc_queuecommand(struct Scsi_Host *host,
 	cmd_request->payload_sz = payload_sz;
 
 	/* Invokes the vsc to start an IO */
-	ret = storvsc_do_io(dev, cmd_request, get_cpu());
-	put_cpu();
+	migrate_disable();
+	ret = storvsc_do_io(dev, cmd_request, smp_processor_id());
+	migrate_enable();
 
 	if (ret)
 		scsi_dma_unmap(scmnd);

From 2e6b5cd6a4b37a95b78cf8c39a979b58c915c8ed Mon Sep 17 00:00:00 2001
From: Alexey Charkov <alchark@flipper.net>
Date: Mon, 9 Feb 2026 19:17:34 +0400
Subject: [PATCH 0050/1303] scsi: ufs: core: Fix RPMB region size detection for
 UFS 2.2

Older UFS spec devices (2.2 and earlier) do not expose per-region RPMB
sizes, as only one RPMB region is supported. In such cases, the size of the
single RPMB region can be deduced from the Logical Block Count and Logical
Block Size fields in the RPMB Unit Descriptor.

Add a fallback mechanism to calculate the RPMB region size from these
fields if the device implements an older spec, so that the RPMB driver can
work with such devices - otherwise it silently skips the whole RPMB.

        Section 14.1.4.6 (RPMB Unit Descriptor)

Link: https://www.jedec.org/system/files/docs/JESD220C-2_2.pdf
Cc: stable@vger.kernel.org
Fixes: b06b8c421485 ("scsi: ufs: core: Add OP-TEE based RPMB driver for UFS devices")
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Alexey Charkov <alchark@flipper.net>
Link: https://patch.msgid.link/20260209-ufs-rpmb-v3-1-b1804e71bd38@flipper.net
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8349fe2090db..12f1bdc70587 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -23,6 +23,7 @@
 #include <linux/pm_opp.h>
 #include <linux/regulator/consumer.h>
 #include <linux/sched/clock.h>
+#include <linux/sizes.h>
 #include <linux/iopoll.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_dbg.h>
@@ -5248,6 +5249,25 @@ static void ufshcd_lu_init(struct ufs_hba *hba, struct scsi_device *sdev)
 		hba->dev_info.rpmb_region_size[1] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION1_SIZE];
 		hba->dev_info.rpmb_region_size[2] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION2_SIZE];
 		hba->dev_info.rpmb_region_size[3] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION3_SIZE];
+
+		if (hba->dev_info.wspecversion <= 0x0220) {
+			/*
+			 * These older spec chips have only one RPMB region,
+			 * sized between 128 kB minimum and 16 MB maximum.
+			 * No per region size fields are provided (respective
+			 * REGIONX_SIZE fields always contain zeros), so get
+			 * it from the logical block count and size fields for
+			 * compatibility
+			 *
+			 * (See JESD220C-2_2 Section 14.1.4.6
+			 * RPMB Unit Descriptor,* offset 13h, 4 bytes)
+			 */
+			hba->dev_info.rpmb_region_size[0] =
+				(get_unaligned_be64(desc_buf
+					+ RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_COUNT)
+				<< desc_buf[RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_SIZE])
+				/ SZ_128K;
+		}
 	}
 
 

From 70ca8caa96ce473647054f5c7b9dab5423902402 Mon Sep 17 00:00:00 2001
From: Tomas Henzl <thenzl@redhat.com>
Date: Tue, 10 Feb 2026 20:18:50 +0100
Subject: [PATCH 0051/1303] scsi: ses: Fix devices attaching to different hosts

On a multipath SAS system some devices don't end up with correct symlinks
from the SCSI device to its enclosure. Some devices even have enclosure
links pointing to enclosures attached to different SCSI hosts.

ses_match_to_enclosure() calls enclosure_for_each_device() which iterates
over all enclosures on the system, not just enclosures attached to the
current SCSI host.

Replace the iteration with a direct call to ses_enclosure_find_by_addr().

Reviewed-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
Link: https://patch.msgid.link/20260210191850.36784-1-thenzl@redhat.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ses.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 789b170da652..98a7367d2f20 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -528,9 +528,8 @@ struct efd {
 };
 
 static int ses_enclosure_find_by_addr(struct enclosure_device *edev,
-				      void *data)
+				      struct efd *efd)
 {
-	struct efd *efd = data;
 	int i;
 	struct ses_component *scomp;
 
@@ -683,7 +682,7 @@ static void ses_match_to_enclosure(struct enclosure_device *edev,
 	if (efd.addr) {
 		efd.dev = &sdev->sdev_gendev;
 
-		enclosure_for_each_device(ses_enclosure_find_by_addr, &efd);
+		ses_enclosure_find_by_addr(edev, &efd);
 	}
 }
 

From 5b313760059c9df7d60aba7832279bcb81b4aec0 Mon Sep 17 00:00:00 2001
From: Won Jung <wone.jung@samsung.com>
Date: Wed, 11 Feb 2026 15:01:05 +0900
Subject: [PATCH 0052/1303] scsi: ufs: core: Reset urgent_bkops_lvl to allow
 runtime PM power mode

Ensures that UFS Runtime PM can achieve power saving after System PM
suspend by resetting hba->urgent_bkops_lvl. Also modify the
ufshcd_bkops_exception_event_handler to avoid setting urgent_bkops_lvl when
status is 0, which helps maintain optimal power management.

On UFS devices supporting UFSHCD_CAP_AUTO_BKOPS_SUSPEND, a BKOPS exception
event can lead to a situation where UFS Runtime PM can't enter low-power
mode states even after the BKOPS exception has been resolved.

BKOPS exception with bkops status 0 occurs, the driver logs:

 "ufshcd_bkops_exception_event_handler: device raised urgent BKOPS exception for bkops status 0"

When a BKOPS exception occurs, ufshcd_bkops_exception_event_handler() reads
the BKOPS status and sets hba->urgent_bkops_lvl to BKOPS_STATUS_NO_OP(0).
This allows the device to perform Runtime PM without changing the UFS power
mode.  (__ufshcd_wl_suspend(hba, UFS_RUNTIME_PM))

During system PM suspend, ufshcd_disable_auto_bkops() is called, disabling
auto bkops. After UFS System PM Resume, when runtime PM attempts to suspend
again, ufshcd_urgent_bkops() is invoked. Since hba->urgent_bkops_lvl
remains at BKOPS_STATUS_NO_OP(0), ufshcd_enable_auto_bkops() is triggered.

However, in ufshcd_bkops_ctrl(), the driver compares the current BKOPS
status with hba->urgent_bkops_lvl, and only enables auto bkops if
curr_status >= hba->urgent_bkops_lvl.  Since both values are 0, the
condition is met

As a result, __ufshcd_wl_suspend(hba, UFS_RUNTIME_PM) skips power mode
transitions and remains in an active state, preventing power saving even
though no urgent BKOPS condition exists.

Signed-off-by: Won Jung <wone.jung@samsung.com>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Link: https://patch.msgid.link/1891546521.01770806581968.JavaMail.epsvc@epcpadp2new
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 12f1bdc70587..3bbc2b51c87b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5982,6 +5982,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 
 	hba->auto_bkops_enabled = false;
 	trace_ufshcd_auto_bkops_state(hba, "Disabled");
+	hba->urgent_bkops_lvl = BKOPS_STATUS_PERF_IMPACT;
 	hba->is_urgent_bkops_lvl_checked = false;
 out:
 	return err;
@@ -6085,7 +6086,7 @@ static void ufshcd_bkops_exception_event_handler(struct ufs_hba *hba)
 	 * impacted or critical. Handle these device by determining their urgent
 	 * bkops status at runtime.
 	 */
-	if (curr_status < BKOPS_STATUS_PERF_IMPACT) {
+	if ((curr_status > BKOPS_STATUS_NO_OP) && (curr_status < BKOPS_STATUS_PERF_IMPACT)) {
 		dev_err(hba->dev, "%s: device raised urgent BKOPS exception for bkops status %d\n",
 				__func__, curr_status);
 		/* update the current status as the urgent bkops level */

From fa96392ebebc8fade2b878acb14cce0f71016503 Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Thu, 12 Feb 2026 12:30:26 +0530
Subject: [PATCH 0053/1303] scsi: mpi3mr: Add NULL checks when resetting
 request and reply queues

The driver encountered a crash during resource cleanup when the reply and
request queues were NULL due to freed memory.  This issue occurred when the
creation of reply or request queues failed, and the driver freed the memory
first, but attempted to mem set the content of the freed memory, leading to
a system crash.

Add NULL pointer checks for reply and request queues before accessing the
reply/request memory during cleanup

Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://patch.msgid.link/20260212070026.30263-1-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr_fw.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 1cfbdb773353..04d4a2aea7d7 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -4806,21 +4806,25 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc)
 	}
 
 	for (i = 0; i < mrioc->num_queues; i++) {
-		mrioc->op_reply_qinfo[i].qid = 0;
-		mrioc->op_reply_qinfo[i].ci = 0;
-		mrioc->op_reply_qinfo[i].num_replies = 0;
-		mrioc->op_reply_qinfo[i].ephase = 0;
-		atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0);
-		atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0);
-		mpi3mr_memset_op_reply_q_buffers(mrioc, i);
+		if (mrioc->op_reply_qinfo) {
+			mrioc->op_reply_qinfo[i].qid = 0;
+			mrioc->op_reply_qinfo[i].ci = 0;
+			mrioc->op_reply_qinfo[i].num_replies = 0;
+			mrioc->op_reply_qinfo[i].ephase = 0;
+			atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0);
+			atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0);
+			mpi3mr_memset_op_reply_q_buffers(mrioc, i);
+		}
 
-		mrioc->req_qinfo[i].ci = 0;
-		mrioc->req_qinfo[i].pi = 0;
-		mrioc->req_qinfo[i].num_requests = 0;
-		mrioc->req_qinfo[i].qid = 0;
-		mrioc->req_qinfo[i].reply_qid = 0;
-		spin_lock_init(&mrioc->req_qinfo[i].q_lock);
-		mpi3mr_memset_op_req_q_buffers(mrioc, i);
+		if (mrioc->req_qinfo) {
+			mrioc->req_qinfo[i].ci = 0;
+			mrioc->req_qinfo[i].pi = 0;
+			mrioc->req_qinfo[i].num_requests = 0;
+			mrioc->req_qinfo[i].qid = 0;
+			mrioc->req_qinfo[i].reply_qid = 0;
+			spin_lock_init(&mrioc->req_qinfo[i].q_lock);
+			mpi3mr_memset_op_req_q_buffers(mrioc, i);
+		}
 	}
 
 	atomic_set(&mrioc->pend_large_data_sz, 0);

From 38353c26db28efd984f51d426eac2396d299cca7 Mon Sep 17 00:00:00 2001
From: Salomon Dushimirimana <salomondush@google.com>
Date: Fri, 13 Feb 2026 19:28:06 +0000
Subject: [PATCH 0054/1303] scsi: pm8001: Fix use-after-free in
 pm8001_queue_command()

Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors
pm8001_queue_command(), however it introduces a potential cause of a double
free scenario when it changes the function to return -ENODEV in case of phy
down/device gone state.

In this path, pm8001_queue_command() updates task status and calls
task_done to indicate to upper layer that the task has been handled.
However, this also frees the underlying SAS task. A -ENODEV is then
returned to the caller. When libsas sas_ata_qc_issue() receives this error
value, it assumes the task wasn't handled/queued by LLDD and proceeds to
clean up and free the task again, resulting in a double free.

Since pm8001_queue_command() handles the SAS task in this case, it should
return 0 to the caller indicating that the task has been handled.

Fixes: e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()")
Signed-off-by: Salomon Dushimirimana <salomondush@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://patch.msgid.link/20260213192806.439432-1-salomondush@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_sas.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 6a8d35aea93a..645524f3fe2d 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -525,8 +525,9 @@ int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags)
 		} else {
 			task->task_done(task);
 		}
-		rc = -ENODEV;
-		goto err_out;
+		spin_unlock_irqrestore(&pm8001_ha->lock, flags);
+		pm8001_dbg(pm8001_ha, IO, "pm8001_task_exec device gone\n");
+		return 0;
 	}
 
 	ccb = pm8001_ccb_alloc(pm8001_ha, pm8001_dev, task);

From af3973e7b4fd91e6884b312526168869fb013d68 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Mon, 16 Feb 2026 15:10:55 +0100
Subject: [PATCH 0055/1303] scsi: snic: Remove unused linkstatus

The (struct vnic_dev).linkstatus buffer is freed in svnic_dev_unregister()
and referenced in svnic_dev_link_status() but never alloc'd. This means
(struct vnic_dev).linkstatus is always null and the dealloc the reference
in svnic_dev_link_status() is dead code.

Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Acked-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://patch.msgid.link/20260216141056.59429-2-fourier.thomas@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/snic/vnic_dev.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/scsi/snic/vnic_dev.c b/drivers/scsi/snic/vnic_dev.c
index 760f3f22095c..c4df0b17c86c 100644
--- a/drivers/scsi/snic/vnic_dev.c
+++ b/drivers/scsi/snic/vnic_dev.c
@@ -42,8 +42,6 @@ struct vnic_dev {
 	struct vnic_devcmd_notify *notify;
 	struct vnic_devcmd_notify notify_copy;
 	dma_addr_t notify_pa;
-	u32 *linkstatus;
-	dma_addr_t linkstatus_pa;
 	struct vnic_stats *stats;
 	dma_addr_t stats_pa;
 	struct vnic_devcmd_fw_info *fw_info;
@@ -650,8 +648,6 @@ int svnic_dev_init(struct vnic_dev *vdev, int arg)
 
 int svnic_dev_link_status(struct vnic_dev *vdev)
 {
-	if (vdev->linkstatus)
-		return *vdev->linkstatus;
 
 	if (!vnic_dev_notify_ready(vdev))
 		return 0;
@@ -686,11 +682,6 @@ void svnic_dev_unregister(struct vnic_dev *vdev)
 				sizeof(struct vnic_devcmd_notify),
 				vdev->notify,
 				vdev->notify_pa);
-		if (vdev->linkstatus)
-			dma_free_coherent(&vdev->pdev->dev,
-				sizeof(u32),
-				vdev->linkstatus,
-				vdev->linkstatus_pa);
 		if (vdev->stats)
 			dma_free_coherent(&vdev->pdev->dev,
 				sizeof(struct vnic_stats),

From 97af85787c1964a7e7b146c5d4e021f089af47ea Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Feb 2026 12:46:58 -0800
Subject: [PATCH 0056/1303] scsi: snic: MAINTAINERS: Update snic maintainers

Update snic maintainers.

Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://patch.msgid.link/20260217204658.5465-1-kartilak@cisco.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 70292bd3ed71..0900af786cce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6115,6 +6115,7 @@ F:	drivers/scsi/fnic/
 
 CISCO SCSI HBA DRIVER
 M:	Karan Tilak Kumar <kartilak@cisco.com>
+M:	Narsimhulu Musini <nmusini@cisco.com>
 M:	Sesidhar Baddela <sebaddel@cisco.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported

From a41dbf5e004edbe1260883c43a8bd134d9cb0c1c Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Sat, 14 Feb 2026 16:22:13 +0100
Subject: [PATCH 0057/1303] mount: hold namespace_sem across copy in
 create_new_namespace()

Fix an oversight when creating a new mount namespace. If someone had the
bright idea to make the real rootfs a shared or dependent mount and it
is later copied the copy will become a peer of the old real rootfs mount
or a dependent mount of it. The namespace semaphore is dropped and we
use mount lock exact to lock the new real root mount. If that fails or
the subsequent do_loopback() fails we rely on the copy of the real root
mount to be cleaned up by path_put(). The problem is that this doesn't
deal with mount propagation and will leave the mounts linked in the
propagation lists.

When creating a new mount namespace create_new_namespace() first
acquires namespace_sem to clone the nullfs root, drops it, then
reacquires it via LOCK_MOUNT_EXACT which takes inode_lock first to
respect the inode_lock -> namespace_sem lock ordering. This
drop-and-reacquire pattern is fragile and was the source of the
propagation cleanup bug fixed in the preceding commit.

Extend lock_mount_exact() with a copy_mount mode that clones the mount
under the locks atomically. When copy_mount is true, path_overmounted()
is skipped since we're copying the mount, not mounting on top of it -
the nullfs root always has rootfs mounted on top so the check would
always fail. If clone_mnt() fails after get_mountpoint() has pinned the
mountpoint, __unlock_mount() is used to properly unpin the mountpoint
and release both locks.

This allows create_new_namespace() to use LOCK_MOUNT_EXACT_COPY which
takes inode_lock and namespace_sem once and holds them throughout the
clone and subsequent mount operations, eliminating the
drop-and-reacquire pattern entirely.

Reported-by: syzbot+a89f9434fb5a001ccd58@syzkaller.appspotmail.com
Fixes: 9b8a0ba68246 ("mount: add OPEN_TREE_NAMESPACE") # mainline only
Link: https://lore.kernel.org/699047f6.050a0220.2757fb.0024.GAE@google.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 117 +++++++++++++++++++++++++------------------------
 1 file changed, 60 insertions(+), 57 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 90700df65f0d..022e59afcb5e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2791,7 +2791,8 @@ static inline void unlock_mount(struct pinned_mountpoint *m)
 }
 
 static void lock_mount_exact(const struct path *path,
-			     struct pinned_mountpoint *mp);
+			     struct pinned_mountpoint *mp, bool copy_mount,
+			     unsigned int copy_flags);
 
 #define LOCK_MOUNT_MAYBE_BENEATH(mp, path, beneath) \
 	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
@@ -2799,7 +2800,10 @@ static void lock_mount_exact(const struct path *path,
 #define LOCK_MOUNT(mp, path) LOCK_MOUNT_MAYBE_BENEATH(mp, (path), false)
 #define LOCK_MOUNT_EXACT(mp, path) \
 	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
-	lock_mount_exact((path), &mp)
+	lock_mount_exact((path), &mp, false, 0)
+#define LOCK_MOUNT_EXACT_COPY(mp, path, copy_flags) \
+	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
+	lock_mount_exact((path), &mp, true, (copy_flags))
 
 static int graft_tree(struct mount *mnt, const struct pinned_mountpoint *mp)
 {
@@ -3073,16 +3077,13 @@ static struct file *open_detached_copy(struct path *path, unsigned int flags)
 	return file;
 }
 
-DEFINE_FREE(put_empty_mnt_ns, struct mnt_namespace *,
-	    if (!IS_ERR_OR_NULL(_T)) free_mnt_ns(_T))
-
 static struct mnt_namespace *create_new_namespace(struct path *path, unsigned int flags)
 {
-	struct mnt_namespace *new_ns __free(put_empty_mnt_ns) = NULL;
-	struct path to_path __free(path_put) = {};
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct user_namespace *user_ns = current_user_ns();
-	struct mount *new_ns_root;
+	struct mnt_namespace *new_ns;
+	struct mount *new_ns_root, *old_ns_root;
+	struct path to_path;
 	struct mount *mnt;
 	unsigned int copy_flags = 0;
 	bool locked = false;
@@ -3094,71 +3095,63 @@ static struct mnt_namespace *create_new_namespace(struct path *path, unsigned in
 	if (IS_ERR(new_ns))
 		return ERR_CAST(new_ns);
 
-	scoped_guard(namespace_excl) {
-		new_ns_root = clone_mnt(ns->root, ns->root->mnt.mnt_root, copy_flags);
-		if (IS_ERR(new_ns_root))
-			return ERR_CAST(new_ns_root);
+	old_ns_root = ns->root;
+	to_path.mnt = &old_ns_root->mnt;
+	to_path.dentry = old_ns_root->mnt.mnt_root;
 
-		/*
-		 * If the real rootfs had a locked mount on top of it somewhere
-		 * in the stack, lock the new mount tree as well so it can't be
-		 * exposed.
-		 */
-		mnt = ns->root;
-		while (mnt->overmount) {
-			mnt = mnt->overmount;
-			if (mnt->mnt.mnt_flags & MNT_LOCKED)
-				locked = true;
-		}
+	VFS_WARN_ON_ONCE(old_ns_root->mnt.mnt_sb->s_type != &nullfs_fs_type);
+
+	LOCK_MOUNT_EXACT_COPY(mp, &to_path, copy_flags);
+	if (IS_ERR(mp.parent)) {
+		free_mnt_ns(new_ns);
+		return ERR_CAST(mp.parent);
+	}
+	new_ns_root = mp.parent;
+
+	/*
+	 * If the real rootfs had a locked mount on top of it somewhere
+	 * in the stack, lock the new mount tree as well so it can't be
+	 * exposed.
+	 */
+	mnt = old_ns_root;
+	while (mnt->overmount) {
+		mnt = mnt->overmount;
+		if (mnt->mnt.mnt_flags & MNT_LOCKED)
+			locked = true;
 	}
 
 	/*
-	 * We dropped the namespace semaphore so we can actually lock
-	 * the copy for mounting. The copied mount isn't attached to any
-	 * mount namespace and it is thus excluded from any propagation.
-	 * So realistically we're isolated and the mount can't be
-	 * overmounted.
-	 */
-
-	/* Borrow the reference from clone_mnt(). */
-	to_path.mnt = &new_ns_root->mnt;
-	to_path.dentry = dget(new_ns_root->mnt.mnt_root);
-
-	/* Now lock for actual mounting. */
-	LOCK_MOUNT_EXACT(mp, &to_path);
-	if (unlikely(IS_ERR(mp.parent)))
-		return ERR_CAST(mp.parent);
-
-	/*
-	 * We don't emulate unshare()ing a mount namespace. We stick to the
-	 * restrictions of creating detached bind-mounts. It has a lot
-	 * saner and simpler semantics.
+	 * We don't emulate unshare()ing a mount namespace. We stick
+	 * to the restrictions of creating detached bind-mounts. It
+	 * has a lot saner and simpler semantics.
 	 */
 	mnt = __do_loopback(path, flags, copy_flags);
-	if (IS_ERR(mnt))
-		return ERR_CAST(mnt);
-
 	scoped_guard(mount_writer) {
+		if (IS_ERR(mnt)) {
+			emptied_ns = new_ns;
+			umount_tree(new_ns_root, 0);
+			return ERR_CAST(mnt);
+		}
+
 		if (locked)
 			mnt->mnt.mnt_flags |= MNT_LOCKED;
 		/*
-		 * Now mount the detached tree on top of the copy of the
-		 * real rootfs we created.
+		 * now mount the detached tree on top of the copy
+		 * of the real rootfs we created.
 		 */
 		attach_mnt(mnt, new_ns_root, mp.mp);
 		if (user_ns != ns->user_ns)
 			lock_mnt_tree(new_ns_root);
 	}
 
-	/* Add all mounts to the new namespace. */
-	for (struct mount *p = new_ns_root; p; p = next_mnt(p, new_ns_root)) {
-		mnt_add_to_ns(new_ns, p);
+	for (mnt = new_ns_root; mnt; mnt = next_mnt(mnt, new_ns_root)) {
+		mnt_add_to_ns(new_ns, mnt);
 		new_ns->nr_mounts++;
 	}
 
-	new_ns->root = real_mount(no_free_ptr(to_path.mnt));
+	new_ns->root = new_ns_root;
 	ns_tree_add_raw(new_ns);
-	return no_free_ptr(new_ns);
+	return new_ns;
 }
 
 static struct file *open_new_namespace(struct path *path, unsigned int flags)
@@ -3840,16 +3833,20 @@ static int do_new_mount(const struct path *path, const char *fstype,
 }
 
 static void lock_mount_exact(const struct path *path,
-			     struct pinned_mountpoint *mp)
+			     struct pinned_mountpoint *mp, bool copy_mount,
+			     unsigned int copy_flags)
 {
 	struct dentry *dentry = path->dentry;
 	int err;
 
+	/* Assert that inode_lock() locked the correct inode. */
+	VFS_WARN_ON_ONCE(copy_mount && !path_mounted(path));
+
 	inode_lock(dentry->d_inode);
 	namespace_lock();
 	if (unlikely(cant_mount(dentry)))
 		err = -ENOENT;
-	else if (path_overmounted(path))
+	else if (!copy_mount && path_overmounted(path))
 		err = -EBUSY;
 	else
 		err = get_mountpoint(dentry, mp);
@@ -3857,9 +3854,15 @@ static void lock_mount_exact(const struct path *path,
 		namespace_unlock();
 		inode_unlock(dentry->d_inode);
 		mp->parent = ERR_PTR(err);
-	} else {
-		mp->parent = real_mount(path->mnt);
+		return;
 	}
+
+	if (copy_mount)
+		mp->parent = clone_mnt(real_mount(path->mnt), dentry, copy_flags);
+	else
+		mp->parent = real_mount(path->mnt);
+	if (unlikely(IS_ERR(mp->parent)))
+		__unlock_mount(mp);
 }
 
 int finish_automount(struct vfsmount *__m, const struct path *path)

From 4a403d7aa9074f527f064ef0806aaab38d14b07c Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 29 Jan 2026 14:52:22 +0100
Subject: [PATCH 0058/1303] namespace: fix proc mount iteration

The m->index isn't updated when m->show() overflows and retains its
value before the current mount causing a restart to start at the same
value. If that happens in short order to due a quickly expanding mount
table this would cause the same mount to be shown again and again.

Ensure that *pos always equals the mount id of the mount that was
returned by start/next. On restart after overflow mnt_find_id_at(*pos)
finds the exact mount. This should avoid duplicates, avoid skips and
should handle concurrent modification just fine.

Cc: <stable@vger.kernel.org>
Fixed: 2eea9ce4310d8 ("mounts: keep list of mounts in an rbtree")
Link: https://patch.msgid.link/20260129-geleckt-treuhand-4bb940acacd9@brauner
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 022e59afcb5e..31483c66ace8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1531,23 +1531,33 @@ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct mount *mnt;
 
 	down_read(&namespace_sem);
 
-	return mnt_find_id_at(p->ns, *pos);
+	mnt = mnt_find_id_at(p->ns, *pos);
+	if (mnt)
+		*pos = mnt->mnt_id_unique;
+	return mnt;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct mount *next = NULL, *mnt = v;
+	struct mount *mnt = v;
 	struct rb_node *node = rb_next(&mnt->mnt_node);
 
-	++*pos;
 	if (node) {
-		next = node_to_mount(node);
+		struct mount *next = node_to_mount(node);
 		*pos = next->mnt_id_unique;
+		return next;
 	}
-	return next;
+
+	/*
+	 * No more mounts. Set pos past current mount's ID so that if
+	 * iteration restarts, mnt_find_id_at() returns NULL.
+	 */
+	*pos = mnt->mnt_id_unique + 1;
+	return NULL;
 }
 
 static void m_stop(struct seq_file *m, void *v)

From ef0b64741a53e47ce8022c973099e969094aa536 Mon Sep 17 00:00:00 2001
From: Jori Koolstra <jkoolstra@xs4all.nl>
Date: Mon, 1 Dec 2025 13:23:38 +0100
Subject: [PATCH 0059/1303] minix: Correct errno in minix_new_inode

The cases (!j || j > sbi->s_ninodes) can never occur unless the
filesystem is broken, so this should not return ENOSPC, but
EFSCORRUPTED.

Signed-off-by: Jori Koolstra <jkoolstra@xs4all.nl>
Link: https://patch.msgid.link/20251201122338.90568-1-jkoolstra@xs4all.nl
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/minix/bitmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c
index 7da66ca184f4..abec438330a7 100644
--- a/fs/minix/bitmap.c
+++ b/fs/minix/bitmap.c
@@ -247,7 +247,7 @@ struct inode *minix_new_inode(const struct inode *dir, umode_t mode)
 	j += i * bits_per_zone;
 	if (!j || j > sbi->s_ninodes) {
 		iput(inode);
-		return ERR_PTR(-ENOSPC);
+		return ERR_PTR(-EFSCORRUPTED);
 	}
 	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
 	inode->i_ino = j;

From 6c4b2243cb6c0755159bd567130d5e12e7b10d9f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 7 Feb 2026 08:25:24 +0000
Subject: [PATCH 0060/1303] unshare: fix unshare_fs() handling

There's an unpleasant corner case in unshare(2), when we have a
CLONE_NEWNS in flags and current->fs hadn't been shared at all; in that
case copy_mnt_ns() gets passed current->fs instead of a private copy,
which causes interesting warts in proof of correctness]

> I guess if private means fs->users == 1, the condition could still be true.

Unfortunately, it's worse than just a convoluted proof of correctness.
Consider the case when we have CLONE_NEWCGROUP in addition to CLONE_NEWNS
(and current->fs->users == 1).

We pass current->fs to copy_mnt_ns(), all right.  Suppose it succeeds and
flips current->fs->{pwd,root} to corresponding locations in the new namespace.
Now we proceed to copy_cgroup_ns(), which fails (e.g. with -ENOMEM).
We call put_mnt_ns() on the namespace created by copy_mnt_ns(), it's
destroyed and its mount tree is dissolved, but...  current->fs->root and
current->fs->pwd are both left pointing to now detached mounts.

They are pinning those, so it's not a UAF, but it leaves the calling
process with unshare(2) failing with -ENOMEM _and_ leaving it with
pwd and root on detached isolated mounts.  The last part is clearly a bug.

There is other fun related to that mess (races with pivot_root(), including
the one between pivot_root() and fork(), of all things), but this one
is easy to isolate and fix - treat CLONE_NEWNS as "allocate a new
fs_struct even if it hadn't been shared in the first place".  Sure, we could
go for something like "if both CLONE_NEWNS *and* one of the things that might
end up failing after copy_mnt_ns() call in create_new_namespaces() are set,
force allocation of new fs_struct", but let's keep it simple - the cost
of copy_fs_struct() is trivial.

Another benefit is that copy_mnt_ns() with CLONE_NEWNS *always* gets
a freshly allocated fs_struct, yet to be attached to anything.  That
seriously simplifies the analysis...

FWIW, that bug had been there since the introduction of unshare(2) ;-/

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://patch.msgid.link/20260207082524.GE3183987@ZenIV
Tested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/fork.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index e832da9d15a4..65113a304518 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3085,7 +3085,7 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 		return 0;
 
 	/* don't need lock here; in the worst case we'll do useless copy */
-	if (fs->users == 1)
+	if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1)
 		return 0;
 
 	*new_fsp = copy_fs_struct(fs);

From 7be41fb00e2c2a823f271a8318b453ca11812f1e Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 29 Oct 2025 08:30:11 +0300
Subject: [PATCH 0061/1303] accel: ethosu: Fix shift overflow in cmd_to_addr()

The "((cmd[0] & 0xff0000) << 16)" shift is zero.  This was intended
to be (((u64)cmd[0] & 0xff0000) << 16).  Move the cast to the correct
location.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/aQGmY64tWcwOGFP4@stanley.mountain
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/accel/ethosu/ethosu_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index 473b5f5d7514..7b073116314b 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -154,7 +154,7 @@ static void cmd_state_init(struct cmd_state *st)
 
 static u64 cmd_to_addr(u32 *cmd)
 {
-	return ((u64)((cmd[0] & 0xff0000) << 16)) | cmd[1];
+	return (((u64)cmd[0] & 0xff0000) << 16) | cmd[1];
 }
 
 static u64 dma_length(struct ethosu_validated_cmdstream_info *info,

From 249013e673fce3506c61063c7cbedd75b4c668d8 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 22:09:21 -0800
Subject: [PATCH 0062/1303] fsnotify: drop unused helper

Remove this helper now that all users have been converted to
fserror_report_metadata as of 7.0-rc1.

Cc: jack@suse.cz
Cc: amir73il@gmail.com
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/177148129543.716249.980530449513340111.stgit@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 28a9cb13fbfa..079c18bcdbde 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -495,19 +495,6 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
-static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
-				    int error)
-{
-	struct fs_error_report report = {
-		.error = error,
-		.inode = inode,
-		.sb = sb,
-	};
-
-	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
-			NULL, NULL, NULL, 0);
-}
-
 static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt)
 {
 	fsnotify_mnt(FS_MNT_ATTACH, ns, mnt);

From 294f54f849d846f4643a67db9b41b63867dc8bfe Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 22:09:37 -0800
Subject: [PATCH 0063/1303] fserror: fix lockdep complaint when igrabbing inode

Christoph Hellwig reported a lockdep splat in generic/108:

 ================================
 WARNING: inconsistent lock state
 6.19.0+ #4827 Tainted: G                 N
 --------------------------------
 inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
 swapper/1/0 [HC1[1]:SC0[0]:HE0:SE1] takes:
 ffff88811ed1b140 (&sb->s_type->i_lock_key#33){?.+.}-{3:3}, at: igrab+0x1a/0xb0
 {HARDIRQ-ON-W} state was registered at:
   lock_acquire+0xca/0x2c0
   _raw_spin_lock+0x2e/0x40
   unlock_new_inode+0x2c/0xc0
   xfs_iget+0xcf4/0x1080
   xfs_trans_metafile_iget+0x3d/0x100
   xfs_metafile_iget+0x2b/0x50
   xfs_mount_setup_metadir+0x20/0x60
   xfs_mountfs+0x457/0xa60
   xfs_fs_fill_super+0x6b3/0xa90
   get_tree_bdev_flags+0x13c/0x1e0
   vfs_get_tree+0x27/0xe0
   vfs_cmd_create+0x54/0xe0
   __do_sys_fsconfig+0x309/0x620
   do_syscall_64+0x8b/0xf80
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
 irq event stamp: 139080
 hardirqs last  enabled at (139079): [<ffffffff813a923c>] do_idle+0x1ec/0x270
 hardirqs last disabled at (139080): [<ffffffff828a8d09>] common_interrupt+0x19/0xe0
 softirqs last  enabled at (139032): [<ffffffff8134a853>] __irq_exit_rcu+0xc3/0x120
 softirqs last disabled at (139025): [<ffffffff8134a853>] __irq_exit_rcu+0xc3/0x120

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&sb->s_type->i_lock_key#33);
   <Interrupt>
     lock(&sb->s_type->i_lock_key#33);

  *** DEADLOCK ***

 1 lock held by swapper/1/0:
  #0: ffff8881052c81a0 (&vblk->vqs[i].lock){-.-.}-{3:3}, at: virtblk_done+0x4b/0x110

 stack backtrace:
 CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Tainted: G                 N  6.19.0+ #4827 PREEMPT(full)
 Tainted: [N]=TEST
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x5b/0x80
  print_usage_bug.part.0+0x22c/0x2c0
  mark_lock+0xa6f/0xe90
  __lock_acquire+0x10b6/0x25e0
  lock_acquire+0xca/0x2c0
  _raw_spin_lock+0x2e/0x40
  igrab+0x1a/0xb0
  fserror_report+0x135/0x260
  iomap_finish_ioend_buffered+0x170/0x210
  clone_endio+0x8f/0x1c0
  blk_update_request+0x1e4/0x4d0
  blk_mq_end_request+0x1b/0x100
  virtblk_done+0x6f/0x110
  vring_interrupt+0x59/0x80
  __handle_irq_event_percpu+0x8a/0x2e0
  handle_irq_event+0x33/0x70
  handle_edge_irq+0xdd/0x1e0
  __common_interrupt+0x6f/0x180
  common_interrupt+0xb7/0xe0
  </IRQ>

It looks like the concern here is that inode::i_lock is sometimes taken
in IRQ context, and sometimes it is held when going to IRQ context,
though it's a little difficult to tell since I think this is a kernel
from after the actual 6.19 release but before 7.0-rc1.

Either way, we don't need to take i_lock, because filesystems should
not report files to fserror if they're about to be freed or have not
yet been exposed to other threads, because the resulting fsnotify report
will be meaningless.

Therefore, bump inode::i_count directly and clarify the preconditions on
the inode being passed in.

Link: https://lore.kernel.org/linux-fsdevel/aY7BndIgQg3ci_6s@infradead.org/
Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/177148129564.716249.3069780698231701540.stgit@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/ioend.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index e4d57cb969f1..4d1ef8a2cee9 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -69,11 +69,57 @@ static u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
 	return folio_count;
 }
 
+static DEFINE_SPINLOCK(failed_ioend_lock);
+static LIST_HEAD(failed_ioend_list);
+
+static void
+iomap_fail_ioends(
+	struct work_struct	*work)
+{
+	struct iomap_ioend	*ioend;
+	struct list_head	tmp;
+	unsigned long		flags;
+
+	spin_lock_irqsave(&failed_ioend_lock, flags);
+	list_replace_init(&failed_ioend_list, &tmp);
+	spin_unlock_irqrestore(&failed_ioend_lock, flags);
+
+	while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
+			io_list))) {
+		list_del_init(&ioend->io_list);
+		iomap_finish_ioend_buffered(ioend);
+		cond_resched();
+	}
+}
+
+static DECLARE_WORK(failed_ioend_work, iomap_fail_ioends);
+
+static void iomap_fail_ioend_buffered(struct iomap_ioend *ioend)
+{
+	unsigned long flags;
+
+	/*
+	 * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions
+	 * in the fserror code.  The caller no longer owns the ioend reference
+	 * after the spinlock drops.
+	 */
+	spin_lock_irqsave(&failed_ioend_lock, flags);
+	if (list_empty(&failed_ioend_list))
+		WARN_ON_ONCE(!schedule_work(&failed_ioend_work));
+	list_add_tail(&ioend->io_list, &failed_ioend_list);
+	spin_unlock_irqrestore(&failed_ioend_lock, flags);
+}
+
 static void ioend_writeback_end_bio(struct bio *bio)
 {
 	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
 
 	ioend->io_error = blk_status_to_errno(bio->bi_status);
+	if (ioend->io_error) {
+		iomap_fail_ioend_buffered(ioend);
+		return;
+	}
+
 	iomap_finish_ioend_buffered(ioend);
 }
 

From 023cd6d90f8aa2ef7b72d84be84a18e61ecebd64 Mon Sep 17 00:00:00 2001
From: Piotr Mazek <pmazek@outlook.com>
Date: Thu, 5 Feb 2026 23:05:02 +0100
Subject: [PATCH 0064/1303] ACPI: PM: Save NVS memory on Lenovo G70-35

[821d6f0359b0614792ab8e2fb93b503e25a65079] prevented machines
produced later than 2012 from saving NVS region to accelerate S3.

Despite being made after 2012, Lenovo G70-35 still needs NVS memory
saving during S3. A quirk is introduced for this platform.

Signed-off-by: Piotr Mazek <pmazek@outlook.com>
[ rjw: Subject adjustment ]
Link: https://patch.msgid.link/GV2PPF3CD5B63CC2442EE3F76F8443EAD90D499A@GV2PPF3CD5B63CC.EURP251.PROD.OUTLOOK.COM
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 66ec81e306d4..132a9df98471 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -386,6 +386,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "80E1"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Lenovo G70-35",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "80Q5"),
+		},
+	},
 	/*
 	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
 	 * the Low Power S0 Idle firmware interface (see

From ab140365fb62c0bdab22b2f516aff563b2559e3b Mon Sep 17 00:00:00 2001
From: Lars Ellenberg <lars.ellenberg@linbit.com>
Date: Thu, 19 Feb 2026 15:20:12 +0100
Subject: [PATCH 0065/1303] drbd: fix "LOGIC BUG" in
 drbd_al_begin_io_nonblock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even though we check that we "should" be able to do lc_get_cumulative()
while holding the device->al_lock spinlock, it may still fail,
if some other code path decided to do lc_try_lock() with bad timing.

If that happened, we logged "LOGIC BUG for enr=...",
but still did not return an error.

The rest of the code now assumed that this request has references
for the relevant activity log extents.

The implcations are that during an active resync, mutual exclusivity of
resync versus application IO is not guaranteed. And a potential crash
at this point may not realizs that these extents could have been target
of in-flight IO and would need to be resynced just in case.

Also, once the request completes, it will give up activity log references it
does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put().

Fix:

Do not crash the kernel for a condition that is harmless during normal
operation: also catch "e->refcnt == 0", not only "e == NULL"
when being noisy about "al_complete_io() called on inactive extent %u\n".

And do not try to be smart and "guess" whether something will work, then
be surprised when it does not.
Deal with the fact that it may or may not work.  If it does not, remember a
possible "partially in activity log" state (only possible for requests that
cross extent boundaries), and return an error code from
drbd_al_begin_io_nonblock().

A latter call for the same request will then resume from where we left off.

Cc: stable@vger.kernel.org
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_actlog.c   | 53 +++++++++++++-----------------
 drivers/block/drbd/drbd_interval.h |  5 ++-
 2 files changed, 27 insertions(+), 31 deletions(-)

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 742b2908ff68..b3dbf6c76e98 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -483,38 +483,20 @@ void drbd_al_begin_io(struct drbd_device *device, struct drbd_interval *i)
 
 int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *i)
 {
-	struct lru_cache *al = device->act_log;
 	/* for bios crossing activity log extent boundaries,
 	 * we may need to activate two extents in one go */
 	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
 	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
-	unsigned nr_al_extents;
-	unsigned available_update_slots;
 	unsigned enr;
 
-	D_ASSERT(device, first <= last);
-
-	nr_al_extents = 1 + last - first; /* worst case: all touched extends are cold. */
-	available_update_slots = min(al->nr_elements - al->used,
-				al->max_pending_changes - al->pending_changes);
-
-	/* We want all necessary updates for a given request within the same transaction
-	 * We could first check how many updates are *actually* needed,
-	 * and use that instead of the worst-case nr_al_extents */
-	if (available_update_slots < nr_al_extents) {
-		/* Too many activity log extents are currently "hot".
-		 *
-		 * If we have accumulated pending changes already,
-		 * we made progress.
-		 *
-		 * If we cannot get even a single pending change through,
-		 * stop the fast path until we made some progress,
-		 * or requests to "cold" extents could be starved. */
-		if (!al->pending_changes)
-			__set_bit(__LC_STARVING, &device->act_log->flags);
-		return -ENOBUFS;
+	if (i->partially_in_al_next_enr) {
+		D_ASSERT(device, first < i->partially_in_al_next_enr);
+		D_ASSERT(device, last >= i->partially_in_al_next_enr);
+		first = i->partially_in_al_next_enr;
 	}
 
+	D_ASSERT(device, first <= last);
+
 	/* Is resync active in this area? */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *tmp;
@@ -529,14 +511,21 @@ int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *
 		}
 	}
 
-	/* Checkout the refcounts.
-	 * Given that we checked for available elements and update slots above,
-	 * this has to be successful. */
+	/* Try to checkout the refcounts. */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *al_ext;
 		al_ext = lc_get_cumulative(device->act_log, enr);
-		if (!al_ext)
-			drbd_info(device, "LOGIC BUG for enr=%u\n", enr);
+
+		if (!al_ext) {
+			/* Did not work. We may have exhausted the possible
+			 * changes per transaction. Or raced with someone
+			 * "locking" it against changes.
+			 * Remember where to continue from.
+			 */
+			if (enr > first)
+				i->partially_in_al_next_enr = enr;
+			return -ENOBUFS;
+		}
 	}
 	return 0;
 }
@@ -556,7 +545,11 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i)
 
 	for (enr = first; enr <= last; enr++) {
 		extent = lc_find(device->act_log, enr);
-		if (!extent) {
+		/* Yes, this masks a bug elsewhere.  However, during normal
+		 * operation this is harmless, so no need to crash the kernel
+		 * by the BUG_ON(refcount == 0) in lc_put().
+		 */
+		if (!extent || extent->refcnt == 0) {
 			drbd_err(device, "al_complete_io() called on inactive extent %u\n", enr);
 			continue;
 		}
diff --git a/drivers/block/drbd/drbd_interval.h b/drivers/block/drbd/drbd_interval.h
index 366489b72fe9..5d3213b81eed 100644
--- a/drivers/block/drbd/drbd_interval.h
+++ b/drivers/block/drbd/drbd_interval.h
@@ -8,12 +8,15 @@
 struct drbd_interval {
 	struct rb_node rb;
 	sector_t sector;		/* start sector of the interval */
-	unsigned int size;		/* size in bytes */
 	sector_t end;			/* highest interval end in subtree */
+	unsigned int size;		/* size in bytes */
 	unsigned int local:1		/* local or remote request? */;
 	unsigned int waiting:1;		/* someone is waiting for completion */
 	unsigned int completed:1;	/* this has been completed already;
 					 * ignore for conflict detection */
+
+	/* to resume a partially successful drbd_al_begin_io_nonblock(); */
+	unsigned int partially_in_al_next_enr;
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)

From 81b1f046ff8a5ad5da2c970cff354b61dfa1d6b1 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 12 Jan 2026 18:04:12 +0100
Subject: [PATCH 0066/1303] drbd: Replace deprecated strcpy with strscpy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

strcpy() has been deprecated [1] because it performs no bounds checking
on the destination buffer, which can lead to buffer overflows. Replace
it with the safer strscpy().  No functional changes.

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_main.c     | 14 +++++++++-----
 drivers/block/drbd/drbd_receiver.c |  4 ++--
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 1f6ac9202b66..ba00b5f21a49 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -32,6 +32,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/random.h>
 #include <linux/reboot.h>
 #include <linux/notifier.h>
@@ -732,9 +733,9 @@ int drbd_send_sync_param(struct drbd_peer_device *peer_device)
 	}
 
 	if (apv >= 88)
-		strcpy(p->verify_alg, nc->verify_alg);
+		strscpy(p->verify_alg, nc->verify_alg);
 	if (apv >= 89)
-		strcpy(p->csums_alg, nc->csums_alg);
+		strscpy(p->csums_alg, nc->csums_alg);
 	rcu_read_unlock();
 
 	return drbd_send_command(peer_device, sock, cmd, size, NULL, 0);
@@ -745,6 +746,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	struct drbd_socket *sock;
 	struct p_protocol *p;
 	struct net_conf *nc;
+	size_t integrity_alg_len;
 	int size, cf;
 
 	sock = &connection->data;
@@ -762,8 +764,10 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	}
 
 	size = sizeof(*p);
-	if (connection->agreed_pro_version >= 87)
-		size += strlen(nc->integrity_alg) + 1;
+	if (connection->agreed_pro_version >= 87) {
+		integrity_alg_len = strlen(nc->integrity_alg) + 1;
+		size += integrity_alg_len;
+	}
 
 	p->protocol      = cpu_to_be32(nc->wire_protocol);
 	p->after_sb_0p   = cpu_to_be32(nc->after_sb_0p);
@@ -778,7 +782,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	p->conn_flags    = cpu_to_be32(cf);
 
 	if (connection->agreed_pro_version >= 87)
-		strcpy(p->integrity_alg, nc->integrity_alg);
+		strscpy(p->integrity_alg, nc->integrity_alg, integrity_alg_len);
 	rcu_read_unlock();
 
 	return __conn_send_command(connection, sock, cmd, size, NULL, 0);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 3de919b6f0e1..3d0a061b6c40 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3801,14 +3801,14 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i
 			*new_net_conf = *old_net_conf;
 
 			if (verify_tfm) {
-				strcpy(new_net_conf->verify_alg, p->verify_alg);
+				strscpy(new_net_conf->verify_alg, p->verify_alg);
 				new_net_conf->verify_alg_len = strlen(p->verify_alg) + 1;
 				crypto_free_shash(peer_device->connection->verify_tfm);
 				peer_device->connection->verify_tfm = verify_tfm;
 				drbd_info(device, "using verify-alg: \"%s\"\n", p->verify_alg);
 			}
 			if (csums_tfm) {
-				strcpy(new_net_conf->csums_alg, p->csums_alg);
+				strscpy(new_net_conf->csums_alg, p->csums_alg);
 				new_net_conf->csums_alg_len = strlen(p->csums_alg) + 1;
 				crypto_free_shash(peer_device->connection->csums_tfm);
 				peer_device->connection->csums_tfm = csums_tfm;

From 6b3e458806e34f1142592f786d3eb0ebac209cc2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:35 +0100
Subject: [PATCH 0067/1303] HID: Document memory allocation properties of
 report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The memory pointer returned by the report_fixup() hook does not get
freed by the caller.  Instead, report_fixup() must return (in return
value and *rsize) a memory buffer with at least the same lifetime as
the input buffer (defined by rdesc and original *rsize).

This is usually achieved using one of the following techniques:

* Returning a pointer and size to a sub-portion of the input buffer
* Returning a pointer to a static buffer
* Allocating a buffer with a devm_*() function,
  which will automatically get freed when the device is removed.

Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 include/linux/hid.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/hid.h b/include/linux/hid.h
index dce862cafbbd..2990b9f94cb5 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -836,6 +836,12 @@ struct hid_usage_id {
  * raw_event and event should return negative on error, any other value will
  * pass the event on to .event() typically return 0 for success.
  *
+ * report_fixup must return a report descriptor pointer whose lifetime is at
+ * least that of the input rdesc.  This is usually done by mutating the input
+ * rdesc and returning it or a sub-portion of it.  In case a new buffer is
+ * allocated and returned, the implementation of report_fixup is responsible for
+ * freeing it later.
+ *
  * input_mapping shall return a negative value to completely ignore this usage
  * (e.g. doubled or invalid usage), zero to continue with parsing of this
  * usage by generic code (no special handling needed) or positive to skip

From 239c15116d80f67d32f00acc34575f1a6b699613 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:36 +0100
Subject: [PATCH 0068/1303] HID: apple: avoid memory leak in
 apple_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The apple_report_fixup() function was returning a
newly kmemdup()-allocated buffer, but never freeing it.

The caller of report_fixup() does not take ownership of the returned
pointer, but it *is* permitted to return a sub-portion of the input
rdesc, whose lifetime is managed by the caller.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-apple.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 233e367cce1d..894adc23367b 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -686,9 +686,7 @@ static const __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			 "fixing up Magic Keyboard battery report descriptor\n");
 		*rsize = *rsize - 1;
-		rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL);
-		if (!rdesc)
-			return NULL;
+		rdesc = rdesc + 1;
 
 		rdesc[0] = 0x05;
 		rdesc[1] = 0x01;

From 91e8c6e601bdc1ccdf886479b6513c01c7e51c2c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:37 +0100
Subject: [PATCH 0069/1303] HID: magicmouse: avoid memory leak in
 magicmouse_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The magicmouse_report_fixup() function was returning a
newly kmemdup()-allocated buffer, but never freeing it.

The caller of report_fixup() does not take ownership of the returned
pointer, but it *is* permitted to return a sub-portion of the input
rdesc, whose lifetime is managed by the caller.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-magicmouse.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 91f621ceb924..17908d52c027 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -994,9 +994,7 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			 "fixing up magicmouse battery report descriptor\n");
 		*rsize = *rsize - 1;
-		rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL);
-		if (!rdesc)
-			return NULL;
+		rdesc = rdesc + 1;
 
 		rdesc[0] = 0x05;
 		rdesc[1] = 0x01;

From 2bad24c17742fc88973d6aea526ce1353f5334a3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:38 +0100
Subject: [PATCH 0070/1303] HID: asus: avoid memory leak in asus_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The asus_report_fixup() function was returning a newly allocated
kmemdup()-allocated buffer, but never freeing it.  Switch to
devm_kzalloc() to ensure the memory is managed and freed automatically
when the device is removed.

The caller of report_fixup() does not take ownership of the returned
pointer, but it is permitted to return a pointer whose lifetime is at
least that of the input buffer.

Also fix a harmless out-of-bounds read by copying only the original
descriptor size.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-asus.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 8ffcd12038e8..7a08e964b9cc 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1399,14 +1399,21 @@ static const __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 */
 		if (*rsize == rsize_orig &&
 			rdesc[offs] == 0x09 && rdesc[offs + 1] == 0x76) {
-			*rsize = rsize_orig + 1;
-			rdesc = kmemdup(rdesc, *rsize, GFP_KERNEL);
-			if (!rdesc)
-				return NULL;
+			__u8 *new_rdesc;
+
+			new_rdesc = devm_kzalloc(&hdev->dev, rsize_orig + 1,
+						 GFP_KERNEL);
+			if (!new_rdesc)
+				return rdesc;
 
 			hid_info(hdev, "Fixing up %s keyb report descriptor\n",
 				drvdata->quirks & QUIRK_T100CHI ?
 				"T100CHI" : "T90CHI");
+
+			memcpy(new_rdesc, rdesc, rsize_orig);
+			*rsize = rsize_orig + 1;
+			rdesc = new_rdesc;
+
 			memmove(rdesc + offs + 4, rdesc + offs + 2, 12);
 			rdesc[offs] = 0x19;
 			rdesc[offs + 1] = 0x00;

From ecfa6f34492c493a9a1dc2900f3edeb01c79946b Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 19 Feb 2026 15:33:54 +0100
Subject: [PATCH 0071/1303] HID: Add HID_CLAIMED_INPUT guards in raw_event
 callbacks missing them

In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at
raw event handle"), we handle the fact that raw event callbacks
can happen even for a HID device that has not been "claimed" causing a
crash if a broken device were attempted to be connected to the system.

Fix up the remaining in-tree HID drivers that forgot to add this same
check to resolve the same issue.

Cc: Jiri Kosina <jikos@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Bastien Nocera <hadess@hadess.net>
Cc: linux-input@vger.kernel.org
Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-cmedia.c          | 2 +-
 drivers/hid/hid-creative-sb0540.c | 2 +-
 drivers/hid/hid-zydacron.c        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-cmedia.c b/drivers/hid/hid-cmedia.c
index 528d7f361215..8bf5649b0c79 100644
--- a/drivers/hid/hid-cmedia.c
+++ b/drivers/hid/hid-cmedia.c
@@ -99,7 +99,7 @@ static int cmhid_raw_event(struct hid_device *hid, struct hid_report *report,
 {
 	struct cmhid *cm = hid_get_drvdata(hid);
 
-	if (len != CM6533_JD_RAWEV_LEN)
+	if (len != CM6533_JD_RAWEV_LEN || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 	if (memcmp(data+CM6533_JD_SFX_OFFSET, ji_sfx, sizeof(ji_sfx)))
 		goto out;
diff --git a/drivers/hid/hid-creative-sb0540.c b/drivers/hid/hid-creative-sb0540.c
index b4c8e7a5d3e0..dfd6add353d1 100644
--- a/drivers/hid/hid-creative-sb0540.c
+++ b/drivers/hid/hid-creative-sb0540.c
@@ -153,7 +153,7 @@ static int creative_sb0540_raw_event(struct hid_device *hid,
 	u64 code, main_code;
 	int key;
 
-	if (len != 6)
+	if (len != 6 || !(hid->claimed & HID_CLAIMED_INPUT))
 		return 0;
 
 	/* From daemons/hw_hiddev.c sb0540_rec() in lirc */
diff --git a/drivers/hid/hid-zydacron.c b/drivers/hid/hid-zydacron.c
index 3bdb26f45592..1aae80f848f5 100644
--- a/drivers/hid/hid-zydacron.c
+++ b/drivers/hid/hid-zydacron.c
@@ -114,7 +114,7 @@ static int zc_raw_event(struct hid_device *hdev, struct hid_report *report,
 	unsigned key;
 	unsigned short index;
 
-	if (report->id == data[0]) {
+	if (report->id == data[0] && (hdev->claimed & HID_CLAIMED_INPUT)) {
 
 		/* break keys */
 		for (index = 0; index < 4; index++) {

From 858d2a4f67ff69e645a43487ef7ea7f28f06deae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Feb 2026 16:12:05 +0000
Subject: [PATCH 0072/1303] tcp: fix potential race in tcp_v6_syn_recv_sock()

Code in tcp_v6_syn_recv_sock() after the call to tcp_v4_syn_recv_sock()
is done too late.

After tcp_v4_syn_recv_sock(), the child socket is already visible
from TCP ehash table and other cpus might use it.

Since newinet->pinet6 is still pointing to the listener ipv6_pinfo
bad things can happen as syzbot found.

Move the problematic code in tcp_v6_mapped_child_init()
and call this new helper from tcp_v4_syn_recv_sock() before
the ehash insertion.

This allows the removal of one tcp_sync_mss(), since
tcp_v4_syn_recv_sock() will call it with the correct
context.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+937b5bbb6a815b3e5d0b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69949275.050a0220.2eeac1.0145.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260217161205.2079883-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_connection_sock.h |  4 +-
 include/net/tcp.h                  |  4 +-
 net/ipv4/syncookies.c              |  2 +-
 net/ipv4/tcp_fastopen.c            |  2 +-
 net/ipv4/tcp_ipv4.c                |  8 ++-
 net/ipv4/tcp_minisocks.c           |  2 +-
 net/ipv6/tcp_ipv6.c                | 98 +++++++++++++-----------------
 net/mptcp/subflow.c                |  6 +-
 net/smc/af_smc.c                   |  6 +-
 9 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ecb362025c4e..5cb3056d6ddc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -42,7 +42,9 @@ struct inet_connection_sock_af_ops {
 				      struct request_sock *req,
 				      struct dst_entry *dst,
 				      struct request_sock *req_unhash,
-				      bool *own_req);
+				      bool *own_req,
+				      void (*opt_child_init)(struct sock *newsk,
+							     const struct sock *sk));
 	u16	    net_header_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  sockptr_t optval, unsigned int optlen);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 40e72b9cb85f..eb8bf63fdafc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -544,7 +544,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req);
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk));
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 569befcf021b..061751aabc8e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -203,7 +203,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	bool own_req;
 
 	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						 NULL, &own_req);
+						 NULL, &own_req, NULL);
 	if (child) {
 		refcount_set(&req->rsk_refcnt, 1);
 		sock_rps_save_rxhash(child, skb);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index b30090cff3cf..df803f088f45 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -333,7 +333,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	bool own_req;
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 NULL, &own_req);
+							 NULL, &own_req, NULL);
 	if (!child)
 		return NULL;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6264fc0b2be5..2980c175d326 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1705,7 +1705,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req)
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk))
 {
 	struct inet_request_sock *ireq;
 	bool found_dup_sk = false;
@@ -1757,6 +1759,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
+#if IS_ENABLED(CONFIG_IPV6)
+	if (opt_child_init)
+		opt_child_init(newsk, sk);
+#endif
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ec128865f5c0..d9c5a43bd281 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -925,7 +925,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * socket is created, wait for troubles.
 	 */
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 req, &own_req);
+							 req, &own_req, NULL);
 	if (!child)
 		goto listen_overflow;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d10487b4e5bf..e46a0efae012 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1312,11 +1312,48 @@ static void tcp_v6_restore_cb(struct sk_buff *skb)
 		sizeof(struct inet6_skb_parm));
 }
 
+/* Called from tcp_v4_syn_recv_sock() for v6_mapped children. */
+static void tcp_v6_mapped_child_init(struct sock *newsk, const struct sock *sk)
+{
+	struct inet_sock *newinet = inet_sk(newsk);
+	struct ipv6_pinfo *newnp;
+
+	newinet->pinet6 = newnp = tcp_inet6_sk(newsk);
+	newinet->ipv6_fl_list = NULL;
+
+	memcpy(newnp, tcp_inet6_sk(sk), sizeof(struct ipv6_pinfo));
+
+	newnp->saddr = newsk->sk_v6_rcv_saddr;
+
+	inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
+	if (sk_is_mptcp(newsk))
+		mptcpv6_handle_mapped(newsk, true);
+	newsk->sk_backlog_rcv = tcp_v4_do_rcv;
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
+	tcp_sk(newsk)->af_specific = &tcp_sock_ipv6_mapped_specific;
+#endif
+
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->pktoptions  = NULL;
+	newnp->opt	   = NULL;
+
+	/* tcp_v4_syn_recv_sock() has initialized newinet->mc_{index,ttl} */
+	newnp->mcast_oif   = newinet->mc_index;
+	newnp->mcast_hops  = newinet->mc_ttl;
+
+	newnp->rcv_flowinfo = 0;
+	if (inet6_test_bit(REPFLOW, sk))
+		newnp->flow_label = 0;
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
 					 struct request_sock *req_unhash,
-					 bool *own_req)
+					 bool *own_req,
+					 void (*opt_child_init)(struct sock *newsk,
+								const struct sock *sk))
 {
 	const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct inet_request_sock *ireq;
@@ -1332,61 +1369,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 #endif
 	struct flowi6 fl6;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		/*
-		 *	v6 mapped
-		 */
-
-		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst,
-					     req_unhash, own_req);
-
-		if (!newsk)
-			return NULL;
-
-		newinet = inet_sk(newsk);
-		newinet->pinet6 = tcp_inet6_sk(newsk);
-		newinet->ipv6_fl_list = NULL;
-
-		newnp = tcp_inet6_sk(newsk);
-		newtp = tcp_sk(newsk);
-
-		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
-
-		newnp->saddr = newsk->sk_v6_rcv_saddr;
-
-		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
-		if (sk_is_mptcp(newsk))
-			mptcpv6_handle_mapped(newsk, true);
-		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
-#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
-		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
-#endif
-
-		newnp->ipv6_mc_list = NULL;
-		newnp->ipv6_ac_list = NULL;
-		newnp->pktoptions  = NULL;
-		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet_iif(skb);
-		newnp->mcast_hops  = ip_hdr(skb)->ttl;
-		newnp->rcv_flowinfo = 0;
-		if (inet6_test_bit(REPFLOW, sk))
-			newnp->flow_label = 0;
-
-		/*
-		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-		 * here, tcp_create_openreq_child now does this for us, see the comment in
-		 * that function for the gory details. -acme
-		 */
-
-		/* It is tricky place. Until this moment IPv4 tcp
-		   worked with IPv6 icsk.icsk_af_ops.
-		   Sync it now.
-		 */
-		tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
-
-		return newsk;
-	}
-
+	if (skb->protocol == htons(ETH_P_IP))
+		return tcp_v4_syn_recv_sock(sk, skb, req, dst,
+					    req_unhash, own_req,
+					    tcp_v6_mapped_child_init);
 	ireq = inet_rsk(req);
 
 	if (sk_acceptq_is_full(sk))
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index f66129f1e649..8b25dd86ffeb 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -808,7 +808,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
@@ -855,7 +857,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 create_child:
 	child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						     req_unhash, own_req);
+						     req_unhash, own_req, opt_child_init);
 
 	if (child && *own_req) {
 		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d8201eb3ac5f..18c56b0d7ad5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -124,7 +124,9 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct smc_sock *smc;
 	struct sock *child;
@@ -142,7 +144,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 
 	/* passthrough to original syn recv sock fct */
 	child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash,
-					       own_req);
+					       own_req, opt_child_init);
 	/* child must not inherit smc or its ops */
 	if (child) {
 		rcu_assign_sk_user_data(child, NULL);

From f891007ab1c77436950d10e09eae54507f1865ff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Feb 2026 14:13:37 +0000
Subject: [PATCH 0073/1303] psp: use sk->sk_hash in psp_write_headers()

udp_flow_src_port() is indirectly using sk->sk_txhash as a base,
because __tcp_transmit_skb() uses skb_set_hash_from_sk().

This is problematic because this field can change over the
lifetime of a TCP flow, thanks to calls to sk_rethink_txhash().

Problem is that some NIC might (ab)use the PSP UDP source port in their
RSS computation, and PSP packets for a given flow could jump
from one queue to another.

In order to avoid surprises, it is safer to let Protective Load
Balancing (PLB) get its entropy from the IPv6 flowlabel,
and change psp_write_headers() to use sk->sk_hash which
does not change for the duration of the flow.

We might add a sysctl to select the behavior, if there
is a need for it.

Fixes: fc724515741a ("psp: provide encapsulation helper for drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-By: Daniel Zahka <daniel.zahka@gmail.com>
Link: https://patch.msgid.link/20260218141337.999945-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/psp/psp_main.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/net/psp/psp_main.c b/net/psp/psp_main.c
index a8534124f626..066222eb56c4 100644
--- a/net/psp/psp_main.c
+++ b/net/psp/psp_main.c
@@ -166,9 +166,46 @@ static void psp_write_headers(struct net *net, struct sk_buff *skb, __be32 spi,
 {
 	struct udphdr *uh = udp_hdr(skb);
 	struct psphdr *psph = (struct psphdr *)(uh + 1);
+	const struct sock *sk = skb->sk;
 
 	uh->dest = htons(PSP_DEFAULT_UDP_PORT);
-	uh->source = udp_flow_src_port(net, skb, 0, 0, false);
+
+	/* A bit of theory: Selection of the source port.
+	 *
+	 * We need some entropy, so that multiple flows use different
+	 * source ports for better RSS spreading at the receiver.
+	 *
+	 * We also need that all packets belonging to one TCP flow
+	 * use the same source port through their duration,
+	 * so that all these packets land in the same receive queue.
+	 *
+	 * udp_flow_src_port() is using sk_txhash, inherited from
+	 * skb_set_hash_from_sk() call in __tcp_transmit_skb().
+	 * This field is subject to reshuffling, thanks to
+	 * sk_rethink_txhash() calls in various TCP functions.
+	 *
+	 * Instead, use sk->sk_hash which is constant through
+	 * the whole flow duration.
+	 */
+	if (likely(sk)) {
+		u32 hash = sk->sk_hash;
+		int min, max;
+
+		/* These operations are cheap, no need to cache the result
+		 * in another socket field.
+		 */
+		inet_get_local_port_range(net, &min, &max);
+		/* Since this is being sent on the wire obfuscate hash a bit
+		 * to minimize possibility that any useful information to an
+		 * attacker is leaked. Only upper 16 bits are relevant in the
+		 * computation for 16 bit port value because we use a
+		 * reciprocal divide.
+		 */
+		hash ^= hash << 16;
+		uh->source = htons((((u64)hash * (max - min)) >> 32) + min);
+	} else {
+		uh->source = udp_flow_src_port(net, skb, 0, 0, false);
+	}
 	uh->check = 0;
 	uh->len = htons(udp_len);
 

From e1512c1db9e8794d8d130addd2615ec27231d994 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Wed, 18 Feb 2026 02:16:43 +0900
Subject: [PATCH 0074/1303] espintcp: Fix race condition in espintcp_close()

This issue was discovered during a code audit.

After cancel_work_sync() is called from espintcp_close(),
espintcp_tx_work() can still be scheduled from paths such as
the Delayed ACK handler or ksoftirqd.
As a result, the espintcp_tx_work() worker may dereference a
freed espintcp ctx or sk.

The following is a simple race scenario:

           cpu0                             cpu1

  espintcp_close()
    cancel_work_sync(&ctx->work);
                                     espintcp_write_space()
                                       schedule_work(&ctx->work);

To prevent this race condition, cancel_work_sync() is
replaced with disable_work_sync().

Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/aZSie7rEdh9Nu0eM@v4bel
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xfrm/espintcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index bf744ac9d5a7..8709df716e98 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -536,7 +536,7 @@ static void espintcp_close(struct sock *sk, long timeout)
 	sk->sk_prot = &tcp_prot;
 	barrier();
 
-	cancel_work_sync(&ctx->work);
+	disable_work_sync(&ctx->work);
 	strp_done(&ctx->strp);
 
 	skb_queue_purge(&ctx->out_queue);

From 64868f5ecadeb359a49bc4485bfa7c497047f13a Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Tue, 17 Feb 2026 17:50:12 +0000
Subject: [PATCH 0075/1303] net: usb: kaweth: remove TX queue manipulation in
 kaweth_set_rx_mode

kaweth_set_rx_mode(), the ndo_set_rx_mode callback, calls
netif_stop_queue() and netif_wake_queue(). These are TX queue flow
control functions unrelated to RX multicast configuration.

The premature netif_wake_queue() can re-enable TX while tx_urb is still
in-flight, leading to a double usb_submit_urb() on the same URB:

kaweth_start_xmit() {
    netif_stop_queue();
    usb_submit_urb(kaweth->tx_urb);
}

kaweth_set_rx_mode() {
    netif_stop_queue();
    netif_wake_queue();             // wakes TX queue before URB is done
}

kaweth_start_xmit() {
    netif_stop_queue();
    usb_submit_urb(kaweth->tx_urb); // URB submitted while active
}

This triggers the WARN in usb_submit_urb():

  "URB submitted while active"

This is a similar class of bug fixed in rtl8150 by

- commit 958baf5eaee3 ("net: usb: Remove disruptive netif_wake_queue in rtl8150_set_multicast").

Also kaweth_set_rx_mode() is already functionally broken, the
real set_rx_mode action is performed by kaweth_async_set_rx_mode(),
which in turn is not a no-op only at ndo_open() time.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Link: https://patch.msgid.link/20260217175012.1234494-1-n7l8m4@u.northwestern.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kaweth.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index c9efb7df892e..e01d14f6c366 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -765,7 +765,6 @@ static void kaweth_set_rx_mode(struct net_device *net)
 
 	netdev_dbg(net, "Setting Rx mode to %d\n", packet_filter_bitmap);
 
-	netif_stop_queue(net);
 
 	if (net->flags & IFF_PROMISC) {
 		packet_filter_bitmap |= KAWETH_PACKET_FILTER_PROMISCUOUS;
@@ -775,7 +774,6 @@ static void kaweth_set_rx_mode(struct net_device *net)
 	}
 
 	kaweth->packet_filter_bitmap = packet_filter_bitmap;
-	netif_wake_queue(net);
 }
 
 /****************************************************************

From f1e2f0ce704e4a14e3f367d3b97d3dd2d8e183b7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20P=C3=A5lsson?= <martin@poleshift.se>
Date: Wed, 18 Feb 2026 05:28:22 +0000
Subject: [PATCH 0076/1303] net: usb: lan78xx: scan all MDIO addresses on
 LAN7801
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The LAN7801 is designed exclusively for external PHYs (unlike the
LAN7800/LAN7850 which have internal PHYs), but lan78xx_mdio_init()
restricts PHY scanning to MDIO addresses 0-7 by setting phy_mask to
~(0xFF). This prevents discovery of external PHYs wired to addresses
outside that range.

One such case is the DP83TC814 100BASE-T1 PHY, which is typically
configured at MDIO address 10 via PHYAD bootstrap pins and goes
undetected with the current mask.

Remove the restrictive phy_mask assignment for the LAN7801 so that the
default mask of 0 applies, allowing all 32 MDIO addresses to be
scanned during bus registration.

Fixes: 02dc1f3d613d ("lan78xx: add LAN7801 MAC only support")
Signed-off-by: Martin Pålsson <martin@poleshift.se>
Link: https://patch.msgid.link/0110019c6f388aff-98d99cf0-4425-4fff-b16b-dea5ad8fafe0-000000@eu-north-1.amazonses.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 00397a807393..065588c9cfa6 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2094,8 +2094,6 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev)
 		dev->mdiobus->phy_mask = ~(1 << 1);
 		break;
 	case ID_REV_CHIP_ID_7801_:
-		/* scan thru PHYAD[2..0] */
-		dev->mdiobus->phy_mask = ~(0xFF);
 		break;
 	}
 

From bfd264fbbbca7a39ea430d7bc2baf8ee2ea958e4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 18 Feb 2026 18:05:51 +0200
Subject: [PATCH 0077/1303] net: dsa: sja1105: protect link replay helpers
 against NULL phylink instance

There is a crash when unbinding the sja1105 driver under special
circumstances:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030
Call trace:
phylink_run_resolve_and_disable+0x10/0x90
sja1105_static_config_reload+0xc0/0x410
sja1105_vlan_filtering+0x100/0x140
dsa_port_vlan_filtering+0x13c/0x368
dsa_port_reset_vlan_filtering.isra.0+0xe8/0x198
dsa_port_bridge_leave+0x130/0x248
dsa_user_changeupper.part.0+0x74/0x158
dsa_user_netdevice_event+0x50c/0xa50
notifier_call_chain+0x78/0x148
raw_notifier_call_chain+0x20/0x38
call_netdevice_notifiers_info+0x58/0xa8
__netdev_upper_dev_unlink+0xac/0x220
netdev_upper_dev_unlink+0x38/0x70
del_nbp+0x1a4/0x320
br_del_if+0x3c/0xd8
br_device_event+0xf8/0x2d8
notifier_call_chain+0x78/0x148
raw_notifier_call_chain+0x20/0x38
call_netdevice_notifiers_info+0x58/0xa8
unregister_netdevice_many_notify+0x314/0x848
unregister_netdevice_queue+0xe8/0xf8
dsa_user_destroy+0x50/0xa8
dsa_port_teardown+0x80/0x98
dsa_switch_teardown_ports+0x4c/0xb8
dsa_switch_deinit+0x94/0xb8
dsa_switch_put_tree+0x2c/0xc0
dsa_unregister_switch+0x38/0x60
sja1105_remove+0x24/0x40
spi_remove+0x38/0x60
device_remove+0x54/0x90
device_release_driver_internal+0x1d4/0x230
device_driver_detach+0x20/0x38
unbind_store+0xbc/0xc8
---[ end trace 0000000000000000 ]---

which requires an explanation.

When a port offloads a bridge, the switch must be reset to change
the VLAN awareness state (the SJA1105_VLAN_FILTERING reason for
sja1105_static_config_reload()). When the port leaves a VLAN-aware
bridge, it must also be reset for the same reason: it is returning
to operation as a VLAN-unaware standalone port.

sja1105_static_config_reload() triggers the phylink link replay helpers.

Because sja1105 is a switch, it has multiple user ports. During unbind,
ports are torn down one by one in dsa_switch_teardown_ports() ->
dsa_port_teardown() -> dsa_user_destroy().

The crash happens when the first user port is not part of the VLAN-aware
bridge, but any other user port is.

Tearing down the first user port causes phylink_destroy() to be called
on dp->pl, and this pointer to be set to NULL. Then, when the second
user port is torn down, this was offloading a VLAN-aware bridge port, so
indirectly it will trigger sja1105_static_config_reload().

The latter function iterates using dsa_switch_for_each_available_port(),
and unconditionally dereferences dp->pl, including for the
aforementioned torn down previous port, and passes that to phylink.
This is where the NULL pointer is coming from.

There are multiple levels at which this could be avoided:
- add an "if (dp->pl)" in sja1105_static_config_reload()
- make the phylink replay helpers NULL-tolerant
- mark ports as DSA_PORT_TYPE_UNUSED after dsa_port_phylink_destroy()
  has run, such that subsequent dsa_switch_for_each_available_port()
  iterations skip them
- disconnect the entire switch at once from switchdev and
  NETDEV_CHANGEUPPER events while unbinding, not just port by port,
  likely using a "ds->unbinding = true" mechanism or similar

however options 3 and 4 are quite heavy and might have side effects.
Although 2 allows to keep the driver simpler, the phylink API it not
NULL-tolerant in general and is not responsible for the NULL pointer
(this is something done by dsa_port_phylink_destroy()). So I went
with 1.

Functionally speaking, skipping the replay helpers for ports without
a phylink instance is fine, because that only happens during driver
removal (an operation which cannot be cancelled). The ports are not
required to work (although they probably still will - untested
assumption - as long as we don't overwrite the last port speed with
SJA1105_SPEED_AUTO).

Fixes: 0b2edc531e0b ("net: dsa: sja1105: let phylink help with the replay of link callbacks")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260218160551.194782-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 71a817c07a90..94d17b06da40 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2278,6 +2278,12 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	 * change it through the dynamic interface later.
 	 */
 	dsa_switch_for_each_available_port(dp, ds) {
+		/* May be called during unbind when we unoffload a VLAN-aware
+		 * bridge from port 1 while port 0 was already torn down
+		 */
+		if (!dp->pl)
+			continue;
+
 		phylink_replay_link_begin(dp->pl);
 		mac[dp->index].speed = priv->info->port_speed[SJA1105_SPEED_AUTO];
 	}
@@ -2334,7 +2340,8 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	}
 
 	dsa_switch_for_each_available_port(dp, ds)
-		phylink_replay_link_end(dp->pl);
+		if (dp->pl)
+			phylink_replay_link_end(dp->pl);
 
 	rc = sja1105_reload_cbs(priv);
 	if (rc < 0)

From f6a495484a27150fb85f943e1a7464da88c2a797 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Thu, 19 Feb 2026 16:10:01 -0600
Subject: [PATCH 0078/1303] proc: Fix pointer error dereference

The function try_lookup_noperm() can return an error pointer. Add check
for error pointer.

Detected by Smatch:
fs/proc/base.c:2148 proc_fill_cache() error:
'child' dereferencing possible ERR_PTR()

Fixes: 1df98b8bbcca ("proc_fill_cache(): clean up, get rid of pointless find_inode_number() use")
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Link: https://patch.msgid.link/20260219221001.1117135-1-ethantidmore06@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/proc/base.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4eec684baca9..4c863d17dfb4 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2128,6 +2128,9 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 	ino_t ino = 1;
 
 	child = try_lookup_noperm(&qname, dir);
+	if (IS_ERR(child))
+		goto end_instantiate;
+
 	if (!child) {
 		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);

From c5f8658f97ec392eeaf355d4e9775ae1f23ca1d3 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Feb 2026 17:06:29 +0800
Subject: [PATCH 0079/1303] drm/imx: parallel-display: check return value of
 devm_drm_bridge_add() in imx_pd_probe()

Return the value of devm_drm_bridge_add() in order to propagate the
error properly, if it fails due to resource allocation failure or bridge
registration failure.

This ensures that the probe function fails safely rather than proceeding
with a potentially incomplete bridge setup.

Fixes: bf7e97910b9f ("drm/imx: parallel-display: add the bridge before attaching it")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://patch.msgid.link/20260204090629.2209542-1-nichen@iscas.ac.cn
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/imx/ipuv3/parallel-display.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
index 6fbf505d2801..590120a33fa0 100644
--- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c
+++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
@@ -256,7 +256,9 @@ static int imx_pd_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, imxpd);
 
-	devm_drm_bridge_add(dev, &imxpd->bridge);
+	ret = devm_drm_bridge_add(dev, &imxpd->bridge);
+	if (ret)
+		return ret;
 
 	return component_add(dev, &imx_pd_ops);
 }

From 496daa2759260374bb9c9b2196a849aa3bc513a8 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Fri, 6 Feb 2026 12:06:21 +0800
Subject: [PATCH 0080/1303] drm/bridge: synopsys: dw-dp: Check return value of
 devm_drm_bridge_add() in dw_dp_bind()

Return the value of devm_drm_bridge_add() in order to propagate the
error properly, if it fails due to resource allocation failure or bridge
registration failure.

This ensures that the bind function fails safely rather than proceeding
with a potentially incomplete bridge setup.

Fixes: b726970486d8 ("drm/bridge: synopsys: dw-dp: add bridge before attaching")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Andy Yan <andyshrk@163.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://patch.msgid.link/20260206040621.4095517-1-nichen@iscas.ac.cn
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/bridge/synopsys/dw-dp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/synopsys/dw-dp.c b/drivers/gpu/drm/bridge/synopsys/dw-dp.c
index 432342452484..07f7a2e0d9f2 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-dp.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-dp.c
@@ -2049,7 +2049,9 @@ struct dw_dp *dw_dp_bind(struct device *dev, struct drm_encoder *encoder,
 	bridge->type = DRM_MODE_CONNECTOR_DisplayPort;
 	bridge->ycbcr_420_allowed = true;
 
-	devm_drm_bridge_add(dev, bridge);
+	ret = devm_drm_bridge_add(dev, bridge);
+	if (ret)
+		return ERR_PTR(ret);
 
 	dp->aux.dev = dev;
 	dp->aux.drm_dev = encoder->dev;

From 803ec1faf7c1823e6e3b1f2aaa81be18528c9436 Mon Sep 17 00:00:00 2001
From: Osama Abdelkader <osama.abdelkader@gmail.com>
Date: Mon, 9 Feb 2026 19:41:14 +0100
Subject: [PATCH 0081/1303] drm/bridge: samsung-dsim: Fix memory leak in error
 path

In samsung_dsim_host_attach(), drm_bridge_add() is called to add the
bridge. However, if samsung_dsim_register_te_irq() or
pdata->host_ops->attach() fails afterwards, the function returns
without removing the bridge, causing a memory leak.

Fix this by adding proper error handling with goto labels to ensure
drm_bridge_remove() is called in all error paths. Also ensure that
samsung_dsim_unregister_te_irq() is called if the attach operation
fails after the TE IRQ has been registered.

samsung_dsim_unregister_te_irq() function is moved without changes
to be before samsung_dsim_host_attach() to avoid forward declaration.

Fixes: e7447128ca4a ("drm: bridge: Generalize Exynos-DSI driver into a Samsung DSIM bridge")
Cc: stable@vger.kernel.org
Signed-off-by: Osama Abdelkader <osama.abdelkader@gmail.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://patch.msgid.link/20260209184115.10937-1-osama.abdelkader@gmail.com
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/bridge/samsung-dsim.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
index eabc4c32f6ab..ad8c6aa49d48 100644
--- a/drivers/gpu/drm/bridge/samsung-dsim.c
+++ b/drivers/gpu/drm/bridge/samsung-dsim.c
@@ -1881,6 +1881,14 @@ static int samsung_dsim_register_te_irq(struct samsung_dsim *dsi, struct device
 	return 0;
 }
 
+static void samsung_dsim_unregister_te_irq(struct samsung_dsim *dsi)
+{
+	if (dsi->te_gpio) {
+		free_irq(gpiod_to_irq(dsi->te_gpio), dsi);
+		gpiod_put(dsi->te_gpio);
+	}
+}
+
 static int samsung_dsim_host_attach(struct mipi_dsi_host *host,
 				    struct mipi_dsi_device *device)
 {
@@ -1955,13 +1963,13 @@ static int samsung_dsim_host_attach(struct mipi_dsi_host *host,
 	if (!(device->mode_flags & MIPI_DSI_MODE_VIDEO)) {
 		ret = samsung_dsim_register_te_irq(dsi, &device->dev);
 		if (ret)
-			return ret;
+			goto err_remove_bridge;
 	}
 
 	if (pdata->host_ops && pdata->host_ops->attach) {
 		ret = pdata->host_ops->attach(dsi, device);
 		if (ret)
-			return ret;
+			goto err_unregister_te_irq;
 	}
 
 	dsi->lanes = device->lanes;
@@ -1969,14 +1977,13 @@ static int samsung_dsim_host_attach(struct mipi_dsi_host *host,
 	dsi->mode_flags = device->mode_flags;
 
 	return 0;
-}
 
-static void samsung_dsim_unregister_te_irq(struct samsung_dsim *dsi)
-{
-	if (dsi->te_gpio) {
-		free_irq(gpiod_to_irq(dsi->te_gpio), dsi);
-		gpiod_put(dsi->te_gpio);
-	}
+err_unregister_te_irq:
+	if (!(device->mode_flags & MIPI_DSI_MODE_VIDEO))
+		samsung_dsim_unregister_te_irq(dsi);
+err_remove_bridge:
+	drm_bridge_remove(&dsi->bridge);
+	return ret;
 }
 
 static int samsung_dsim_host_detach(struct mipi_dsi_host *host,

From 0d195d3b205ca90db30d70d09d7bb6909aac178f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?=
 <christoph.boehmwalder@linbit.com>
Date: Fri, 20 Feb 2026 12:39:37 +0100
Subject: [PATCH 0082/1303] drbd: fix null-pointer dereference on local read
 error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to
__req_mod() with a NULL peer_device:

  __req_mod(req, what, NULL, &m);

The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this
NULL peer_device to drbd_set_out_of_sync(), which dereferences it,
causing a null-pointer dereference.

Fix this by obtaining the peer_device via first_peer_device(device),
matching how drbd_req_destroy() handles the same situation.

Cc: stable@vger.kernel.org
Reported-by: Tuo Li <islituo@gmail.com>
Link: https://lore.kernel.org/linux-block/20260104165355.151864-1-islituo@gmail.com
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_req.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d15826f6ee81..70f75ef07945 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -621,7 +621,8 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		break;
 
 	case READ_COMPLETED_WITH_ERROR:
-		drbd_set_out_of_sync(peer_device, req->i.sector, req->i.size);
+		drbd_set_out_of_sync(first_peer_device(device),
+				req->i.sector, req->i.size);
 		drbd_report_io_error(device, req);
 		__drbd_chk_io_error(device, DRBD_READ_ERROR);
 		fallthrough;

From 9b8eeccd7110d10f9c1b1aa456f5efac23e4e383 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Thu, 19 Feb 2026 11:24:00 -0800
Subject: [PATCH 0083/1303] MAINTAINERS: update enic and usnic maintainers

Remove Christian Benvenuti from the enic/usnic maintainer lists because he
is no longer working on the drivers and the email address is no longer valid.
Keep Satish Kharat as the enic maintainer and the usnic co-maintainer.

Signed-off-by: Satish Kharat <satishkh@cisco.com>
Acked-by: Leon Romanovsky <leon@kernel.org>
Link: https://patch.msgid.link/20260219-enic-maintainers-update-v2-v1-1-c58aa11c2ea8@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index b8d8a5c41597..c00b5f5d4203 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6219,14 +6219,13 @@ S:	Supported
 F:	drivers/scsi/snic/
 
 CISCO VIC ETHERNET NIC DRIVER
-M:	Christian Benvenuti <benve@cisco.com>
 M:	Satish Kharat <satishkh@cisco.com>
 S:	Maintained
 F:	drivers/net/ethernet/cisco/enic/
 
 CISCO VIC LOW LATENCY NIC DRIVER
-M:	Christian Benvenuti <benve@cisco.com>
 M:	Nelson Escobar <neescoba@cisco.com>
+M:	Satish Kharat <satishkh@cisco.com>
 S:	Supported
 F:	drivers/infiniband/hw/usnic/
 

From 2bb995e6155cb4f254574598cbd6fe1dcc99766a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 18 Feb 2026 16:56:00 -0800
Subject: [PATCH 0084/1303] net: phy: qcom: qca807x: normalize return value of
 gpio_get

The GPIO get callback is expected to return 0 or 1 (or a negative error
code). Ensure that the value returned by qca807x_gpio_get() is
normalized to the [0, 1] range.

Fixes: 86ef402d805d ("gpiolib: sanitize the return value of gpio_chip::get()")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/aZZeyr2ysqqk2GqA@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index d8f1ce5a7128..6004da5741af 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -375,7 +375,7 @@ static int qca807x_gpio_get(struct gpio_chip *gc, unsigned int offset)
 	reg = QCA807X_MMD7_LED_FORCE_CTRL(offset);
 	val = phy_read_mmd(priv->phy, MDIO_MMD_AN, reg);
 
-	return FIELD_GET(QCA807X_GPIO_FORCE_MODE_MASK, val);
+	return !!FIELD_GET(QCA807X_GPIO_FORCE_MODE_MASK, val);
 }
 
 static int qca807x_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)

From 594163ea88a03bdb412063af50fc7177ef3cbeae Mon Sep 17 00:00:00 2001
From: Linus Walleij <linusw@kernel.org>
Date: Thu, 19 Feb 2026 12:38:50 +0100
Subject: [PATCH 0085/1303] net: ethernet: xscale: Check for PTP support
 properly

In ixp4xx_get_ts_info() ixp46x_ptp_find() is called
unconditionally despite this feature only existing on
ixp46x, leading to the following splat from tcpdump:

root@OpenWrt:~# tcpdump -vv -X -i eth0
(...)
Unable to handle kernel NULL pointer dereference at virtual address
  00000238 when read
(...)
Call trace:
 ptp_clock_index from ixp46x_ptp_find+0x1c/0x38
 ixp46x_ptp_find from ixp4xx_get_ts_info+0x4c/0x64
 ixp4xx_get_ts_info from __ethtool_get_ts_info+0x90/0x108
 __ethtool_get_ts_info from __dev_ethtool+0xa00/0x2648
 __dev_ethtool from dev_ethtool+0x160/0x234
 dev_ethtool from dev_ioctl+0x2cc/0x460
 dev_ioctl from sock_ioctl+0x1ec/0x524
 sock_ioctl from sys_ioctl+0x51c/0xa94
 sys_ioctl from ret_fast_syscall+0x0/0x44
 (...)
Segmentation fault

Check for ixp46x in ixp46x_ptp_find() before trying to set up
PTP to avoid this.

To avoid altering the returned error code from ixp4xx_hwtstamp_set()
which before this patch was -EOPNOTSUPP, we return -EOPNOTSUPP
from ixp4xx_hwtstamp_set() if ixp46x_ptp_find() fails no matter
the error code. The helper function ixp46x_ptp_find() helper
returns -ENODEV.

Fixes: 9055a2f59162 ("ixp4xx_eth: make ptp support a platform driver")
Signed-off-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260219-ixp4xx-fix-ethernet-v3-1-f235ccc3cd46@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xscale/ixp4xx_eth.c | 5 +----
 drivers/net/ethernet/xscale/ptp_ixp46x.c | 3 +++
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index e1e7f65553e7..b0faa0f1780d 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -403,15 +403,12 @@ static int ixp4xx_hwtstamp_set(struct net_device *netdev,
 	int ret;
 	int ch;
 
-	if (!cpu_is_ixp46x())
-		return -EOPNOTSUPP;
-
 	if (!netif_running(netdev))
 		return -EINVAL;
 
 	ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
 	if (ret)
-		return ret;
+		return -EOPNOTSUPP;
 
 	ch = PORT2CHANNEL(port);
 	regs = port->timesync_regs;
diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c
index 94203eb46e6b..93c64db22a69 100644
--- a/drivers/net/ethernet/xscale/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@@ -232,6 +232,9 @@ static struct ixp_clock ixp_clock;
 
 int ixp46x_ptp_find(struct ixp46x_ts_regs *__iomem *regs, int *phc_index)
 {
+	if (!cpu_is_ixp46x())
+		return -ENODEV;
+
 	*regs = ixp_clock.regs;
 	*phc_index = ptp_clock_index(ixp_clock.ptp_clock);
 

From 470c7ca2b4c3e3a51feeb952b7f97a775b5c49cd Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Thu, 19 Feb 2026 17:31:31 +0000
Subject: [PATCH 0086/1303] udplite: Fix null-ptr-deref in
 __udp_enqueue_schedule_skb().

syzbot reported null-ptr-deref of udp_sk(sk)->udp_prod_queue. [0]

Since the cited commit, udp_lib_init_sock() can fail, as can
udp_init_sock() and udpv6_init_sock().

Let's handle the error in udplite_sk_init() and udplitev6_sk_init().

[0]:
BUG: KASAN: null-ptr-deref in instrument_atomic_read include/linux/instrumented.h:82 [inline]
BUG: KASAN: null-ptr-deref in atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
BUG: KASAN: null-ptr-deref in __udp_enqueue_schedule_skb+0x151/0x1480 net/ipv4/udp.c:1719
Read of size 4 at addr 0000000000000008 by task syz.2.18/2944

CPU: 1 UID: 0 PID: 2944 Comm: syz.2.18 Not tainted syzkaller #0 PREEMPTLAZY
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
Call Trace:
 <IRQ>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 kasan_report+0xa2/0xe0 mm/kasan/report.c:595
 check_region_inline mm/kasan/generic.c:-1 [inline]
 kasan_check_range+0x264/0x2c0 mm/kasan/generic.c:200
 instrument_atomic_read include/linux/instrumented.h:82 [inline]
 atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
 __udp_enqueue_schedule_skb+0x151/0x1480 net/ipv4/udp.c:1719
 __udpv6_queue_rcv_skb net/ipv6/udp.c:795 [inline]
 udpv6_queue_rcv_one_skb+0xa2e/0x1ad0 net/ipv6/udp.c:906
 udp6_unicast_rcv_skb+0x227/0x380 net/ipv6/udp.c:1064
 ip6_protocol_deliver_rcu+0xe17/0x1540 net/ipv6/ip6_input.c:438
 ip6_input_finish+0x191/0x350 net/ipv6/ip6_input.c:489
 NF_HOOK+0x354/0x3f0 include/linux/netfilter.h:318
 ip6_input+0x16c/0x2b0 net/ipv6/ip6_input.c:500
 NF_HOOK+0x354/0x3f0 include/linux/netfilter.h:318
 __netif_receive_skb_one_core net/core/dev.c:6149 [inline]
 __netif_receive_skb+0xd3/0x370 net/core/dev.c:6262
 process_backlog+0x4d6/0x1160 net/core/dev.c:6614
 __napi_poll+0xae/0x320 net/core/dev.c:7678
 napi_poll net/core/dev.c:7741 [inline]
 net_rx_action+0x60d/0xdc0 net/core/dev.c:7893
 handle_softirqs+0x209/0x8d0 kernel/softirq.c:622
 do_softirq+0x52/0x90 kernel/softirq.c:523
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0xe7/0x120 kernel/softirq.c:450
 local_bh_enable include/linux/bottom_half.h:33 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:924 [inline]
 __dev_queue_xmit+0x109c/0x2dc0 net/core/dev.c:4856
 __ip6_finish_output net/ipv6/ip6_output.c:-1 [inline]
 ip6_finish_output+0x158/0x4e0 net/ipv6/ip6_output.c:219
 NF_HOOK_COND include/linux/netfilter.h:307 [inline]
 ip6_output+0x342/0x580 net/ipv6/ip6_output.c:246
 ip6_send_skb+0x1d7/0x3c0 net/ipv6/ip6_output.c:1984
 udp_v6_send_skb+0x9a5/0x1770 net/ipv6/udp.c:1442
 udp_v6_push_pending_frames+0xa2/0x140 net/ipv6/udp.c:1469
 udpv6_sendmsg+0xfe0/0x2830 net/ipv6/udp.c:1759
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg+0xe5/0x270 net/socket.c:742
 __sys_sendto+0x3eb/0x580 net/socket.c:2206
 __do_sys_sendto net/socket.c:2213 [inline]
 __se_sys_sendto net/socket.c:2209 [inline]
 __x64_sys_sendto+0xde/0x100 net/socket.c:2209
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd2/0xf20 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f67b4d9c629
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f67b5c98028 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f67b5015fa0 RCX: 00007f67b4d9c629
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007f67b4e32b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000040000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f67b5016038 R14: 00007f67b5015fa0 R15: 00007ffe3cb66dd8
 </TASK>

Fixes: b650bf0977d3 ("udp: remove busylock and add per NUMA queues")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260219173142.310741-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udplite.c | 3 +--
 net/ipv6/udplite.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index d3e621a11a1a..826e9e79eb19 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -20,10 +20,9 @@ EXPORT_SYMBOL(udplite_table);
 /* Designate sk as UDP-Lite socket */
 static int udplite_sk_init(struct sock *sk)
 {
-	udp_init_sock(sk);
 	pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
 		     "please contact the netdev mailing list\n");
-	return 0;
+	return udp_init_sock(sk);
 }
 
 static int udplite_rcv(struct sk_buff *skb)
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 2cec542437f7..e867721cda4d 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -16,10 +16,9 @@
 
 static int udplitev6_sk_init(struct sock *sk)
 {
-	udpv6_init_sock(sk);
 	pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
 		     "please contact the netdev mailing list\n");
-	return 0;
+	return udpv6_init_sock(sk);
 }
 
 static int udplitev6_rcv(struct sk_buff *skb)

From e123d9302d223767bd910bfbcfe607bae909f8ac Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:11 -0800
Subject: [PATCH 0087/1303] bnxt_en: Fix RSS context delete logic

We need to free the corresponding RSS context VNIC
in FW everytime an RSS context is deleted in driver.
Commit 667ac333dbb7 added a check to delete the VNIC
in FW only when netif_running() is true to help delete
RSS contexts with interface down.

Having that condition will make the driver leak VNICs
in FW whenever close() happens with active RSS contexts.
On the subsequent open(), as part of RSS context restoration,
we will end up trying to create extra VNICs for which we
did not make any reservation. FW can fail this request,
thereby making us lose active RSS contexts.

Suppose an RSS context is deleted already and we try to
process a delete request again, then the HWRM functions
will check for validity of the request and they simply
return if the resource is already freed. So, even for
delete-when-down cases, netif_running() check is not
necessary.

Remove the netif_running() condition check when deleting
an RSS context.

Reported-by: Jakub Kicinski <kicinski@meta.com>
Fixes: 667ac333dbb7 ("eth: bnxt: allow deleting RSS contexts when the device is down")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fb45e1dd1dd7..7768d9753e2d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10889,12 +10889,10 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	struct bnxt_ntuple_filter *ntp_fltr;
 	int i;
 
-	if (netif_running(bp->dev)) {
-		bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
-		for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
-			if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
-				bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
-		}
+	bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
+	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
+		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
+			bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
 	}
 	if (!all)
 		return;

From c1bbd9900d65ac65b9fce9f129e3369a04871570 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:12 -0800
Subject: [PATCH 0088/1303] bnxt_en: Fix deleting of Ntuple filters

Ntuple filters can be deleted when the interface
is down. The current code blindly sends the filter
delete command to FW. When the interface is down, all
the VNICs are deleted in the FW. When the VNIC is
freed in the FW, all the associated filters are also
freed. We need not send the free command explicitly.
Sending such command will generate FW error in the
dmesg.

In order to fix this, we can safely return from
bnxt_hwrm_cfa_ntuple_filter_free() when BNXT_STATE_OPEN
is not true which confirms the VNICs have been deleted.

Fixes: 8336a974f37d ("bnxt_en: Save user configured filters in a lookup list")
Suggested-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7768d9753e2d..8c73a723d23f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6240,6 +6240,9 @@ int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 	int rc;
 
 	set_bit(BNXT_FLTR_FW_DELETED, &fltr->base.state);
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state))
+		return 0;
+
 	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
 	if (rc)
 		return rc;

From ce5a0f4612dbacc805fe16719f9f6bd18352b70d Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:13 -0800
Subject: [PATCH 0089/1303] selftests: drv-net: rss_ctx: test RSS contexts
 persist after ifdown/up

Add a test to verify that RSS contexts persist across interface
down/up along with their associated Ntuple filters. Another test
that creates contexts/rules keeping interface down and test their
persistence is also added.

Tested on bnxt_en:

 TAP version 13
 1..1
 # timeout set to 0
 # selftests: drivers/net/hw: rss_ctx.py
 # TAP version 13
 # 1..2
 # ok 1 rss_ctx.test_rss_context_persist_create_and_ifdown
 # ok 2 rss_ctx.test_rss_context_persist_ifdown_and_create # SKIP Create context not supported with interface down
 # # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:1 error:0

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/hw/rss_ctx.py       | 100 +++++++++++++++++-
 1 file changed, 98 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ed7e405682f0..b9b7527c2c6b 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -4,13 +4,15 @@
 import datetime
 import random
 import re
+import time
 from lib.py import ksft_run, ksft_pr, ksft_exit
 from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import ksft_disruptive
 from lib.py import rand_port
-from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
+from lib.py import cmd, ethtool, ip, defer, GenerateTraffic, CmdExitFailure, wait_file
 
 
 def _rss_key_str(key):
@@ -809,6 +811,98 @@ def test_rss_default_context_rule(cfg):
                           'noise' : (0, 1) })
 
 
+@ksft_disruptive
+def test_rss_context_persist_ifupdown(cfg, pre_down=False):
+    """
+    Test that RSS contexts and their associated ntuple filters persist across
+    an interface down/up cycle.
+
+    """
+
+    require_ntuple(cfg)
+
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 6:
+        try:
+            ethtool(f"-L {cfg.ifname} combined 6")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except Exception as exc:
+            raise KsftSkipEx("Not enough queues for the test") from exc
+
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    ifup = defer(ip, f"link set dev {cfg.ifname} up")
+    if pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+
+    try:
+        ctx1_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+        defer(ethtool, f"-X {cfg.ifname} context {ctx1_id} delete")
+    except CmdExitFailure as exc:
+        raise KsftSkipEx("Create context not supported with interface down") from exc
+
+    ctx2_id = ethtool_create(cfg, "-X", "context new start 4 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx2_id} delete")
+
+    port_ctx2 = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_ctx2} context {ctx2_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    if not pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+    ifup.exec()
+
+    wait_file(f"/sys/class/net/{cfg.ifname}/carrier",
+        lambda x: x.strip() == "1", deadline=20)
+
+    remote_addr = cfg.remote_addr_v[cfg.addr_ipver]
+    for _ in range(10):
+        if cmd(f"ping -c 1 -W 1 {remote_addr}", fail=False).ret == 0:
+            break
+        time.sleep(1)
+    else:
+        raise KsftSkipEx("Cannot reach remote host after interface up")
+
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True)
+
+    data1 = [c for c in ctxs if c.get('context') == ctx1_id]
+    ksft_eq(len(data1), 1, f"Context {ctx1_id} should persist after ifup")
+
+    data2 = [c for c in ctxs if c.get('context') == ctx2_id]
+    ksft_eq(len(data2), 1, f"Context {ctx2_id} should persist after ifup")
+
+    _ntuple_rule_check(cfg, ntuple_id, ctx2_id)
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    main_traffic = sum(cnts[0:2])
+    ksft_ge(main_traffic, 18000, f"Main context traffic distribution: {cnts}")
+    ksft_lt(sum(cnts[2:6]), 500, f"Other context queues should be mostly empty: {cnts}")
+
+    _send_traffic_check(cfg, port_ctx2, f"context {ctx2_id}",
+                        {'target': (4, 5),
+                         'noise': (0, 1),
+                         'empty': (2, 3)})
+
+
+def test_rss_context_persist_create_and_ifdown(cfg):
+    """
+    Create RSS contexts then cycle the interface down and up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=False)
+
+
+def test_rss_context_persist_ifdown_and_create(cfg):
+    """
+    Bring interface down first, then create RSS contexts and bring up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=True)
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.context_cnt = None
@@ -823,7 +917,9 @@ def main() -> None:
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
                   test_flow_add_context_missing,
                   test_delete_rss_context_busy, test_rss_ntuple_addition,
-                  test_rss_default_context_rule],
+                  test_rss_default_context_rule,
+                  test_rss_context_persist_create_and_ifdown,
+                  test_rss_context_persist_ifdown_and_create],
                  args=(cfg, ))
     ksft_exit()
 

From d4f687fbbce45b5e88438e89b5e26c0c15847992 Mon Sep 17 00:00:00 2001
From: Ralf Lici <ralf@mandelbit.com>
Date: Wed, 18 Feb 2026 21:08:26 +0100
Subject: [PATCH 0090/1303] ovpn: tcp - fix packet extraction from stream

When processing TCP stream data in ovpn_tcp_recv, we receive large
cloned skbs from __strp_rcv that may contain multiple coalesced packets.
The current implementation has two bugs:

1. Header offset overflow: Using pskb_pull with large offsets on
   coalesced skbs causes skb->data - skb->head to exceed the u16 storage
   of skb->network_header. This causes skb_reset_network_header to fail
   on the inner decapsulated packet, resulting in packet drops.

2. Unaligned protocol headers: Extracting packets from arbitrary
   positions within the coalesced TCP stream provides no alignment
   guarantees for the packet data causing performance penalties on
   architectures without efficient unaligned access. Additionally,
   openvpn's 2-byte length prefix on TCP packets causes the subsequent
   4-byte opcode and packet ID fields to be inherently misaligned.

Fix both issues by allocating a new skb for each openvpn packet and
using skb_copy_bits to extract only the packet content into the new
buffer, skipping the 2-byte length prefix. Also, check the length before
invoking the function that performs the allocation to avoid creating an
invalid skb.

If the packet has to be forwarded to userspace the 2-byte prefix can be
pushed to the head safely, without misalignment.

As a side effect, this approach also avoids the expensive linearization
that pskb_pull triggers on cloned skbs with page fragments. In testing,
this resulted in TCP throughput improvements of up to 74%.

Fixes: 11851cbd60ea ("ovpn: implement TCP transport")
Signed-off-by: Ralf Lici <ralf@mandelbit.com>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ovpn/tcp.c | 57 ++++++++++++++++++++++++++++--------------
 1 file changed, 38 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
index ec2bbc28c196..5499c1572f3e 100644
--- a/drivers/net/ovpn/tcp.c
+++ b/drivers/net/ovpn/tcp.c
@@ -70,37 +70,56 @@ static void ovpn_tcp_to_userspace(struct ovpn_peer *peer, struct sock *sk,
 	peer->tcp.sk_cb.sk_data_ready(sk);
 }
 
+static struct sk_buff *ovpn_tcp_skb_packet(const struct ovpn_peer *peer,
+					   struct sk_buff *orig_skb,
+					   const int pkt_len, const int pkt_off)
+{
+	struct sk_buff *ovpn_skb;
+	int err;
+
+	/* create a new skb with only the content of the current packet */
+	ovpn_skb = netdev_alloc_skb(peer->ovpn->dev, pkt_len);
+	if (unlikely(!ovpn_skb))
+		goto err;
+
+	skb_copy_header(ovpn_skb, orig_skb);
+	err = skb_copy_bits(orig_skb, pkt_off, skb_put(ovpn_skb, pkt_len),
+			    pkt_len);
+	if (unlikely(err)) {
+		net_warn_ratelimited("%s: skb_copy_bits failed for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		kfree_skb(ovpn_skb);
+		goto err;
+	}
+
+	consume_skb(orig_skb);
+	return ovpn_skb;
+err:
+	kfree_skb(orig_skb);
+	return NULL;
+}
+
 static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
 {
 	struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp);
 	struct strp_msg *msg = strp_msg(skb);
-	size_t pkt_len = msg->full_len - 2;
-	size_t off = msg->offset + 2;
+	int pkt_len = msg->full_len - 2;
 	u8 opcode;
 
-	/* ensure skb->data points to the beginning of the openvpn packet */
-	if (!pskb_pull(skb, off)) {
-		net_warn_ratelimited("%s: packet too small for peer %u\n",
-				     netdev_name(peer->ovpn->dev), peer->id);
-		goto err;
-	}
-
-	/* strparser does not trim the skb for us, therefore we do it now */
-	if (pskb_trim(skb, pkt_len) != 0) {
-		net_warn_ratelimited("%s: trimming skb failed for peer %u\n",
-				     netdev_name(peer->ovpn->dev), peer->id);
-		goto err;
-	}
-
-	/* we need the first 4 bytes of data to be accessible
+	/* we need at least 4 bytes of data in the packet
 	 * to extract the opcode and the key ID later on
 	 */
-	if (!pskb_may_pull(skb, OVPN_OPCODE_SIZE)) {
+	if (unlikely(pkt_len < OVPN_OPCODE_SIZE)) {
 		net_warn_ratelimited("%s: packet too small to fetch opcode for peer %u\n",
 				     netdev_name(peer->ovpn->dev), peer->id);
 		goto err;
 	}
 
+	/* extract the packet into a new skb */
+	skb = ovpn_tcp_skb_packet(peer, skb, pkt_len, msg->offset + 2);
+	if (unlikely(!skb))
+		goto err;
+
 	/* DATA_V2 packets are handled in kernel, the rest goes to user space */
 	opcode = ovpn_opcode_from_skb(skb, 0);
 	if (unlikely(opcode != OVPN_DATA_V2)) {
@@ -113,7 +132,7 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
 		/* The packet size header must be there when sending the packet
 		 * to userspace, therefore we put it back
 		 */
-		skb_push(skb, 2);
+		*(__be16 *)__skb_push(skb, sizeof(u16)) = htons(pkt_len);
 		ovpn_tcp_to_userspace(peer, strp->sk, skb);
 		return;
 	}

From 97d5c8f5c09a604c4873c8348f58de3cea69a7df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomasz=20Paku=C5=82a?= <tomasz.pakula.oficjalny@gmail.com>
Date: Wed, 4 Feb 2026 22:44:55 +0100
Subject: [PATCH 0091/1303] HID: pidff: Fix condition effect bit clearing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As reported by MPDarkGuy on discord, NULL pointer dereferences were
happening because not all the conditional effects bits were cleared.

Properly clear all conditional effect bits from ffbit

Fixes: 7f3d7bc0df4b ("HID: pidff: Better quirk assigment when searching for fields")
Cc: stable@vger.kernel.org # 6.18.x
Signed-off-by: Tomasz Pakuła <tomasz.pakula.oficjalny@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/usbhid/hid-pidff.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c
index a4e700b40ba9..56d6af39ba81 100644
--- a/drivers/hid/usbhid/hid-pidff.c
+++ b/drivers/hid/usbhid/hid-pidff.c
@@ -1452,10 +1452,13 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 		hid_warn(pidff->hid, "unknown ramp effect layout\n");
 
 	if (PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) {
-		if (test_and_clear_bit(FF_SPRING, dev->ffbit)   ||
-		    test_and_clear_bit(FF_DAMPER, dev->ffbit)   ||
-		    test_and_clear_bit(FF_FRICTION, dev->ffbit) ||
-		    test_and_clear_bit(FF_INERTIA, dev->ffbit))
+		bool test = false;
+
+		test |= test_and_clear_bit(FF_SPRING, dev->ffbit);
+		test |= test_and_clear_bit(FF_DAMPER, dev->ffbit);
+		test |= test_and_clear_bit(FF_FRICTION, dev->ffbit);
+		test |= test_and_clear_bit(FF_INERTIA, dev->ffbit);
+		if (test)
 			hid_warn(pidff->hid, "unknown condition effect layout\n");
 	}
 

From cfc83a3c71517b59c1047db57da31e26a9dc2f33 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Mon, 16 Feb 2026 11:20:29 +0100
Subject: [PATCH 0092/1303] batman-adv: Avoid double-rtnl_lock ELP metric
 worker
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

batadv_v_elp_get_throughput() might be called when the RTNL lock is already
held. This could be problematic when the work queue item is cancelled via
cancel_delayed_work_sync() in batadv_v_elp_iface_disable(). In this case,
an rtnl_lock() would cause a deadlock.

To avoid this, rtnl_trylock() was used in this function to skip the
retrieval of the ethtool information in case the RTNL lock was already
held.

But for cfg80211 interfaces, batadv_get_real_netdev() was called - which
also uses rtnl_lock(). The approach for __ethtool_get_link_ksettings() must
also be used instead and the lockless version __batadv_get_real_netdev()
has to be called.

Cc: stable@vger.kernel.org
Fixes: 8c8ecc98f5c6 ("batman-adv: Drop unmanaged ELP metric worker")
Reported-by: Christian Schmidbauer <github@grische.xyz>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Tested-by: Sören Skaarup <freifunk_nordm4nn@gmx.de>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_v_elp.c      | 10 +++++++++-
 net/batman-adv/hard-interface.c |  8 ++++----
 net/batman-adv/hard-interface.h |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index cb16c1ed2a58..fe832093d421 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh,
 			/* unsupported WiFi driver version */
 			goto default_throughput;
 
-		real_netdev = batadv_get_real_netdev(hard_iface->net_dev);
+		/* only use rtnl_trylock because the elp worker will be cancelled while
+		 * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise
+		 * wait forever when the elp work_item was started and it is then also
+		 * trying to rtnl_lock
+		 */
+		if (!rtnl_trylock())
+			return false;
+		real_netdev = __batadv_get_real_netdev(hard_iface->net_dev);
+		rtnl_unlock();
 		if (!real_netdev)
 			goto default_throughput;
 
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 5113f879736b..1c488049d554 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev)
 }
 
 /**
- * batadv_get_real_netdevice() - check if the given netdev struct is a virtual
+ * __batadv_get_real_netdev() - check if the given netdev struct is a virtual
  *  interface on top of another 'real' interface
  * @netdev: the device to check
  *
@@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev)
  * Return: the 'real' net device or the original net device and NULL in case
  *  of an error.
  */
-static struct net_device *batadv_get_real_netdevice(struct net_device *netdev)
+struct net_device *__batadv_get_real_netdev(struct net_device *netdev)
 {
 	struct batadv_hard_iface *hard_iface = NULL;
 	struct net_device *real_netdev = NULL;
@@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device)
 	struct net_device *real_netdev;
 
 	rtnl_lock();
-	real_netdev = batadv_get_real_netdevice(net_device);
+	real_netdev = __batadv_get_real_netdev(net_device);
 	rtnl_unlock();
 
 	return real_netdev;
@@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device)
 	if (batadv_is_cfg80211_netdev(net_device))
 		wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT;
 
-	real_netdev = batadv_get_real_netdevice(net_device);
+	real_netdev = __batadv_get_real_netdev(net_device);
 	if (!real_netdev)
 		return wifi_flags;
 
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 9db8a310961e..9ba8fb2bdceb 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -67,6 +67,7 @@ enum batadv_hard_if_bcast {
 
 extern struct notifier_block batadv_hard_if_notifier;
 
+struct net_device *__batadv_get_real_netdev(struct net_device *net_device);
 struct net_device *batadv_get_real_netdev(struct net_device *net_device);
 bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface);
 bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface);

From 08f97454b7fa39bfcf82524955c771d2d693d6fe Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 22 Feb 2026 13:35:13 +0000
Subject: [PATCH 0093/1303] KVM: arm64: Fix protected mode handling of pages
 larger than 4kB

Since 3669ddd8fa8b5 ("KVM: arm64: Add a range to pkvm_mappings"),
pKVM tracks the memory that has been mapped into a guest in a
side data structure. Crucially, it uses it to find out whether
a page has already been mapped, and therefore refuses to map it
twice. So far, so good.

However, this very patch completely breaks non-4kB page support,
with guests being unable to boot. The most obvious symptom is that
we take the same fault repeatedly, and not making forward progress.
A quick investigation shows that this is because of the above
rejection code.

As it turns out, there are multiple issues at play:

- while the HPFAR_EL2 register gives you the faulting IPA minus
  the bottom 12 bits, it will still give you the extra bits that
  are part of the page offset for anything larger than 4kB,
  even for a level-3 mapping

- pkvm_pgtable_stage2_map() assumes that the address passed as
  a parameter is aligned to the size of the intended mapping

- the faulting address is only aligned for a non-page mapping

When the planets are suitably aligned (pun intended), the guest
faults on a page by accessing it past the bottom 4kB, and extra bits
get set in the HPFAR_EL2 register. If this results in a page mapping
(which is likely with large granule sizes), nothing aligns it further
down, and pkvm_mapping_iter_first() finds an intersection that
doesn't really exist. We assume this is a spurious fault and return
-EAGAIN. And again...

This doesn't hit outside of the protected code, as the page table
code always aligns the IPA down to a page boundary, hiding the issue
for everyone else.

Fix it by always forcing the alignment on vma_pagesize, irrespective
of the value of vma_pagesize.

Fixes: 3669ddd8fa8b5 ("KVM: arm64: Add a range to pkvm_mappings")
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://https://patch.msgid.link/20260222141000.3084258-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/kvm/mmu.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c5d259810b2..3952415c4f83 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1753,14 +1753,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	/*
-	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
-	 * ensure we find the right PFN and lay down the mapping in the right
-	 * place.
+	 * Both the canonical IPA and fault IPA must be aligned to the
+	 * mapping size to ensure we find the right PFN and lay down the
+	 * mapping in the right place.
 	 */
-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
-		fault_ipa &= ~(vma_pagesize - 1);
-		ipa &= ~(vma_pagesize - 1);
-	}
+	fault_ipa = ALIGN_DOWN(fault_ipa, vma_pagesize);
+	ipa = ALIGN_DOWN(ipa, vma_pagesize);
 
 	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);

From 663c28469d3274d6456f206a6671c91493d85ff1 Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Sat, 21 Feb 2026 01:59:44 -0300
Subject: [PATCH 0094/1303] smb: client: fix cifs_pick_channel when channels
 are equally loaded

cifs_pick_channel uses (start % chan_count) when channels are equally
loaded, but that can return a channel that failed the eligibility
checks.

Drop the fallback and return the scan-selected channel instead. If none
is eligible, keep the existing behavior of using the primary channel.

Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Acked-by: Meetakshi Setiya <msetiya@microsoft.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/transport.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 75697f6d2566..05f8099047e1 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -807,16 +807,21 @@ cifs_cancelled_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 }
 
 /*
- * Return a channel (master if none) of @ses that can be used to send
- * regular requests.
+ * cifs_pick_channel - pick an eligible channel for network operations
  *
- * If we are currently binding a new channel (negprot/sess.setup),
- * return the new incomplete channel.
+ * @ses: session reference
+ *
+ * Select an eligible channel (not terminating and not marked as needing
+ * reconnect), preferring the least loaded one. If no eligible channel is
+ * found, fall back to the primary channel (index 0).
+ *
+ * Return: TCP_Server_Info pointer for the chosen channel, or NULL if @ses is
+ * NULL.
  */
 struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 {
 	uint index = 0;
-	unsigned int min_in_flight = UINT_MAX, max_in_flight = 0;
+	unsigned int min_in_flight = UINT_MAX;
 	struct TCP_Server_Info *server = NULL;
 	int i, start, cur;
 
@@ -846,14 +851,8 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 			min_in_flight = server->in_flight;
 			index = cur;
 		}
-		if (server->in_flight > max_in_flight)
-			max_in_flight = server->in_flight;
 	}
 
-	/* if all channels are equally loaded, fall back to round-robin */
-	if (min_in_flight == max_in_flight)
-		index = (uint)start % ses->chan_count;
-
 	server = ses->chans[index].server;
 	spin_unlock(&ses->chan_lock);
 

From 2692c614f8f05929d692b3dbfd3faef1f00fbaf0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 10 Feb 2026 14:58:22 +0100
Subject: [PATCH 0095/1303] device property: Allow secondary lookup in
 fwnode_get_next_child_node()

When device_get_child_node_count() got split to the fwnode and device
respective APIs, the fwnode didn't inherit the ability to traverse over
the secondary fwnode. Hence any user, that switches from device to fwnode
API misses this feature. In particular, this was revealed by the commit
1490cbb9dbfd ("device property: Split fwnode_get_child_node_count()")
that effectively broke the GPIO enumeration on Intel Galileo boards.
Fix this by moving the secondary lookup from device to fwnode API.

Note, in general no device_*() API should go into the depth of the fwnode
implementation.

Fixes: 114dbb4fa7c4 ("drivers property: When no children in primary, try secondary")
Cc: stable@vger.kernel.org
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Link: https://patch.msgid.link/20260210135822.47335-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/property.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 6a63860579dd..8d9a34be57fb 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -797,7 +797,18 @@ struct fwnode_handle *
 fwnode_get_next_child_node(const struct fwnode_handle *fwnode,
 			   struct fwnode_handle *child)
 {
-	return fwnode_call_ptr_op(fwnode, get_next_child_node, child);
+	struct fwnode_handle *next;
+
+	if (IS_ERR_OR_NULL(fwnode))
+		return NULL;
+
+	/* Try to find a child in primary fwnode */
+	next = fwnode_call_ptr_op(fwnode, get_next_child_node, child);
+	if (next)
+		return next;
+
+	/* When no more children in primary, continue with secondary */
+	return fwnode_call_ptr_op(fwnode->secondary, get_next_child_node, child);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
 
@@ -841,19 +852,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node);
 struct fwnode_handle *device_get_next_child_node(const struct device *dev,
 						 struct fwnode_handle *child)
 {
-	const struct fwnode_handle *fwnode = dev_fwnode(dev);
-	struct fwnode_handle *next;
-
-	if (IS_ERR_OR_NULL(fwnode))
-		return NULL;
-
-	/* Try to find a child in primary fwnode */
-	next = fwnode_get_next_child_node(fwnode, child);
-	if (next)
-		return next;
-
-	/* When no more children in primary, continue with secondary */
-	return fwnode_get_next_child_node(fwnode->secondary, child);
+	return fwnode_get_next_child_node(dev_fwnode(dev), child);
 }
 EXPORT_SYMBOL_GPL(device_get_next_child_node);
 

From 5dd69b864911ae3847365e8bafe7854e79fbeecb Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 29 Jan 2026 09:51:10 -0800
Subject: [PATCH 0096/1303] hwmon: (macsmc) Fix regressions in Apple Silicon
 SMC hwmon driver

The recently added macsmc-hwmon driver contained several critical
bugs in its sensor population logic and float conversion routines.

Specifically:
- The voltage sensor population loop used the wrong prefix ("volt-"
  instead of "voltage-") and incorrectly assigned sensors to the
  temperature sensor array (hwmon->temp.sensors) instead of the
  voltage sensor array (hwmon->volt.sensors). This would lead to
  out-of-bounds memory access or data corruption when both temperature
  and voltage sensors were present.
- The float conversion in macsmc_hwmon_write_f32() had flawed exponent
  logic for values >= 2^24 and lacked masking for the mantissa, which
  could lead to incorrect values being written to the SMC.

Fix these issues to ensure correct sensor registration and reliable
manual fan control.

Confirm that the reported overflow in FIELD_PREP is fixed by declaring
macsmc_hwmon_write_f32() as __always_inline for a compile test.

Fixes: 785205fd8139 ("hwmon: Add Apple Silicon SMC hwmon driver")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://lore.kernel.org/linux-hwmon/20260119195817.GA1035354@ax162/
Cc: James Calligeros <jcalligeros99@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Neal Gompa <neal@gompa.dev>
Cc: Janne Grunau <j@jannau.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Link: https://lore.kernel.org/r/20260129175112.3751907-2-linux@roeck-us.net
Reviewed-by: James Calligeros <jcalligeros99@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/macsmc-hwmon.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c
index 1c0bbec7e8eb..40d25c81b443 100644
--- a/drivers/hwmon/macsmc-hwmon.c
+++ b/drivers/hwmon/macsmc-hwmon.c
@@ -228,25 +228,22 @@ static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value)
 {
 	u64 val;
 	u32 fval = 0;
-	int exp = 0, neg;
+	int exp, neg;
 
+	neg = value < 0;
 	val = abs(value);
-	neg = val != value;
 
 	if (val) {
-		int msb = __fls(val) - exp;
+		exp = __fls(val);
 
-		if (msb > 23) {
-			val >>= msb - FLT_MANT_BIAS;
-			exp -= msb - FLT_MANT_BIAS;
-		} else if (msb < 23) {
-			val <<= FLT_MANT_BIAS - msb;
-			exp += msb;
-		}
+		if (exp > 23)
+			val >>= exp - 23;
+		else
+			val <<= 23 - exp;
 
 		fval = FIELD_PREP(FLT_SIGN_MASK, neg) |
 		       FIELD_PREP(FLT_EXP_MASK, exp + FLT_EXP_BIAS) |
-		       FIELD_PREP(FLT_MANT_MASK, val);
+		       FIELD_PREP(FLT_MANT_MASK, val & FLT_MANT_MASK);
 	}
 
 	return apple_smc_write_u32(smc, key, fval);
@@ -663,8 +660,8 @@ static int macsmc_hwmon_populate_sensors(struct macsmc_hwmon *hwmon,
 		if (!hwmon->volt.sensors)
 			return -ENOMEM;
 
-		for_each_child_of_node_with_prefix(hwmon_node, key_node, "volt-") {
-			sensor = &hwmon->temp.sensors[hwmon->temp.count];
+		for_each_child_of_node_with_prefix(hwmon_node, key_node, "voltage-") {
+			sensor = &hwmon->volt.sensors[hwmon->volt.count];
 			if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) {
 				sensor->attrs = HWMON_I_INPUT;
 

From 579b86f3c26fee97996e68c1cbfb7461711f3de3 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 29 Jan 2026 09:51:11 -0800
Subject: [PATCH 0097/1303] hwmon: (macsmc) Fix overflows, underflows, and sign
 extension

The macsmc-hwmon driver experienced several issues related to value
scaling and type conversion:

1. macsmc_hwmon_read_f32_scaled() clipped values to INT_MAX/INT_MIN.
   On 64-bit systems, hwmon supports long values, so clipping to
   32-bit range was premature and caused loss of range for high-power
   sensors. Changed it to use long and clip to LONG_MAX/LONG_MIN.
2. The overflow check in macsmc_hwmon_read_f32_scaled() used 1UL,
   which is 32-bit on some platforms. Switched to 1ULL.
3. macsmc_hwmon_read_key() used a u32 temporary variable for f32
   values. When assigned to a 64-bit long, negative values were
   zero-extended instead of sign-extended, resulting in large
   positive numbers.
4. macsmc_hwmon_read_ioft_scaled() used mult_frac() which could
   overflow during intermediate multiplication. Switched to
   mul_u64_u32_div() to handle the 64-bit multiplication safely.
5. ioft values (unsigned 48.16) could overflow long when scaled
   by 1,000,000. Added explicit clipping to LONG_MAX in the caller.
6. macsmc_hwmon_write_f32() truncated its long argument to int,
   potentially causing issues for large values.

Fix these issues by using appropriate types and helper functions.

Fixes: 785205fd8139 ("hwmon: Add Apple Silicon SMC hwmon driver")
Cc: James Calligeros <jcalligeros99@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Neal Gompa <neal@gompa.dev>
Cc: Janne Grunau <j@jannau.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20260129175112.3751907-3-linux@roeck-us.net
Reviewed-by: James Calligeros <jcalligeros99@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/macsmc-hwmon.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c
index 40d25c81b443..1500ec2cc9f8 100644
--- a/drivers/hwmon/macsmc-hwmon.c
+++ b/drivers/hwmon/macsmc-hwmon.c
@@ -22,6 +22,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/hwmon.h>
+#include <linux/math64.h>
 #include <linux/mfd/macsmc.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -130,7 +131,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key,
 	if (ret < 0)
 		return ret;
 
-	*p = mult_frac(val, scale, 65536);
+	*p = mul_u64_u32_div(val, scale, 65536);
 
 	return 0;
 }
@@ -140,7 +141,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key,
  * them.
  */
 static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key,
-					int *p, int scale)
+					long *p, int scale)
 {
 	u32 fval;
 	u64 val;
@@ -162,21 +163,21 @@ static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key,
 		val = 0;
 	else if (exp < 0)
 		val >>= -exp;
-	else if (exp != 0 && (val & ~((1UL << (64 - exp)) - 1))) /* overflow */
+	else if (exp != 0 && (val & ~((1ULL << (64 - exp)) - 1))) /* overflow */
 		val = U64_MAX;
 	else
 		val <<= exp;
 
 	if (fval & FLT_SIGN_MASK) {
-		if (val > (-(s64)INT_MIN))
-			*p = INT_MIN;
+		if (val > (u64)LONG_MAX + 1)
+			*p = LONG_MIN;
 		else
-			*p = -val;
+			*p = -(long)val;
 	} else {
-		if (val > INT_MAX)
-			*p = INT_MAX;
+		if (val > (u64)LONG_MAX)
+			*p = LONG_MAX;
 		else
-			*p = val;
+			*p = (long)val;
 	}
 
 	return 0;
@@ -195,7 +196,7 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 	switch (sensor->info.type_code) {
 	/* 32-bit IEEE 754 float */
 	case __SMC_KEY('f', 'l', 't', ' '): {
-		u32 flt_ = 0;
+		long flt_ = 0;
 
 		ret = macsmc_hwmon_read_f32_scaled(smc, sensor->macsmc_key,
 						   &flt_, scale);
@@ -214,7 +215,10 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 		if (ret)
 			return ret;
 
-		*val = (long)ioft;
+		if (ioft > LONG_MAX)
+			*val = LONG_MAX;
+		else
+			*val = (long)ioft;
 		break;
 	}
 	default:
@@ -224,7 +228,7 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 	return 0;
 }
 
-static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value)
+static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, long value)
 {
 	u64 val;
 	u32 fval = 0;

From ac209a7d816d918582d0d6387e93d02679f9c8ed Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 14 Feb 2026 17:03:27 -0800
Subject: [PATCH 0098/1303] hwmon: (emc1403) correct a malformed email address

Add a closing '>' to Kalhan's emaill address.

line 60:  Kalhan Trisal <kalhan.trisal@intel.com

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20260215010327.1687304-1-rdunlap@infradead.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/emc1403.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/hwmon/emc1403.rst b/Documentation/hwmon/emc1403.rst
index 57f833b1a800..77060d515323 100644
--- a/Documentation/hwmon/emc1403.rst
+++ b/Documentation/hwmon/emc1403.rst
@@ -57,7 +57,7 @@ Supported chips:
 	- https://ww1.microchip.com/downloads/en/DeviceDoc/EMC1438%20DS%20Rev.%201.0%20(04-29-10).pdf
 
 Author:
-    Kalhan Trisal <kalhan.trisal@intel.com
+    Kalhan Trisal <kalhan.trisal@intel.com>
 
 
 Description

From b7497b5a99f54ab8dcda5b14a308385b2fb03d8d Mon Sep 17 00:00:00 2001
From: Hao Yu <haoyufine@gmail.com>
Date: Mon, 23 Feb 2026 01:03:31 +0800
Subject: [PATCH 0099/1303] hwmon: (aht10) Fix initialization commands for
 AHT20

According to the AHT20 datasheet (updated to V1.0 after the 2023.09
version), the initialization command for AHT20 is 0b10111110 (0xBE).
The previous sequence (0xE1) used in earlier versions is no longer
compatible with newer AHT20 sensors. Update the initialization
command to ensure the sensor is properly initialized.

While at it, use binary notation for DHT20_CMD_INIT to match the notation
used in the datasheet.

Fixes: d2abcb5cc885 ("hwmon: (aht10) Add support for compatible aht20")
Signed-off-by: Hao Yu <haoyufine@gmail.com>
Link: https://lore.kernel.org/r/20260222170332.1616-3-haoyufine@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/aht10.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/aht10.c b/drivers/hwmon/aht10.c
index 007befdba977..4ce019d2cc80 100644
--- a/drivers/hwmon/aht10.c
+++ b/drivers/hwmon/aht10.c
@@ -37,7 +37,9 @@
 #define AHT10_CMD_MEAS	0b10101100
 #define AHT10_CMD_RST	0b10111010
 
-#define DHT20_CMD_INIT	0x71
+#define AHT20_CMD_INIT	0b10111110
+
+#define DHT20_CMD_INIT	0b01110001
 
 /*
  * Flags in the answer byte/command
@@ -341,7 +343,7 @@ static int aht10_probe(struct i2c_client *client)
 		data->meas_size = AHT20_MEAS_SIZE;
 		data->crc8 = true;
 		crc8_populate_msb(crc8_table, AHT20_CRC8_POLY);
-		data->init_cmd = AHT10_CMD_INIT;
+		data->init_cmd = AHT20_CMD_INIT;
 		break;
 	case dht20:
 		data->meas_size = AHT20_MEAS_SIZE;

From be704107e79696e855aa41e901a926039b6d2410 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Thu, 19 Feb 2026 16:55:30 -0600
Subject: [PATCH 0100/1303] regulator: dt-bindings: mt6359: make regulator
 names unique

Update the example devicetree with unique regulator names for all
regulators. This reflects the same change made to the actual .dtsi file.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260219-mtk-mt6359-fix-regulator-names-v1-2-ee0fcebfe1d9@baylibre.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/mt6359-regulator.yaml       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
index d6b3b5a5c0b3..fe4ac9350ba0 100644
--- a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
@@ -287,7 +287,7 @@ examples:
           regulator-max-microvolt = <1700000>;
         };
         mt6359_vrfck_1_ldo_reg: ldo_vrfck_1 {
-          regulator-name = "vrfck";
+          regulator-name = "vrfck_1";
           regulator-min-microvolt = <1240000>;
           regulator-max-microvolt = <1600000>;
         };
@@ -309,7 +309,7 @@ examples:
           regulator-max-microvolt = <3300000>;
         };
         mt6359_vemc_1_ldo_reg: ldo_vemc_1 {
-          regulator-name = "vemc";
+          regulator-name = "vemc_1";
           regulator-min-microvolt = <2500000>;
           regulator-max-microvolt = <3300000>;
         };

From bfcaf4e8ae9b4f52b97fb04ce03be3a01d41cdd0 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 16 Feb 2026 14:14:33 +0100
Subject: [PATCH 0101/1303] rust: io: macro_export io_define_read!() and
 io_define_write!()

Currently, the define_read!() and define_write!() I/O macros are crate
public. The only user outside of the I/O module is PCI (for the
configurations space I/O backend). Consequently, when CONFIG_PCI=n this
causes a compile time warning [1].

In order to fix this, rename the macros to io_define_read!() and
io_define_write!() and use #[macro_export] to export them.

This is better than making the crate public visibility conditional, as
eventually subsystems will have their own crate.

Also, I/O backends are valid to be implemented by drivers as well. For
instance, there are devices (such as GPUs) that run firmware which
allows to program other devices only accessible through the primary
device through indirect I/O.

Since the macros are now public, also add the corresponding
documentation.

Fixes: 121d87b28e1d ("rust: io: separate generic I/O helpers from MMIO implementation")
Reported-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Closes: https://lore.kernel.org/driver-core/CANiq72khOYkt6t5zwMvSiyZvWWHMZuNCMERXu=7K=_5tT-8Pgg@mail.gmail.com/ [1]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Link: https://patch.msgid.link/20260216131534.65008-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/io.rs     | 131 ++++++++++++++++++++++++++++--------------
 rust/kernel/pci/io.rs |  24 ++++----
 2 files changed, 101 insertions(+), 54 deletions(-)

diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs
index c1cca7b438c3..e5fba6bf6db0 100644
--- a/rust/kernel/io.rs
+++ b/rust/kernel/io.rs
@@ -139,9 +139,9 @@ pub fn maxsize(&self) -> usize {
 
 /// Internal helper macros used to invoke C MMIO read functions.
 ///
-/// This macro is intended to be used by higher-level MMIO access macros (define_read) and provides
-/// a unified expansion for infallible vs. fallible read semantics. It emits a direct call into the
-/// corresponding C helper and performs the required cast to the Rust return type.
+/// This macro is intended to be used by higher-level MMIO access macros (io_define_read) and
+/// provides a unified expansion for infallible vs. fallible read semantics. It emits a direct call
+/// into the corresponding C helper and performs the required cast to the Rust return type.
 ///
 /// # Parameters
 ///
@@ -166,9 +166,9 @@ macro_rules! call_mmio_read {
 
 /// Internal helper macros used to invoke C MMIO write functions.
 ///
-/// This macro is intended to be used by higher-level MMIO access macros (define_write) and provides
-/// a unified expansion for infallible vs. fallible write semantics. It emits a direct call into the
-/// corresponding C helper and performs the required cast to the Rust return type.
+/// This macro is intended to be used by higher-level MMIO access macros (io_define_write) and
+/// provides a unified expansion for infallible vs. fallible write semantics. It emits a direct call
+/// into the corresponding C helper and performs the required cast to the Rust return type.
 ///
 /// # Parameters
 ///
@@ -193,7 +193,30 @@ macro_rules! call_mmio_write {
     }};
 }
 
-macro_rules! define_read {
+/// Generates an accessor method for reading from an I/O backend.
+///
+/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
+/// (infallible) or runtime bounds-checked (fallible) read methods. It abstracts the address
+/// calculation and bounds checking, and delegates the actual I/O read operation to a specified
+/// helper macro, making it generic over different I/O backends.
+///
+/// # Parameters
+///
+/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
+///   `IoKnownSize` for compile-time checks and returns the value directly. `fallible` performs
+///   runtime checks against `maxsize()` and returns a `Result<T>`.
+/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
+///   `#[cfg(CONFIG_64BIT)]` or inline directives).
+/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
+/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `read32`,
+///   `try_read8`).
+/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
+///   (e.g., `call_mmio_read`).
+/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
+///   `$call_macro`.
+/// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`).
+#[macro_export]
+macro_rules! io_define_read {
     (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) ->
      $type_name:ty) => {
         /// Read IO data from a given offset known at compile time.
@@ -226,9 +249,33 @@ macro_rules! define_read {
         }
     };
 }
-pub(crate) use define_read;
+pub use io_define_read;
 
-macro_rules! define_write {
+/// Generates an accessor method for writing to an I/O backend.
+///
+/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
+/// (infallible) or runtime bounds-checked (fallible) write methods. It abstracts the address
+/// calculation and bounds checking, and delegates the actual I/O write operation to a specified
+/// helper macro, making it generic over different I/O backends.
+///
+/// # Parameters
+///
+/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
+///   `IoKnownSize` for compile-time checks and returns `()`. `fallible` performs runtime checks
+///   against `maxsize()` and returns a `Result`.
+/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
+///   `#[cfg(CONFIG_64BIT)]` or inline directives).
+/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
+/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `write32`,
+///   `try_write8`).
+/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
+///   (e.g., `call_mmio_write`).
+/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
+///   `$call_macro`.
+/// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use
+///   of `<-` before the type to denote a write operation.
+#[macro_export]
+macro_rules! io_define_write {
     (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <-
      $type_name:ty) => {
         /// Write IO data from a given offset known at compile time.
@@ -259,7 +306,7 @@ macro_rules! define_write {
         }
     };
 }
-pub(crate) use define_write;
+pub use io_define_write;
 
 /// Checks whether an access of type `U` at the given `offset`
 /// is valid within this region.
@@ -509,40 +556,40 @@ fn maxsize(&self) -> usize {
         self.0.maxsize()
     }
 
-    define_read!(fallible, try_read8, call_mmio_read(readb) -> u8);
-    define_read!(fallible, try_read16, call_mmio_read(readw) -> u16);
-    define_read!(fallible, try_read32, call_mmio_read(readl) -> u32);
-    define_read!(
+    io_define_read!(fallible, try_read8, call_mmio_read(readb) -> u8);
+    io_define_read!(fallible, try_read16, call_mmio_read(readw) -> u16);
+    io_define_read!(fallible, try_read32, call_mmio_read(readl) -> u32);
+    io_define_read!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         try_read64,
         call_mmio_read(readq) -> u64
     );
 
-    define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8);
-    define_write!(fallible, try_write16, call_mmio_write(writew) <- u16);
-    define_write!(fallible, try_write32, call_mmio_write(writel) <- u32);
-    define_write!(
+    io_define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8);
+    io_define_write!(fallible, try_write16, call_mmio_write(writew) <- u16);
+    io_define_write!(fallible, try_write32, call_mmio_write(writel) <- u32);
+    io_define_write!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         try_write64,
         call_mmio_write(writeq) <- u64
     );
 
-    define_read!(infallible, read8, call_mmio_read(readb) -> u8);
-    define_read!(infallible, read16, call_mmio_read(readw) -> u16);
-    define_read!(infallible, read32, call_mmio_read(readl) -> u32);
-    define_read!(
+    io_define_read!(infallible, read8, call_mmio_read(readb) -> u8);
+    io_define_read!(infallible, read16, call_mmio_read(readw) -> u16);
+    io_define_read!(infallible, read32, call_mmio_read(readl) -> u32);
+    io_define_read!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         read64,
         call_mmio_read(readq) -> u64
     );
 
-    define_write!(infallible, write8, call_mmio_write(writeb) <- u8);
-    define_write!(infallible, write16, call_mmio_write(writew) <- u16);
-    define_write!(infallible, write32, call_mmio_write(writel) <- u32);
-    define_write!(
+    io_define_write!(infallible, write8, call_mmio_write(writeb) <- u8);
+    io_define_write!(infallible, write16, call_mmio_write(writew) <- u16);
+    io_define_write!(infallible, write32, call_mmio_write(writel) <- u32);
+    io_define_write!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         write64,
@@ -566,40 +613,40 @@ pub unsafe fn from_raw(raw: &MmioRaw<SIZE>) -> &Self {
         unsafe { &*core::ptr::from_ref(raw).cast() }
     }
 
-    define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    define_read!(
+    io_define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
+    io_define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
+    io_define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
+    io_define_read!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         pub read64_relaxed,
         call_mmio_read(readq_relaxed) -> u64
     );
 
-    define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    define_read!(
+    io_define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
+    io_define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
+    io_define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
+    io_define_read!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         pub try_read64_relaxed,
         call_mmio_read(readq_relaxed) -> u64
     );
 
-    define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    define_write!(
+    io_define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
+    io_define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
+    io_define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
+    io_define_write!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         pub write64_relaxed,
         call_mmio_write(writeq_relaxed) <- u64
     );
 
-    define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    define_write!(
+    io_define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
+    io_define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
+    io_define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
+    io_define_write!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         pub try_write64_relaxed,
diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs
index 6ca4cf75594c..fb6edab2aea7 100644
--- a/rust/kernel/pci/io.rs
+++ b/rust/kernel/pci/io.rs
@@ -8,8 +8,8 @@
     device,
     devres::Devres,
     io::{
-        define_read,
-        define_write,
+        io_define_read,
+        io_define_write,
         Io,
         IoCapable,
         IoKnownSize,
@@ -88,7 +88,7 @@ pub struct ConfigSpace<'a, S: ConfigSpaceKind = Extended> {
 /// Internal helper macros used to invoke C PCI configuration space read functions.
 ///
 /// This macro is intended to be used by higher-level PCI configuration space access macros
-/// (define_read) and provides a unified expansion for infallible vs. fallible read semantics. It
+/// (io_define_read) and provides a unified expansion for infallible vs. fallible read semantics. It
 /// emits a direct call into the corresponding C helper and performs the required cast to the Rust
 /// return type.
 ///
@@ -117,9 +117,9 @@ macro_rules! call_config_read {
 /// Internal helper macros used to invoke C PCI configuration space write functions.
 ///
 /// This macro is intended to be used by higher-level PCI configuration space access macros
-/// (define_write) and provides a unified expansion for infallible vs. fallible read semantics. It
-/// emits a direct call into the corresponding C helper and performs the required cast to the Rust
-/// return type.
+/// (io_define_write) and provides a unified expansion for infallible vs. fallible read semantics.
+/// It emits a direct call into the corresponding C helper and performs the required cast to the
+/// Rust return type.
 ///
 /// # Parameters
 ///
@@ -163,13 +163,13 @@ fn maxsize(&self) -> usize {
     // PCI configuration space does not support fallible operations.
     // The default implementations from the Io trait are not used.
 
-    define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8);
-    define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16);
-    define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32);
+    io_define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8);
+    io_define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16);
+    io_define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32);
 
-    define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8);
-    define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16);
-    define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32);
+    io_define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8);
+    io_define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16);
+    io_define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32);
 }
 
 impl<'a, S: ConfigSpaceKind> IoKnownSize for ConfigSpace<'a, S> {

From c5794709bc9105935dbedef8b9cf9c06f2b559fa Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Tue, 17 Feb 2026 20:28:29 -0800
Subject: [PATCH 0102/1303] ksmbd: Compare MACs in constant time

To prevent timing attacks, MAC comparisons need to be constant-time.
Replace the memcmp() with the correct function, crypto_memneq().

Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/Kconfig   | 1 +
 fs/smb/server/auth.c    | 4 +++-
 fs/smb/server/smb2pdu.c | 5 +++--
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig
index 2775162c535c..12594879cb64 100644
--- a/fs/smb/server/Kconfig
+++ b/fs/smb/server/Kconfig
@@ -13,6 +13,7 @@ config SMB_SERVER
 	select CRYPTO_LIB_MD5
 	select CRYPTO_LIB_SHA256
 	select CRYPTO_LIB_SHA512
+	select CRYPTO_LIB_UTILS
 	select CRYPTO_CMAC
 	select CRYPTO_AEAD2
 	select CRYPTO_CCM
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 580c4d303dc3..5fe8c667c6b1 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -15,6 +15,7 @@
 #include <crypto/aead.h>
 #include <crypto/md5.h>
 #include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 
@@ -165,7 +166,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess,
 			     ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE,
 			     sess->sess_key);
 
-	if (memcmp(ntlmv2->ntlmv2_hash, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE) != 0)
+	if (crypto_memneq(ntlmv2->ntlmv2_hash, ntlmv2_rsp,
+			  CIFS_HMAC_MD5_HASH_SIZE))
 		return -EINVAL;
 	return 0;
 }
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 95901a78951c..743c629fe7ec 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4,6 +4,7 @@
  *   Copyright (C) 2018 Samsung Electronics Co., Ltd.
  */
 
+#include <crypto/utils.h>
 #include <linux/inetdevice.h>
 #include <net/addrconf.h>
 #include <linux/syscalls.h>
@@ -8880,7 +8881,7 @@ int smb2_check_sign_req(struct ksmbd_work *work)
 	ksmbd_sign_smb2_pdu(work->conn, work->sess->sess_key, iov, 1,
 			    signature);
 
-	if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
 		pr_err("bad smb2 signature\n");
 		return 0;
 	}
@@ -8968,7 +8969,7 @@ int smb3_check_sign_req(struct ksmbd_work *work)
 	if (ksmbd_sign_smb3_pdu(conn, signing_key, iov, 1, signature))
 		return 0;
 
-	if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
 		pr_err("bad smb2 signature\n");
 		return 0;
 	}

From 6b4f875aac344cdd52a1f34cc70ed2f874a65757 Mon Sep 17 00:00:00 2001
From: Nicholas Carlini <nicholas@carlini.com>
Date: Thu, 19 Feb 2026 20:58:57 +0900
Subject: [PATCH 0103/1303] ksmbd: fix signededness bug in
 smb_direct_prepare_negotiation()

smb_direct_prepare_negotiation() casts an unsigned __u32 value
from sp->max_recv_size and req->preferred_send_size to a signed
int before computing min_t(int, ...). A maliciously provided
preferred_send_size of 0x80000000 will return as smaller than
max_recv_size, and then be used to set the maximum allowed
alowed receive size for the next message.

By sending a second message with a large value (>1420 bytes)
the attacker can then achieve a heap buffer overflow.

This fix replaces min_t(int, ...) with min_t(u32)

Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Signed-off-by: Nicholas Carlini <nicholas@carlini.com>
Reviewed-by: Stefan Metzmacher <metze@samba.org>
Acked-by: Stefan Metzmacher <metze@samba.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_rdma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 7c53b78b818e..188572491d53 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2540,9 +2540,9 @@ static int smb_direct_prepare(struct ksmbd_transport *t)
 		goto put;
 
 	req = (struct smbdirect_negotiate_req *)recvmsg->packet;
-	sp->max_recv_size = min_t(int, sp->max_recv_size,
+	sp->max_recv_size = min_t(u32, sp->max_recv_size,
 				  le32_to_cpu(req->preferred_send_size));
-	sp->max_send_size = min_t(int, sp->max_send_size,
+	sp->max_send_size = min_t(u32, sp->max_send_size,
 				  le32_to_cpu(req->max_receive_size));
 	sp->max_fragmented_send_size =
 		le32_to_cpu(req->max_fragmented_size);

From 47322c469d4a63ac45b705ca83680671ff71c975 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 9 Feb 2026 16:38:05 +0100
Subject: [PATCH 0104/1303] dma-mapping: avoid random addr value print out on
 error path

dma_addr is unitialized in dma_direct_map_phys() when swiotlb is forced
and DMA_ATTR_MMIO is set which leads to random value print out in
warning. Fix that by just returning DMA_MAPPING_ERROR.

Fixes: e53d29f957b3 ("dma-mapping: convert dma_direct_*map_page to be phys_addr_t based")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260209153809.250835-2-jiri@resnulli.us
---
 kernel/dma/direct.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index f476c63b668c..e89f175e9c2d 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -85,7 +85,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 
 	if (is_swiotlb_force_bounce(dev)) {
 		if (attrs & DMA_ATTR_MMIO)
-			goto err_overflow;
+			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}

From d5b5e8149af0f5efed58653cbebf1cb3258ce49a Mon Sep 17 00:00:00 2001
From: Stian Halseth <stian@itx.no>
Date: Wed, 18 Feb 2026 13:00:24 +0100
Subject: [PATCH 0105/1303] sparc: Fix page alignment in dma mapping

'phys' may include an offset within the page, while previously used
'base_paddr' was already page-aligned. This caused incorrect DMA mapping
in dma_4u_map_phys and dma_4v_map_phys.

Fix both functions by masking 'phys' with IO_PAGE_MASK, covering both
generic SPARC code and sun4v.

Fixes: 38c0d0ebf520 ("sparc: Use physical address DMA mapping")
Reported-by: Stian Halseth <stian@itx.no>
Closes: https://github.com/sparclinux/issues/issues/75
Suggested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Stian Halseth <stian@itx.no>
Tested-by: Nathaniel Roach <nroach44@nroach44.id.au>
Tested-by: Han Gao <gaohan@iscas.ac.cn> # on SPARC Enterprise T5220
[mszyprow: adjusted commit description a bit]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260218120056.3366-2-stian@itx.no
---
 arch/sparc/kernel/iommu.c     | 2 ++
 arch/sparc/kernel/pci_sun4v.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 46ef88bc9c26..7613ab0ffb89 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys,
 	if (direction != DMA_TO_DEVICE)
 		iopte_protection |= IOPTE_WRITE;
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE)
 		iopte_val(*base) = iopte_protection | phys;
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 440284cc804e..61f14b4c8f90 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys,
 
 	iommu_batch_start(dev, prot, entry);
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) {
 		long err = iommu_batch_add(phys, mask);
 		if (unlikely(err < 0L))

From c8d7f21ead727485ebf965e2b4d42d4a4f0840f6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 9 Feb 2026 19:12:20 +0100
Subject: [PATCH 0106/1303] wifi: cfg80211: wext: fix IGTK key ID off-by-one

The IGTK key ID must be 4 or 5, but the code checks against
key ID + 1, so must check against 5/6 rather than 4/5. Fix
that.

Reported-by: Jouni Malinen <j@w1.fi>
Fixes: 08645126dd24 ("cfg80211: implement wext key handling")
Link: https://patch.msgid.link/20260209181220.362205-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/wext-compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 1241fda78a68..680500fa57cf 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -684,7 +684,7 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev,
 
 	idx = erq->flags & IW_ENCODE_INDEX;
 	if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) {
-		if (idx < 4 || idx > 5) {
+		if (idx < 5 || idx > 6) {
 			idx = wdev->wext.default_mgmt_key;
 			if (idx < 0)
 				return -EINVAL;

From 767d23ade706d5fa51c36168e92a9c5533c351a1 Mon Sep 17 00:00:00 2001
From: Daniil Dulov <d.dulov@aladdin.ru>
Date: Wed, 11 Feb 2026 11:20:24 +0300
Subject: [PATCH 0107/1303] wifi: cfg80211: cancel rfkill_block work in
 wiphy_unregister()

There is a use-after-free error in cfg80211_shutdown_all_interfaces found
by syzkaller:

BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x116/0x1f0
 print_report+0xcd/0x630
 kasan_report+0xe0/0x110
 cfg80211_shutdown_all_interfaces+0x213/0x220
 cfg80211_rfkill_block_work+0x1e/0x30
 process_one_work+0x9cf/0x1b70
 worker_thread+0x6c8/0xf10
 kthread+0x3c5/0x780
 ret_from_fork+0x56d/0x700
 ret_from_fork_asm+0x1a/0x30
 </TASK>

The problem arises due to the rfkill_block work is not cancelled when wiphy
is being unregistered. In order to fix the issue cancel the corresponding
work in wiphy_unregister().

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 1f87f7d3a3b4 ("cfg80211: add rfkill support")
Cc: stable@vger.kernel.org
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
Link: https://patch.msgid.link/20260211082024.1967588-1-d.dulov@aladdin.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 9af85d655027..d35cf04cbc81 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1212,6 +1212,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	/* this has nothing to do now but make sure it's gone */
 	cancel_work_sync(&rdev->wiphy_work);
 
+	cancel_work_sync(&rdev->rfkill_block);
 	cancel_work_sync(&rdev->conn_work);
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);

From c854758abe0b8d86f9c43dc060ff56a0ee5b31e0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 17 Feb 2026 13:05:26 +0100
Subject: [PATCH 0108/1303] wifi: radiotap: reject radiotap with unknown bits

The radiotap parser is currently only used with the radiotap
namespace (not with vendor namespaces), but if the undefined
field 18 is used, the alignment/size is unknown as well. In
this case, iterator->_next_ns_data isn't initialized (it's
only set for skipping vendor namespaces), and syzbot points
out that we later compare against this uninitialized value.

Fix this by moving the rejection of unknown radiotap fields
down to after the in-namespace lookup, so it will really use
iterator->_next_ns_data only for vendor namespaces, even in
case undefined fields are present.

Cc: stable@vger.kernel.org
Fixes: 33e5a2f776e3 ("wireless: update radiotap parser")
Reported-by: syzbot+b09c1af8764c0097bb19@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/69944a91.a70a0220.2c38d7.00fc.GAE@google.com
Link: https://patch.msgid.link/20260217120526.162647-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/radiotap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 326faea38ca3..c85eaa583a46 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -239,14 +239,14 @@ int ieee80211_radiotap_iterator_next(
 		default:
 			if (!iterator->current_namespace ||
 			    iterator->_arg_index >= iterator->current_namespace->n_bits) {
-				if (iterator->current_namespace == &radiotap_ns)
-					return -ENOENT;
 				align = 0;
 			} else {
 				align = iterator->current_namespace->align_size[iterator->_arg_index].align;
 				size = iterator->current_namespace->align_size[iterator->_arg_index].size;
 			}
 			if (!align) {
+				if (iterator->current_namespace == &radiotap_ns)
+					return -ENOENT;
 				/* skip all subsequent data */
 				iterator->_arg = iterator->_next_ns_data;
 				/* give up on this namespace */

From 243307a0d1b0d01538e202c00454c28b21d4432e Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 3 Feb 2026 11:21:33 +0100
Subject: [PATCH 0109/1303] wifi: brcmfmac: Fix potential kernel oops when
 probe fails

When probe of the sdio brcmfmac device fails for some reasons (i.e.
missing firmware), the sdiodev->bus is set to error instead of NULL, thus
the cleanup later in brcmf_sdio_remove() tries to free resources via
invalid bus pointer. This happens because sdiodev->bus is set 2 times:
first in brcmf_sdio_probe() and second time in brcmf_sdiod_probe(). Fix
this by chaning the brcmf_sdio_probe() function to return the error code
and set sdio->bus only there.

Fixes: 0ff0843310b7 ("wifi: brcmfmac: Add optional lpo clock enable support")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Arend van Spriel<arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20260203102133.1478331-1-m.szyprowski@samsung.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 7 +++----
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c   | 7 ++++---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h   | 2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 6a3f187320fc..13952dfeb3e3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -951,11 +951,10 @@ int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev)
 		goto out;
 
 	/* try to attach to the target device */
-	sdiodev->bus = brcmf_sdio_probe(sdiodev);
-	if (IS_ERR(sdiodev->bus)) {
-		ret = PTR_ERR(sdiodev->bus);
+	ret = brcmf_sdio_probe(sdiodev);
+	if (ret)
 		goto out;
-	}
+
 	brcmf_sdiod_host_fixup(sdiodev->func2->card->host);
 out:
 	if (ret)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 8cf9d7e7c3f7..4e6ed02c1591 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4445,7 +4445,7 @@ brcmf_sdio_prepare_fw_request(struct brcmf_sdio *bus)
 	return fwreq;
 }
 
-struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
+int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 {
 	int ret;
 	struct brcmf_sdio *bus;
@@ -4551,11 +4551,12 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 		goto fail;
 	}
 
-	return bus;
+	return 0;
 
 fail:
 	brcmf_sdio_remove(bus);
-	return ERR_PTR(ret);
+	sdiodev->bus = NULL;
+	return ret;
 }
 
 /* Detach and free everything */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 0d18ed15b403..80180d5c6c87 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -358,7 +358,7 @@ void brcmf_sdiod_freezer_uncount(struct brcmf_sdio_dev *sdiodev);
 int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev);
 int brcmf_sdiod_remove(struct brcmf_sdio_dev *sdiodev);
 
-struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
+int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
 void brcmf_sdio_remove(struct brcmf_sdio *bus);
 void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr);
 

From c9f3a593137d862d424130343e77d4b5260a4f5a Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Fri, 30 Jan 2026 16:38:47 +0100
Subject: [PATCH 0110/1303] iio: imu: inv_icm42600: fix odr switch to the same
 value

ODR switch is done in 2 steps when FIFO is on : change the ODR register
value and acknowledge change when reading the FIFO ODR change flag.
When we are switching to the same odr value, we end up waiting for a
FIFO ODR flag that is never happening.

Fix the issue by doing nothing and exiting properly when we are
switching to the same ODR value.

Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c | 2 ++
 drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c  | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index 54760d8f92a2..0ab6eddf0543 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -651,6 +651,8 @@ static int inv_icm42600_accel_write_odr(struct iio_dev *indio_dev,
 		return -EINVAL;
 
 	conf.odr = inv_icm42600_accel_odr_conv[idx / 2];
+	if (conf.odr == st->conf.accel.odr)
+		return 0;
 
 	pm_runtime_get_sync(dev);
 	mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index 7ef0a25ec74f..11339ddf1da3 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -358,6 +358,8 @@ static int inv_icm42600_gyro_write_odr(struct iio_dev *indio_dev,
 		return -EINVAL;
 
 	conf.odr = inv_icm42600_gyro_odr_conv[idx / 2];
+	if (conf.odr == st->conf.gyro.odr)
+		return 0;
 
 	pm_runtime_get_sync(dev);
 	mutex_lock(&st->lock);

From ffd32db8263d2d785a2c419486a450dc80693235 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Fri, 30 Jan 2026 17:10:23 +0100
Subject: [PATCH 0111/1303] iio: imu: inv_icm42600: fix odr switch when turning
 buffer off

ODR switch is done in 2 steps when FIFO is on : change the ODR register
value and acknowledge change when reading the FIFO ODR change flag.
When we are switching odr and turning buffer off just afterward, we are
losing the FIFO ODR change flag and ODR switch is blocked.

Fix the issue by force applying any waiting ODR change when turning
buffer off.

Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
index ada968be954d..68a395758031 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
@@ -371,6 +371,8 @@ static int inv_icm42600_buffer_predisable(struct iio_dev *indio_dev)
 static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev)
 {
 	struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev);
+	struct inv_icm42600_sensor_state *sensor_st = iio_priv(indio_dev);
+	struct inv_sensors_timestamp *ts = &sensor_st->ts;
 	struct device *dev = regmap_get_device(st->map);
 	unsigned int sensor;
 	unsigned int *watermark;
@@ -392,6 +394,8 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev)
 
 	mutex_lock(&st->lock);
 
+	inv_sensors_timestamp_apply_odr(ts, 0, 0, 0);
+
 	ret = inv_icm42600_buffer_set_fifo_en(st, st->fifo.en & ~sensor);
 	if (ret)
 		goto out_unlock;

From dd72e6c3cdea05cad24e99710939086f7a113fb5 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 30 Jan 2026 13:30:20 +0200
Subject: [PATCH 0112/1303] iio: light: bh1780: fix PM runtime leak on error
 path

Move pm_runtime_put_autosuspend() before the error check to ensure
the PM runtime reference count is always decremented after
pm_runtime_get_sync(), regardless of whether the read operation
succeeds or fails.

Fixes: 1f0477f18306 ("iio: light: new driver for the ROHM BH1780")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/bh1780.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c
index 5d3c6d5276ba..a740d1f992a8 100644
--- a/drivers/iio/light/bh1780.c
+++ b/drivers/iio/light/bh1780.c
@@ -109,9 +109,9 @@ static int bh1780_read_raw(struct iio_dev *indio_dev,
 		case IIO_LIGHT:
 			pm_runtime_get_sync(&bh1780->client->dev);
 			value = bh1780_read_word(bh1780, BH1780_REG_DLOW);
+			pm_runtime_put_autosuspend(&bh1780->client->dev);
 			if (value < 0)
 				return value;
-			pm_runtime_put_autosuspend(&bh1780->client->dev);
 			*val = value;
 
 			return IIO_VAL_INT;

From 6c8bf4b604a8a6346ca71f1c027fa01c2c2e04cb Mon Sep 17 00:00:00 2001
From: SeungJu Cheon <suunj1331@gmail.com>
Date: Sat, 24 Jan 2026 04:47:58 +0900
Subject: [PATCH 0113/1303] iio: frequency: adf4377: Fix duplicated soft reset
 mask

The regmap_read_poll_timeout() uses ADF4377_0000_SOFT_RESET_R_MSK
twice instead of checking both SOFT_RESET_MSK (bit 0) and
SOFT_RESET_R_MSK (bit 7). This causes an incomplete reset status check.

The code first sets both SOFT_RESET and SOFT_RESET_R bits to 1 via
regmap_update_bits(), then polls for them to be cleared. Since we set
both bits before polling, we should be waiting for both to clear.

Fix by using both masks as done in regmap_update_bits() above.

Fixes: eda549e2e524 ("iio: frequency: adf4377: add support for ADF4377")
Signed-off-by: SeungJu Cheon <suunj1331@gmail.com>
Cc: Stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/frequency/adf4377.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
index fa686f785fa4..8e2da218d48a 100644
--- a/drivers/iio/frequency/adf4377.c
+++ b/drivers/iio/frequency/adf4377.c
@@ -508,7 +508,7 @@ static int adf4377_soft_reset(struct adf4377_state *st)
 		return ret;
 
 	return regmap_read_poll_timeout(st->regmap, 0x0, read_val,
-					!(read_val & (ADF4377_0000_SOFT_RESET_R_MSK |
+					!(read_val & (ADF4377_0000_SOFT_RESET_MSK |
 					ADF4377_0000_SOFT_RESET_R_MSK)), 200, 200 * 100);
 }
 

From d23d763e00ace4e9c59f8d33e0713d401133ba88 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Wed, 31 Dec 2025 22:14:16 +0100
Subject: [PATCH 0114/1303] iio: imu: inv-mpu9150: fix irq ack preventing irq
 storms

IRQ needs to be acked. for some odd reasons, reading from irq status does
not reliable help, enable acking from any register to be on the safe side
and read the irq status register. Comments in the code indicate a known
unreliability with that register.
The blamed commit was tested with mpu6050 in lg,p895 and lg,p880 according
to Tested-bys. But with the MPU9150 in the Epson Moverio BT-200 this leads
to irq storms without properly acking the irq.

Fixes: 0a3b517c8089 ("iio: imu: inv_mpu6050: fix interrupt status read for old buggy chips")
Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Acked-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_mpu6050/inv_mpu_core.c    | 8 ++++++++
 drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h     | 2 ++
 drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c | 5 ++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index b2fa1f4957a5..5796896d54cd 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -1943,6 +1943,14 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name,
 			irq_type);
 		return -EINVAL;
 	}
+
+	/*
+	 * Acking interrupts by status register does not work reliably
+	 * but seem to work when this bit is set.
+	 */
+	if (st->chip_type == INV_MPU9150)
+		st->irq_mask |= INV_MPU6050_INT_RD_CLEAR;
+
 	device_set_wakeup_capable(dev, true);
 
 	st->vdd_supply = devm_regulator_get(dev, "vdd");
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
index 211901f8b8eb..6239b1a803f7 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
@@ -390,6 +390,8 @@ struct inv_mpu6050_state {
 /* enable level triggering */
 #define INV_MPU6050_LATCH_INT_EN	0x20
 #define INV_MPU6050_BIT_BYPASS_EN	0x2
+/* allow acking interrupts by any register read */
+#define INV_MPU6050_INT_RD_CLEAR	0x10
 
 /* Allowed timestamp period jitter in percent */
 #define INV_MPU6050_TS_PERIOD_JITTER	4
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 10a473342075..22c1ce66f99e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -248,7 +248,6 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
 	switch (st->chip_type) {
 	case INV_MPU6000:
 	case INV_MPU6050:
-	case INV_MPU9150:
 		/*
 		 * WoM is not supported and interrupt status read seems to be broken for
 		 * some chips. Since data ready is the only interrupt, bypass interrupt
@@ -257,6 +256,10 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
 		wom_bits = 0;
 		int_status = INV_MPU6050_BIT_RAW_DATA_RDY_INT;
 		goto data_ready_interrupt;
+	case INV_MPU9150:
+		/* IRQ needs to be acked */
+		wom_bits = 0;
+		break;
 	case INV_MPU6500:
 	case INV_MPU6515:
 	case INV_MPU6880:

From 85e4614524dca6c0a43874f475a17de2b9725648 Mon Sep 17 00:00:00 2001
From: Lukas Schmid <lukas.schmid@netcube.li>
Date: Mon, 2 Feb 2026 21:15:35 +0100
Subject: [PATCH 0115/1303] iio: potentiometer: mcp4131: fix double application
 of wiper shift

The MCP4131 wiper address is shifted twice when preparing the SPI
command in mcp4131_write_raw().

The address is already shifted when assigned to the local variable
"address", but is then shifted again when written to data->buf[0].
This results in an incorrect command being sent to the device and
breaks wiper writes to the second channel.

Remove the second shift and use the pre-shifted address directly
when composing the SPI transfer.

Fixes: 22d199a53910 ("iio: potentiometer: add driver for Microchip MCP413X/414X/415X/416X/423X/424X/425X/426X")
Signed-off-by: Lukas Schmid <lukas.schmid@netcube.li>#
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/potentiometer/mcp4131.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/potentiometer/mcp4131.c b/drivers/iio/potentiometer/mcp4131.c
index ad082827aad5..56c9111ef5e8 100644
--- a/drivers/iio/potentiometer/mcp4131.c
+++ b/drivers/iio/potentiometer/mcp4131.c
@@ -221,7 +221,7 @@ static int mcp4131_write_raw(struct iio_dev *indio_dev,
 
 	mutex_lock(&data->lock);
 
-	data->buf[0] = address << MCP4131_WIPER_SHIFT;
+	data->buf[0] = address;
 	data->buf[0] |= MCP4131_WRITE | (val >> 8);
 	data->buf[1] = val & 0xFF; /* 8 bits here */
 

From 7ef74d961d1ad6ec72b50887ca119d7f98f07717 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Thu, 5 Feb 2026 17:59:14 +0100
Subject: [PATCH 0116/1303] iio: imu: inv_icm45600: fix INT1 drive bit inverted

Drive bit must be set for open-drain mode and be cleared for push-pull
mode.

Referring to datasheet DS-000576_ICM-45605.pdf section 17.23
INT1_CONFIG2.

Fixes: 06674a72cf7a ("iio: imu: inv_icm45600: add buffer support in iio devices")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm45600/inv_icm45600.h      | 2 +-
 drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600.h b/drivers/iio/imu/inv_icm45600/inv_icm45600.h
index c5b5446f6c3b..1c796d4b2a40 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600.h
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600.h
@@ -205,7 +205,7 @@ struct inv_icm45600_sensor_state {
 #define INV_ICM45600_SPI_SLEW_RATE_38NS			0
 
 #define INV_ICM45600_REG_INT1_CONFIG2			0x0018
-#define INV_ICM45600_INT1_CONFIG2_PUSH_PULL		BIT(2)
+#define INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN		BIT(2)
 #define INV_ICM45600_INT1_CONFIG2_LATCHED		BIT(1)
 #define INV_ICM45600_INT1_CONFIG2_ACTIVE_HIGH		BIT(0)
 #define INV_ICM45600_INT1_CONFIG2_ACTIVE_LOW		0x00
diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
index 25bd9757a594..e4638926a10c 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
@@ -637,8 +637,8 @@ static int inv_icm45600_irq_init(struct inv_icm45600_state *st, int irq,
 		break;
 	}
 
-	if (!open_drain)
-		val |= INV_ICM45600_INT1_CONFIG2_PUSH_PULL;
+	if (open_drain)
+		val |= INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN;
 
 	ret = regmap_write(st->map, INV_ICM45600_REG_INT1_CONFIG2, val);
 	if (ret)

From 5187e03b817c26c1c3bcb2645a612ea935c4be89 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 4 Feb 2026 15:00:33 +0100
Subject: [PATCH 0117/1303] iio: dac: ds4424: reject -128 RAW value

The DS442x DAC uses sign-magnitude encoding, so -128 cannot be represented
in hardware (7-bit magnitude).

Previously, passing -128 resulted in a truncated value that programmed
0mA (magnitude 0) instead of the expected maximum negative current,
effectively failing silently.

Reject -128 to avoid producing the wrong current.

Fixes: d632a2bd8ffc ("iio: dac: ds4422/ds4424 dac driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ds4424.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ds4424.c b/drivers/iio/dac/ds4424.c
index 6dda8918975a..c61868f2de31 100644
--- a/drivers/iio/dac/ds4424.c
+++ b/drivers/iio/dac/ds4424.c
@@ -140,7 +140,7 @@ static int ds4424_write_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		if (val < S8_MIN || val > S8_MAX)
+		if (val <= S8_MIN || val > S8_MAX)
 			return -EINVAL;
 
 		if (val > 0) {

From f55b9510cd9437da3a0efa08b089caeb47595ff1 Mon Sep 17 00:00:00 2001
From: Chris Spencer <spencercw@gmail.com>
Date: Thu, 5 Feb 2026 14:55:45 +0000
Subject: [PATCH 0118/1303] iio: chemical: bme680: Fix measurement wait
 duration calculation

This function refers to the Bosch BME680 API as the source of the
calculation, but one of the constants does not match the Bosch
implementation. This appears to be a simple transposition of two digits,
resulting in a wait time that is too short. This can cause the following
'device measurement cycle incomplete' check to occasionally fail, returning
EBUSY to user space.

Adjust the constant to match the Bosch implementation and resolve the EBUSY
errors.

Fixes: 4241665e6ea0 ("iio: chemical: bme680: Fix sensor data read operation")
Link: https://github.com/boschsensortec/BME68x_SensorAPI/blob/v4.4.8/bme68x.c#L521
Signed-off-by: Chris Spencer <spencercw@gmail.com>
Acked-by: Vasileios Amoiridis <vassilisamir@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/bme680_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c
index 70f81c4a96ba..24e0b59e2fdf 100644
--- a/drivers/iio/chemical/bme680_core.c
+++ b/drivers/iio/chemical/bme680_core.c
@@ -613,7 +613,7 @@ static int bme680_wait_for_eoc(struct bme680_data *data)
 	 * + heater duration
 	 */
 	int wait_eoc_us = ((data->oversampling_temp + data->oversampling_press +
-			   data->oversampling_humid) * 1936) + (477 * 4) +
+			   data->oversampling_humid) * 1963) + (477 * 4) +
 			   (477 * 5) + 1000 + (data->heater_dur * 1000);
 
 	fsleep(wait_eoc_us);

From 585b90c0161ab77416fe3acdbdc55b978e33e16c Mon Sep 17 00:00:00 2001
From: Yasin Lee <yasin.lee.x@gmail.com>
Date: Fri, 13 Feb 2026 23:14:43 +0800
Subject: [PATCH 0119/1303] iio: proximity: hx9023s: fix assignment order for
 __counted_by

Initialize fw_size before copying firmware data into the flexible
array member to match the __counted_by() annotation. This fixes the
incorrect assignment order that triggers runtime safety checks.

Fixes: e9ed97be4fcc ("iio: proximity: hx9023s: Added firmware file parsing functionality")
Signed-off-by: Yasin Lee <yasin.lee.x@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/hx9023s.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index 2918dfc0df54..ad839db6b326 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -1034,9 +1034,8 @@ static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data
 	if (!bin)
 		return -ENOMEM;
 
-	memcpy(bin->data, fw->data, fw->size);
-
 	bin->fw_size = fw->size;
+	memcpy(bin->data, fw->data, bin->fw_size);
 	bin->fw_ver = bin->data[FW_VER_OFFSET];
 	bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET);
 

From a318cfc0853706f1d6ce682dba660bc455d674ef Mon Sep 17 00:00:00 2001
From: Yasin Lee <yasin.lee.x@gmail.com>
Date: Fri, 13 Feb 2026 23:14:44 +0800
Subject: [PATCH 0120/1303] iio: proximity: hx9023s: Protect against division
 by zero in set_samp_freq

Avoid division by zero when sampling frequency is unspecified.

Fixes: 60df548277b7 ("iio: proximity: Add driver support for TYHX's HX9023S capacitive proximity sensor")
Signed-off-by: Yasin Lee <yasin.lee.x@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/hx9023s.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index ad839db6b326..17e00ee2b6f8 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -719,6 +719,9 @@ static int hx9023s_set_samp_freq(struct hx9023s_data *data, int val, int val2)
 	struct device *dev = regmap_get_device(data->regmap);
 	unsigned int i, period_ms;
 
+	if (!val && !val2)
+		return -EINVAL;
+
 	period_ms = div_u64(NANO, (val * MEGA + val2));
 
 	for (i = 0; i < ARRAY_SIZE(hx9023s_samp_freq_table); i++) {

From 82ee91d6b15f06b6094eea2c26afe0032fe8e177 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Tue, 10 Feb 2026 18:49:50 +0200
Subject: [PATCH 0121/1303] iio: magnetometer: tlv493d: remove erroneous shift
 in X-axis data

TLV493D_BX2_MAG_X_AXIS_LSB is defined as GENMASK(7, 4). FIELD_GET()
already right-shifts bits [7:4] to [3:0], so the additional >> 4
discards most of the X-axis low nibble. The Y and Z axes correctly
omit this extra shift. Remove it.

Fixes: 106511d280c7 ("iio: magnetometer: add support for Infineon TLV493D 3D Magentic sensor")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/magnetometer/tlv493d.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/magnetometer/tlv493d.c b/drivers/iio/magnetometer/tlv493d.c
index ec53fd40277b..e5e050af2b74 100644
--- a/drivers/iio/magnetometer/tlv493d.c
+++ b/drivers/iio/magnetometer/tlv493d.c
@@ -171,7 +171,7 @@ static s16 tlv493d_get_channel_data(u8 *b, enum tlv493d_channels ch)
 	switch (ch) {
 	case TLV493D_AXIS_X:
 		val = FIELD_GET(TLV493D_BX_MAG_X_AXIS_MSB, b[TLV493D_RD_REG_BX]) << 4 |
-		      FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]) >> 4;
+		      FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]);
 		break;
 	case TLV493D_AXIS_Y:
 		val = FIELD_GET(TLV493D_BY_MAG_Y_AXIS_MSB, b[TLV493D_RD_REG_BY]) << 4 |

From 216345f98cae7fcc84f49728c67478ac00321c87 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Feb 2026 14:46:07 +0200
Subject: [PATCH 0122/1303] iio: chemical: sps30_i2c: fix buffer size in
 sps30_i2c_read_meas()

sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead
of the intended __be32 element size (4 bytes). Use sizeof(*meas) to
correctly match the buffer element type.

Fixes: 8f3f13085278 ("iio: sps30: separate core and interface specific code")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Acked-by: Tomasz Duszynski <tduszyns@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/sps30_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c
index f692c089d17b..c92f04990c34 100644
--- a/drivers/iio/chemical/sps30_i2c.c
+++ b/drivers/iio/chemical/sps30_i2c.c
@@ -171,7 +171,7 @@ static int sps30_i2c_read_meas(struct sps30_state *state, __be32 *meas, size_t n
 	if (!sps30_i2c_meas_ready(state))
 		return -ETIMEDOUT;
 
-	return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(num) * num);
+	return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(*meas) * num);
 }
 
 static int sps30_i2c_clean_fan(struct sps30_state *state)

From c3914ce1963c4db25e186112c90fa5d2361e9e0a Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Feb 2026 14:46:08 +0200
Subject: [PATCH 0123/1303] iio: chemical: sps30_serial: fix buffer size in
 sps30_serial_read_meas()

sizeof(num) evaluates to sizeof(size_t) which is 8 bytes on 64-bit,
but the buffer elements are only 4 bytes. The same function already
uses sizeof(*meas) on line 312, making the mismatch evident. Use
sizeof(*meas) consistently.

Fixes: b2e171f5a5c6 ("iio: sps30: add support for serial interface")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Acked-by: Tomasz Duszynski <tduszyns@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/sps30_serial.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c
index 008bc88590f3..a5e6bc08d5fd 100644
--- a/drivers/iio/chemical/sps30_serial.c
+++ b/drivers/iio/chemical/sps30_serial.c
@@ -303,7 +303,7 @@ static int sps30_serial_read_meas(struct sps30_state *state, __be32 *meas, size_
 	if (msleep_interruptible(1000))
 		return -EINTR;
 
-	ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(num));
+	ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(*meas));
 	if (ret < 0)
 		return ret;
 	/* if measurements aren't ready sensor returns empty frame */

From dd6183e42719cc54057579b8e6be5348cecfeda7 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Sat, 14 Feb 2026 12:46:37 -0600
Subject: [PATCH 0124/1303] iio: adc: ad7768-1: Fix ERR_PTR dereference in
 ad7768_fill_scale_tbl

The function iio_get_current_scan_type() can return an error pointer,
the return value scan_type is not checked for this and immediately
dereferenced which can cause a kernel panic.

Add check for IS_ERR() and propagate the error back.

Fixes: ff085189cb17 ("iio: adc: ad7768-1: add support for ADAQ776x-1 ADC Family")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202602051234.5gArzLyZ-lkp@intel.com/
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7768-1.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index fcd8aea7152e..e16dede687d3 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -531,7 +531,7 @@ static int ad7768_reg_access(struct iio_dev *indio_dev,
 	return ret;
 }
 
-static void ad7768_fill_scale_tbl(struct iio_dev *dev)
+static int ad7768_fill_scale_tbl(struct iio_dev *dev)
 {
 	struct ad7768_state *st = iio_priv(dev);
 	const struct iio_scan_type *scan_type;
@@ -541,6 +541,11 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev)
 	u64 tmp2;
 
 	scan_type = iio_get_current_scan_type(dev, &dev->channels[0]);
+	if (IS_ERR(scan_type)) {
+		dev_err(&st->spi->dev, "Failed to get scan type.\n");
+		return PTR_ERR(scan_type);
+	}
+
 	if (scan_type->sign == 's')
 		val2 = scan_type->realbits - 1;
 	else
@@ -565,6 +570,8 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev)
 		st->scale_tbl[i][0] = tmp0; /* Integer part */
 		st->scale_tbl[i][1] = abs(tmp1); /* Fractional part */
 	}
+
+	return 0;
 }
 
 static int ad7768_set_sinc3_dec_rate(struct ad7768_state *st,
@@ -669,7 +676,9 @@ static int ad7768_configure_dig_fil(struct iio_dev *dev,
 	}
 
 	/* Update scale table: scale values vary according to the precision */
-	ad7768_fill_scale_tbl(dev);
+	ret = ad7768_fill_scale_tbl(dev);
+	if (ret)
+		return ret;
 
 	ad7768_fill_samp_freq_tbl(st);
 

From 91f950b4cbb1aa9ea4eb3999f1463e8044b717fb Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 16 Feb 2026 11:57:55 +0200
Subject: [PATCH 0125/1303] iio: gyro: mpu3050-i2c: fix pm_runtime error
 handling

The return value of pm_runtime_get_sync() is not checked, and the
function always returns success. This allows I2C mux operations to
proceed even when the device fails to resume.

Use pm_runtime_resume_and_get() and propagate its return value to
properly handle resume failures.

Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-i2c.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/gyro/mpu3050-i2c.c b/drivers/iio/gyro/mpu3050-i2c.c
index 092878f2c886..6549b22e643d 100644
--- a/drivers/iio/gyro/mpu3050-i2c.c
+++ b/drivers/iio/gyro/mpu3050-i2c.c
@@ -19,8 +19,7 @@ static int mpu3050_i2c_bypass_select(struct i2c_mux_core *mux, u32 chan_id)
 	struct mpu3050 *mpu3050 = i2c_mux_priv(mux);
 
 	/* Just power up the device, that is all that is needed */
-	pm_runtime_get_sync(mpu3050->dev);
-	return 0;
+	return pm_runtime_resume_and_get(mpu3050->dev);
 }
 
 static int mpu3050_i2c_bypass_deselect(struct i2c_mux_core *mux, u32 chan_id)

From acc3949aab3e8094641a9c7c2768de1958c88378 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 16 Feb 2026 11:57:56 +0200
Subject: [PATCH 0126/1303] iio: gyro: mpu3050-core: fix pm_runtime error
 handling

The return value of pm_runtime_get_sync() is not checked, allowing
the driver to access hardware that may fail to resume. The device
usage count is also unconditionally incremented. Use
pm_runtime_resume_and_get() which propagates errors and avoids
incrementing the usage count on failure.

In preenable, add pm_runtime_put_autosuspend() on set_8khz_samplerate()
failure since postdisable does not run when preenable fails.

Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index ee2fcd20545d..317e7b217ec6 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -322,7 +322,9 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev,
 		}
 	case IIO_CHAN_INFO_RAW:
 		/* Resume device */
-		pm_runtime_get_sync(mpu3050->dev);
+		ret = pm_runtime_resume_and_get(mpu3050->dev);
+		if (ret)
+			return ret;
 		mutex_lock(&mpu3050->lock);
 
 		ret = mpu3050_set_8khz_samplerate(mpu3050);
@@ -647,14 +649,20 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p)
 static int mpu3050_buffer_preenable(struct iio_dev *indio_dev)
 {
 	struct mpu3050 *mpu3050 = iio_priv(indio_dev);
+	int ret;
 
-	pm_runtime_get_sync(mpu3050->dev);
+	ret = pm_runtime_resume_and_get(mpu3050->dev);
+	if (ret)
+		return ret;
 
 	/* Unless we have OUR trigger active, run at full speed */
-	if (!mpu3050->hw_irq_trigger)
-		return mpu3050_set_8khz_samplerate(mpu3050);
+	if (!mpu3050->hw_irq_trigger) {
+		ret = mpu3050_set_8khz_samplerate(mpu3050);
+		if (ret)
+			pm_runtime_put_autosuspend(mpu3050->dev);
+	}
 
-	return 0;
+	return ret;
 }
 
 static int mpu3050_buffer_postdisable(struct iio_dev *indio_dev)

From 064234044056c93a3719d6893e6e5a26a94a61b6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Nuno=20S=C3=A1?= <nuno.sa@analog.com>
Date: Mon, 16 Feb 2026 13:24:27 +0000
Subject: [PATCH 0127/1303] iio: buffer: Fix wait_queue not being removed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the edge case where the IIO device is unregistered while we're
buffering, we were directly returning an error without removing the wait
queue. Instead, set 'ret' and break out of the loop.

Fixes: 9eeee3b0bf19 ("iio: Add output buffer support")
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index f15a180dc49e..46f36a6ed271 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -228,8 +228,10 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf,
 	written = 0;
 	add_wait_queue(&rb->pollq, &wait);
 	do {
-		if (!indio_dev->info)
-			return -ENODEV;
+		if (!indio_dev->info) {
+			ret = -ENODEV;
+			break;
+		}
 
 		if (!iio_buffer_space_available(rb)) {
 			if (signal_pending(current)) {

From 2617595538be8a2f270ad13fccb9f56007b292d7 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Tue, 17 Feb 2026 11:44:50 +0100
Subject: [PATCH 0128/1303] iio: imu: inv_icm45600: fix regulator put warning
 when probe fails

When the driver probe fails we encounter a regulator put warning
because vddio regulator is not stopped before release. The issue
comes from pm_runtime not already setup when core probe fails and
the vddio regulator disable callback is called.

Fix the issue by setting pm_runtime active early before vddio
regulator resource cleanup. This requires to cut pm_runtime
set_active and enable in 2 function calls.

Fixes: 7ff021a3faca ("iio: imu: inv_icm45600: add new inv_icm45600 driver")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
index e4638926a10c..d49053161a65 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
@@ -744,6 +744,11 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi
 	 */
 	fsleep(5 * USEC_PER_MSEC);
 
+	/* set pm_runtime active early for disable vddio resource cleanup */
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		return ret;
+
 	ret = inv_icm45600_enable_regulator_vddio(st);
 	if (ret)
 		return ret;
@@ -776,7 +781,7 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi
 	if (ret)
 		return ret;
 
-	ret = devm_pm_runtime_set_active_enabled(dev);
+	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
 

From 9990cd4f8827bd1ae3fb6eb7407630d8d463c430 Mon Sep 17 00:00:00 2001
From: Radu Sabau <radu.sabau@analog.com>
Date: Fri, 20 Feb 2026 16:16:41 +0200
Subject: [PATCH 0129/1303] iio: imu: adis: Fix NULL pointer dereference in
 adis_init

The adis_init() function dereferences adis->ops to check if the
individual function pointers (write, read, reset) are NULL, but does
not first check if adis->ops itself is NULL.

Drivers like adis16480, adis16490, adis16545 and others do not set
custom ops and rely on adis_init() assigning the defaults. Since struct
adis is zero-initialized by devm_iio_device_alloc(), adis->ops is NULL
when adis_init() is called, causing a NULL pointer dereference:

    Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
    pc : adis_init+0xc0/0x118
    Call trace:
     adis_init+0xc0/0x118
     adis16480_probe+0xe0/0x670

Fix this by checking if adis->ops is NULL before dereferencing it,
falling through to assign the default ops in that case.

Fixes: 3b29bcee8f6f ("iio: imu: adis: Add custom ops struct")
Signed-off-by: Radu Sabau <radu.sabau@analog.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index d160147cce0b..a2bc1d14ed91 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -526,7 +526,7 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 
 	adis->spi = spi;
 	adis->data = data;
-	if (!adis->ops->write && !adis->ops->read && !adis->ops->reset)
+	if (!adis->ops)
 		adis->ops = &adis_default_ops;
 	else if (!adis->ops->write || !adis->ops->read || !adis->ops->reset)
 		return -EINVAL;

From 25723454f67980712234a42caca606b6710fd1e1 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wenst@chromium.org>
Date: Tue, 10 Feb 2026 18:03:34 +0800
Subject: [PATCH 0130/1303] wifi: mwifiex: Fix dev_alloc_name() return value
 check

dev_alloc_name() returns the allocated ID on success, which could be
over 0.

Fix the return value check to check for negative error codes.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/aYmsQfujoAe5qO02@stanley.mountain/
Fixes: 7bab5bdb81e3 ("wifi: mwifiex: Allocate dev name earlier for interface workqueue name")
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://patch.msgid.link/20260210100337.1131279-1-wenst@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index a66d18e380fc..bc0a946e8e6e 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -3148,7 +3148,7 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 	SET_NETDEV_DEV(dev, adapter->dev);
 
 	ret = dev_alloc_name(dev, name);
-	if (ret)
+	if (ret < 0)
 		goto err_alloc_name;
 
 	priv->dfs_cac_workqueue = alloc_workqueue("MWIFIEX_DFS_CAC-%s",

From 03cc8f90d0537fcd4985c3319b4fafbf2e3fb1f0 Mon Sep 17 00:00:00 2001
From: Daniel Hodges <git@danielhodges.dev>
Date: Fri, 6 Feb 2026 14:53:56 -0500
Subject: [PATCH 0131/1303] wifi: libertas: fix use-after-free in
 lbs_free_adapter()

The lbs_free_adapter() function uses timer_delete() (non-synchronous)
for both command_timer and tx_lockup_timer before the structure is
freed. This is incorrect because timer_delete() does not wait for
any running timer callback to complete.

If a timer callback is executing when lbs_free_adapter() is called,
the callback will access freed memory since lbs_cfg_free() frees the
containing structure immediately after lbs_free_adapter() returns.

Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler)
access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields,
which would all be use-after-free violations.

Use timer_delete_sync() instead to ensure any running timer callback
has completed before returning.

This bug was introduced in commit 8f641d93c38a ("libertas: detect TX
lockups and reset hardware") where del_timer() was used instead of
del_timer_sync() in the cleanup path. The command_timer has had the
same issue since the driver was first written.

Fixes: 8f641d93c38a ("libertas: detect TX lockups and reset hardware")
Fixes: 954ee164f4f4 ("[PATCH] libertas: reorganize and simplify init sequence")
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Hodges <git@danielhodges.dev>
Link: https://patch.msgid.link/20260206195356.15647-1-git@danielhodges.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/libertas/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c
index d44e02c6fe38..dd97f1b61f4d 100644
--- a/drivers/net/wireless/marvell/libertas/main.c
+++ b/drivers/net/wireless/marvell/libertas/main.c
@@ -799,8 +799,8 @@ static void lbs_free_adapter(struct lbs_private *priv)
 {
 	lbs_free_cmd_buffer(priv);
 	kfifo_free(&priv->event_fifo);
-	timer_delete(&priv->command_timer);
-	timer_delete(&priv->tx_lockup_timer);
+	timer_delete_sync(&priv->command_timer);
+	timer_delete_sync(&priv->tx_lockup_timer);
 }
 
 static const struct net_device_ops lbs_netdev_ops = {

From 2259d14499d16b115ef8d5d2ddc867e2be7cb5b5 Mon Sep 17 00:00:00 2001
From: Ramanathan Choodamani <quic_rchoodam@quicinc.com>
Date: Thu, 5 Feb 2026 15:12:16 +0530
Subject: [PATCH 0132/1303] wifi: mac80211: set default WMM parameters on all
 links

Currently, mac80211 only initializes default WMM parameters
on the deflink during do_open(). For MLO cases, this
leaves the additional links without proper WMM defaults
if hostapd does not supply per-link WMM parameters, leading
to inconsistent QoS behavior across links.

Set default WMM parameters for each link during
ieee80211_vif_update_links(), because this ensures all
individual links in an MLD have valid WMM settings during
bring-up and behave consistently across different BSS.

Signed-off-by: Ramanathan Choodamani <quic_rchoodam@quicinc.com>
Signed-off-by: Aishwarya R <aishwarya.r@oss.qualcomm.com>
Link: https://patch.msgid.link/20260205094216.3093542-1-aishwarya.r@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/link.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 17bf55dabd31..a1f67bab8ba1 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -281,6 +281,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS];
 	struct ieee80211_link_data *old_data[IEEE80211_MLD_MAX_NUM_LINKS];
 	bool use_deflink = old_links == 0; /* set for error case */
+	bool non_sta = sdata->vif.type != NL80211_IFTYPE_STATION;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
@@ -337,6 +338,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
 		link = links[link_id];
 		ieee80211_link_init(sdata, link_id, &link->data, &link->conf);
 		ieee80211_link_setup(&link->data);
+		ieee80211_set_wmm_default(&link->data, true, non_sta);
 	}
 
 	if (new_links == 0)

From 1cb3c20688fc8380c9b365d03aea7e84faf6a9fd Mon Sep 17 00:00:00 2001
From: Sean Rhodes <sean@starlabs.systems>
Date: Thu, 19 Feb 2026 20:14:26 +0000
Subject: [PATCH 0133/1303] ALSA: hda/realtek: Fix speaker pop on Star Labs
 StarFighter

On Star Labs StarFighter (Realtek ALC233/235), the internal speakers can
emit an audible pop when entering or leaving runtime suspend.

Mute the speaker output paths via snd_hda_gen_shutup_speakers() in the
Realtek shutup callback before the codec is powered down.

This is enough to avoid the pop without special EAPD handling.

Test results:
- runtime PM pop fixed
- still reaches D3 (PCI 0000:00:1f.3 power_state=D3hot)
- does not address pops on cold boot (G3 exit) or around display manager
  start/shutdown

journalctl -k (boot):
- snd_hda_codec_alc269 hdaudioC0D0: ALC233: picked fixup for PCI SSID
  7017:2014
- snd_hda_codec_alc269 hdaudioC0D0: autoconfig for ALC233: line_outs=1
  (0x1b/0x0/0x0/0x0/0x0) type:speaker

Suggested-by: Takashi Iwai <tiwai@suse.com>
Tested-by: Sean Rhodes <sean@starlabs.systems>
Signed-off-by: Sean Rhodes <sean@starlabs.systems>
Link: https://patch.msgid.link/4d5fb71b132bb283fd41c622b8413770b2065242.1771532060.git.sean@starlabs.systems
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 36053042ca77..9f64bb97c3f9 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -1017,6 +1017,24 @@ static int alc269_resume(struct hda_codec *codec)
 	return 0;
 }
 
+#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS	30
+
+static void starlabs_starfighter_shutup(struct hda_codec *codec)
+{
+	if (snd_hda_gen_shutup_speakers(codec))
+		msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS);
+}
+
+static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec,
+					      const struct hda_fixup *fix,
+					      int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->shutup = starlabs_starfighter_shutup;
+}
+
 static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec,
 						 const struct hda_fixup *fix, int action)
 {
@@ -4040,6 +4058,7 @@ enum {
 	ALC245_FIXUP_CLEVO_NOISY_MIC,
 	ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE,
 	ALC233_FIXUP_MEDION_MTL_SPK,
+	ALC233_FIXUP_STARLABS_STARFIGHTER,
 	ALC294_FIXUP_BASS_SPEAKER_15,
 	ALC283_FIXUP_DELL_HP_RESUME,
 	ALC294_FIXUP_ASUS_CS35L41_SPI_2,
@@ -6499,6 +6518,10 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 	},
+	[ALC233_FIXUP_STARLABS_STARFIGHTER] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_starlabs_starfighter,
+	},
 	[ALC294_FIXUP_BASS_SPEAKER_15] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc294_fixup_bass_speaker_15,
@@ -7651,6 +7674,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x2782, 0x4900, "MEDION E15443", ALC233_FIXUP_MEDION_MTL_SPK),
+	SND_PCI_QUIRK(0x7017, 0x2014, "Star Labs StarFighter", ALC233_FIXUP_STARLABS_STARFIGHTER),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
@@ -7747,6 +7771,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"},
 	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
+	{.id = ALC233_FIXUP_STARLABS_STARFIGHTER, .name = "starlabs-starfighter"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
 	{.id = ALC269_FIXUP_SONY_VAIO, .name = "vaio"},
 	{.id = ALC269_FIXUP_DELL_M101Z, .name = "dell-m101z"},

From 1d241483368f2fd87fbaba64d6aec6bad3a1e12e Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Fri, 20 Feb 2026 21:58:48 +1030
Subject: [PATCH 0134/1303] ALSA: scarlett2: Fix DSP filter control array
 handling

scarlett2_add_dsp_ctls() was incorrectly storing the precomp and PEQ
filter coefficient control pointers into the precomp_flt_switch_ctls
and peq_flt_switch_ctls arrays instead of the intended targets
precomp_flt_ctls and peq_flt_ctls. Pass NULL instead, as the filter
coefficient control pointers are not used, and remove the unused
precomp_flt_ctls and peq_flt_ctls arrays from struct scarlett2_data.

Additionally, scarlett2_update_filter_values() was reading
dsp_input_count * peq_flt_count values for
SCARLETT2_CONFIG_PEQ_FLT_SWITCH, but the peq_flt_switch array is
indexed only by dsp_input_count (one switch per DSP input, not per
filter). Fix the read count.

Fixes: b64678eb4e70 ("ALSA: scarlett2: Add DSP controls")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://patch.msgid.link/86497b71db060677d97c38a6ce5f89bb3b25361b.1771581197.git.g@b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_scarlett2.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index 85a0316889d4..ef3150581eab 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -1328,8 +1328,6 @@ struct scarlett2_data {
 	struct snd_kcontrol *mux_ctls[SCARLETT2_MUX_MAX];
 	struct snd_kcontrol *mix_ctls[SCARLETT2_MIX_MAX];
 	struct snd_kcontrol *compressor_ctls[SCARLETT2_COMPRESSOR_CTLS_MAX];
-	struct snd_kcontrol *precomp_flt_ctls[SCARLETT2_PRECOMP_FLT_CTLS_MAX];
-	struct snd_kcontrol *peq_flt_ctls[SCARLETT2_PEQ_FLT_CTLS_MAX];
 	struct snd_kcontrol *precomp_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX];
 	struct snd_kcontrol *peq_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX];
 	struct snd_kcontrol *direct_monitor_ctl;
@@ -3447,7 +3445,6 @@ static int scarlett2_update_autogain(struct usb_mixer_interface *mixer)
 			private->autogain_status[i] =
 				private->num_autogain_status_texts - 1;
 
-
 	for (i = 0; i < SCARLETT2_AG_TARGET_COUNT; i++)
 		if (scarlett2_has_config_item(private,
 					      scarlett2_ag_target_configs[i])) {
@@ -5372,8 +5369,7 @@ static int scarlett2_update_filter_values(struct usb_mixer_interface *mixer)
 
 	err = scarlett2_usb_get_config(
 		mixer, SCARLETT2_CONFIG_PEQ_FLT_SWITCH,
-		info->dsp_input_count * info->peq_flt_count,
-		private->peq_flt_switch);
+		info->dsp_input_count, private->peq_flt_switch);
 	if (err < 0)
 		return err;
 
@@ -6546,7 +6542,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i)
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_precomp_flt_ctl,
 			i * info->precomp_flt_count + j,
-			1, s, &private->precomp_flt_switch_ctls[j]);
+			1, s, NULL);
 		if (err < 0)
 			return err;
 	}
@@ -6556,7 +6552,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i)
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_peq_flt_ctl,
 			i * info->peq_flt_count + j,
-			1, s, &private->peq_flt_switch_ctls[j]);
+			1, s, NULL);
 		if (err < 0)
 			return err;
 	}

From cbddd303416456db5ceeedaf9e262096f079e861 Mon Sep 17 00:00:00 2001
From: Panagiotis Foliadis <pfoliadis@posteo.net>
Date: Sat, 21 Feb 2026 19:40:58 +0000
Subject: [PATCH 0135/1303] ALSA: hda/realtek: Add quirk for Acer Aspire
 V3-572G

The Acer Aspire V3-572G has a combo jack (ALC283) but the BIOS
sets pin 0x19 to 0x411111f0 (not connected), so the headset mic
is not detected.

Add a quirk to override pin 0x19 as a headset mic and enable
headset mode.

Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221075
Suggested-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Panagiotis Foliadis <pfoliadis@posteo.net>
Reviewed-by: Charalampos Mitrodimas <charmitro@posteo.net>
Link: https://patch.msgid.link/20260221-fix-detect-mic-v1-1-b6e427b5275d@posteo.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 9f64bb97c3f9..bba173645b1f 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6614,6 +6614,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
+	SND_PCI_QUIRK(0x1025, 0x0943, "Acer Aspire V3-572G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),

From 43a44fb7f2fa163926b23149805e989ba2395db1 Mon Sep 17 00:00:00 2001
From: Juhyung Park <qkrwngud825@gmail.com>
Date: Sun, 22 Feb 2026 21:26:08 +0900
Subject: [PATCH 0136/1303] ALSA: hda/realtek: fix model name typo for Samsung
 Galaxy Book Flex (NT950QCG-X716)

There's no product named "Samsung Galaxy Flex Book".
Use the correct "Samsung Galaxy Book Flex" name.

Link: https://www.samsung.com/sec/support/model/NT950QCG-X716
Link: https://www.samsung.com/us/computing/galaxy-books/galaxy-book-flex/galaxy-book-flex-15-6-qled-512gb-storage-s-pen-included-np950qcg-k01us
Cc: <stable@vger.kernel.org>
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Link: https://patch.msgid.link/20260222122609.281191-1-qkrwngud825@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index bba173645b1f..7166cbeb0925 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7335,7 +7335,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
-	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),

From 9fb16a5c5ff93058851099a2b80a899b0c53fe3f Mon Sep 17 00:00:00 2001
From: Juhyung Park <qkrwngud825@gmail.com>
Date: Sun, 22 Feb 2026 21:26:09 +0900
Subject: [PATCH 0137/1303] ALSA: hda/realtek: add quirk for Samsung Galaxy
 Book Flex (NT950QCT-A38A)

Similar to other Samsung laptops, NT950QCT also requires the
ALC298_FIXUP_SAMSUNG_AMP quirk applied.

Cc: <stable@vger.kernel.org>
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Link: https://patch.msgid.link/20260222122609.281191-2-qkrwngud825@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 7166cbeb0925..43ecfc63ef87 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7335,6 +7335,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),

From 24d2d3c5f94007a5a0554065ab7349bb69e28bcb Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:33:45 +1030
Subject: [PATCH 0138/1303] ALSA: usb-audio: Improve Focusrite sample rate
 filtering

Replace the bLength == 10 max_rate check in
focusrite_valid_sample_rate() with filtering that also examines the
bmControls VAL_ALT_SETTINGS bit.

When VAL_ALT_SETTINGS is readable, the device uses strict
per-altsetting rate filtering (only the highest rate pair for that
altsetting is valid). When it is not readable, all rates up to
max_rate are valid.

For devices without the bLength == 10 Format Type descriptor extension
but with VAL_ALT_SETTINGS readable and multiple altsettings (only seen
in Scarlett 18i8 3rd Gen playback), fall back to the Focusrite
convention: alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.

This produces correct rate tables for all tested Focusrite devices
(all Scarlett 2nd, 3rd, and 4th Gen, Clarett+, and Vocaster) using
only USB descriptors, allowing QUIRK_FLAG_VALIDATE_RATES to be removed
for Focusrite in the next commit.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/7e18c1f393a6ecb6fc75dd867a2c4dbe135e3e22.1771594828.git.g@b4.vu
---
 sound/usb/format.c | 70 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 65 insertions(+), 5 deletions(-)

diff --git a/sound/usb/format.c b/sound/usb/format.c
index 64cfe4a9d8cd..1207c507882a 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -305,17 +305,48 @@ static bool s1810c_valid_sample_rate(struct audioformat *fp,
 }
 
 /*
- * Many Focusrite devices supports a limited set of sampling rates per
- * altsetting. Maximum rate is exposed in the last 4 bytes of Format Type
- * descriptor which has a non-standard bLength = 10.
+ * Focusrite devices use rate pairs: 44100/48000, 88200/96000, and
+ * 176400/192000. Return true if rate is in the pair for max_rate.
+ */
+static bool focusrite_rate_pair(unsigned int rate,
+				unsigned int max_rate)
+{
+	switch (max_rate) {
+	case 48000:  return rate == 44100 || rate == 48000;
+	case 96000:  return rate == 88200 || rate == 96000;
+	case 192000: return rate == 176400 || rate == 192000;
+	default:     return true;
+	}
+}
+
+/*
+ * Focusrite devices report all supported rates in a single clock
+ * source but only a subset is valid per altsetting.
+ *
+ * Detection uses two descriptor features:
+ *
+ * 1. Format Type descriptor bLength == 10: non-standard extension
+ *    with max sample rate in bytes 6..9.
+ *
+ * 2. bmControls VAL_ALT_SETTINGS readable bit: when set, the device
+ *    only supports the highest rate pair for that altsetting, and when
+ *    clear, all rates up to max_rate are valid.
+ *
+ * For devices without the bLength == 10 extension but with
+ * VAL_ALT_SETTINGS readable and multiple altsettings (only seen in
+ * Scarlett 18i8 3rd Gen playback), fall back to the Focusrite
+ * convention: alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.
  */
 static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 					struct audioformat *fp,
 					unsigned int rate)
 {
+	struct usb_interface *iface;
 	struct usb_host_interface *alts;
+	struct uac2_as_header_descriptor *as;
 	unsigned char *fmt;
 	unsigned int max_rate;
+	bool val_alt;
 
 	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
 	if (!alts)
@@ -326,9 +357,21 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 	if (!fmt)
 		return true;
 
+	as = snd_usb_find_csint_desc(alts->extra, alts->extralen,
+				     NULL, UAC_AS_GENERAL);
+	if (!as)
+		return true;
+
+	val_alt = uac_v2v3_control_is_readable(as->bmControls,
+					       UAC2_AS_VAL_ALT_SETTINGS);
+
 	if (fmt[0] == 10) { /* bLength */
 		max_rate = combine_quad(&fmt[6]);
 
+		if (val_alt)
+			return focusrite_rate_pair(rate, max_rate);
+
+		/* No val_alt: rates fall through from higher */
 		switch (max_rate) {
 		case 192000:
 			if (rate == 176400 || rate == 192000)
@@ -344,12 +387,29 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 			usb_audio_info(chip,
 				"%u:%d : unexpected max rate: %u\n",
 				fp->iface, fp->altsetting, max_rate);
-
 			return true;
 		}
 	}
 
-	return true;
+	if (!val_alt)
+		return true;
+
+	/* Multi-altsetting device with val_alt but no max_rate
+	 * in the format descriptor. Use Focusrite convention:
+	 * alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.
+	 */
+	iface = usb_ifnum_to_if(chip->dev, fp->iface);
+	if (!iface || iface->num_altsetting <= 2)
+		return true;
+
+	switch (fp->altsetting) {
+	case 1:		max_rate = 48000; break;
+	case 2:		max_rate = 96000; break;
+	case 3:		max_rate = 192000; break;
+	default:	return true;
+	}
+
+	return focusrite_rate_pair(rate, max_rate);
 }
 
 /*

From a8cc55bf81a45772cad44c83ea7bb0e98431094a Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:34:48 +1030
Subject: [PATCH 0139/1303] ALSA: usb-audio: Remove VALIDATE_RATES quirk for
 Focusrite devices

Remove QUIRK_FLAG_VALIDATE_RATES for Focusrite. With the previous
commit, focusrite_valid_sample_rate() produces correct rate tables
without USB probing.

QUIRK_FLAG_VALIDATE_RATES sends SET_CUR requests for each rate (~25ms
each) and leaves the device at 192kHz. This is a problem because that
rate: 1) disables the internal mixer, so outputs are silent until an
application opens the PCM and sets a lower rate, and 2) the Air and
Safe modes get disabled.

Fixes: 5963e5262180 ("ALSA: usb-audio: Enable rate validation for Scarlett devices")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/09b9c012024c998c4ca14bd876ef0dce0d0b6101.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 4cac0dfb0094..3164c9431d29 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,7 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
-		   QUIRK_FLAG_VALIDATE_RATES),
+		   0),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),
 	VENDOR_FLG(0x152a, /* Thesycon devices */

From 38c322068a26a01d7ff64da92179e68cdde9860b Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:36:35 +1030
Subject: [PATCH 0140/1303] ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP

Add a quirk flag to skip the usb_set_interface(),
snd_usb_init_pitch(), and snd_usb_init_sample_rate() calls in
__snd_usb_parse_audio_interface(). These are redundant with
snd_usb_endpoint_prepare() at stream-open time.

Enable the quirk for Focusrite devices, as init_sample_rate(rate_max)
sets 192kHz during probing, which disables the internal mixer and Air
and Safe modes.

Fixes: 16f1f838442d ("Revert "ALSA: usb-audio: Drop superfluous interface setup at parsing"")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/65a7909b15f9feb76c2a6f4f8814c240ddc50737.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c   | 3 ++-
 sound/usb/stream.c   | 3 +++
 sound/usb/usbaudio.h | 6 ++++++
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3164c9431d29..b13d0f4d25ac 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,7 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
-		   0),
+		   QUIRK_FLAG_SKIP_IFACE_SETUP),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),
 	VENDOR_FLG(0x152a, /* Thesycon devices */
@@ -2506,6 +2506,7 @@ static const char *const snd_usb_audio_quirk_flag_names[] = {
 	QUIRK_STRING_ENTRY(MIC_RES_384),
 	QUIRK_STRING_ENTRY(MIXER_PLAYBACK_MIN_MUTE),
 	QUIRK_STRING_ENTRY(MIXER_CAPTURE_MIN_MUTE),
+	QUIRK_STRING_ENTRY(SKIP_IFACE_SETUP),
 	NULL
 };
 
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index ac4d92065dd9..d38c39e28f38 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -1259,6 +1259,9 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip,
 			set_iface_first = true;
 
 		/* try to set the interface... */
+		if (chip->quirk_flags & QUIRK_FLAG_SKIP_IFACE_SETUP)
+			continue;
+
 		usb_set_interface(chip->dev, iface_no, 0);
 		if (set_iface_first)
 			usb_set_interface(chip->dev, iface_no, altno);
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 79978cae9799..085530cf62d9 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -224,6 +224,10 @@ extern bool snd_usb_skip_validation;
  *  playback value represents muted state instead of minimum audible volume
  * QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE
  *  Similar to QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE, but for capture streams
+ * QUIRK_FLAG_SKIP_IFACE_SETUP
+ *  Skip the probe-time interface setup (usb_set_interface,
+ *  init_pitch, init_sample_rate); redundant with
+ *  snd_usb_endpoint_prepare() at stream-open time
  */
 
 enum {
@@ -253,6 +257,7 @@ enum {
 	QUIRK_TYPE_MIC_RES_384			= 23,
 	QUIRK_TYPE_MIXER_PLAYBACK_MIN_MUTE	= 24,
 	QUIRK_TYPE_MIXER_CAPTURE_MIN_MUTE	= 25,
+	QUIRK_TYPE_SKIP_IFACE_SETUP		= 26,
 /* Please also edit snd_usb_audio_quirk_flag_names */
 };
 
@@ -284,5 +289,6 @@ enum {
 #define QUIRK_FLAG_MIC_RES_384			QUIRK_FLAG(MIC_RES_384)
 #define QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE	QUIRK_FLAG(MIXER_PLAYBACK_MIN_MUTE)
 #define QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE	QUIRK_FLAG(MIXER_CAPTURE_MIN_MUTE)
+#define QUIRK_FLAG_SKIP_IFACE_SETUP		QUIRK_FLAG(SKIP_IFACE_SETUP)
 
 #endif /* __USBAUDIO_H */

From 0d58273be0b9c3cec3be5488ca37f6ddbaf13cf0 Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:36:56 +1030
Subject: [PATCH 0141/1303] ALSA: usb-audio: Skip clock selector for Focusrite
 devices

Add QUIRK_FLAG_SKIP_CLOCK_SELECTOR for Focusrite devices.

During interface parsing, snd_usb_clock_find_source() reads the clock
selector value then writes it back unchanged. On Focusrite devices
this redundant write results in a ~300ms delay per altsetting, adding
~1.8s to probe time on a typical device with 6 altsettings.

Enabling SKIP_CLOCK_SELECTOR skips the redundant write-back.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/00e53ae0a508b41516b41833daa17823381a649c.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index b13d0f4d25ac..fbceed8e8d36 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,6 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
+		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),

From 1f96b84835eafb3e6f366dc3a66c0e69504cec9d Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Thu, 5 Feb 2026 13:55:45 +0100
Subject: [PATCH 0142/1303] pinctrl: equilibrium: rename irq_chip function
 callbacks

Renaming of the irq_chip callback functions to improve clarity.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 48b55c5bf8d4..49c8232b525a 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -23,7 +23,7 @@
 #define PIN_NAME_LEN	10
 #define PAD_REG_OFF	0x100
 
-static void eqbr_gpio_disable_irq(struct irq_data *d)
+static void eqbr_irq_mask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d)
 	gpiochip_disable_irq(gc, offset);
 }
 
-static void eqbr_gpio_enable_irq(struct irq_data *d)
+static void eqbr_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_ack_irq(struct irq_data *d)
+static void eqbr_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -62,10 +62,10 @@ static void eqbr_gpio_ack_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_mask_ack_irq(struct irq_data *d)
+static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_gpio_disable_irq(d);
-	eqbr_gpio_ack_irq(d);
+	eqbr_irq_mask(d);
+	eqbr_irq_ack(d);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
@@ -92,7 +92,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type,
 	return 0;
 }
 
-static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+static int eqbr_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -166,11 +166,11 @@ static void eqbr_irq_handler(struct irq_desc *desc)
 
 static const struct irq_chip eqbr_irq_chip = {
 	.name = "gpio_irq",
-	.irq_mask = eqbr_gpio_disable_irq,
-	.irq_unmask = eqbr_gpio_enable_irq,
-	.irq_ack = eqbr_gpio_ack_irq,
-	.irq_mask_ack = eqbr_gpio_mask_ack_irq,
-	.irq_set_type = eqbr_gpio_set_irq_type,
+	.irq_ack = eqbr_irq_ack,
+	.irq_mask = eqbr_irq_mask,
+	.irq_mask_ack = eqbr_irq_mask_ack,
+	.irq_unmask = eqbr_irq_unmask,
+	.irq_set_type = eqbr_irq_set_type,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };

From 3e00b1b332e54ba50cca6691f628b9c06574024f Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Thu, 5 Feb 2026 13:55:46 +0100
Subject: [PATCH 0143/1303] pinctrl: equilibrium: fix warning trace on load

The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also
called in the callback function 'eqbr_irq_mask_ack()'. This is done to
avoid source code duplication. The problem, is that in the function
'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()'

This generates the following warning trace in the log for every gpio on
load.

[    6.088111] ------------[ cut here ]------------
[    6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50
[    6.097847] Modules linked in:
[    6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G        W          6.12.59+ #0
[    6.097847] Tainted: [W]=WARN
[    6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50
[    6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40
[    6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046
[    6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008
[    6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0
[    6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000
[    6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514
[    6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000
[    6.097847] FS:  0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000
[    6.097847] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0
[    6.097847] Call Trace:
[    6.097847]  <TASK>
[    6.097847]  ? eqbr_irq_mask+0x63/0x70
[    6.097847]  ? no_action+0x10/0x10
[    6.097847]  eqbr_irq_mask_ack+0x11/0x60

In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the
interrupt is not disabled here.

To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()'
function. Implement instead this directly without disabling the interrupts.

Fixes: 52066a53bd11 ("pinctrl: equilibrium: Convert to immutable irq_chip")
Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 49c8232b525a..ba1c867b7b89 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -64,8 +64,15 @@ static void eqbr_irq_ack(struct irq_data *d)
 
 static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_irq_mask(d);
-	eqbr_irq_ack(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
+	unsigned int offset = irqd_to_hwirq(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&gctrl->lock, flags);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNCR);
+	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,

From 09a30b7a035f9f4ac918c8a9af89d70e43462152 Mon Sep 17 00:00:00 2001
From: Maulik Shah <maulik.shah@oss.qualcomm.com>
Date: Mon, 9 Feb 2026 09:33:44 +0530
Subject: [PATCH 0144/1303] pinctrl: qcom: qcs615: Add missing dual edge GPIO
 IRQ errata flag

Wakeup capable GPIOs uses PDC as parent IRQ chip and PDC on qcs615 do not
support dual edge IRQs. Add missing wakeirq_dual_edge_errata configuration
to enable workaround for dual edge GPIO IRQs.

Fixes: b698f36a9d40 ("pinctrl: qcom: add the tlmm driver for QCS615 platform")
Signed-off-by: Maulik Shah <maulik.shah@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/qcom/pinctrl-qcs615.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
index 4dfa820d4e77..f1c827ddbfbf 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs615.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = {
 	.ntiles = ARRAY_SIZE(qcs615_tiles),
 	.wakeirq_map = qcs615_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static const struct of_device_id qcs615_tlmm_of_match[] = {

From 32e0a7ad9c841f46549ccac0f1cca347a40d8685 Mon Sep 17 00:00:00 2001
From: Daniel J Blueman <daniel@quora.org>
Date: Fri, 20 Feb 2026 17:34:51 +0800
Subject: [PATCH 0145/1303] gpio: shared: fix memory leaks

On a Snapdragon X1 Elite laptop (Lenovo Yoga Slim 7x), kmemleak reports
three sets of:

unreferenced object 0xffff00080187f400 (size 1024):
  comm "swapper/0", pid 1, jiffies 4294667327
  hex dump (first 32 bytes):
    58 bd 70 01 08 00 ff ff 58 bd 70 01 08 00 ff ff  X.p.....X.p.....
    00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00  ................
  backtrace (crc 1665d1f8):
    kmemleak_alloc+0xf4/0x12c
    __kmalloc_cache_noprof+0x370/0x49c
    gpio_shared_make_ref+0x70/0x16c
    gpio_shared_of_traverse+0x4e8/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_init+0x34/0x1c4
    do_one_initcall+0x50/0x280
    kernel_init_freeable+0x290/0x33c
    kernel_init+0x28/0x14c
    ret_from_fork+0x10/0x20

unreferenced object 0xffff00080170c140 (size 8):
  comm "swapper/0", pid 1, jiffies 4294667327
  hex dump (first 8 bytes):
    72 65 73 65 74 00 00 00                          reset...
  backtrace (crc fc24536):
    kmemleak_alloc+0xf4/0x12c
    __kmalloc_node_track_caller_noprof+0x3c4/0x584
    kstrdup+0x4c/0xcc
    gpio_shared_make_ref+0x8c/0x16c
    gpio_shared_of_traverse+0x4e8/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_init+0x34/0x1c4
    do_one_initcall+0x50/0x280
    kernel_init_freeable+0x290/0x33c
    kernel_init+0x28/0x14c
    ret_from_fork+0x10/0x20

Fix this by decrementing the reference count of each list entry rather than
only the first.

Fix verified on the same laptop.

Fixes: a060b8c511abb gpiolib: implement low-level, shared GPIO support
Signed-off-by: Daniel J Blueman <daniel@quora.org>
Link: https://patch.msgid.link/20260220093452.101655-1-daniel@quora.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib-shared.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c
index d2614ace4de1..17a7128b6bd9 100644
--- a/drivers/gpio/gpiolib-shared.c
+++ b/drivers/gpio/gpiolib-shared.c
@@ -748,14 +748,14 @@ static bool gpio_shared_entry_is_really_shared(struct gpio_shared_entry *entry)
 static void gpio_shared_free_exclusive(void)
 {
 	struct gpio_shared_entry *entry, *epos;
+	struct gpio_shared_ref *ref, *rpos;
 
 	list_for_each_entry_safe(entry, epos, &gpio_shared_list, list) {
 		if (gpio_shared_entry_is_really_shared(entry))
 			continue;
 
-		gpio_shared_drop_ref(list_first_entry(&entry->refs,
-						      struct gpio_shared_ref,
-						      list));
+		list_for_each_entry_safe(ref, rpos, &entry->refs, list)
+			gpio_shared_drop_ref(ref);
 		gpio_shared_drop_entry(entry);
 	}
 }

From 03c0d030f5874eec6ce22750b2b8751d6d4303b5 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Sat, 14 Feb 2026 03:02:48 +0000
Subject: [PATCH 0146/1303] erofs: allow sharing page cache with the same aops
 only

Inode with identical data but different @aops cannot be mixed
because the page cache is managed by different subsystems (e.g.,
@aops for compressed on-disk inodes cannot handle plain on-disk
inodes).

In this patch, we never allow inodes to share the page cache
among plain, compressed, and fileio cases. When a shared inode
is created, we initialize @aops that is the same as the initial
real inode, and subsequent inodes cannot share the page cache
if the inferred @aops differ from the corresponding shared inode.

This is reasonable as a first step because, in typical use cases,
if an inode is compressible, it will fall into compressed
inodes across different filesystem images unless users use plain
filesystems. However, in that cases, users will use plain
filesystems all the time.

Fixes: 5ef3208e3be5 ("erofs: introduce the page cache share feature")
Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/inode.c    |  7 ++++++-
 fs/erofs/internal.h | 16 +++++++---------
 fs/erofs/ishare.c   | 14 +++++++++-----
 3 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 4f86169c23f1..4b3d21402e10 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -222,6 +222,7 @@ static int erofs_read_inode(struct inode *inode)
 
 static int erofs_fill_inode(struct inode *inode)
 {
+	const struct address_space_operations *aops;
 	int err;
 
 	trace_erofs_fill_inode(inode);
@@ -254,7 +255,11 @@ static int erofs_fill_inode(struct inode *inode)
 	}
 
 	mapping_set_large_folios(inode->i_mapping);
-	return erofs_inode_set_aops(inode, inode, false);
+	aops = erofs_get_aops(inode, false);
+	if (IS_ERR(aops))
+		return PTR_ERR(aops);
+	inode->i_mapping->a_ops = aops;
+	return 0;
 }
 
 /*
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index d1634455e389..a4f0a42cf8c3 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -471,26 +471,24 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
 	return NULL;
 }
 
-static inline int erofs_inode_set_aops(struct inode *inode,
-				       struct inode *realinode, bool no_fscache)
+static inline const struct address_space_operations *
+erofs_get_aops(struct inode *realinode, bool no_fscache)
 {
 	if (erofs_inode_is_data_compressed(EROFS_I(realinode)->datalayout)) {
 		if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP))
-			return -EOPNOTSUPP;
+			return ERR_PTR(-EOPNOTSUPP);
 		DO_ONCE_LITE_IF(realinode->i_blkbits != PAGE_SHIFT,
 			  erofs_info, realinode->i_sb,
 			  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
-		inode->i_mapping->a_ops = &z_erofs_aops;
-		return 0;
+		return &z_erofs_aops;
 	}
-	inode->i_mapping->a_ops = &erofs_aops;
 	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !no_fscache &&
 	    erofs_is_fscache_mode(realinode->i_sb))
-		inode->i_mapping->a_ops = &erofs_fscache_access_aops;
+		return &erofs_fscache_access_aops;
 	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) &&
 	    erofs_is_fileio_mode(EROFS_SB(realinode->i_sb)))
-		inode->i_mapping->a_ops = &erofs_fileio_aops;
-	return 0;
+		return &erofs_fileio_aops;
+	return &erofs_aops;
 }
 
 int erofs_register_sysfs(struct super_block *sb);
diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c
index ce980320a8b9..829d50d5c717 100644
--- a/fs/erofs/ishare.c
+++ b/fs/erofs/ishare.c
@@ -40,10 +40,14 @@ bool erofs_ishare_fill_inode(struct inode *inode)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
 	struct erofs_inode *vi = EROFS_I(inode);
+	const struct address_space_operations *aops;
 	struct erofs_inode_fingerprint fp;
 	struct inode *sharedinode;
 	unsigned long hash;
 
+	aops = erofs_get_aops(inode, true);
+	if (IS_ERR(aops))
+		return false;
 	if (erofs_xattr_fill_inode_fingerprint(&fp, inode, sbi->domain_id))
 		return false;
 	hash = xxh32(fp.opaque, fp.size, 0);
@@ -56,15 +60,15 @@ bool erofs_ishare_fill_inode(struct inode *inode)
 	}
 
 	if (inode_state_read_once(sharedinode) & I_NEW) {
-		if (erofs_inode_set_aops(sharedinode, inode, true)) {
-			iget_failed(sharedinode);
-			kfree(fp.opaque);
-			return false;
-		}
+		sharedinode->i_mapping->a_ops = aops;
 		sharedinode->i_size = vi->vfs_inode.i_size;
 		unlock_new_inode(sharedinode);
 	} else {
 		kfree(fp.opaque);
+		if (aops != sharedinode->i_mapping->a_ops) {
+			iput(sharedinode);
+			return false;
+		}
 		if (sharedinode->i_size != vi->vfs_inode.i_size) {
 			_erofs_printk(inode->i_sb, KERN_WARNING
 				"size(%lld:%lld) not matches for the same fingerprint\n",

From aa280a08e7d8fae58557acc345b36b3dc329d595 Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Tue, 6 Jan 2026 13:15:04 +0000
Subject: [PATCH 0147/1303] x86/fred: Correct speculative safety in
 fred_extint()

array_index_nospec() is no use if the result gets spilled to the stack, as
it makes the believed safe-under-speculation value subject to memory
predictions.

For all practical purposes, this means array_index_nospec() must be used in
the expression that accesses the array.

As the code currently stands, it's the wrong side of irqentry_enter(), and
'index' is put into %ebp across the function call.

Remove the index variable and reposition array_index_nospec(), so it's
calculated immediately before the array access.

Fixes: 14619d912b65 ("x86/fred: FRED entry/exit and dispatch code")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260106131504.679932-1-andrew.cooper3@citrix.com
---
 arch/x86/entry/entry_fred.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index a9b72997103d..88c757ac8ccd 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -160,8 +160,6 @@ void __init fred_complete_exception_setup(void)
 static noinstr void fred_extint(struct pt_regs *regs)
 {
 	unsigned int vector = regs->fred_ss.vector;
-	unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR,
-						NR_SYSTEM_VECTORS);
 
 	if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR))
 		return;
@@ -170,7 +168,8 @@ static noinstr void fred_extint(struct pt_regs *regs)
 		irqentry_state_t state = irqentry_enter(regs);
 
 		instrumentation_begin();
-		sysvec_table[index](regs);
+		sysvec_table[array_index_nospec(vector - FIRST_SYSTEM_VECTOR,
+						NR_SYSTEM_VECTORS)](regs);
 		instrumentation_end();
 		irqentry_exit(regs, state);
 	} else {

From a0cb371b521dde44f32cfe954b6ef6f82b407393 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Sat, 10 Jan 2026 11:47:37 +0800
Subject: [PATCH 0148/1303] x86/bug: Handle __WARN_printf() trap in
 early_fixup_exception()

The commit 5b472b6e5bd9 ("x86_64/bug: Implement __WARN_printf()")
implemented __WARN_printf(), which changed the mechanism to use UD1
instead of UD2. However, it only handles the trap in the runtime IDT
handler, while the early booting IDT handler lacks this handling. As a
result, the usage of WARN() before the runtime IDT setup can lead to
kernel crashes. Since KMSAN is enabled after the runtime IDT setup, it
is safe to use handle_bug() directly in early_fixup_exception() to
address this issue.

Fixes: 5b472b6e5bd9 ("x86_64/bug: Implement __WARN_printf()")
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/c4fb3645f60d3a78629d9870e8fcc8535281c24f.1768016713.git.houwenlong.hwl@antgroup.com
---
 arch/x86/include/asm/traps.h | 2 ++
 arch/x86/kernel/traps.c      | 2 +-
 arch/x86/mm/extable.c        | 7 ++-----
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 869b88061801..3f24cc472ce9 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -25,6 +25,8 @@ extern int ibt_selftest_noendbr(void);
 void handle_invalid_op(struct pt_regs *regs);
 #endif
 
+noinstr bool handle_bug(struct pt_regs *regs);
+
 static inline int get_si_code(unsigned long condition)
 {
 	if (condition & DR_STEP)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 5a6a772e0a6c..4dbff8ef9b1c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -397,7 +397,7 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
-static noinstr bool handle_bug(struct pt_regs *regs)
+noinstr bool handle_bug(struct pt_regs *regs)
 {
 	unsigned long addr = regs->ip;
 	bool handled = false;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 2fdc1f1f5adb..6b9ff1c6cafa 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -411,14 +411,11 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 		return;
 
 	if (trapnr == X86_TRAP_UD) {
-		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
+		if (handle_bug(regs))
 			return;
-		}
 
 		/*
-		 * If this was a BUG and report_bug returns or if this
+		 * If this was a BUG and handle_bug returns or if this
 		 * was just a normal #UD, we want to continue onward and
 		 * crash.
 		 */

From 24c8147abb39618d74fcc36e325765e8fe7bdd7a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Feb 2026 13:59:43 +0100
Subject: [PATCH 0149/1303] x86/cfi: Fix CFI rewrite for odd alignments

Rustam reported his clang builds did not boot properly; turns out his
.config has: CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B=y set.

Fix up the FineIBT code to deal with this unusual alignment.

Fixes: 931ab63664f0 ("x86/ibt: Implement FineIBT")
Reported-by: Rustam Kovhaev <rkovhaev@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Rustam Kovhaev <rkovhaev@gmail.com>
---
 arch/x86/include/asm/cfi.h     | 12 ++++++++----
 arch/x86/include/asm/linkage.h |  4 ++--
 arch/x86/kernel/alternative.c  | 29 ++++++++++++++++++++++-------
 arch/x86/net/bpf_jit_comp.c    | 13 ++-----------
 4 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index c40b9ebc1fb4..ab3fbbd947ed 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -111,6 +111,12 @@ extern bhi_thunk __bhi_args_end[];
 
 struct pt_regs;
 
+#ifdef CONFIG_CALL_PADDING
+#define CFI_OFFSET (CONFIG_FUNCTION_PADDING_CFI+5)
+#else
+#define CFI_OFFSET 5
+#endif
+
 #ifdef CONFIG_CFI
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
 #define __bpfcall
@@ -119,11 +125,9 @@ static inline int cfi_get_offset(void)
 {
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		return 16;
+		return /* fineibt_prefix_size */ 16;
 	case CFI_KCFI:
-		if (IS_ENABLED(CONFIG_CALL_PADDING))
-			return 16;
-		return 5;
+		return CFI_OFFSET;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 9d38ae744a2e..a7294656ad90 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -68,7 +68,7 @@
  * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the
  * CFI symbol layout changes.
  *
- * Without CALL_THUNKS:
+ * Without CALL_PADDING:
  *
  * 	.align	FUNCTION_ALIGNMENT
  * __cfi_##name:
@@ -77,7 +77,7 @@
  * 	.long	__kcfi_typeid_##name
  * name:
  *
- * With CALL_THUNKS:
+ * With CALL_PADDING:
  *
  * 	.align FUNCTION_ALIGNMENT
  * __cfi_##name:
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a888ae0f01fb..e87da25d1236 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1182,7 +1182,7 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 
 		poison_endbr(addr);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16);
+			poison_cfi(addr - CFI_OFFSET);
 	}
 }
 
@@ -1389,6 +1389,8 @@ extern u8 fineibt_preamble_end[];
 #define fineibt_preamble_ud   0x13
 #define fineibt_preamble_hash 5
 
+#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE)
+
 /*
  * <fineibt_caller_start>:
  *  0:   b8 78 56 34 12          mov    $0x12345678, %eax
@@ -1634,7 +1636,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 		 * have determined there are no indirect calls to it and we
 		 * don't need no CFI either.
 		 */
-		if (!is_endbr(addr + 16))
+		if (!is_endbr(addr + CFI_OFFSET))
 			continue;
 
 		hash = decode_preamble_hash(addr, &arity);
@@ -1642,6 +1644,15 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
+		/*
+		 * FineIBT relies on being at func-16, so if the preamble is
+		 * actually larger than that, place it the tail end.
+		 *
+		 * NOTE: this is possible with things like DEBUG_CALL_THUNKS
+		 * and DEBUG_FORCE_FUNCTION_ALIGN_64B.
+		 */
+		addr += CFI_OFFSET - fineibt_prefix_size;
+
 		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
 		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
 		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
@@ -1664,10 +1675,10 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end)
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		if (!exact_endbr(addr + 16))
+		if (!exact_endbr(addr + CFI_OFFSET))
 			continue;
 
-		poison_endbr(addr + 16);
+		poison_endbr(addr + CFI_OFFSET);
 	}
 }
 
@@ -1772,7 +1783,8 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	if (FINEIBT_WARN(fineibt_preamble_size, 20)			||
 	    FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20)	||
 	    FINEIBT_WARN(fineibt_caller_size, 14)			||
-	    FINEIBT_WARN(fineibt_paranoid_size, 20))
+	    FINEIBT_WARN(fineibt_paranoid_size, 20)			||
+	    WARN_ON_ONCE(CFI_OFFSET < fineibt_prefix_size))
 		return;
 
 	if (cfi_mode == CFI_AUTO) {
@@ -1885,6 +1897,11 @@ static void poison_cfi(void *addr)
 	 */
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
+		/*
+		 * FineIBT preamble is at func-16.
+		 */
+		addr += CFI_OFFSET - fineibt_prefix_size;
+
 		/*
 		 * FineIBT prefix should start with an ENDBR.
 		 */
@@ -1923,8 +1940,6 @@ static void poison_cfi(void *addr)
 	}
 }
 
-#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE)
-
 /*
  * When regs->ip points to a 0xD6 byte in the FineIBT preamble,
  * return true and fill out target and type.
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8f10080e6fe3..e9b78040d703 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -438,17 +438,8 @@ static void emit_kcfi(u8 **pprog, u32 hash)
 
 	EMIT1_off32(0xb8, hash);			/* movl $hash, %eax	*/
 #ifdef CONFIG_CALL_PADDING
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
+	for (int i = 0; i < CONFIG_FUNCTION_PADDING_CFI; i++)
+		EMIT1(0x90);
 #endif
 	EMIT_ENDBR();
 

From 237dc6a054f6787c2a8f61c59086030267e5e1c5 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 18 Dec 2025 19:20:29 +0100
Subject: [PATCH 0150/1303] x86/headers: Replace __ASSEMBLY__ stragglers with
 __ASSEMBLER__

After converting the __ASSEMBLY__ statements to __ASSEMBLER__ in
commit 24a295e4ef1ca ("x86/headers: Replace __ASSEMBLY__ with
__ASSEMBLER__ in non-UAPI headers"), some new code has been
added that uses __ASSEMBLY__ again. Convert these stragglers, too.

This is a mechanical patch, done with a simple "sed -i" command.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251218182029.166993-1-thuth@redhat.com
---
 arch/x86/include/asm/bug.h           | 6 +++---
 arch/x86/include/asm/irqflags.h      | 4 ++--
 arch/x86/include/asm/percpu.h        | 2 +-
 arch/x86/include/asm/runtime-const.h | 6 +++---
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 9b4e04690e1a..80c1696d8d59 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -7,7 +7,7 @@
 #include <linux/objtool.h>
 #include <asm/asm.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct bug_entry;
 extern void __WARN_trap(struct bug_entry *bug, ...);
 #endif
@@ -137,7 +137,7 @@ do {									\
 
 #ifdef HAVE_ARCH_BUG_FORMAT_ARGS
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/static_call_types.h>
 DECLARE_STATIC_CALL(WARN_trap, __WARN_trap);
 
@@ -153,7 +153,7 @@ struct arch_va_list {
 	struct sysv_va_list args;
 };
 extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs);
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define __WARN_bug_entry(flags, format) ({				\
 	struct bug_entry *bug;						\
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index a1193e9d65f2..462754b0bf8a 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -77,7 +77,7 @@ static __always_inline void native_local_irq_restore(unsigned long flags)
 #endif
 
 #ifndef CONFIG_PARAVIRT
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Used in the idle loop; sti takes one instruction cycle
  * to complete:
@@ -95,7 +95,7 @@ static __always_inline void halt(void)
 {
 	native_halt();
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_PARAVIRT */
 
 #ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index c55058f3d75e..409981468cba 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,7 +20,7 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#else /* !__ASSEMBLY__: */
+#else /* !__ASSEMBLER__: */
 
 #include <linux/args.h>
 #include <linux/bits.h>
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index e5a13dc8816e..4cd94fdcb45e 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -6,7 +6,7 @@
   #error "Cannot use runtime-const infrastructure from modules"
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro RUNTIME_CONST_PTR sym reg
 	movq	$0x0123456789abcdef, %\reg
@@ -16,7 +16,7 @@
 	.popsection
 .endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define runtime_const_ptr(sym) ({				\
 	typeof(sym) __ret;					\
@@ -74,5 +74,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 	}
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif

From b3d99f43c72b56cf7a104a364e7fb34b0702828b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 9 Feb 2026 15:28:16 +0100
Subject: [PATCH 0151/1303] sched/fair: Fix zero_vruntime tracking

It turns out that zero_vruntime tracking is broken when there is but a single
task running. Current update paths are through __{en,de}queue_entity(), and
when there is but a single task, pick_next_task() will always return that one
task, and put_prev_set_next_task() will end up in neither function.

This can cause entity_key() to grow indefinitely large and cause overflows,
leading to much pain and suffering.

Furtermore, doing update_zero_vruntime() from __{de,en}queue_entity(), which
are called from {set_next,put_prev}_entity() has problems because:

 - set_next_entity() calls __dequeue_entity() before it does cfs_rq->curr = se.
   This means the avg_vruntime() will see the removal but not current, missing
   the entity for accounting.

 - put_prev_entity() calls __enqueue_entity() before it does cfs_rq->curr =
   NULL. This means the avg_vruntime() will see the addition *and* current,
   leading to double accounting.

Both cases are incorrect/inconsistent.

Noting that avg_vruntime is already called on each {en,de}queue, remove the
explicit avg_vruntime() calls (which removes an extra 64bit division for each
{en,de}queue) and have avg_vruntime() update zero_vruntime itself.

Additionally, have the tick call avg_vruntime() -- discarding the result, but
for the side-effect of updating zero_vruntime.

While there, optimize avg_vruntime() by noting that the average of one value is
rather trivial to compute.

Test case:
  # taskset -c -p 1 $$
  # taskset -c 2 bash -c 'while :; do :; done&'
  # cat /sys/kernel/debug/sched/debug | awk '/^cpu#/ {P=0} /^cpu#2,/ {P=1} {if (P) print $0}' | grep -e zero_vruntime -e "^>"

PRE:
    .zero_vruntime                 : 31316.407903
  >R            bash   487     50787.345112   E       50789.145972           2.800000     50780.298364        16     120         0.000000         0.000000         0.000000        /
    .zero_vruntime                 : 382548.253179
  >R            bash   487    427275.204288   E      427276.003584           2.800000    427268.157540        23     120         0.000000         0.000000         0.000000        /

POST:
    .zero_vruntime                 : 17259.709467
  >R            bash   526     17259.709467   E       17262.509467           2.800000     16915.031624         9     120         0.000000         0.000000         0.000000        /
    .zero_vruntime                 : 18702.723356
  >R            bash   526     18702.723356   E       18705.523356           2.800000     18358.045513         9     120         0.000000         0.000000         0.000000        /

Fixes: 79f3f9bedd14 ("sched/eevdf: Fix min_vruntime vs avg_vruntime")
Reported-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260219080624.438854780%40infradead.org
---
 kernel/sched/fair.c | 84 ++++++++++++++++++++++++++++++---------------
 1 file changed, 57 insertions(+), 27 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eea99ec01a3f..56dddd4fd208 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -589,6 +589,21 @@ static inline bool entity_before(const struct sched_entity *a,
 	return vruntime_cmp(a->deadline, "<", b->deadline);
 }
 
+/*
+ * Per avg_vruntime() below, cfs_rq::zero_vruntime is only slightly stale
+ * and this value should be no more than two lag bounds. Which puts it in the
+ * general order of:
+ *
+ *	(slice + TICK_NSEC) << NICE_0_LOAD_SHIFT
+ *
+ * which is around 44 bits in size (on 64bit); that is 20 for
+ * NICE_0_LOAD_SHIFT, another 20 for NSEC_PER_MSEC and then a handful for
+ * however many msec the actual slice+tick ends up begin.
+ *
+ * (disregarding the actual divide-by-weight part makes for the worst case
+ * weight of 2, which nicely cancels vs the fuzz in zero_vruntime not actually
+ * being the zero-lag point).
+ */
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return vruntime_op(se->vruntime, "-", cfs_rq->zero_vruntime);
@@ -676,39 +691,61 @@ sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static inline
-void sum_w_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta)
 {
 	/*
-	 * v' = v + d ==> sum_w_vruntime' = sum_runtime - d*sum_weight
+	 * v' = v + d ==> sum_w_vruntime' = sum_w_vruntime - d*sum_weight
 	 */
 	cfs_rq->sum_w_vruntime -= cfs_rq->sum_weight * delta;
+	cfs_rq->zero_vruntime += delta;
 }
 
 /*
- * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * Specifically: avg_vruntime() + 0 must result in entity_eligible() := true
  * For this to be so, the result of this function must have a left bias.
+ *
+ * Called in:
+ *  - place_entity()      -- before enqueue
+ *  - update_entity_lag() -- before dequeue
+ *  - entity_tick()
+ *
+ * This means it is one entry 'behind' but that puts it close enough to where
+ * the bound on entity_key() is at most two lag bounds.
  */
 u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	s64 avg = cfs_rq->sum_w_vruntime;
-	long load = cfs_rq->sum_weight;
+	long weight = cfs_rq->sum_weight;
+	s64 delta = 0;
 
-	if (curr && curr->on_rq) {
-		unsigned long weight = scale_load_down(curr->load.weight);
+	if (curr && !curr->on_rq)
+		curr = NULL;
 
-		avg += entity_key(cfs_rq, curr) * weight;
-		load += weight;
-	}
+	if (weight) {
+		s64 runtime = cfs_rq->sum_w_vruntime;
+
+		if (curr) {
+			unsigned long w = scale_load_down(curr->load.weight);
+
+			runtime += entity_key(cfs_rq, curr) * w;
+			weight += w;
+		}
 
-	if (load) {
 		/* sign flips effective floor / ceiling */
-		if (avg < 0)
-			avg -= (load - 1);
-		avg = div_s64(avg, load);
+		if (runtime < 0)
+			runtime -= (weight - 1);
+
+		delta = div_s64(runtime, weight);
+	} else if (curr) {
+		/*
+		 * When there is but one element, it is the average.
+		 */
+		delta = curr->vruntime - cfs_rq->zero_vruntime;
 	}
 
-	return cfs_rq->zero_vruntime + avg;
+	update_zero_vruntime(cfs_rq, delta);
+
+	return cfs_rq->zero_vruntime;
 }
 
 /*
@@ -777,16 +814,6 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return vruntime_eligible(cfs_rq, se->vruntime);
 }
 
-static void update_zero_vruntime(struct cfs_rq *cfs_rq)
-{
-	u64 vruntime = avg_vruntime(cfs_rq);
-	s64 delta = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime);
-
-	sum_w_vruntime_update(cfs_rq, delta);
-
-	cfs_rq->zero_vruntime = vruntime;
-}
-
 static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *root = __pick_root_entity(cfs_rq);
@@ -856,7 +883,6 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	sum_w_vruntime_add(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 	se->min_vruntime = se->vruntime;
 	se->min_slice = se->slice;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
@@ -868,7 +894,6 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				  &min_vruntime_cb);
 	sum_w_vruntime_sub(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 }
 
 struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
@@ -5524,6 +5549,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	update_load_avg(cfs_rq, curr, UPDATE_TG);
 	update_cfs_group(curr);
 
+	/*
+	 * Pulls along cfs_rq::zero_vruntime.
+	 */
+	avg_vruntime(cfs_rq);
+
 #ifdef CONFIG_SCHED_HRTICK
 	/*
 	 * queued ticks are scheduled to match the slice, so don't bother

From bcd74b2ffdd0a2233adbf26b65c62fc69a809c8e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 23 Jan 2026 16:49:09 +0100
Subject: [PATCH 0152/1303] sched/fair: Only set slice protection at pick time

We should not (re)set slice protection in the sched_change pattern
which calls put_prev_task() / set_next_task().

Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260219080624.561421378%40infradead.org
---
 kernel/sched/fair.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56dddd4fd208..f2b46c33a8c5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5445,7 +5445,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 }
 
 static void
-set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
 {
 	clear_buddies(cfs_rq, se);
 
@@ -5460,7 +5460,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 
-		set_protect_slice(cfs_rq, se);
+		if (first)
+			set_protect_slice(cfs_rq, se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -8978,13 +8979,13 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 				pse = parent_entity(pse);
 			}
 			if (se_depth >= pse_depth) {
-				set_next_entity(cfs_rq_of(se), se);
+				set_next_entity(cfs_rq_of(se), se, true);
 				se = parent_entity(se);
 			}
 		}
 
 		put_prev_entity(cfs_rq, pse);
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, true);
 
 		__set_next_task_fair(rq, p, true);
 	}
@@ -13598,7 +13599,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, first);
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		account_cfs_rq_runtime(cfs_rq, 0);
 	}

From ff38424030f98976150e42ca35f4b00e6ab8fa23 Mon Sep 17 00:00:00 2001
From: Wang Tao <wangtao554@huawei.com>
Date: Tue, 20 Jan 2026 12:31:13 +0000
Subject: [PATCH 0153/1303] sched/eevdf: Update se->vprot in reweight_entity()

In the EEVDF framework with Run-to-Parity protection, `se->vprot` is an
independent variable defining the virtual protection timestamp.

When `reweight_entity()` is called (e.g., via nice/renice), it performs
the following actions to preserve Lag consistency:
 1. Scales `se->vlag` based on the new weight.
 2. Calls `place_entity()`, which recalculates `se->vruntime` based on
    the new weight and scaled lag.

However, the current implementation fails to update `se->vprot`, leading
to mismatches between the task's actual runtime and its expected duration.

Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption")
Suggested-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Wang Tao <wangtao554@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260120123113.3518950-1-wangtao554@huawei.com
---
 kernel/sched/fair.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f2b46c33a8c5..93fa5b8313e4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3815,6 +3815,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
+	bool rel_vprot = false;
+	u64 vprot;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
@@ -3822,6 +3824,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		update_entity_lag(cfs_rq, se);
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
+		if (curr && protect_slice(se)) {
+			vprot = se->vprot - se->vruntime;
+			rel_vprot = true;
+		}
+
 		cfs_rq->nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
@@ -3837,6 +3844,9 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	if (se->rel_deadline)
 		se->deadline = div_s64(se->deadline * se->load.weight, weight);
 
+	if (rel_vprot)
+		vprot = div_s64(vprot * se->load.weight, weight);
+
 	update_load_set(&se->load, weight);
 
 	do {
@@ -3848,6 +3858,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		place_entity(cfs_rq, se, 0);
+		if (rel_vprot)
+			se->vprot = se->vruntime + vprot;
 		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);

From 6e3c0a4e1ad1e0455b7880fad02b3ee179f56c09 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 22 Apr 2025 12:16:28 +0200
Subject: [PATCH 0154/1303] sched/fair: Fix lag clamp

Vincent reported that he was seeing undue lag clamping in a mixed
slice workload. Implement the max_slice tracking as per the todo
comment.

Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
Reported-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20250422101628.GA33555@noisy.programming.kicks-ass.net
---
 include/linux/sched.h |  1 +
 kernel/sched/fair.c   | 39 +++++++++++++++++++++++++++++++++++----
 2 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 074ad4ef3d81..a7b4a980eb2f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -579,6 +579,7 @@ struct sched_entity {
 	u64				deadline;
 	u64				min_vruntime;
 	u64				min_slice;
+	u64				max_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 93fa5b8313e4..f4446cbe8ffa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -748,6 +748,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 	return cfs_rq->zero_vruntime;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
+
 /*
  * lag_i = S - s_i = w_i * (V - v_i)
  *
@@ -761,17 +763,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  * EEVDF gives the following limit for a steady state system:
  *
  *   -r_max < lag < max(r_max, q)
- *
- * XXX could add max_slice to the augmented data to track this.
  */
 static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
 	s64 vlag, limit;
 
 	WARN_ON_ONCE(!se->on_rq);
 
 	vlag = avg_vruntime(cfs_rq) - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+	limit = calc_delta_fair(max_slice, se);
 
 	se->vlag = clamp(vlag, -limit, limit);
 }
@@ -829,6 +830,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
 	return min_slice;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 max_slice = 0ULL;
+
+	if (curr && curr->on_rq)
+		max_slice = curr->slice;
+
+	if (root)
+		max_slice = max(max_slice, root->max_slice);
+
+	return max_slice;
+}
+
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 {
 	return entity_before(__node_2_se(a), __node_2_se(b));
@@ -853,6 +869,15 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n
 	}
 }
 
+static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->max_slice > se->max_slice)
+			se->max_slice = rse->max_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
@@ -860,6 +885,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
 	u64 old_min_vruntime = se->min_vruntime;
 	u64 old_min_slice = se->min_slice;
+	u64 old_max_slice = se->max_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
@@ -870,8 +896,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 	__min_slice_update(se, node->rb_right);
 	__min_slice_update(se, node->rb_left);
 
+	se->max_slice = se->slice;
+	__max_slice_update(se, node->rb_right);
+	__max_slice_update(se, node->rb_left);
+
 	return se->min_vruntime == old_min_vruntime &&
-	       se->min_slice == old_min_slice;
+	       se->min_slice == old_min_slice &&
+	       se->max_slice == old_max_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,

From 4c652a47722f69c6f2685f05b17490ea97f643a8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Feb 2026 08:41:13 +0100
Subject: [PATCH 0155/1303] rseq: Mark rseq_arm_slice_extension_timer()
 __always_inline

objtool warns about this function being called inside of a uaccess
section:

kernel/entry/common.o: warning: objtool: irqentry_exit+0x1dc: call to rseq_arm_slice_extension_timer() with UACCESS enabled

Interestingly, this happens with CONFIG_RSEQ_SLICE_EXTENSION disabled,
so this is an empty function, as the normal implementation is
already marked __always_inline.

I could reproduce this multiple times with gcc-11 but not with gcc-15,
so the compiler probably got better at identifying the trivial function.

Mark all the empty helpers for !RSEQ_SLICE_EXTENSION as __always_inline
for consistency, avoiding this warning.

Fixes: 0ac3b5c3dc45 ("rseq: Implement time slice extension enforcement timer")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260206074122.709580-1-arnd@kernel.org
---
 include/linux/rseq_entry.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index cbc4a791618b..c6831c93cd6e 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -216,10 +216,10 @@ static __always_inline bool rseq_grant_slice_extension(bool work_pending)
 }
 
 #else /* CONFIG_RSEQ_SLICE_EXTENSION */
-static inline bool rseq_slice_extension_enabled(void) { return false; }
-static inline bool rseq_arm_slice_extension_timer(void) { return false; }
-static inline void rseq_slice_clear_grant(struct task_struct *t) { }
-static inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
+static __always_inline bool rseq_slice_extension_enabled(void) { return false; }
+static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
+static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);

From 5324953c06bd929c135d9e04be391ee2c11b5a19 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 18 Feb 2026 17:33:29 +0100
Subject: [PATCH 0156/1303] sched/core: Fix wakeup_preempt's next_class
 tracking

Kernel test robot reported that
tools/testing/selftests/kvm/hardware_disable_test was failing due to
commit 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt()
and rq_modified_*()")

It turns out there were two related problems that could lead to a
missed preemption:

 - when hitting newidle balance from the idle thread, it would elevate
   rb->next_class from &idle_sched_class to &fair_sched_class, causing
   later wakeup_preempt() calls to not hit the sched_class_above()
   case, and not issue resched_curr().

   Notably, this modification pattern should only lower the
   next_class, and never raise it. Create two new helper functions to
   wrap this.

 - when doing schedule_idle(), it was possible to miss (re)setting
   rq->next_class to &idle_sched_class, leading to the very same
   problem.

Cc: Sean Christopherson <seanjc@google.com>
Fixes: 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt() and rq_modified_*()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202602122157.4e861298-lkp@intel.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260218163329.GQ1395416@noisy.programming.kicks-ass.net
---
 kernel/sched/core.c  |  1 +
 kernel/sched/ext.c   |  4 ++--
 kernel/sched/fair.c  |  4 ++--
 kernel/sched/sched.h | 11 +++++++++++
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 759777694c78..b7f77c165a6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6830,6 +6830,7 @@ static void __sched notrace __schedule(int sched_mode)
 		/* SCX must consult the BPF scheduler to tell if rq is empty */
 		if (!rq->nr_running && !scx_enabled()) {
 			next = prev;
+			rq->next_class = &idle_sched_class;
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 62b1f3ac5630..06cc0a4aec66 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2460,7 +2460,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq->next_class = &ext_sched_class;
+	rq_modified_begin(rq, &ext_sched_class);
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);
@@ -2475,7 +2475,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	 * If @force_scx is true, always try to pick a SCHED_EXT task,
 	 * regardless of any higher-priority sched classes activity.
 	 */
-	if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class))
+	if (!force_scx && rq_modified_above(rq, &ext_sched_class))
 		return RETRY_TASK;
 
 	keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f4446cbe8ffa..bf948db905ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12982,7 +12982,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	this_rq->next_class = &fair_sched_class;
+	rq_modified_begin(this_rq, &fair_sched_class);
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {
@@ -13049,7 +13049,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (sched_class_above(this_rq->next_class, &fair_sched_class))
+	if (rq_modified_above(this_rq, &fair_sched_class))
 		pulled_task = -1;
 
 out:
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b82fb70a9d54..43bbf0693cca 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2748,6 +2748,17 @@ static inline const struct sched_class *next_active_class(const struct sched_cla
 
 #define sched_class_above(_a, _b)	((_a) < (_b))
 
+static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class)
+{
+	if (sched_class_above(rq->next_class, class))
+		rq->next_class = class;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class)
+{
+	return sched_class_above(rq->next_class, class);
+}
+
 static inline bool sched_stop_runnable(struct rq *rq)
 {
 	return rq->stop && task_on_rq_queued(rq->stop);

From 26d43a90be81fc90e26688a51d3ec83188602731 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Fri, 20 Feb 2026 15:06:40 -0500
Subject: [PATCH 0157/1303] rseq: Clarify rseq registration rseq_size bound
 check comment

The rseq registration validates that the rseq_size argument is greater
or equal to 32 (the original rseq size), but the comment associated with
this check does not clearly state this.

Clarify the comment to that effect.

Fixes: ee3e3ac05c26 ("rseq: Introduce extensible rseq ABI")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260220200642.1317826-2-mathieu.desnoyers@efficios.com
---
 kernel/rseq.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index b0973d19f366..e349f86cc945 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -449,8 +449,9 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32
 	 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
 	 * size, the required alignment is the original struct rseq alignment.
 	 *
-	 * In order to be valid, rseq_len is either the original rseq size, or
-	 * large enough to contain all supported fields, as communicated to
+	 * The rseq_len is required to be greater or equal to the original rseq
+	 * size. In order to be valid, rseq_len is either the original rseq size,
+	 * or large enough to contain all supported fields, as communicated to
 	 * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
 	 */
 	if (rseq_len < ORIG_RSEQ_SIZE ||

From 3b68df978133ac3d46d570af065a73debbb68248 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Fri, 20 Feb 2026 15:06:41 -0500
Subject: [PATCH 0158/1303] rseq: slice ext: Ensure rseq feature size differs
 from original rseq size

Before rseq became extensible, its original size was 32 bytes even
though the active rseq area was only 20 bytes. This had the following
impact in terms of userspace ecosystem evolution:

* The GNU libc between 2.35 and 2.39 expose a __rseq_size symbol set
  to 32, even though the size of the active rseq area is really 20.
* The GNU libc 2.40 changes this __rseq_size to 20, thus making it
  express the active rseq area.
* Starting from glibc 2.41, __rseq_size corresponds to the
  AT_RSEQ_FEATURE_SIZE from getauxval(3).

This means that users of __rseq_size can always expect it to
correspond to the active rseq area, except for the value 32, for
which the active rseq area is 20 bytes.

Exposing a 32 bytes feature size would make life needlessly painful
for userspace. Therefore, add a reserved field at the end of the
rseq area to bump the feature size to 33 bytes. This reserved field
is expected to be replaced with whatever field will come next,
expecting that this field will be larger than 1 byte.

The effect of this change is to increase the size from 32 to 64 bytes
before we actually have fields using that memory.

Clarify the allocation size and alignment requirements in the struct
rseq uapi comment.

Change the value returned by getauxval(AT_RSEQ_ALIGN) to return the
value of the active rseq area size rounded up to next power of 2, which
guarantees that the rseq structure will always be aligned on the nearest
power of two large enough to contain it, even as it grows. Change the
alignment check in the rseq registration accordingly.

This will minimize the amount of ABI corner-cases we need to document
and require userspace to play games with. The rule stays simple when
__rseq_size != 32:

  #define rseq_field_available(field)	(__rseq_size >= offsetofend(struct rseq_abi, field))

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260220200642.1317826-3-mathieu.desnoyers@efficios.com
---
 fs/binfmt_elf.c           |  3 ++-
 include/linux/rseq.h      | 12 ++++++++++++
 include/uapi/linux/rseq.h | 26 ++++++++++++++++++++++----
 kernel/rseq.c             |  3 ++-
 4 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 8e89cc5b2820..fb857faaf0d6 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -47,6 +47,7 @@
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <uapi/linux/rseq.h>
+#include <linux/rseq.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
@@ -286,7 +287,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	}
 #ifdef CONFIG_RSEQ
 	NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end));
-	NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq));
+	NEW_AUX_ENT(AT_RSEQ_ALIGN, rseq_alloc_align());
 #endif
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index 7a01a0760405..b9d62fc2140d 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags)
 		t->rseq = current->rseq;
 }
 
+/*
+ * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq
+ * registration. This is the active rseq area size rounded up to next
+ * power of 2, which guarantees that the rseq structure will always be
+ * aligned on the nearest power of two large enough to contain it, even
+ * as it grows.
+ */
+static inline unsigned int rseq_alloc_align(void)
+{
+	return 1U << get_count_order(offsetof(struct rseq, end));
+}
+
 #else /* CONFIG_RSEQ */
 static inline void rseq_handle_slowpath(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 863c4a00a66b..f69344fe6c08 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -87,10 +87,17 @@ struct rseq_slice_ctrl {
 };
 
 /*
- * struct rseq is aligned on 4 * 8 bytes to ensure it is always
- * contained within a single cache-line.
+ * The original size and alignment of the allocation for struct rseq is
+ * 32 bytes.
  *
- * A single struct rseq per thread is allowed.
+ * The allocation size needs to be greater or equal to
+ * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to
+ * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32).
+ *
+ * As an alternative, userspace is allowed to use both the original size
+ * and alignment of 32 bytes for backward compatibility.
+ *
+ * A single active struct rseq registration per thread is allowed.
  */
 struct rseq {
 	/*
@@ -180,10 +187,21 @@ struct rseq {
 	 */
 	struct rseq_slice_ctrl slice_ctrl;
 
+	/*
+	 * Before rseq became extensible, its original size was 32 bytes even
+	 * though the active rseq area was only 20 bytes.
+	 * Exposing a 32 bytes feature size would make life needlessly painful
+	 * for userspace. Therefore, add a reserved byte after byte 32
+	 * to bump the rseq feature size from 32 to 33.
+	 * The next field to be added to the rseq area will be larger
+	 * than one byte, and will replace this reserved byte.
+	 */
+	__u8 __reserved;
+
 	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
-} __attribute__((aligned(4 * sizeof(__u64))));
+} __attribute__((aligned(32)));
 
 #endif /* _UAPI_LINUX_RSEQ_H */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index e349f86cc945..38d3ef540760 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -80,6 +80,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/types.h>
+#include <linux/rseq.h>
 #include <asm/ptrace.h>
 
 #define CREATE_TRACE_POINTS
@@ -456,7 +457,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32
 	 */
 	if (rseq_len < ORIG_RSEQ_SIZE ||
 	    (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
-	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) ||
 					    rseq_len < offsetof(struct rseq, end))))
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))

From 486ff5ad49bc50315bcaf6d45f04a33ef0a45ced Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 2 Jun 2025 21:51:05 -0700
Subject: [PATCH 0159/1303] perf/core: Fix invalid wait context in
 ctx_sched_in()

Lockdep found a bug in the event scheduling when a pinned event was
failed and wakes up the threads in the ring buffer like below.

It seems it should not grab a wait-queue lock under perf-context lock.
Let's do it with irq_work.

  [   39.913691] =============================
  [   39.914157] [ BUG: Invalid wait context ]
  [   39.914623] 6.15.0-next-20250530-next-2025053 #1 Not tainted
  [   39.915271] -----------------------------
  [   39.915731] repro/837 is trying to lock:
  [   39.916191] ffff88801acfabd8 (&event->waitq){....}-{3:3}, at: __wake_up+0x26/0x60
  [   39.917182] other info that might help us debug this:
  [   39.917761] context-{5:5}
  [   39.918079] 4 locks held by repro/837:
  [   39.918530]  #0: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: __perf_event_task_sched_in+0xd1/0xbc0
  [   39.919612]  #1: ffff88806ca3c6f8 (&cpuctx_lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1a7/0xbc0
  [   39.920748]  #2: ffff88800d91fc18 (&ctx->lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1f9/0xbc0
  [   39.921819]  #3: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: perf_event_wakeup+0x6c/0x470

Fixes: f4b07fd62d4d ("perf/core: Use POLLHUP for a pinned event in error")
Closes: https://lore.kernel.org/lkml/aD2w50VDvGIH95Pf@ly-workstation
Reported-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Link: https://patch.msgid.link/20250603045105.1731451-1-namhyung@kernel.org
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ac70d68217b6..4f86d22f281a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4138,7 +4138,8 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			if (*perf_event_fasync(event))
 				event->pending_kill = POLL_ERR;
 
-			perf_event_wakeup(event);
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending_irq);
 		} else {
 			struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu);
 

From 6a8a48644c4b804123e59dbfc5d6cd29a0194046 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Mon, 9 Feb 2026 16:52:25 -0800
Subject: [PATCH 0160/1303] perf/x86/intel/uncore: Add per-scheduler IMC CAS
 count events

IMC on SPR and EMR does not support sub-channels.  In contrast, CPUs
that use gnr_uncores[] (e.g. Granite Rapids and Sierra Forest)
implement two command schedulers (SCH0/SCH1) per memory channel,
providing logically independent command and data paths.

Do not reuse the spr_uncore_imc[] configuration for these CPUs.
Instead, introduce a dedicated gnr_uncore_imc[] with per-scheduler
events, so userspace can monitor SCH0 and SCH1 independently.

On these CPUs, replace cas_count_{read,write} with
cas_count_{read,write}_sch{0,1}.  This may break existing userspace
that relies on cas_count_{read,write}, prompting it to switch to the
per-scheduler events, as the legacy event reports only partial
traffic (SCH0).

Fixes: 632c4bf6d007 ("perf/x86/intel/uncore: Support Granite Rapids")
Fixes: cb4a6ccf3583 ("perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge")
Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260210005225.20311-1-zide.chen@intel.com
---
 arch/x86/events/intel/uncore_snbep.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 5ed6e0b7e715..0a1d08136cc1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6497,6 +6497,32 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct uncore_event_desc gnr_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x01,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0,  "event=0x05,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1,  "event=0x06,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type gnr_uncore_imc = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "imc",
+	.fixed_ctr_bits		= 48,
+	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
+	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
+	.event_descs		= gnr_uncore_imc_events,
+};
+
 static struct intel_uncore_type gnr_uncore_pciex8 = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "pciex8",
@@ -6544,7 +6570,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	NULL,
 	&spr_uncore_pcu,
 	&gnr_uncore_ubox,
-	&spr_uncore_imc,
+	&gnr_uncore_imc,
 	NULL,
 	&gnr_uncore_upi,
 	NULL,

From 77de62ad3de3967818c3dbe656b7336ebee461d2 Mon Sep 17 00:00:00 2001
From: Haocheng Yu <yuhaocheng035@gmail.com>
Date: Tue, 3 Feb 2026 00:20:56 +0800
Subject: [PATCH 0161/1303] perf/core: Fix refcount bug and potential UAF in
 perf_mmap

Syzkaller reported a refcount_t: addition on 0; use-after-free warning
in perf_mmap.

The issue is caused by a race condition between a failing mmap() setup
and a concurrent mmap() on a dependent event (e.g., using output
redirection).

In perf_mmap(), the ring_buffer (rb) is allocated and assigned to
event->rb with the mmap_mutex held. The mutex is then released to
perform map_range().

If map_range() fails, perf_mmap_close() is called to clean up.
However, since the mutex was dropped, another thread attaching to
this event (via inherited events or output redirection) can acquire
the mutex, observe the valid event->rb pointer, and attempt to
increment its reference count. If the cleanup path has already
dropped the reference count to zero, this results in a
use-after-free or refcount saturation warning.

Fix this by extending the scope of mmap_mutex to cover the
map_range() call. This ensures that the ring buffer initialization
and mapping (or cleanup on failure) happens atomically effectively,
preventing other threads from accessing a half-initialized or
dying ring buffer.

Closes: https://lore.kernel.org/oe-kbuild-all/202602020208.m7KIjdzW-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Haocheng Yu <yuhaocheng035@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260202162057.7237-1-yuhaocheng035@gmail.com
---
 kernel/events/core.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4f86d22f281a..22a0f405585b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7465,29 +7465,29 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = perf_mmap_aux(vma, event, nr_pages);
 		if (ret)
 			return ret;
+
+		/*
+		 * Since pinned accounting is per vm we cannot allow fork() to copy our
+		 * vma.
+		 */
+		vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
+		vma->vm_ops = &perf_mmap_vmops;
+
+		mapped = get_mapped(event, event_mapped);
+		if (mapped)
+			mapped(event, vma->vm_mm);
+
+		/*
+		 * Try to map it into the page table. On fail, invoke
+		 * perf_mmap_close() to undo the above, as the callsite expects
+		 * full cleanup in this case and therefore does not invoke
+		 * vmops::close().
+		 */
+		ret = map_range(event->rb, vma);
+		if (ret)
+			perf_mmap_close(vma);
 	}
 
-	/*
-	 * Since pinned accounting is per vm we cannot allow fork() to copy our
-	 * vma.
-	 */
-	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
-	vma->vm_ops = &perf_mmap_vmops;
-
-	mapped = get_mapped(event, event_mapped);
-	if (mapped)
-		mapped(event, vma->vm_mm);
-
-	/*
-	 * Try to map it into the page table. On fail, invoke
-	 * perf_mmap_close() to undo the above, as the callsite expects
-	 * full cleanup in this case and therefore does not invoke
-	 * vmops::close().
-	 */
-	ret = map_range(event->rb, vma);
-	if (ret)
-		perf_mmap_close(vma);
-
 	return ret;
 }
 

From eb4a7139e97374f42b7242cc754e77f1623fbcd5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Thu, 12 Feb 2026 08:27:31 +0200
Subject: [PATCH 0162/1303] drm/i915/alpm: ALPM disable fixes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PORT_ALPM_CTL is supposed to be written only before link training. Remove
writing it from ALPM disable.

Also clearing ALPM_CTL_ALPM_AUX_LESS_ENABLE and is not about disabling ALPM
but switching to AUX-Wake ALPM. Stop touching this bit on ALPM disable.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7153
Fixes: 1ccbf135862b ("drm/i915/psr: Enable ALPM on source side for eDP Panel replay")
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Michał Grzelak <michal.grzelak@intel.com>
Link: https://patch.msgid.link/20260212062731.397801-1-jouni.hogander@intel.com
(cherry picked from commit 008304c9ae75c772d3460040de56e12112cdf5e6)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index 7ce8c674bb03..07ffee38974b 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -562,12 +562,7 @@ void intel_alpm_disable(struct intel_dp *intel_dp)
 	mutex_lock(&intel_dp->alpm.lock);
 
 	intel_de_rmw(display, ALPM_CTL(display, cpu_transcoder),
-		     ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE |
-		     ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0);
-
-	intel_de_rmw(display,
-		     PORT_ALPM_CTL(cpu_transcoder),
-		     PORT_ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0);
+		     ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE, 0);
 
 	drm_dbg_kms(display->drm, "Disabling ALPM\n");
 	mutex_unlock(&intel_dp->alpm.lock);

From ec2cceadfae72304ca19650f9cac4b2a97b8a2fc Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Date: Thu, 19 Feb 2026 10:51:33 +0100
Subject: [PATCH 0163/1303] gpiolib: normalize the return value of gc->get() on
 behalf of buggy drivers

Commit 86ef402d805d ("gpiolib: sanitize the return value of
gpio_chip::get()") started checking the return value of the .get()
callback in struct gpio_chip. Now - almost a year later - it turns out
that there are quite a few drivers in tree that can break with this
change. Partially revert it: normalize the return value in GPIO core but
also emit a warning.

Cc: stable@vger.kernel.org
Fixes: 86ef402d805d ("gpiolib: sanitize the return value of gpio_chip::get()")
Reported-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Closes: https://lore.kernel.org/all/aZSkqGTqMp_57qC7@google.com/
Reviewed-by: Linus Walleij <linusw@kernel.org>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Link: https://patch.msgid.link/20260219-gpiolib-set-normalize-v2-1-f84630e45796@oss.qualcomm.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86a171e96b0e..ada572aaebd6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3267,8 +3267,12 @@ static int gpiochip_get(struct gpio_chip *gc, unsigned int offset)
 
 	/* Make sure this is called after checking for gc->get(). */
 	ret = gc->get(gc, offset);
-	if (ret > 1)
-		ret = -EBADE;
+	if (ret > 1) {
+		gpiochip_warn(gc,
+			"invalid return value from gc->get(): %d, consider fixing the driver\n",
+			ret);
+		ret = !!ret;
+	}
 
 	return ret;
 }

From af12e64ae0661546e8b4f5d30d55c5f53a11efe7 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 20 Jan 2026 22:26:46 +0800
Subject: [PATCH 0164/1303] mmc: mmci: Fix device_node reference leak in
 of_get_dml_pipe_index()

When calling of_parse_phandle_with_args(), the caller is responsible
to call of_node_put() to release the reference of device node.
In of_get_dml_pipe_index(), it does not release the reference.

Fixes: 9cb15142d0e3 ("mmc: mmci: Add qcom dml support to the driver.")
Signed-off-by: Felix Gu <gu_0233@qq.com>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mmci_qcom_dml.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mmc/host/mmci_qcom_dml.c b/drivers/mmc/host/mmci_qcom_dml.c
index 3da6112fbe39..67371389cc33 100644
--- a/drivers/mmc/host/mmci_qcom_dml.c
+++ b/drivers/mmc/host/mmci_qcom_dml.c
@@ -109,6 +109,7 @@ static int of_get_dml_pipe_index(struct device_node *np, const char *name)
 				       &dma_spec))
 		return -ENODEV;
 
+	of_node_put(dma_spec.np);
 	if (dma_spec.args_count)
 		return dma_spec.args[0];
 

From 6465a8bbb0f6ad98aeb66dc9ea19c32c193a610b Mon Sep 17 00:00:00 2001
From: Shawn Lin <shawn.lin@rock-chips.com>
Date: Fri, 16 Jan 2026 08:55:30 +0800
Subject: [PATCH 0165/1303] mmc: dw_mmc-rockchip: Fix runtime PM support for
 internal phase support

RK3576 is the first platform to introduce internal phase support, and
subsequent platforms are expected to adopt a similar design. In this
architecture, runtime suspend powers off the attached power domain, which
resets registers, including vendor-specific ones such as SDMMC_TIMING_CON0,
SDMMC_TIMING_CON1, and SDMMC_MISC_CON. These registers must be saved and
restored, a requirement that falls outside the scope of the dw_mmc core.

Fixes: 59903441f5e4 ("mmc: dw_mmc-rockchip: Add internal phase support")
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Tested-by: Marco Schirrmeister <mschirrmeister@gmail.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc-rockchip.c | 38 +++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 4e3423a19bdf..ac069d0c42b2 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -36,6 +36,8 @@ struct dw_mci_rockchip_priv_data {
 	int			default_sample_phase;
 	int			num_phases;
 	bool			internal_phase;
+	int                     sample_phase;
+	int                     drv_phase;
 };
 
 /*
@@ -573,9 +575,43 @@ static void dw_mci_rockchip_remove(struct platform_device *pdev)
 	dw_mci_pltfm_remove(pdev);
 }
 
+static int dw_mci_rockchip_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dw_mci *host = platform_get_drvdata(pdev);
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
+
+	if (priv->internal_phase) {
+		priv->sample_phase = rockchip_mmc_get_phase(host, true);
+		priv->drv_phase = rockchip_mmc_get_phase(host, false);
+	}
+
+	return dw_mci_runtime_suspend(dev);
+}
+
+static int dw_mci_rockchip_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dw_mci *host = platform_get_drvdata(pdev);
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
+	int ret;
+
+	ret = dw_mci_runtime_resume(dev);
+	if (ret)
+		return ret;
+
+	if (priv->internal_phase) {
+		rockchip_mmc_set_phase(host, true, priv->sample_phase);
+		rockchip_mmc_set_phase(host, false, priv->drv_phase);
+		mci_writel(host, MISC_CON, MEM_CLK_AUTOGATE_ENABLE);
+	}
+
+	return ret;
+}
+
 static const struct dev_pm_ops dw_mci_rockchip_dev_pm_ops = {
 	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
-	RUNTIME_PM_OPS(dw_mci_runtime_suspend, dw_mci_runtime_resume, NULL)
+	RUNTIME_PM_OPS(dw_mci_rockchip_runtime_suspend, dw_mci_rockchip_runtime_resume, NULL)
 };
 
 static struct platform_driver dw_mci_rockchip_pltfm_driver = {

From 79ad471530e0baef0dce991816013df55e401d9c Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Mon, 16 Feb 2026 14:15:43 -0500
Subject: [PATCH 0166/1303] mmc: sdhci-brcmstb: use correct register offset for
 V1 pin_sel restore

The restore path for SDIO_CFG_CORE_V1 was incorrectly using
SDIO_CFG_SD_PIN_SEL (offset 0x44) instead of SDIO_CFG_V1_SD_PIN_SEL
(offset 0x54), causing the wrong register to be written on resume.
The save path already uses the correct V1-specific offset. This
affects BCM7445 and BCM72116 platforms which use the V1 config core.

Fixes: b7e614802e3f ("mmc: sdhci-brcmstb: save and restore registers during PM")
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Cc: stable@vger.kernel.org
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-brcmstb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index c9442499876c..57e45951644e 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -116,7 +116,7 @@ static void sdhci_brcmstb_restore_regs(struct mmc_host *mmc, enum cfg_core_ver v
 		writel(sr->boot_main_ctl, priv->boot_regs + SDIO_BOOT_MAIN_CTL);
 
 	if (ver == SDIO_CFG_CORE_V1) {
-		writel(sr->sd_pin_sel, cr + SDIO_CFG_SD_PIN_SEL);
+		writel(sr->sd_pin_sel, cr + SDIO_CFG_V1_SD_PIN_SEL);
 		return;
 	}
 

From 162d331d833dc73a3e905a24c44dd33732af1fc5 Mon Sep 17 00:00:00 2001
From: Ariel Silver <arielsilver77@gmail.com>
Date: Fri, 20 Feb 2026 10:11:29 +0000
Subject: [PATCH 0167/1303] wifi: mac80211: bounds-check link_id in
 ieee80211_ml_reconfiguration

link_id is taken from the ML Reconfiguration element (control & 0x000f),
so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS
(15) elements, so index 15 is out-of-bounds. Skip subelements with
link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds
write.

Fixes: 8eb8dd2ffbbb ("wifi: mac80211: Support link removal using Reconfiguration ML element")
Reported-by: Ariel Silver <arielsilver77@gmail.com>
Signed-off-by: Ariel Silver <arielsilver77@gmail.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260220101129.1202657-1-Ariel.Silver@cybereason.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e83582b2c377..d43204ee330e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7085,6 +7085,9 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 		control = le16_to_cpu(prof->control);
 		link_id = control & IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID;
 
+		if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS)
+			continue;
+
 		removed_links |= BIT(link_id);
 
 		/* the MAC address should not be included, but handle it */

From 6510e1324bcdc8caf21f6d17efe27604c48f0d64 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 23 Feb 2026 09:36:16 +0000
Subject: [PATCH 0168/1303] ASoC: cs42l43: Report insert for exotic peripherals

For some exotic peripherals the type detect can return a reserved value
of 0x4. This will currently return an error and not report anything to
user-space, update this to report the insert normally.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260223093616.3800350-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43-jack.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index b83bc4de1301..3e04e6897b14 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -699,6 +699,7 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
 	switch (type & CS42L43_HSDET_TYPE_STS_MASK) {
 	case 0x0: // CTIA
 	case 0x1: // OMTP
+	case 0x4:
 		return cs42l43_run_load_detect(priv, true);
 	case 0x2: // 3-pole
 		return cs42l43_run_load_detect(priv, false);

From 901084c51a0a8fb42a3f37d2e9c62083c495f824 Mon Sep 17 00:00:00 2001
From: Penghe Geng <pgeng@nvidia.com>
Date: Thu, 19 Feb 2026 15:29:54 -0500
Subject: [PATCH 0169/1303] mmc: core: Avoid bitfield RMW for claim/retune
 flags

Move claimed and retune control flags out of the bitfield word to
avoid unrelated RMW side effects in asynchronous contexts.

The host->claimed bit shared a word with retune flags. Writes to claimed
in __mmc_claim_host() or retune_now in mmc_mq_queue_rq() can overwrite
other bits when concurrent updates happen in other contexts, triggering
spurious WARN_ON(!host->claimed). Convert claimed, can_retune,
retune_now and retune_paused to bool to remove shared-word coupling.

Fixes: 6c0cedd1ef952 ("mmc: core: Introduce host claiming by context")
Fixes: 1e8e55b67030c ("mmc: block: Add CQE support")
Cc: stable@vger.kernel.org
Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Penghe Geng <pgeng@nvidia.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/host.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index e0e2c265e5d1..ba84f02c2a10 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -486,14 +486,12 @@ struct mmc_host {
 
 	struct mmc_ios		ios;		/* current io bus settings */
 
+	bool			claimed;	/* host exclusively claimed */
+
 	/* group bitfields together to minimize padding */
 	unsigned int		use_spi_crc:1;
-	unsigned int		claimed:1;	/* host exclusively claimed */
 	unsigned int		doing_init_tune:1; /* initial tuning in progress */
-	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
-	unsigned int		retune_now:1;	/* do re-tuning at next req */
-	unsigned int		retune_paused:1; /* re-tuning is temporarily disabled */
 	unsigned int		retune_crc_disable:1; /* don't trigger retune upon crc */
 	unsigned int		can_dma_map_merge:1; /* merging can be used */
 	unsigned int		vqmmc_enabled:1; /* vqmmc regulator is enabled */
@@ -508,6 +506,9 @@ struct mmc_host {
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
+	bool			can_retune;	/* re-tuning can be used */
+	bool			retune_now;	/* do re-tuning at next req */
+	bool			retune_paused;	/* re-tuning is temporarily disabled */
 	int			need_retune;	/* re-tuning is needed */
 	int			hold_retune;	/* hold off re-tuning */
 	unsigned int		retune_period;	/* re-tuning period in secs */

From 7a73801fdaf8aee90d23ba77976082a48d156a21 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 22 Dec 2025 21:29:41 +0100
Subject: [PATCH 0170/1303] pmdomain: imx: gpcv2: Discard pm_runtime_put()
 return value

Passing pm_runtime_put() return value to the callers is not particularly
useful.

Returning an error code from pm_runtime_put() merely means that it has
not queued up a work item to check whether or not the device can be
suspended and there are many perfectly valid situations in which that
can happen, like after writing "on" to the devices' runtime PM "control"
attribute in sysfs for one example.

Accordingly, update imx_pgc_domain_suspend() to simply discard the
return value of pm_runtime_put() and always return success to the
caller.

This will facilitate a planned change of the pm_runtime_put() return
type to void in the future.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peng Fan <peng.fan@nxp.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/15658107.tv2OnDr8pf@rafael.j.wysocki
---
 drivers/pmdomain/imx/gpcv2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c
index cff738e4d546..a829f8da5be7 100644
--- a/drivers/pmdomain/imx/gpcv2.c
+++ b/drivers/pmdomain/imx/gpcv2.c
@@ -1416,7 +1416,9 @@ static int imx_pgc_domain_suspend(struct device *dev)
 
 static int imx_pgc_domain_resume(struct device *dev)
 {
-	return pm_runtime_put(dev);
+	pm_runtime_put(dev);
+
+	return 0;
 }
 #endif
 

From 3afd8df024339c7da1a5a0302f3987866dd16e40 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 22 Dec 2025 21:36:25 +0100
Subject: [PATCH 0171/1303] PM: runtime: Change pm_runtime_put() return type to
 void

The primary role of pm_runtime_put() is to decrement the runtime PM
usage counter of the given device.  It always does that regardless of
the value returned by it later.

In addition, if the runtime PM usage counter after decrementation turns
out to be zero, a work item is queued up to check whether or not the
device can be suspended.  This is not guaranteed to succeed though and
even if it is successful, the device may still not be suspended going
forward.

There are multiple valid reasons why pm_runtime_put() may not decide to
queue up the work item mentioned above, including, but not limited to,
the case when user space has written "on" to the device's runtime PM
"control" file in sysfs.  In all of those cases, pm_runtime_put()
returns a negative error code (even though the device's runtime PM
usage counter has been successfully decremented by it) which is very
confusing.  In fact, its return value should only be used for debug
purposes and care should be taken when doing it even in that case.

Accordingly, to avoid the confusion mentioned above, change the return
type of pm_runtime_put() to void.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Link: https://patch.msgid.link/14387202.RDIVbhacDa@rafael.j.wysocki
---
 include/linux/pm_runtime.h | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 41037c513f06..64921b10ac74 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev)
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_idle().
- *
- * Return:
- * * 1: Success. Usage counter dropped to zero, but device was already suspended.
- * * 0: Success.
- * * -EINVAL: Runtime PM error.
- * * -EACCES: Runtime PM disabled.
- * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status
- *            change ongoing.
- * * -EBUSY: Runtime PM child_count non-zero.
- * * -EPERM: Device PM QoS resume latency 0.
- * * -EINPROGRESS: Suspend already in progress.
- * * -ENOSYS: CONFIG_PM not enabled.
  */
-static inline int pm_runtime_put(struct device *dev)
+static inline void pm_runtime_put(struct device *dev)
 {
-	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
+	__pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
 /**

From 3c99a545b372c77b5d39715968a141f523eccbf2 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Wed, 18 Feb 2026 10:32:35 +0530
Subject: [PATCH 0172/1303] platform/x86: hp-wmi: Add Omen 16-xd0xxx fan and
 thermal support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-xd0xxx (board ID: 8BCD) has the same WMI interface as
other Victus S boards, but requires quirks for correctly switching
thermal profile (similar to HP Omen 16-wf1xxx, board ID: 8C78).

Add the DMI board name to victus_s_thermal_profile_boards[] table and
map it to omen_v1_thermal_params.

Testing on HP Omen 16-xd0xxx confirmed that platform profile is
registered successfully and fan RPMs are readable and controllable.

Tested-by: Varad Amol Pisale <varadpisale.work@gmail.com>
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260218050235.94687-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 304d9ac63c8a..b91965117edd 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -177,6 +177,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") },
 		.driver_data = (void *)&victus_s_thermal_params,
 	},
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD4") },
 		.driver_data = (void *)&victus_s_thermal_params,

From 7d87ed70fc95482c12edf9493c249b6413be485e Mon Sep 17 00:00:00 2001
From: Hans de Goede <johannes.goede@oss.qualcomm.com>
Date: Tue, 17 Feb 2026 14:23:46 +0100
Subject: [PATCH 0173/1303] platform/x86: touchscreen_dmi: Add quirk for
 y-inverted Goodix touchscreen on SUPI S10
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The touchscreen on the SUPI S10 tablet reports inverted Y coordinates,
causing touch input to be mirrored vertically relative to the display.

Add a quirk to set the "touchscreen-inverted-y" boolean device-property
on the touchscreen device, so that the goodix_ts driver will fixup
the coordinates.

Reported-by: Yajat Kumar <yajatapps3@gmail.com>
Closes: https://lore.kernel.org/linux-input/20251230221639.582406-1-yajatapps3@gmail.com/
Tested-by: Yajat Kumar <yajatapps3@gmail.com>
Signed-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260217132346.34535-1-johannes.goede@oss.qualcomm.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/touchscreen_dmi.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index bdc19cd8d3ed..d83c387821ea 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -410,6 +410,16 @@ static const struct ts_dmi_data gdix1002_upside_down_data = {
 	.properties	= gdix1001_upside_down_props,
 };
 
+static const struct property_entry gdix1001_y_inverted_props[] = {
+	PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+	{ }
+};
+
+static const struct ts_dmi_data gdix1001_y_inverted_data = {
+	.acpi_name	= "GDIX1001",
+	.properties	= gdix1001_y_inverted_props,
+};
+
 static const struct property_entry gp_electronic_t701_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-size-x", 960),
 	PROPERTY_ENTRY_U32("touchscreen-size-y", 640),
@@ -1658,6 +1668,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_SKU, "PN20170413488"),
 		},
 	},
+	{
+		/* SUPI S10 */
+		.driver_data = (void *)&gdix1001_y_inverted_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SUPI"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "S10"),
+		},
+	},
 	{
 		/* Techbite Arc 11.6 */
 		.driver_data = (void *)&techbite_arc_11_6_data,

From 13fa3aaf02edaad9b41fc61d7f6326d2b6a4bf80 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Mon, 16 Feb 2026 12:50:03 +0530
Subject: [PATCH 0174/1303] platform/x86: hp-wmi: Add Omen 16-wf0xxx fan and
 thermal support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-wf0xxx (board ID: 8BAB) has the same WMI interface as
other Victus S boards, but requires quirks for correctly switching
thermal profile (similar to HP Omen 16-wf1xxx, board ID: 8C78).

Add the DMI board name to victus_s_thermal_profile_boards[] table and
map it to omen_v1_thermal_params.

Testing on HP Omen 16-wf0xxx confirmed that platform profile is
registered successfully and fan RPMs are readable and controllable.

Suggested-by: Noah Provenzano <noahpro@gmail.com>
Tested-by: Juan Martin Morales <juanm4morales@gmail.com>
Reported-by: Juan Martin Morales <juanm4morales@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220639
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260216072003.90151-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index b91965117edd..bde74a02ccb3 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -173,6 +173,10 @@ static const char * const victus_thermal_profile_boards[] = {
 
 /* DMI Board names of Victus 16-r and Victus 16-s laptops */
 static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = {
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") },
 		.driver_data = (void *)&victus_s_thermal_params,

From 53e977b1d50c46f2c4ec3865cd13a822f58ad3cd Mon Sep 17 00:00:00 2001
From: Jonathan Teh <jonathan.teh@outlook.com>
Date: Mon, 16 Feb 2026 01:01:29 +0000
Subject: [PATCH 0175/1303] platform/x86: thinkpad_acpi: Fix errors reading
 battery thresholds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Check whether the battery supports the relevant charge threshold before
reading the value to silence these errors:

thinkpad_acpi: acpi_evalf(BCTG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCTG: evaluate failed
thinkpad_acpi: acpi_evalf(BCSG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCSG: evaluate failed

when reading the charge thresholds via sysfs on platforms that do not
support them such as the ThinkPad T400.

Fixes: 2801b9683f74 ("thinkpad_acpi: Add support for battery thresholds")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=202619
Signed-off-by: Jonathan Teh <jonathan.teh@outlook.com>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://patch.msgid.link/MI0P293MB01967B206E1CA6F337EBFB12926CA@MI0P293MB0196.ITAP293.PROD.OUTLOOK.COM
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/lenovo/thinkpad_acpi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/lenovo/thinkpad_acpi.c b/drivers/platform/x86/lenovo/thinkpad_acpi.c
index f9c736777908..8982d92dfd97 100644
--- a/drivers/platform/x86/lenovo/thinkpad_acpi.c
+++ b/drivers/platform/x86/lenovo/thinkpad_acpi.c
@@ -9525,14 +9525,16 @@ static int tpacpi_battery_get(int what, int battery, int *ret)
 {
 	switch (what) {
 	case THRESHOLD_START:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery))
+		if (!battery_info.batteries[battery].start_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery)))
 			return -ENODEV;
 
 		/* The value is in the low 8 bits of the response */
 		*ret = *ret & 0xFF;
 		return 0;
 	case THRESHOLD_STOP:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery))
+		if (!battery_info.batteries[battery].stop_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery)))
 			return -ENODEV;
 		/* Value is in lower 8 bits */
 		*ret = *ret & 0xFF;

From 6b3fa0615cd8432148581de62a52f83847af3d70 Mon Sep 17 00:00:00 2001
From: Peter Metz <peter.metz@unarin.com>
Date: Thu, 12 Feb 2026 23:46:27 -0500
Subject: [PATCH 0176/1303] platform/x86: intel-hid: Add Dell 14 Plus 2-in-1 to
 dmi_vgbs_allow_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Dell 14 Plus 2-in-1 (model DB04250) requires the VGBS allow list
entry to correctly enable the tablet mode switch. Without this, the
chassis state is not reported, and the hinge rotation only emits
unknown scancodes.

Verified on Dell 14 Plus 2-in-1 DB04250.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221090
Signed-off-by: Peter Metz <peter.metz@unarin.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260213044627.203638-1-peter.metz@unarin.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 0f8684f4464b..60ce32f591ff 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -189,6 +189,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell Pro Rugged 12 Tablet RA02260"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 14 Plus 2-in-1 DB04250"),
+		},
+	},
 	{ }
 };
 

From 857f5036f8fd729e097efbe3ba421b75e27346cb Mon Sep 17 00:00:00 2001
From: Peter Metz <peter.metz@unarin.com>
Date: Fri, 13 Feb 2026 17:58:02 -0500
Subject: [PATCH 0177/1303] platform/x86: intel-hid: Add Dell 16 Plus 2-in-1 to
 dmi_vgbs_allow_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Dell 16 Plus 2-in-1 (model DB06250) requires the VGBS allow list
entry to correctly enable the tablet mode switch. Without this, the
chassis state is not reported, and the hinge rotation only emits
unknown scancodes.

Link: https://lore.kernel.org/platform-driver-x86/CAP3yi-BWm0LqkhfzTrGy5n-KQ=3+T8eRMoR+Z+7Ke2VJB43kTA@mail.gmail.com/
Signed-off-by: Peter Metz <peter.metz@unarin.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260213230310.299974-1-peter.metz@unarin.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 60ce32f591ff..a8ae2dba7ffd 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -195,6 +195,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 14 Plus 2-in-1 DB04250"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 16 Plus 2-in-1 DB06250"),
+		},
+	},
 	{ }
 };
 

From 37da69dbaa60a778ffa67a066b77d287d704c659 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Wed, 11 Feb 2026 22:26:59 +0100
Subject: [PATCH 0178/1303] platform/x86: asus-armoury: add support for G733QS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model G733QS.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260211212659.16542-1-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 6e9703bd5017..001c011fdd56 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1708,6 +1708,20 @@ static const struct dmi_system_id power_limits[] = {
 			.requires_fan_curve = true,
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "G733QS"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 15,
+				.ppt_pl2_sppt_max = 80,
+			},
+			.requires_fan_curve = false,
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G814J"),

From 32fc4168fa56f6301d858c778a3d712774e9657e Mon Sep 17 00:00:00 2001
From: Azamat Almazbek uulu <almazbek1608@gmail.com>
Date: Sat, 21 Feb 2026 12:48:13 +0100
Subject: [PATCH 0179/1303] ASoC: amd: yc: Add ASUS EXPERTBOOK BM1503CDA to
 quirk table

The ASUS ExpertBook BM1503CDA (Ryzen 5 7535U, Barcelo-R) has an
internal DMIC connected through the AMD ACP (Audio CoProcessor)
but is missing from the DMI quirk table, so the acp6x machine
driver probe returns -ENODEV and no DMIC capture device is created.

Add the DMI entry so the internal microphone works out of the box.

Signed-off-by: Azamat Almazbek uulu <almazbek1608@gmail.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://patch.msgid.link/20260221114813.5610-1-almazbek1608@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index f1a63475100d..7af4daeb4c6f 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -703,6 +703,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 				DMI_MATCH(DMI_PRODUCT_NAME, "Vivobook_ASUSLaptop M6501RR_M6501RR"),
 			}
 		},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"),
+		}
+	},
 	{}
 };
 

From 4b73231b2a61c4142a027613d277a19c484dfcc3 Mon Sep 17 00:00:00 2001
From: Yufan Chen <ericterminal@gmail.com>
Date: Sun, 22 Feb 2026 18:40:35 +0800
Subject: [PATCH 0180/1303] regulator: tps65185: check devm_kzalloc() result in
 probe

tps65185_probe() dereferences the allocation result immediately by using data->regmap. If devm_kzalloc() returns NULL under memory pressure, this leads to a NULL pointer dereference.

Add the missing allocation check and return -ENOMEM on failure.

Signed-off-by: Yufan Chen <ericterminal@gmail.com>
Link: https://patch.msgid.link/20260222104035.90790-1-ericterminal@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps65185.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/regulator/tps65185.c b/drivers/regulator/tps65185.c
index 3286c9ab33d0..786622d8d598 100644
--- a/drivers/regulator/tps65185.c
+++ b/drivers/regulator/tps65185.c
@@ -332,6 +332,9 @@ static int tps65185_probe(struct i2c_client *client)
 	int i;
 
 	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
 	data->regmap = devm_regmap_init_i2c(client, &regmap_config);
 	if (IS_ERR(data->regmap))
 		return dev_err_probe(&client->dev, PTR_ERR(data->regmap),

From f895e5df80316a308c2f7d64d13a78494630ea05 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Thu, 12 Feb 2026 21:52:48 -0600
Subject: [PATCH 0181/1303] ipmi:si: Don't block module unload if the BMC is
 messed up

If the BMC is in a bad state, don't bother waiting for queues messages
since there can't be any.  Otherwise the unload is blocked until the
BMC is back in a good state.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_si_intf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 0049e3792ba1..3667033fcc51 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2234,7 +2234,8 @@ static void wait_msg_processed(struct smi_info *smi_info)
 	unsigned long jiffies_now;
 	long time_diff;
 
-	while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) {
+	while (smi_info->si_state != SI_HOSED &&
+		    (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL))) {
 		jiffies_now = jiffies;
 		time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies)
 		     * SI_USEC_PER_JIFFY);

From 62cd145453d577113f993efd025f258dd86aa183 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Thu, 12 Feb 2026 21:56:54 -0600
Subject: [PATCH 0182/1303] ipmi:msghandler: Handle error returns from the SMI
 sender

It used to be, until recently, that the sender operation on the low
level interfaces would not fail.  That's not the case any more with
recent changes.

So check the return value from the sender operation, and propagate it
back up from there and handle the errors in all places.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_msghandler.c | 102 +++++++++++++++++++---------
 1 file changed, 69 insertions(+), 33 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a042b1596933..f8c3c1e44520 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -1887,19 +1887,32 @@ static struct ipmi_smi_msg *smi_add_send_msg(struct ipmi_smi *intf,
 	return smi_msg;
 }
 
-static void smi_send(struct ipmi_smi *intf,
+static int smi_send(struct ipmi_smi *intf,
 		     const struct ipmi_smi_handlers *handlers,
 		     struct ipmi_smi_msg *smi_msg, int priority)
 {
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	unsigned long flags = 0;
+	int rv = 0;
 
 	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	smi_msg = smi_add_send_msg(intf, smi_msg, priority);
 	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
-	if (smi_msg)
-		handlers->sender(intf->send_info, smi_msg);
+	if (smi_msg) {
+		rv = handlers->sender(intf->send_info, smi_msg);
+		if (rv) {
+			ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
+			intf->curr_msg = NULL;
+			ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
+			/*
+			 * Something may have been added to the transmit
+			 * queue, so schedule a check for that.
+			 */
+			queue_work(system_wq, &intf->smi_work);
+		}
+	}
+	return rv;
 }
 
 static bool is_maintenance_mode_cmd(struct kernel_ipmi_msg *msg)
@@ -2312,6 +2325,7 @@ static int i_ipmi_request(struct ipmi_user     *user,
 	struct ipmi_recv_msg *recv_msg;
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	int rv = 0;
+	bool in_seq_table = false;
 
 	if (supplied_recv) {
 		recv_msg = supplied_recv;
@@ -2365,33 +2379,50 @@ static int i_ipmi_request(struct ipmi_user     *user,
 		rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg,
 				     source_address, source_lun,
 				     retries, retry_time_ms);
+		in_seq_table = true;
 	} else if (is_ipmb_direct_addr(addr)) {
 		rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg,
 					    recv_msg, source_lun);
 	} else if (is_lan_addr(addr)) {
 		rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg,
 				    source_lun, retries, retry_time_ms);
+		in_seq_table = true;
 	} else {
-	    /* Unknown address type. */
+		/* Unknown address type. */
 		ipmi_inc_stat(intf, sent_invalid_commands);
 		rv = -EINVAL;
 	}
 
-	if (rv) {
+	if (!rv) {
+		dev_dbg(intf->si_dev, "Send: %*ph\n",
+			smi_msg->data_size, smi_msg->data);
+
+		rv = smi_send(intf, intf->handlers, smi_msg, priority);
+		if (rv != IPMI_CC_NO_ERROR)
+			/* smi_send() returns an IPMI err, return a Linux one. */
+			rv = -EIO;
+		if (rv && in_seq_table) {
+			/*
+			 * If it's in the sequence table, it will be
+			 * retried later, so ignore errors.
+			 */
+			rv = 0;
+			/* But we need to fix the timeout. */
+			intf_start_seq_timer(intf, smi_msg->msgid);
+			ipmi_free_smi_msg(smi_msg);
+			smi_msg = NULL;
+		}
+	}
 out_err:
+	if (!run_to_completion)
+		mutex_unlock(&intf->users_mutex);
+
+	if (rv) {
 		if (!supplied_smi)
 			ipmi_free_smi_msg(smi_msg);
 		if (!supplied_recv)
 			ipmi_free_recv_msg(recv_msg);
-	} else {
-		dev_dbg(intf->si_dev, "Send: %*ph\n",
-			smi_msg->data_size, smi_msg->data);
-
-		smi_send(intf, intf->handlers, smi_msg, priority);
 	}
-	if (!run_to_completion)
-		mutex_unlock(&intf->users_mutex);
-
 	return rv;
 }
 
@@ -3965,12 +3996,12 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf,
 		dev_dbg(intf->si_dev, "Invalid command: %*ph\n",
 			msg->data_size, msg->data);
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		ipmb_addr = (struct ipmi_ipmb_addr *) &recv_msg->addr;
@@ -4044,12 +4075,12 @@ static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf,
 		msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE;
 		msg->data_size = 5;
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr;
@@ -4189,7 +4220,7 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf,
 				  struct ipmi_smi_msg *msg)
 {
 	struct cmd_rcvr          *rcvr;
-	int                      rv = 0;
+	int                      rv = 0; /* Free by default */
 	unsigned char            netfn;
 	unsigned char            cmd;
 	unsigned char            chan;
@@ -4242,12 +4273,12 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf,
 		dev_dbg(intf->si_dev, "Invalid command: %*ph\n",
 			msg->data_size, msg->data);
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		lan_addr = (struct ipmi_lan_addr *) &recv_msg->addr;
@@ -5056,7 +5087,12 @@ static void check_msg_timeout(struct ipmi_smi *intf, struct seq_table *ent,
 				ipmi_inc_stat(intf,
 					      retransmitted_ipmb_commands);
 
-			smi_send(intf, intf->handlers, smi_msg, 0);
+			/* If this fails we'll retry later or timeout. */
+			if (smi_send(intf, intf->handlers, smi_msg, 0) != IPMI_CC_NO_ERROR) {
+				/* But fix the timeout. */
+				intf_start_seq_timer(intf, smi_msg->msgid);
+				ipmi_free_smi_msg(smi_msg);
+			}
 		} else
 			ipmi_free_smi_msg(smi_msg);
 

From cae66f1a1dcd23e17da5a015ef9d731129f9d2dd Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 13 Feb 2026 00:15:04 -0600
Subject: [PATCH 0183/1303] ipmi:si: Fix check for a misbehaving BMC

There is a race on checking the state in the sender, it needs to be
checked under a lock.  But you also need a check to avoid issues with
a misbehaving BMC for run to completion mode.  So leave the check at
the beginning for run to completion, and add a check under the lock
to avoid the race.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_si_intf.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 3667033fcc51..6eda61664aaa 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -924,9 +924,14 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg)
 {
 	struct smi_info   *smi_info = send_info;
 	unsigned long     flags;
+	int rv = IPMI_CC_NO_ERROR;
 
 	debug_timestamp(smi_info, "Enqueue");
 
+	/*
+	 * Check here for run to completion mode.  A check under lock is
+	 * later.
+	 */
 	if (smi_info->si_state == SI_HOSED)
 		return IPMI_BUS_ERR;
 
@@ -940,18 +945,15 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg)
 	}
 
 	spin_lock_irqsave(&smi_info->si_lock, flags);
-	/*
-	 * The following two lines don't need to be under the lock for
-	 * the lock's sake, but they do need SMP memory barriers to
-	 * avoid getting things out of order.  We are already claiming
-	 * the lock, anyway, so just do it under the lock to avoid the
-	 * ordering problem.
-	 */
-	BUG_ON(smi_info->waiting_msg);
-	smi_info->waiting_msg = msg;
-	check_start_timer_thread(smi_info);
+	if (smi_info->si_state == SI_HOSED) {
+		rv = IPMI_BUS_ERR;
+	} else {
+		BUG_ON(smi_info->waiting_msg);
+		smi_info->waiting_msg = msg;
+		check_start_timer_thread(smi_info);
+	}
 	spin_unlock_irqrestore(&smi_info->si_lock, flags);
-	return IPMI_CC_NO_ERROR;
+	return rv;
 }
 
 static void set_run_to_completion(void *send_info, bool i_run_to_completion)

From 8225489ddb900656cc21573b4e1b00c9181fd777 Mon Sep 17 00:00:00 2001
From: Artem Lytkin <iprintercanon@gmail.com>
Date: Mon, 16 Feb 2026 20:20:38 +0000
Subject: [PATCH 0184/1303] staging: sm750fb: add missing pci_release_region on
 error and removal

hw_sm750_map() calls pci_request_region() but never releases the
region on error paths or in lynxfb_pci_remove(). This causes a
resource leak that prevents the PCI region from being mapped again
after driver removal or a failed probe. A TODO comment in the code
acknowledges this missing cleanup.

Restructure the error handling in hw_sm750_map() to properly release
the PCI region on ioremap failures, and add pci_release_region() to
lynxfb_pci_remove().

Signed-off-by: Artem Lytkin <iprintercanon@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260216202038.1828-1-iprintercanon@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/sm750fb/sm750.c    |  1 +
 drivers/staging/sm750fb/sm750_hw.c | 22 +++++++++++-----------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c
index dec1f6b88a7d..62f6e0cdff4d 100644
--- a/drivers/staging/sm750fb/sm750.c
+++ b/drivers/staging/sm750fb/sm750.c
@@ -1123,6 +1123,7 @@ static void lynxfb_pci_remove(struct pci_dev *pdev)
 
 	iounmap(sm750_dev->pvReg);
 	iounmap(sm750_dev->pvMem);
+	pci_release_region(pdev, 1);
 	kfree(g_settings);
 }
 
diff --git a/drivers/staging/sm750fb/sm750_hw.c b/drivers/staging/sm750fb/sm750_hw.c
index a29faee91c78..f60b152a647d 100644
--- a/drivers/staging/sm750fb/sm750_hw.c
+++ b/drivers/staging/sm750fb/sm750_hw.c
@@ -36,16 +36,11 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 
 	pr_info("mmio phyAddr = %lx\n", sm750_dev->vidreg_start);
 
-	/*
-	 * reserve the vidreg space of smi adaptor
-	 * if you do this, you need to add release region code
-	 * in lynxfb_remove, or memory will not be mapped again
-	 * successfully
-	 */
+	/* reserve the vidreg space of smi adaptor */
 	ret = pci_request_region(pdev, 1, "sm750fb");
 	if (ret) {
 		pr_err("Can not request PCI regions.\n");
-		goto exit;
+		return ret;
 	}
 
 	/* now map mmio and vidmem */
@@ -54,7 +49,7 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 	if (!sm750_dev->pvReg) {
 		pr_err("mmio failed\n");
 		ret = -EFAULT;
-		goto exit;
+		goto err_release_region;
 	}
 	pr_info("mmio virtual addr = %p\n", sm750_dev->pvReg);
 
@@ -79,13 +74,18 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 	sm750_dev->pvMem =
 		ioremap_wc(sm750_dev->vidmem_start, sm750_dev->vidmem_size);
 	if (!sm750_dev->pvMem) {
-		iounmap(sm750_dev->pvReg);
 		pr_err("Map video memory failed\n");
 		ret = -EFAULT;
-		goto exit;
+		goto err_unmap_reg;
 	}
 	pr_info("video memory vaddr = %p\n", sm750_dev->pvMem);
-exit:
+
+	return 0;
+
+err_unmap_reg:
+	iounmap(sm750_dev->pvReg);
+err_release_region:
+	pci_release_region(pdev, 1);
 	return ret;
 }
 

From f0109b9d3e1e455429279d602f6276e34689750a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 14:31:35 +0100
Subject: [PATCH 0185/1303] staging: rtl8723bs: properly validate the data in
 rtw_get_ie_ex()

Just like in commit 154828bf9559 ("staging: rtl8723bs: fix out-of-bounds
read in rtw_get_ie() parser"), we don't trust the data in the frame so
we should check the length better before acting on it

Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Tested-by: Navaneeth K <knavaneeth786@gmail.com>
Reviewed-by: Navaneeth K <knavaneeth786@gmail.com>
Link: https://patch.msgid.link/2026022336-arrange-footwork-6e54@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8723bs/core/rtw_ieee80211.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
index 6cf217e21593..3e2b5e6b07f9 100644
--- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
+++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
@@ -186,20 +186,25 @@ u8 *rtw_get_ie_ex(u8 *in_ie, uint in_len, u8 eid, u8 *oui, u8 oui_len, u8 *ie, u
 
 	cnt = 0;
 
-	while (cnt < in_len) {
+	while (cnt + 2 <= in_len) {
+		u8 ie_len = in_ie[cnt + 1];
+
+		if (cnt + 2 + ie_len > in_len)
+			break;
+
 		if (eid == in_ie[cnt]
-			&& (!oui || !memcmp(&in_ie[cnt+2], oui, oui_len))) {
+			&& (!oui || (ie_len >= oui_len && !memcmp(&in_ie[cnt + 2], oui, oui_len)))) {
 			target_ie = &in_ie[cnt];
 
 			if (ie)
-				memcpy(ie, &in_ie[cnt], in_ie[cnt+1]+2);
+				memcpy(ie, &in_ie[cnt], ie_len + 2);
 
 			if (ielen)
-				*ielen = in_ie[cnt+1]+2;
+				*ielen = ie_len + 2;
 
 			break;
 		}
-		cnt += in_ie[cnt+1]+2; /* goto next */
+		cnt += ie_len + 2; /* goto next */
 	}
 
 	return target_ie;

From 2a7b7652b1bb3fadc3bd47d622bfb127a93ab6b0 Mon Sep 17 00:00:00 2001
From: Leif Skunberg <diamondback@cohunt.app>
Date: Tue, 10 Feb 2026 14:21:29 +0100
Subject: [PATCH 0186/1303] platform/x86: int3472: Handle GPIO type 0x10
 (DOVDD)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Lenovo ThinkPad X1 Fold 16 Gen 1 has an OV5675 sensor (ACPI HID
OVTI5675) behind an INT3472 discrete PMIC controller. The INT3472
_DSM returns GPIO type 0x10 for one of the pins, which controls the
DOVDD (digital I/O power) regulator enable.

Type 0x10 is not currently handled by the driver, causing the GPIO to
be ignored with a warning. Add INT3472_GPIO_TYPE_DOVDD (0x10) and
handle it as a regulator with con_id "dovdd" to match the supply name
used by sensor drivers (e.g. ov5675).

Also increase GPIO_SUPPLY_NAME_LENGTH from 5 to 6 to accommodate
the "dovdd" name (5 chars + null terminator).

Signed-off-by: Leif Skunberg <diamondback@cohunt.app>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260210132129.17943-1-diamondback@cohunt.app
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/int3472/discrete.c | 7 +++++++
 include/linux/platform_data/x86/int3472.h     | 5 +++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 1455d9a7afca..1c65ce87cde0 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -223,6 +223,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
 		*con_id = "avdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
+	case INT3472_GPIO_TYPE_DOVDD:
+		*con_id = "dovdd";
+		*gpio_flags = GPIO_ACTIVE_HIGH;
+		break;
 	case INT3472_GPIO_TYPE_HANDSHAKE:
 		*con_id = "dvdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
@@ -251,6 +255,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
  * 0x0b Power enable
  * 0x0c Clock enable
  * 0x0d Privacy LED
+ * 0x10 DOVDD (digital I/O voltage)
  * 0x13 Hotplug detect
  *
  * There are some known platform specific quirks where that does not quite
@@ -332,6 +337,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	case INT3472_GPIO_TYPE_CLK_ENABLE:
 	case INT3472_GPIO_TYPE_PRIVACY_LED:
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
+	case INT3472_GPIO_TYPE_DOVDD:
 	case INT3472_GPIO_TYPE_HANDSHAKE:
 		gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, con_id, gpio_flags);
 		if (IS_ERR(gpio)) {
@@ -356,6 +362,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 		case INT3472_GPIO_TYPE_POWER_ENABLE:
 			second_sensor = int3472->quirks.avdd_second_sensor;
 			fallthrough;
+		case INT3472_GPIO_TYPE_DOVDD:
 		case INT3472_GPIO_TYPE_HANDSHAKE:
 			ret = skl_int3472_register_regulator(int3472, gpio, enable_time_us,
 							     con_id, second_sensor);
diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h
index b1b837583d54..dbe745dc88d5 100644
--- a/include/linux/platform_data/x86/int3472.h
+++ b/include/linux/platform_data/x86/int3472.h
@@ -26,6 +26,7 @@
 #define INT3472_GPIO_TYPE_POWER_ENABLE				0x0b
 #define INT3472_GPIO_TYPE_CLK_ENABLE				0x0c
 #define INT3472_GPIO_TYPE_PRIVACY_LED				0x0d
+#define INT3472_GPIO_TYPE_DOVDD					0x10
 #define INT3472_GPIO_TYPE_HANDSHAKE				0x12
 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT			0x13
 
@@ -33,8 +34,8 @@
 #define INT3472_MAX_SENSOR_GPIOS				3
 #define INT3472_MAX_REGULATORS					3
 
-/* E.g. "avdd\0" */
-#define GPIO_SUPPLY_NAME_LENGTH				5
+/* E.g. "dovdd\0" */
+#define GPIO_SUPPLY_NAME_LENGTH				6
 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */
 #define GPIO_REGULATOR_NAME_LENGTH				(12 + GPIO_SUPPLY_NAME_LENGTH)
 /* lower- and upper-case mapping */

From b38d478dad79e61e8a65931021bdfd7a71741212 Mon Sep 17 00:00:00 2001
From: Leif Skunberg <diamondback@cohunt.app>
Date: Tue, 10 Feb 2026 09:56:25 +0100
Subject: [PATCH 0187/1303] platform/x86: intel-hid: Enable 5-button array on
 ThinkPad X1 Fold 16 Gen 1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Lenovo ThinkPad X1 Fold 16 Gen 1 has physical volume up/down
buttons that are handled through the intel-hid 5-button array
interface. The firmware does not advertise 5-button array support via
HEBC, so the driver relies on a DMI allowlist to enable it.

Add the ThinkPad X1 Fold 16 Gen 1 to the button_array_table so the
volume buttons work out of the box.

Signed-off-by: Leif Skunberg <diamondback@cohunt.app>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260210085625.34380-1-diamondback@cohunt.app
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index a8ae2dba7ffd..95c405c8bac0 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -135,6 +135,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
 		},
 	},
+	{
+		.ident = "Lenovo ThinkPad X1 Fold 16 Gen 1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Fold 16 Gen 1"),
+		},
+	},
 	{
 		.ident = "Microsoft Surface Go 3",
 		.matches = {

From 249f05e625c6e6c14b27fd34a2f06a1afb9b456d Mon Sep 17 00:00:00 2001
From: Victor Lattaro Volpini <victorlattaro@proton.me>
Date: Tue, 10 Feb 2026 00:00:52 +0000
Subject: [PATCH 0188/1303] platform/x86: hp-wmi: Add Victus 16-d0xxx support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch enables Victus thermal profile support for the HP
Victus 16-d0xxx. It does so by adding model's DMI board name 88F8 to
victus_thermal_profile_boards.

Tested on a Victus 16-d0xxx:
  - Victus thermal profile choices available (quiet, balanced, performance)
    instead of the default ones (cool, quiet, balanced, performance);
  - Profile switching works correctly;
  - About 4% increase in FPS using benchmark Cyberpunk 2077 on
  performance profile;
  - No noticeable regressions.

Signed-off-by: Victor Lattaro Volpini <victorlattaro@proton.me>
Link: https://patch.msgid.link/20260210000048.250280-1-victorlattaro@proton.me
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index bde74a02ccb3..40165138cfbd 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -166,8 +166,9 @@ static const char * const omen_timed_thermal_profile_boards[] = {
 	"8BAD",
 };
 
-/* DMI Board names of Victus 16-d1xxx laptops */
+/* DMI Board names of Victus 16-d laptops */
 static const char * const victus_thermal_profile_boards[] = {
+	"88F8",
 	"8A25",
 };
 

From 26a7601471f62b95d56a81c3a8ccb551b5a6630f Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Sat, 7 Feb 2026 12:16:34 -0500
Subject: [PATCH 0189/1303] platform/x86: dell-wmi: Add audio/mic mute key
 codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add audio/mic mute key codes found in Alienware m18 r1 AMD.

Cc: stable@vger.kernel.org
Tested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Suggested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Acked-by: Pali Rohár <pali@kernel.org>
Link: https://patch.msgid.link/20260207-mute-keys-v2-1-c55e5471c9c1@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-wmi-base.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c
index 4eefbade2f5e..e7a411ae9ca1 100644
--- a/drivers/platform/x86/dell/dell-wmi-base.c
+++ b/drivers/platform/x86/dell/dell-wmi-base.c
@@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = {
 static const struct key_entry dell_wmi_keymap_type_0000[] = {
 	{ KE_IGNORE, 0x003a, { KEY_CAPSLOCK } },
 
+	/* Audio mute toggle */
+	{ KE_KEY,    0x0109, { KEY_MUTE } },
+
+	/* Mic mute toggle */
+	{ KE_KEY,    0x0150, { KEY_MICMUTE } },
+
 	/* Meta key lock */
 	{ KE_IGNORE, 0xe000, { KEY_RIGHTMETA } },
 

From 729ffcffa73069cb066fd54a2bc7b09e5f782d48 Mon Sep 17 00:00:00 2001
From: Anton Plotnikov <plotnikovanton@gmail.com>
Date: Tue, 3 Feb 2026 18:48:32 +0200
Subject: [PATCH 0190/1303] platform/x86: hp-wmi: add Omen 14-fb1xxx (board
 8E41) support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reverse engineering of the HP Omen Windows utility shows that for performance
mode it uses the same codes listed in hp_thermal_profile_omen_v1. Therefore it
seems sufficient to add the board model name to omen_thermal_profile_boards.

Tested on Omen 14-fb1xxx: CPU power in performance profile reaches the Windows
limit (65W), instead of 45W in automatic BIOS mode. Max fan speed was reached
as well.

Link: https://patch.msgid.link/20260203164832.40514-1-plotnikovanton@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 40165138cfbd..68ede7e5757a 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -146,6 +146,7 @@ static const char * const omen_thermal_profile_boards[] = {
 	"8900", "8901", "8902", "8912", "8917", "8918", "8949", "894A", "89EB",
 	"8A15", "8A42",
 	"8BAD",
+	"8E41",
 };
 
 /* DMI Board names of Omen laptops that are specifically set to be thermal

From bd5914caeb4b2de233992c31babccda88041b035 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Thu, 29 Jan 2026 12:19:24 -0500
Subject: [PATCH 0191/1303] platform/x86: alienware-wmi-wmax: Add G-Mode
 support to m18 laptops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Alienware m18 laptops support G-Mode. Therefore, match them with
G-Series quirks.

Cc: stable@vger.kernel.org
Tested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://patch.msgid.link/20260129-m18-gmode-v1-1-48be521487b9@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/alienware-wmi-wmax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index e69b50162bb1..d1b4df91401b 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -175,7 +175,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18"),
 		},
-		.driver_data = &generic_quirks,
+		.driver_data = &g_series_quirks,
 	},
 	{
 		.ident = "Alienware x15",

From e3aa6feaf0cc30a3c941d15ff04bc1005a8aa315 Mon Sep 17 00:00:00 2001
From: Jesse Guo <JesseGuoTech@outlook.com>
Date: Mon, 26 Jan 2026 04:48:26 +0800
Subject: [PATCH 0192/1303] platform/x86: redmi-wmi: Add more hotkey mappings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds more Fn hotkeys (like Refresh rate toggle).
Additionally, remap the setup key from KEY_SETUP to KEY_CONFIG.
As KEY_CONFIG is supported by Desktop Environments for launching
system settings, whereas KEY_SETUP is often ignored by userspace.

Signed-off-by: Jesse Guo <JesseGuoTech@outlook.com>
Reviewed-by: Gladyshev Ilya <foxido@foxido.dev>
Link: https://patch.msgid.link/TYCPR01MB6851636256C39B170F2312E5D192A@TYCPR01MB6851.jpnprd01.prod.outlook.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/redmi-wmi.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/redmi-wmi.c b/drivers/platform/x86/redmi-wmi.c
index 949236b93a32..e5cb348e3a39 100644
--- a/drivers/platform/x86/redmi-wmi.c
+++ b/drivers/platform/x86/redmi-wmi.c
@@ -20,7 +20,10 @@
 static const struct key_entry redmi_wmi_keymap[] = {
 	{KE_KEY, 0x00000201,	{KEY_SELECTIVE_SCREENSHOT}},
 	{KE_KEY, 0x00000301,	{KEY_ALL_APPLICATIONS}},
-	{KE_KEY, 0x00001b01,	{KEY_SETUP}},
+	{KE_KEY, 0x00001b01,	{KEY_CONFIG}},
+	{KE_KEY, 0x00011b01,	{KEY_CONFIG}},
+	{KE_KEY, 0x00010101,	{KEY_SWITCHVIDEOMODE}},
+	{KE_KEY, 0x00001a01,	{KEY_REFRESH_RATE_TOGGLE}},
 
 	/* AI button has code for each position */
 	{KE_KEY, 0x00011801,	{KEY_ASSISTANT}},
@@ -32,6 +35,26 @@ static const struct key_entry redmi_wmi_keymap[] = {
 	{KE_IGNORE, 0x00050501, {}},
 	{KE_IGNORE, 0x000a0501, {}},
 
+	/* Xiaomi G Command Center */
+	{KE_KEY, 0x00010a01,	{KEY_VENDOR}},
+
+	/* OEM preset power mode */
+	{KE_IGNORE, 0x00011601, {}},
+	{KE_IGNORE, 0x00021601, {}},
+	{KE_IGNORE, 0x00031601, {}},
+	{KE_IGNORE, 0x00041601, {}},
+
+	/* Fn Lock state */
+	{KE_IGNORE, 0x00000701, {}},
+	{KE_IGNORE, 0x00010701, {}},
+
+	/* Fn+`/1/2/3/4 */
+	{KE_KEY, 0x00011101, {KEY_F13}},
+	{KE_KEY, 0x00011201, {KEY_F14}},
+	{KE_KEY, 0x00011301, {KEY_F15}},
+	{KE_KEY, 0x00011401, {KEY_F16}},
+	{KE_KEY, 0x00011501, {KEY_F17}},
+
 	{KE_END}
 };
 

From 318c58852e686c009825ae8c071080b9ccdd2af0 Mon Sep 17 00:00:00 2001
From: Gregory Price <gourry@gourry.net>
Date: Wed, 11 Feb 2026 14:22:27 -0500
Subject: [PATCH 0193/1303] cxl/memdev: fix deadlock in cxl_memdev_autoremove()
 on attach failure

cxl_memdev_autoremove() takes device_lock(&cxlmd->dev) via guard(device)
and then calls cxl_memdev_unregister() when the attach callback was
provided but cxl_mem_probe() failed to bind.

cxl_memdev_unregister() calls
  cdev_device_del()
    device_del()
      bus_remove_device()
        device_release_driver()

This path is reached when a driver uses the @attach parameter to
devm_cxl_add_memdev() and the CXL topology fails to enumerate (e.g.
DVSEC range registers decode outside platform-defined CXL ranges,
causing the endpoint port probe to fail).

Add cxl_memdev_attach_failed() to set the scope of the check correctly.

Reported-by: kreview-c94b85d6d2
Fixes: 29317f8dc6ed ("cxl/mem: Introduce cxl_memdev_attach for CXL-dependent operation")
Signed-off-by: Gregory Price <gourry@gourry.net>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Link: https://patch.msgid.link/20260211192228.2148713-1-gourry@gourry.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/memdev.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index f547d8ac34c7..273c22118d3d 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -1089,10 +1089,8 @@ static int cxlmd_add(struct cxl_memdev *cxlmd, struct cxl_dev_state *cxlds)
 DEFINE_FREE(put_cxlmd, struct cxl_memdev *,
 	    if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
 
-static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
+static bool cxl_memdev_attach_failed(struct cxl_memdev *cxlmd)
 {
-	int rc;
-
 	/*
 	 * If @attach is provided fail if the driver is not attached upon
 	 * return. Note that failure here could be the result of a race to
@@ -1100,7 +1098,14 @@ static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
 	 * succeeded and then cxl_mem unbound before the lock is acquired.
 	 */
 	guard(device)(&cxlmd->dev);
-	if (cxlmd->attach && !cxlmd->dev.driver) {
+	return (cxlmd->attach && !cxlmd->dev.driver);
+}
+
+static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
+{
+	int rc;
+
+	if (cxl_memdev_attach_failed(cxlmd)) {
 		cxl_memdev_unregister(cxlmd);
 		return ERR_PTR(-ENXIO);
 	}

From 2d53dfacf067968a9ff90c03700fb9b28049f4c6 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:50:58 +0100
Subject: [PATCH 0194/1303] platform/x86: uniwill-laptop: Rename FN lock and
 super key lock attrs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that both sysfs attributes actually directly control
the FN lock status/super key enable status, rather than the
triggering of the associated events. This behavior was first observed
on a Tuxedo notebook and was belived to be a hardware quirk.
However, it seems that i simply misunderstood the manual of the
OEM software for Intel NUC devices. The correct behavior is:

- fn_lock_toggle_enable enables/disables FN lock mode
- super_key_toggle_enable enables/disables the super key

Rename both sysfs attributes to avoid confusing users.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-2-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../ABI/testing/sysfs-driver-uniwill-laptop   | 10 ++--
 .../admin-guide/laptops/uniwill-laptop.rst    |  2 +-
 drivers/platform/x86/uniwill/uniwill-acpi.c   | 58 ++++++++++---------
 drivers/platform/x86/uniwill/uniwill-wmi.h    |  6 +-
 4 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
index eaeb659793d2..2df70792968f 100644
--- a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
+++ b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
@@ -1,4 +1,4 @@
-What:		/sys/bus/platform/devices/INOU0000:XX/fn_lock_toggle_enable
+What:		/sys/bus/platform/devices/INOU0000:XX/fn_lock
 Date:		November 2025
 KernelVersion:	6.19
 Contact:	Armin Wolf <W_Armin@gmx.de>
@@ -8,15 +8,15 @@ Description:
 
 		Reading this file returns the current enable status of the FN lock functionality.
 
-What:		/sys/bus/platform/devices/INOU0000:XX/super_key_toggle_enable
+What:		/sys/bus/platform/devices/INOU0000:XX/super_key_enable
 Date:		November 2025
 KernelVersion:	6.19
 Contact:	Armin Wolf <W_Armin@gmx.de>
 Description:
-                Allows userspace applications to enable/disable the super key functionality
-                of the integrated keyboard by writing "1"/"0" into this file.
+		Allows userspace applications to enable/disable the super key of the integrated
+		keyboard by writing "1"/"0" into this file.
 
-		Reading this file returns the current enable status of the super key functionality.
+		Reading this file returns the current enable status of the super key.
 
 What:		/sys/bus/platform/devices/INOU0000:XX/touchpad_toggle_enable
 Date:		November 2025
diff --git a/Documentation/admin-guide/laptops/uniwill-laptop.rst b/Documentation/admin-guide/laptops/uniwill-laptop.rst
index a16baf15516b..aff5f57a6bd4 100644
--- a/Documentation/admin-guide/laptops/uniwill-laptop.rst
+++ b/Documentation/admin-guide/laptops/uniwill-laptop.rst
@@ -24,7 +24,7 @@ Keyboard settings
 
 The ``uniwill-laptop`` driver allows the user to enable/disable:
 
- - the FN and super key lock functionality of the integrated keyboard
+ - the FN lock and super key of the integrated keyboard
  - the touchpad toggle functionality of the integrated touchpad
 
 See Documentation/ABI/testing/sysfs-driver-uniwill-laptop for details.
diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index fee93537aa43..440724016885 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -314,8 +314,8 @@
 #define LED_CHANNELS		3
 #define LED_MAX_BRIGHTNESS	200
 
-#define UNIWILL_FEATURE_FN_LOCK_TOGGLE		BIT(0)
-#define UNIWILL_FEATURE_SUPER_KEY_TOGGLE	BIT(1)
+#define UNIWILL_FEATURE_FN_LOCK			BIT(0)
+#define UNIWILL_FEATURE_SUPER_KEY		BIT(1)
 #define UNIWILL_FEATURE_TOUCHPAD_TOGGLE		BIT(2)
 #define UNIWILL_FEATURE_LIGHTBAR		BIT(3)
 #define UNIWILL_FEATURE_BATTERY			BIT(4)
@@ -377,11 +377,15 @@ static const struct key_entry uniwill_keymap[] = {
 	{ KE_IGNORE,    UNIWILL_OSD_CAPSLOCK,                   { KEY_CAPSLOCK }},
 	{ KE_IGNORE,    UNIWILL_OSD_NUMLOCK,                    { KEY_NUMLOCK }},
 
-	/* Reported when the user locks/unlocks the super key */
-	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE,      { KEY_UNKNOWN }},
-	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE,     { KEY_UNKNOWN }},
+	/*
+	 * Reported when the user enables/disables the super key.
+	 * Those events might even be reported when the change was done
+	 * using the sysfs attribute!
+	 */
+	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_DISABLE,		{ KEY_UNKNOWN }},
+	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_ENABLE,		{ KEY_UNKNOWN }},
 	/* Optional, might not be reported by all devices */
-	{ KE_IGNORE,	UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED,	{ KEY_UNKNOWN }},
+	{ KE_IGNORE,	UNIWILL_OSD_SUPER_KEY_STATE_CHANGED,	{ KEY_UNKNOWN }},
 
 	/* Reported in manual mode when toggling the airplane mode status */
 	{ KE_KEY,       UNIWILL_OSD_RFKILL,                     { KEY_RFKILL }},
@@ -600,8 +604,8 @@ static const struct regmap_config uniwill_ec_config = {
 	.use_single_write = true,
 };
 
-static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_attribute *attr,
-					   const char *buf, size_t count)
+static ssize_t fn_lock_store(struct device *dev, struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -624,8 +628,7 @@ static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_att
 	return count;
 }
 
-static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attribute *attr,
-					  char *buf)
+static ssize_t fn_lock_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -638,10 +641,10 @@ static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attr
 	return sysfs_emit(buf, "%d\n", !!(value & FN_LOCK_STATUS));
 }
 
-static DEVICE_ATTR_RW(fn_lock_toggle_enable);
+static DEVICE_ATTR_RW(fn_lock);
 
-static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_attribute *attr,
-					     const char *buf, size_t count)
+static ssize_t super_key_enable_store(struct device *dev, struct device_attribute *attr,
+				      const char *buf, size_t count)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -673,8 +676,7 @@ static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_a
 	return count;
 }
 
-static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_attribute *attr,
-					    char *buf)
+static ssize_t super_key_enable_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -687,7 +689,7 @@ static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_at
 	return sysfs_emit(buf, "%d\n", !(value & SUPER_KEY_LOCK_STATUS));
 }
 
-static DEVICE_ATTR_RW(super_key_toggle_enable);
+static DEVICE_ATTR_RW(super_key_enable);
 
 static ssize_t touchpad_toggle_enable_store(struct device *dev, struct device_attribute *attr,
 					    const char *buf, size_t count)
@@ -881,8 +883,8 @@ static int uniwill_nvidia_ctgp_init(struct uniwill_data *data)
 
 static struct attribute *uniwill_attrs[] = {
 	/* Keyboard-related */
-	&dev_attr_fn_lock_toggle_enable.attr,
-	&dev_attr_super_key_toggle_enable.attr,
+	&dev_attr_fn_lock.attr,
+	&dev_attr_super_key_enable.attr,
 	&dev_attr_touchpad_toggle_enable.attr,
 	/* Lightbar-related */
 	&dev_attr_rainbow_animation.attr,
@@ -897,13 +899,13 @@ static umode_t uniwill_attr_is_visible(struct kobject *kobj, struct attribute *a
 	struct device *dev = kobj_to_dev(kobj);
 	struct uniwill_data *data = dev_get_drvdata(dev);
 
-	if (attr == &dev_attr_fn_lock_toggle_enable.attr) {
-		if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK_TOGGLE))
+	if (attr == &dev_attr_fn_lock.attr) {
+		if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
 			return attr->mode;
 	}
 
-	if (attr == &dev_attr_super_key_toggle_enable.attr) {
-		if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (attr == &dev_attr_super_key_enable.attr) {
+		if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 			return attr->mode;
 	}
 
@@ -1505,7 +1507,7 @@ static void uniwill_shutdown(struct platform_device *pdev)
 
 static int uniwill_suspend_keyboard(struct uniwill_data *data)
 {
-	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
 
 	/*
@@ -1565,7 +1567,7 @@ static int uniwill_resume_keyboard(struct uniwill_data *data)
 	unsigned int value;
 	int ret;
 
-	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
 
 	ret = regmap_read(data->regmap, EC_ADDR_SWITCH_STATUS, &value);
@@ -1643,16 +1645,16 @@ static struct platform_driver uniwill_driver = {
 };
 
 static struct uniwill_device_descriptor lapac71h_descriptor __initdata = {
-	.features = UNIWILL_FEATURE_FN_LOCK_TOGGLE |
-		    UNIWILL_FEATURE_SUPER_KEY_TOGGLE |
+	.features = UNIWILL_FEATURE_FN_LOCK |
+		    UNIWILL_FEATURE_SUPER_KEY |
 		    UNIWILL_FEATURE_TOUCHPAD_TOGGLE |
 		    UNIWILL_FEATURE_BATTERY |
 		    UNIWILL_FEATURE_HWMON,
 };
 
 static struct uniwill_device_descriptor lapkc71f_descriptor __initdata = {
-	.features = UNIWILL_FEATURE_FN_LOCK_TOGGLE |
-		    UNIWILL_FEATURE_SUPER_KEY_TOGGLE |
+	.features = UNIWILL_FEATURE_FN_LOCK |
+		    UNIWILL_FEATURE_SUPER_KEY |
 		    UNIWILL_FEATURE_TOUCHPAD_TOGGLE |
 		    UNIWILL_FEATURE_LIGHTBAR |
 		    UNIWILL_FEATURE_BATTERY |
diff --git a/drivers/platform/x86/uniwill/uniwill-wmi.h b/drivers/platform/x86/uniwill/uniwill-wmi.h
index 48783b2e9ffb..fb1910c0f741 100644
--- a/drivers/platform/x86/uniwill/uniwill-wmi.h
+++ b/drivers/platform/x86/uniwill/uniwill-wmi.h
@@ -64,8 +64,8 @@
 #define UNIWILL_OSD_KB_LED_LEVEL3		0x3E
 #define UNIWILL_OSD_KB_LED_LEVEL4		0x3F
 
-#define UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE	0x40
-#define UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE	0x41
+#define UNIWILL_OSD_SUPER_KEY_DISABLE		0x40
+#define UNIWILL_OSD_SUPER_KEY_ENABLE		0x41
 
 #define UNIWILL_OSD_MENU_JP			0x42
 
@@ -74,7 +74,7 @@
 
 #define UNIWILL_OSD_RFKILL			0xA4
 
-#define UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED	0xA5
+#define UNIWILL_OSD_SUPER_KEY_STATE_CHANGED	0xA5
 
 #define UNIWILL_OSD_LIGHTBAR_STATE_CHANGED	0xA6
 

From 67e7eb4c130a74c5da9ab43316e00ed3186d1811 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:50:59 +0100
Subject: [PATCH 0195/1303] platform/x86: uniwill-laptop: Fix crash on
 unexpected battery event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On devices that have not UNIWILL_FEATURE_BATTERY set, the underlying
hardware might still send the UNIWILL_OSD_BATTERY_ALERT event. In such
a situation, the driver will access uninitialized data structures when
handling said event.

Prevent this by only handling the UNIWILL_OSD_BATTERY_ALERT event when
UNIWILL_FEATURE_BATTERY is set.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-3-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index 440724016885..e0f3740a6d3a 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -1359,6 +1359,9 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action
 
 	switch (action) {
 	case UNIWILL_OSD_BATTERY_ALERT:
+		if (!uniwill_device_supports(data, UNIWILL_FEATURE_BATTERY))
+			return NOTIFY_DONE;
+
 		mutex_lock(&data->battery_lock);
 		list_for_each_entry(entry, &data->batteries, head) {
 			power_supply_changed(entry->battery);

From 2be519d94544e226636c185e28ec1a72d01aab87 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:51:00 +0100
Subject: [PATCH 0196/1303] platform/x86: uniwill-laptop: Mark FN lock status
 as being volatile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that the FN lock status can be changed by the underlying
hardware when the user presses a special key combination. Mark the
associated register as volatile to prevent regmap from caching said
value. Also add the necessary suspend/resume handling.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-4-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 39 ++++++++++++++++++---
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index e0f3740a6d3a..73b3d909e2b0 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -330,6 +330,7 @@ struct uniwill_data {
 	struct acpi_battery_hook hook;
 	unsigned int last_charge_ctrl;
 	struct mutex battery_lock;	/* Protects the list of currently registered batteries */
+	unsigned int last_status;
 	unsigned int last_switch_status;
 	struct mutex super_key_lock;	/* Protects the toggling of the super key lock state */
 	struct list_head batteries;
@@ -580,6 +581,7 @@ static bool uniwill_volatile_reg(struct device *dev, unsigned int reg)
 	case EC_ADDR_SECOND_FAN_RPM_1:
 	case EC_ADDR_SECOND_FAN_RPM_2:
 	case EC_ADDR_BAT_ALERT:
+	case EC_ADDR_BIOS_OEM:
 	case EC_ADDR_PWM_1:
 	case EC_ADDR_PWM_2:
 	case EC_ADDR_TRIGGER:
@@ -1508,7 +1510,19 @@ static void uniwill_shutdown(struct platform_device *pdev)
 	regmap_clear_bits(data->regmap, EC_ADDR_AP_OEM, ENABLE_MANUAL_CTRL);
 }
 
-static int uniwill_suspend_keyboard(struct uniwill_data *data)
+static int uniwill_suspend_fn_lock(struct uniwill_data *data)
+{
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+		return 0;
+
+	/*
+	 * The EC_ADDR_BIOS_OEM is marked as volatile, so we have to restore it
+	 * ourselves.
+	 */
+	return regmap_read(data->regmap, EC_ADDR_BIOS_OEM, &data->last_status);
+}
+
+static int uniwill_suspend_super_key(struct uniwill_data *data)
 {
 	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
@@ -1547,7 +1561,11 @@ static int uniwill_suspend(struct device *dev)
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	ret = uniwill_suspend_keyboard(data);
+	ret = uniwill_suspend_fn_lock(data);
+	if (ret < 0)
+		return ret;
+
+	ret = uniwill_suspend_super_key(data);
 	if (ret < 0)
 		return ret;
 
@@ -1565,7 +1583,16 @@ static int uniwill_suspend(struct device *dev)
 	return 0;
 }
 
-static int uniwill_resume_keyboard(struct uniwill_data *data)
+static int uniwill_resume_fn_lock(struct uniwill_data *data)
+{
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+		return 0;
+
+	return regmap_update_bits(data->regmap, EC_ADDR_BIOS_OEM, FN_LOCK_STATUS,
+				  data->last_status);
+}
+
+static int uniwill_resume_super_key(struct uniwill_data *data)
 {
 	unsigned int value;
 	int ret;
@@ -1613,7 +1640,11 @@ static int uniwill_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	ret = uniwill_resume_keyboard(data);
+	ret = uniwill_resume_fn_lock(data);
+	if (ret < 0)
+		return ret;
+
+	ret = uniwill_resume_super_key(data);
 	if (ret < 0)
 		return ret;
 

From 9836feedcf559449e82eb0f741084086780104e5 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:51:01 +0100
Subject: [PATCH 0197/1303] platform/x86: uniwill-laptop: Handle FN lock event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On many devices, the user can toggle the Fn lock state by
pressing Fn + Esc. Forward the associated event to the fn_lock
sysfs attribute as a poll notification.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-5-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index 73b3d909e2b0..6341dca20b76 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -406,9 +406,6 @@ static const struct key_entry uniwill_keymap[] = {
 	/* Reported when the user wants to toggle the mute status */
 	{ KE_IGNORE,    UNIWILL_OSD_MUTE,                       { KEY_MUTE }},
 
-	/* Reported when the user locks/unlocks the Fn key */
-	{ KE_IGNORE,    UNIWILL_OSD_FN_LOCK,                    { KEY_FN_ESC }},
-
 	/* Reported when the user wants to toggle the brightness of the keyboard */
 	{ KE_KEY,       UNIWILL_OSD_KBDILLUMTOGGLE,             { KEY_KBDILLUMTOGGLE }},
 	{ KE_KEY,       UNIWILL_OSD_KB_LED_LEVEL0,              { KEY_KBDILLUMTOGGLE }},
@@ -1376,6 +1373,13 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action
 		 * gets implemented.
 		 */
 
+		return NOTIFY_OK;
+	case UNIWILL_OSD_FN_LOCK:
+		if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+			return NOTIFY_DONE;
+
+		sysfs_notify(&data->dev->kobj, NULL, "fn_lock");
+
 		return NOTIFY_OK;
 	default:
 		mutex_lock(&data->input_lock);

From ec197dca8735f7627e5cff7e3fa8839b53a28514 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Sun, 22 Feb 2026 08:33:52 +0000
Subject: [PATCH 0198/1303] KVM: arm64: Revert accidental drop of
 kvm_uninit_stage2_mmu() for non-NV VMs

Commit 0c4762e26879 ("KVM: arm64: nv: Avoid NV stage-2 code when NV is
not supported") added an early return to several functions in
arch/arm64/kvm/nested.c to prevent a UBSAN shift-out-of-bounds error
when accessing the pgt union for non-nested VMs.

However, this early return was inadvertently applied to
kvm_arch_flush_shadow_all() as well, causing it to skip the call to
kvm_uninit_stage2_mmu(kvm) for all non-nested VMs.

For pKVM, skipping this teardown means the host never unshares the
guest's memory with the EL2 hypervisor. When the host kernel later
recycles these leaked pages for a new VM, it attempts to re-share them.
The hypervisor correctly rejects this with -EPERM, triggering a host
WARN_ON and hanging the guest.

Fix this by dropping the early return from kvm_arch_flush_shadow_all().
The for-loop guarding the nested MMU cleanup already bounds itself when
nested_mmus_size == 0, allowing execution to proceed to
kvm_uninit_stage2_mmu() as intended.

Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/60916cb6-f460-4751-b910-f63c58700ad0@sirena.org.uk/
Fixes: 0c4762e26879 ("KVM: arm64: nv: Avoid NV stage-2 code when NV is not supported")
Signed-off-by: Fuad Tabba <tabba@google.com>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260222083352.89503-1-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index eeea5e692370..7f1ea85dc67a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1154,9 +1154,6 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	int i;
 
-	if (!kvm->arch.nested_mmus_size)
-		return;
-
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 

From 822655e6751dde2df7ddaa828c5aba217726c5a2 Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Mon, 23 Feb 2026 09:29:00 -0700
Subject: [PATCH 0199/1303] cxl/port: Introduce port_to_host() helper

In CXL subsystem, a port has its own host device for the port creation
and removal. The host of CXL root and all the first level ports is the
platform firmware device, the host of other ports is their parent port's
device. Create this new helper to much easier to get the host of a cxl
port.

Introduce port_to_host() and use it to replace all places where using
open coded to get the host of a port.

Remove endpoint_host() as its functionality can be replaced by
port_to_host().

[dj: Squashed commit 1 and 3 in the series to commit 1. ]

Signed-off-by: Li Ming <ming.li@zohomail.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260210-fix-port-enumeration-failure-v3-1-06acce0b9ead@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/core.h | 18 ++++++++++++++++++
 drivers/cxl/core/port.c | 29 +++--------------------------
 2 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 007b8aff0238..5b0570df0fd9 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -152,6 +152,24 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 					struct access_coordinate *c);
 
+static inline struct device *port_to_host(struct cxl_port *port)
+{
+	struct cxl_port *parent = is_cxl_root(port) ? NULL :
+				  to_cxl_port(port->dev.parent);
+
+	/*
+	 * The host of CXL root port and the first level of ports is
+	 * the platform firmware device, the host of all other ports
+	 * is their parent port.
+	 */
+	if (!parent)
+		return port->uport_dev;
+	else if (is_cxl_root(parent))
+		return parent->uport_dev;
+	else
+		return &parent->dev;
+}
+
 static inline struct device *dport_to_host(struct cxl_dport *dport)
 {
 	struct cxl_port *port = dport->port;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b69c2529744c..6be150e645b6 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -615,22 +615,8 @@ struct cxl_port *parent_port_of(struct cxl_port *port)
 static void unregister_port(void *_port)
 {
 	struct cxl_port *port = _port;
-	struct cxl_port *parent = parent_port_of(port);
-	struct device *lock_dev;
 
-	/*
-	 * CXL root port's and the first level of ports are unregistered
-	 * under the platform firmware device lock, all other ports are
-	 * unregistered while holding their parent port lock.
-	 */
-	if (!parent)
-		lock_dev = port->uport_dev;
-	else if (is_cxl_root(parent))
-		lock_dev = parent->uport_dev;
-	else
-		lock_dev = &parent->dev;
-
-	device_lock_assert(lock_dev);
+	device_lock_assert(port_to_host(port));
 	port->dead = true;
 	device_unregister(&port->dev);
 }
@@ -1427,20 +1413,11 @@ static struct device *grandparent(struct device *dev)
 	return NULL;
 }
 
-static struct device *endpoint_host(struct cxl_port *endpoint)
-{
-	struct cxl_port *port = to_cxl_port(endpoint->dev.parent);
-
-	if (is_cxl_root(port))
-		return port->uport_dev;
-	return &port->dev;
-}
-
 static void delete_endpoint(void *data)
 {
 	struct cxl_memdev *cxlmd = data;
 	struct cxl_port *endpoint = cxlmd->endpoint;
-	struct device *host = endpoint_host(endpoint);
+	struct device *host = port_to_host(endpoint);
 
 	scoped_guard(device, host) {
 		if (host->driver && !endpoint->dead) {
@@ -1456,7 +1433,7 @@ static void delete_endpoint(void *data)
 
 int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
 {
-	struct device *host = endpoint_host(endpoint);
+	struct device *host = port_to_host(endpoint);
 	struct device *dev = &cxlmd->dev;
 
 	get_device(host);

From 0066688dbcdcf51680f499936faffe6d0e94194e Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Tue, 10 Feb 2026 19:46:57 +0800
Subject: [PATCH 0200/1303] cxl/port: Hold port host lock during dport adding.

CXL testing environment can trigger following trace
 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000092: 0000 [#1] SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000490-0x0000000000000497]
 RIP: 0010:cxl_dpa_to_region+0x105/0x1f0 [cxl_core]
 Call Trace:
  <TASK>
  cxl_event_trace_record+0xd1/0xa70 [cxl_core]
  __cxl_event_trace_record+0x12f/0x1e0 [cxl_core]
  cxl_mem_get_records_log+0x261/0x500 [cxl_core]
  cxl_mem_get_event_records+0x7c/0xc0 [cxl_core]
  cxl_mock_mem_probe+0xd38/0x1c60 [cxl_mock_mem]
  platform_probe+0x9d/0x130
  really_probe+0x1c8/0x960
  __driver_probe_device+0x187/0x3e0
  driver_probe_device+0x45/0x120
  __device_attach_driver+0x15d/0x280

When CXL subsystem adds a cxl port to a hierarchy, there is a small
window where the new port becomes visible before it is bound to a
driver. This happens because device_add() adds a device to bus device
list before bus_probe_device() binds it to a driver.
So if two cxl memdevs are trying to add a dport to a same port via
devm_cxl_enumerate_ports(), the second cxl memdev may observe the port
and attempt to add a dport, but fails because the port has not yet been
attached to cxl port driver. That causes the memdev->endpoint can not be
updated.

The sequence is like:

CPU 0					CPU 1
devm_cxl_enumerate_ports()
  # port not found, add it
  add_port_attach_ep()
    # hold the parent port lock
    # to add the new port
    devm_cxl_create_port()
      device_add()
	# Add dev to bus devs list
	bus_add_device()
					devm_cxl_enumerate_ports()
					  # found the port
					  find_cxl_port_by_uport()
					  # hold port lock to add a dport
					  device_lock(the port)
					  find_or_add_dport()
					    cxl_port_add_dport()
					      return -ENXIO because port->dev.driver is NULL
					  device_unlock(the port)
	bus_probe_device()
	  # hold the port lock
	  # for attaching
	  device_lock(the port)
	    attaching the new port
	  device_unlock(the port)

To fix this race, require that dport addition holds the host lock
of the target port(the host of CXL root and all cxl host bridge ports is
the platform firmware device, the host of all other ports is their
parent port). The CXL subsystem already requires holding the host lock
while attaching a new port. Therefore, successfully acquiring the host
lock guarantees that port attaching has completed.

Fixes: 4f06d81e7c6a ("cxl: Defer dport allocation for switch ports")
Signed-off-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Link: https://patch.msgid.link/20260210-fix-port-enumeration-failure-v3-2-06acce0b9ead@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/port.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 6be150e645b6..0c5957d1d329 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1767,7 +1767,16 @@ static struct cxl_dport *find_or_add_dport(struct cxl_port *port,
 {
 	struct cxl_dport *dport;
 
-	device_lock_assert(&port->dev);
+	/*
+	 * The port is already visible in CXL hierarchy, but it may still
+	 * be in the process of binding to the CXL port driver at this point.
+	 *
+	 * port creation and driver binding are protected by the port's host
+	 * lock, so acquire the host lock here to ensure the port has completed
+	 * driver binding before proceeding with dport addition.
+	 */
+	guard(device)(port_to_host(port));
+	guard(device)(&port->dev);
 	dport = cxl_find_dport_by_dev(port, dport_dev);
 	if (!dport) {
 		dport = probe_dport(port, dport_dev);
@@ -1834,13 +1843,11 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
 			 * RP port enumerated by cxl_acpi without dport will
 			 * have the dport added here.
 			 */
-			scoped_guard(device, &port->dev) {
-				dport = find_or_add_dport(port, dport_dev);
-				if (IS_ERR(dport)) {
-					if (PTR_ERR(dport) == -EAGAIN)
-						goto retry;
-					return PTR_ERR(dport);
-				}
+			dport = find_or_add_dport(port, dport_dev);
+			if (IS_ERR(dport)) {
+				if (PTR_ERR(dport) == -EAGAIN)
+					goto retry;
+				return PTR_ERR(dport);
 			}
 
 			rc = cxl_add_ep(dport, &cxlmd->dev);

From 410666a298c34ebd57256fde6b24c96bd23059a2 Mon Sep 17 00:00:00 2001
From: Roberto Bergantinos Corpas <rbergant@redhat.com>
Date: Thu, 19 Feb 2026 13:04:40 +0100
Subject: [PATCH 0201/1303] nfs: return EISDIR on nfs3_proc_create if d_alias
 is a dir

If we found an alias through nfs3_do_create/nfs_add_or_obtain
/d_splice_alias which happens to be a dir dentry, we don't return
any error, and simply forget about this alias, but the original
dentry we were adding and passed as parameter remains negative.

This later causes an oops on nfs_atomic_open_v23/finish_open since we
supply a negative dentry to do_dentry_open.

This has been observed running lustre-racer, where dirs and files are
created/removed concurrently with the same name and O_EXCL is not
used to open files (frequent file redirection).

While d_splice_alias typically returns a directory alias or NULL, we
explicitly check d_is_dir() to ensure that we don't attempt to perform
file operations (like finish_open) on a directory inode, which triggers
the observed oops.

Fixes: 7c6c5249f061 ("NFS: add atomic_open for NFSv3 to handle O_TRUNC correctly.")
Reviewed-by: Olga Kornievskaia <okorniev@redhat.com>
Reviewed-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: Roberto Bergantinos Corpas <rbergant@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/nfs3proc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 3e2de45c95fe..be2aebf62056 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -392,8 +392,13 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	if (status != 0)
 		goto out_release_acls;
 
-	if (d_alias)
+	if (d_alias) {
+		if (d_is_dir(d_alias)) {
+			status = -EISDIR;
+			goto out_dput;
+		}
 		dentry = d_alias;
+	}
 
 	/* When we created the file with exclusive semantics, make
 	 * sure we set the attributes afterwards. */

From 9d851afa482680bdd7c158cc8720284dc9ecb5fe Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sat, 21 Feb 2026 23:40:42 +0800
Subject: [PATCH 0202/1303] selftests/sched_ext: Abort test loop on signal

The runner sets exit_req on SIGINT/SIGTERM but ignores it during the
main loop. This prevents users from cleanly interrupting a test run.

Check exit_req each iteration to safely break out on exit signals.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/runner.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c
index 5748d2c69903..761c21f96404 100644
--- a/tools/testing/selftests/sched_ext/runner.c
+++ b/tools/testing/selftests/sched_ext/runner.c
@@ -166,6 +166,9 @@ int main(int argc, char **argv)
 		enum scx_test_status status;
 		struct scx_test *test = &__scx_tests[i];
 
+		if (exit_req)
+			break;
+
 		if (list) {
 			printf("%s\n", test->name);
 			if (i == (__scx_num_tests - 1))

From 08fe1b5166fdc81b010d7bf39cd6440620e7931e Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 5 Feb 2026 22:02:37 -0800
Subject: [PATCH 0203/1303] accel/amdxdna: Remove buffer size check when
 creating command BO

Large command buffers may be used, and they do not always need to be
mapped or accessed by the driver. Performing a size check at command BO
creation time unnecessarily rejects valid use cases.

Remove the buffer size check from command BO creation, and defer vmap
and size validation to the paths where the driver actually needs to map
and access the command buffer.

Fixes: ac49797c1815 ("accel/amdxdna: Add GEM buffer object management")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260206060237.4050492-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/amdxdna_gem.c | 38 ++++++++++++++---------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c
index 8c290ddd3251..d60db49ead71 100644
--- a/drivers/accel/amdxdna/amdxdna_gem.c
+++ b/drivers/accel/amdxdna/amdxdna_gem.c
@@ -21,8 +21,6 @@
 #include "amdxdna_pci_drv.h"
 #include "amdxdna_ubuf.h"
 
-#define XDNA_MAX_CMD_BO_SIZE	SZ_32K
-
 MODULE_IMPORT_NS("DMA_BUF");
 
 static int
@@ -745,12 +743,6 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev,
 {
 	struct amdxdna_dev *xdna = to_xdna_dev(dev);
 	struct amdxdna_gem_obj *abo;
-	int ret;
-
-	if (args->size > XDNA_MAX_CMD_BO_SIZE) {
-		XDNA_ERR(xdna, "Command bo size 0x%llx too large", args->size);
-		return ERR_PTR(-EINVAL);
-	}
 
 	if (args->size < sizeof(struct amdxdna_cmd)) {
 		XDNA_DBG(xdna, "Command BO size 0x%llx too small", args->size);
@@ -764,17 +756,7 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev,
 	abo->type = AMDXDNA_BO_CMD;
 	abo->client = filp->driver_priv;
 
-	ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva);
-	if (ret) {
-		XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret);
-		goto release_obj;
-	}
-
 	return abo;
-
-release_obj:
-	drm_gem_object_put(to_gobj(abo));
-	return ERR_PTR(ret);
 }
 
 int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
@@ -871,6 +853,7 @@ struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client,
 	struct amdxdna_dev *xdna = client->xdna;
 	struct amdxdna_gem_obj *abo;
 	struct drm_gem_object *gobj;
+	int ret;
 
 	gobj = drm_gem_object_lookup(client->filp, bo_hdl);
 	if (!gobj) {
@@ -879,9 +862,26 @@ struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client,
 	}
 
 	abo = to_xdna_obj(gobj);
-	if (bo_type == AMDXDNA_BO_INVALID || abo->type == bo_type)
+	if (bo_type != AMDXDNA_BO_INVALID && abo->type != bo_type)
+		goto put_obj;
+
+	if (bo_type != AMDXDNA_BO_CMD || abo->mem.kva)
 		return abo;
 
+	if (abo->mem.size > SZ_32K) {
+		XDNA_ERR(xdna, "Cmd bo is too big %ld", abo->mem.size);
+		goto put_obj;
+	}
+
+	ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva);
+	if (ret) {
+		XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret);
+		goto put_obj;
+	}
+
+	return abo;
+
+put_obj:
 	drm_gem_object_put(gobj);
 	return NULL;
 }

From c68a6af400ca80596e8c37de0a1cb564aa9da8a4 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 5 Feb 2026 22:02:51 -0800
Subject: [PATCH 0204/1303] accel/amdxdna: Switch to always use chained command

Preempt commands are only supported when submitted as chained commands.
To ensure preempt support works consistently, always submit commands in
chained command format.

Set force_cmdlist to true so that single commands are filled using the
chained command layout, enabling correct handling of preempt commands.

Fixes: 3a0ff7b98af4 ("accel/amdxdna: Support preemption requests")
Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260206060251.4050512-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 4503c7c77a3e..7140c3f96362 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -23,9 +23,9 @@
 #include "amdxdna_pci_drv.h"
 #include "amdxdna_pm.h"
 
-static bool force_cmdlist;
+static bool force_cmdlist = true;
 module_param(force_cmdlist, bool, 0600);
-MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)");
+MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default true)");
 
 #define HWCTX_MAX_TIMEOUT	60000 /* milliseconds */
 

From 8363c02863332992a1822688da41f881d88d1631 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 5 Feb 2026 22:03:06 -0800
Subject: [PATCH 0205/1303] accel/amdxdna: Fix crash when destroying a
 suspended hardware context

If userspace issues an ioctl to destroy a hardware context that has
already been automatically suspended, the driver may crash because the
mailbox channel pointer is NULL for the suspended context.

Fix this by checking the mailbox channel pointer in aie2_destroy_context()
before accessing it.

Fixes: 97f27573837e ("accel/amdxdna: Fix potential NULL pointer dereference in context cleanup")
Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260206060306.4050531-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_message.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 7d7dcfeaf794..ab1178850c47 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -318,6 +318,9 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc
 	struct amdxdna_dev *xdna = ndev->xdna;
 	int ret;
 
+	if (!hwctx->priv->mbox_chann)
+		return 0;
+
 	xdna_mailbox_stop_channel(hwctx->priv->mbox_chann);
 	ret = aie2_destroy_context_req(ndev, hwctx->fw_ctx_id);
 	xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann);

From 57aa3917a3b3bd805a3679371f97a1ceda3c5510 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Feb 2026 10:42:51 -0600
Subject: [PATCH 0206/1303] accel/amdxdna: Reduce log noise during process
 termination

During process termination, several error messages are logged that are
not actual errors but expected conditions when a process is killed or
interrupted. This creates unnecessary noise in the kernel log.

The specific scenarios are:

1. HMM invalidation returns -ERESTARTSYS when the wait is interrupted by
   a signal during process cleanup. This is expected when a process is
   being terminated and should not be logged as an error.

2. Context destruction returns -ENODEV when the firmware or device has
   already stopped, which commonly occurs during cleanup if the device
   was already torn down. This is also an expected condition during
   orderly shutdown.

Downgrade these expected error conditions from error level to debug level
to reduce log noise while still keeping genuine errors visible.

Fixes: 97f27573837e ("accel/amdxdna: Fix potential NULL pointer dereference in context cleanup")
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260210164521.1094274-3-mario.limonciello@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c     | 6 ++++--
 drivers/accel/amdxdna/aie2_message.c | 4 +++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 7140c3f96362..e13be7608462 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -497,7 +497,7 @@ static void aie2_release_resource(struct amdxdna_hwctx *hwctx)
 
 	if (AIE2_FEATURE_ON(xdna->dev_handle, AIE2_TEMPORAL_ONLY)) {
 		ret = aie2_destroy_context(xdna->dev_handle, hwctx);
-		if (ret)
+		if (ret && ret != -ENODEV)
 			XDNA_ERR(xdna, "Destroy temporal only context failed, ret %d", ret);
 	} else {
 		ret = xrs_release_resource(xdna->xrs_hdl, (uintptr_t)hwctx);
@@ -1070,6 +1070,8 @@ void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo,
 
 	ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP,
 				    true, MAX_SCHEDULE_TIMEOUT);
-	if (!ret || ret == -ERESTARTSYS)
+	if (!ret)
 		XDNA_ERR(xdna, "Failed to wait for bo, ret %ld", ret);
+	else if (ret == -ERESTARTSYS)
+		XDNA_DBG(xdna, "Wait for bo interrupted by signal");
 }
diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index ab1178850c47..5d80c5837745 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -216,8 +216,10 @@ static int aie2_destroy_context_req(struct amdxdna_dev_hdl *ndev, u32 id)
 
 	req.context_id = id;
 	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
-	if (ret)
+	if (ret && ret != -ENODEV)
 		XDNA_WARN(xdna, "Destroy context failed, ret %d", ret);
+	else if (ret == -ENODEV)
+		XDNA_DBG(xdna, "Destroy context: device already stopped");
 
 	return ret;
 }

From 1aa82181a3c285c7351523d587f7981ae4c015c8 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 11 Feb 2026 12:46:44 -0800
Subject: [PATCH 0207/1303] accel/amdxdna: Fix dead lock for suspend and resume

When an application issues a query IOCTL while auto suspend is running,
a deadlock can occur. The query path holds dev_lock and then calls
pm_runtime_resume_and_get(), which waits for the ongoing suspend to
complete. Meanwhile, the suspend callback attempts to acquire dev_lock
and blocks, resulting in a deadlock.

Fix this by releasing dev_lock before calling pm_runtime_resume_and_get()
and reacquiring it after the call completes. Also acquire dev_lock in the
resume callback to keep the locking consistent.

Fixes: 063db451832b ("accel/amdxdna: Enhance runtime power management")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260211204644.722758-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c    |  4 ++--
 drivers/accel/amdxdna/aie2_pci.c    |  7 +++----
 drivers/accel/amdxdna/aie2_pm.c     |  2 +-
 drivers/accel/amdxdna/amdxdna_ctx.c | 19 +++++++------------
 drivers/accel/amdxdna/amdxdna_pm.c  |  2 ++
 drivers/accel/amdxdna/amdxdna_pm.h  | 11 +++++++++++
 6 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index e13be7608462..8d79fafd889a 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -629,7 +629,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx)
 		goto free_entity;
 	}
 
-	ret = amdxdna_pm_resume_get(xdna);
+	ret = amdxdna_pm_resume_get_locked(xdna);
 	if (ret)
 		goto free_col_list;
 
@@ -760,7 +760,7 @@ static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size
 	if (!hwctx->cus)
 		return -ENOMEM;
 
-	ret = amdxdna_pm_resume_get(xdna);
+	ret = amdxdna_pm_resume_get_locked(xdna);
 	if (ret)
 		goto free_cus;
 
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 2a51b2658bfc..07e369507818 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -451,7 +451,6 @@ static int aie2_hw_suspend(struct amdxdna_dev *xdna)
 {
 	struct amdxdna_client *client;
 
-	guard(mutex)(&xdna->dev_lock);
 	list_for_each_entry(client, &xdna->client_list, node)
 		aie2_hwctx_suspend(client);
 
@@ -951,7 +950,7 @@ static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_i
 	if (!drm_dev_enter(&xdna->ddev, &idx))
 		return -ENODEV;
 
-	ret = amdxdna_pm_resume_get(xdna);
+	ret = amdxdna_pm_resume_get_locked(xdna);
 	if (ret)
 		goto dev_exit;
 
@@ -1044,7 +1043,7 @@ static int aie2_get_array(struct amdxdna_client *client,
 	if (!drm_dev_enter(&xdna->ddev, &idx))
 		return -ENODEV;
 
-	ret = amdxdna_pm_resume_get(xdna);
+	ret = amdxdna_pm_resume_get_locked(xdna);
 	if (ret)
 		goto dev_exit;
 
@@ -1134,7 +1133,7 @@ static int aie2_set_state(struct amdxdna_client *client,
 	if (!drm_dev_enter(&xdna->ddev, &idx))
 		return -ENODEV;
 
-	ret = amdxdna_pm_resume_get(xdna);
+	ret = amdxdna_pm_resume_get_locked(xdna);
 	if (ret)
 		goto dev_exit;
 
diff --git a/drivers/accel/amdxdna/aie2_pm.c b/drivers/accel/amdxdna/aie2_pm.c
index 579b8be13b18..29bd4403a94d 100644
--- a/drivers/accel/amdxdna/aie2_pm.c
+++ b/drivers/accel/amdxdna/aie2_pm.c
@@ -31,7 +31,7 @@ int aie2_pm_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
 {
 	int ret;
 
-	ret = amdxdna_pm_resume_get(ndev->xdna);
+	ret = amdxdna_pm_resume_get_locked(ndev->xdna);
 	if (ret)
 		return ret;
 
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
index 59fa3800b9d3..5173456bbb61 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -266,9 +266,9 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
 	struct amdxdna_drm_config_hwctx *args = data;
 	struct amdxdna_dev *xdna = to_xdna_dev(dev);
 	struct amdxdna_hwctx *hwctx;
-	int ret, idx;
 	u32 buf_size;
 	void *buf;
+	int ret;
 	u64 val;
 
 	if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad)))
@@ -310,20 +310,17 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
 		return -EINVAL;
 	}
 
-	mutex_lock(&xdna->dev_lock);
-	idx = srcu_read_lock(&client->hwctx_srcu);
+	guard(mutex)(&xdna->dev_lock);
 	hwctx = xa_load(&client->hwctx_xa, args->handle);
 	if (!hwctx) {
 		XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle);
 		ret = -EINVAL;
-		goto unlock_srcu;
+		goto free_buf;
 	}
 
 	ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size);
 
-unlock_srcu:
-	srcu_read_unlock(&client->hwctx_srcu, idx);
-	mutex_unlock(&xdna->dev_lock);
+free_buf:
 	kfree(buf);
 	return ret;
 }
@@ -334,7 +331,7 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl)
 	struct amdxdna_hwctx *hwctx;
 	struct amdxdna_gem_obj *abo;
 	struct drm_gem_object *gobj;
-	int ret, idx;
+	int ret;
 
 	if (!xdna->dev_info->ops->hwctx_sync_debug_bo)
 		return -EOPNOTSUPP;
@@ -345,17 +342,15 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl)
 
 	abo = to_xdna_obj(gobj);
 	guard(mutex)(&xdna->dev_lock);
-	idx = srcu_read_lock(&client->hwctx_srcu);
 	hwctx = xa_load(&client->hwctx_xa, abo->assigned_hwctx);
 	if (!hwctx) {
 		ret = -EINVAL;
-		goto unlock_srcu;
+		goto put_obj;
 	}
 
 	ret = xdna->dev_info->ops->hwctx_sync_debug_bo(hwctx, debug_bo_hdl);
 
-unlock_srcu:
-	srcu_read_unlock(&client->hwctx_srcu, idx);
+put_obj:
 	drm_gem_object_put(gobj);
 	return ret;
 }
diff --git a/drivers/accel/amdxdna/amdxdna_pm.c b/drivers/accel/amdxdna/amdxdna_pm.c
index d024d480521c..b1fafddd7ad5 100644
--- a/drivers/accel/amdxdna/amdxdna_pm.c
+++ b/drivers/accel/amdxdna/amdxdna_pm.c
@@ -16,6 +16,7 @@ int amdxdna_pm_suspend(struct device *dev)
 	struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev));
 	int ret = -EOPNOTSUPP;
 
+	guard(mutex)(&xdna->dev_lock);
 	if (xdna->dev_info->ops->suspend)
 		ret = xdna->dev_info->ops->suspend(xdna);
 
@@ -28,6 +29,7 @@ int amdxdna_pm_resume(struct device *dev)
 	struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev));
 	int ret = -EOPNOTSUPP;
 
+	guard(mutex)(&xdna->dev_lock);
 	if (xdna->dev_info->ops->resume)
 		ret = xdna->dev_info->ops->resume(xdna);
 
diff --git a/drivers/accel/amdxdna/amdxdna_pm.h b/drivers/accel/amdxdna/amdxdna_pm.h
index 77b2d6e45570..3d26b973e0e3 100644
--- a/drivers/accel/amdxdna/amdxdna_pm.h
+++ b/drivers/accel/amdxdna/amdxdna_pm.h
@@ -15,4 +15,15 @@ void amdxdna_pm_suspend_put(struct amdxdna_dev *xdna);
 void amdxdna_pm_init(struct amdxdna_dev *xdna);
 void amdxdna_pm_fini(struct amdxdna_dev *xdna);
 
+static inline int amdxdna_pm_resume_get_locked(struct amdxdna_dev *xdna)
+{
+	int ret;
+
+	mutex_unlock(&xdna->dev_lock);
+	ret = amdxdna_pm_resume_get(xdna);
+	mutex_lock(&xdna->dev_lock);
+
+	return ret;
+}
+
 #endif /* _AMDXDNA_PM_H_ */

From fdb65acfe655f844ae1e88696b9656d3ef5bb8fb Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 11 Feb 2026 12:47:16 -0800
Subject: [PATCH 0208/1303] accel/amdxdna: Fix suspend failure after enabling
 turbo mode

Enabling turbo mode disables hardware clock gating. Suspend requires
hardware clock gating to be re-enabled, otherwise suspend will fail.
Fix this by calling aie2_runtime_cfg() from aie2_hw_stop() to
re-enable clock gating during suspend. Also ensure that firmware is
initialized in aie2_hw_start() before modifying clock-gating
settings during resume.

Fixes: f4d7b8a6bc8c ("accel/amdxdna: Enhance power management settings")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260211204716.722788-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_pci.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 07e369507818..4b3e6bb97bd2 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -323,6 +323,7 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna)
 		return;
 	}
 
+	aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, NULL);
 	aie2_mgmt_fw_fini(ndev);
 	xdna_mailbox_stop_channel(ndev->mgmt_chann);
 	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
@@ -406,18 +407,18 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 		goto stop_psp;
 	}
 
-	ret = aie2_pm_init(ndev);
-	if (ret) {
-		XDNA_ERR(xdna, "failed to init pm, ret %d", ret);
-		goto destroy_mgmt_chann;
-	}
-
 	ret = aie2_mgmt_fw_init(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret);
 		goto destroy_mgmt_chann;
 	}
 
+	ret = aie2_pm_init(ndev);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to init pm, ret %d", ret);
+		goto destroy_mgmt_chann;
+	}
+
 	ret = aie2_mgmt_fw_query(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "failed to query fw, ret %d", ret);

From 07efce5a6611af6714ea3ef65694e0c8dd7e44f5 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 11 Feb 2026 12:53:41 -0800
Subject: [PATCH 0209/1303] accel/amdxdna: Fix command hang on suspended
 hardware context

When a hardware context is suspended, the job scheduler is stopped. If a
command is submitted while the context is suspended, the job is queued in
the scheduler but aie2_sched_job_run() is never invoked to restart the
hardware context. As a result, the command hangs.

Fix this by modifying the hardware context suspend routine to keep the job
scheduler running so that queued jobs can trigger context restart properly.

Fixes: aac243092b70 ("accel/amdxdna: Add command execution")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260211205341.722982-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 8d79fafd889a..25845bd5e507 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -53,6 +53,7 @@ static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwct
 {
 	drm_sched_stop(&hwctx->priv->sched, bad_job);
 	aie2_destroy_context(xdna->dev_handle, hwctx);
+	drm_sched_start(&hwctx->priv->sched, 0);
 }
 
 static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx)
@@ -80,7 +81,6 @@ static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hw
 	}
 
 out:
-	drm_sched_start(&hwctx->priv->sched, 0);
 	XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret);
 	return ret;
 }
@@ -297,19 +297,23 @@ aie2_sched_job_run(struct drm_sched_job *sched_job)
 	struct dma_fence *fence;
 	int ret;
 
-	if (!hwctx->priv->mbox_chann)
+	ret = amdxdna_pm_resume_get(hwctx->client->xdna);
+	if (ret)
 		return NULL;
 
-	if (!mmget_not_zero(job->mm))
+	if (!hwctx->priv->mbox_chann) {
+		amdxdna_pm_suspend_put(hwctx->client->xdna);
+		return NULL;
+	}
+
+	if (!mmget_not_zero(job->mm)) {
+		amdxdna_pm_suspend_put(hwctx->client->xdna);
 		return ERR_PTR(-ESRCH);
+	}
 
 	kref_get(&job->refcnt);
 	fence = dma_fence_get(job->fence);
 
-	ret = amdxdna_pm_resume_get(hwctx->client->xdna);
-	if (ret)
-		goto out;
-
 	if (job->drv_cmd) {
 		switch (job->drv_cmd->opcode) {
 		case SYNC_DEBUG_BO:

From 1110a949675ebd56b3f0286e664ea543f745801c Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Tue, 17 Feb 2026 10:54:15 -0800
Subject: [PATCH 0210/1303] accel/amdxdna: Fix out-of-bounds memset in command
 slot handling

The remaining space in a command slot may be smaller than the size of
the command header. Clearing the command header with memset() before
verifying the available slot space can result in an out-of-bounds write
and memory corruption.

Fix this by moving the memset() call after the size validation.

Fixes: 3d32eb7a5ecf ("accel/amdxdna: Fix cu_idx being cleared by memset() during command setup")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260217185415.1781908-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_message.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 5d80c5837745..277a27bce850 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -699,11 +699,11 @@ aie2_cmdlist_fill_npu_cf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *siz
 	u32 cmd_len;
 	void *cmd;
 
-	memset(npu_slot, 0, sizeof(*npu_slot));
 	cmd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len);
 	if (*size < sizeof(*npu_slot) + cmd_len)
 		return -EINVAL;
 
+	memset(npu_slot, 0, sizeof(*npu_slot));
 	npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo);
 	if (npu_slot->cu_idx == INVALID_CU_IDX)
 		return -EINVAL;
@@ -724,7 +724,6 @@ aie2_cmdlist_fill_npu_dpu(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si
 	u32 cmd_len;
 	u32 arg_sz;
 
-	memset(npu_slot, 0, sizeof(*npu_slot));
 	sn = amdxdna_cmd_get_payload(cmd_bo, &cmd_len);
 	arg_sz = cmd_len - sizeof(*sn);
 	if (cmd_len < sizeof(*sn) || arg_sz > MAX_NPU_ARGS_SIZE)
@@ -733,6 +732,7 @@ aie2_cmdlist_fill_npu_dpu(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si
 	if (*size < sizeof(*npu_slot) + arg_sz)
 		return -EINVAL;
 
+	memset(npu_slot, 0, sizeof(*npu_slot));
 	npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo);
 	if (npu_slot->cu_idx == INVALID_CU_IDX)
 		return -EINVAL;
@@ -756,7 +756,6 @@ aie2_cmdlist_fill_npu_preempt(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t
 	u32 cmd_len;
 	u32 arg_sz;
 
-	memset(npu_slot, 0, sizeof(*npu_slot));
 	pd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len);
 	arg_sz = cmd_len - sizeof(*pd);
 	if (cmd_len < sizeof(*pd) || arg_sz > MAX_NPU_ARGS_SIZE)
@@ -765,6 +764,7 @@ aie2_cmdlist_fill_npu_preempt(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t
 	if (*size < sizeof(*npu_slot) + arg_sz)
 		return -EINVAL;
 
+	memset(npu_slot, 0, sizeof(*npu_slot));
 	npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo);
 	if (npu_slot->cu_idx == INVALID_CU_IDX)
 		return -EINVAL;
@@ -792,7 +792,6 @@ aie2_cmdlist_fill_npu_elf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si
 	u32 cmd_len;
 	u32 arg_sz;
 
-	memset(npu_slot, 0, sizeof(*npu_slot));
 	pd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len);
 	arg_sz = cmd_len - sizeof(*pd);
 	if (cmd_len < sizeof(*pd) || arg_sz > MAX_NPU_ARGS_SIZE)
@@ -801,6 +800,7 @@ aie2_cmdlist_fill_npu_elf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si
 	if (*size < sizeof(*npu_slot) + arg_sz)
 		return -EINVAL;
 
+	memset(npu_slot, 0, sizeof(*npu_slot));
 	npu_slot->type = EXEC_NPU_TYPE_ELF;
 	npu_slot->inst_buf_addr = pd->inst_buf;
 	npu_slot->save_buf_addr = pd->save_buf;

From 03808abb1d868aed7478a11a82e5bb4b3f1ca6d6 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Tue, 17 Feb 2026 11:28:15 -0800
Subject: [PATCH 0211/1303] accel/amdxdna: Prevent ubuf size overflow

The ubuf size calculation may overflow, resulting in an undersized
allocation and possible memory corruption.

Use check_add_overflow() helpers to validate the size calculation before
allocation.

Fixes: bd72d4acda10 ("accel/amdxdna: Support user space allocated buffer")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260217192815.1784689-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/amdxdna_ubuf.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.c b/drivers/accel/amdxdna/amdxdna_ubuf.c
index b509f10b155c..fb71d6e3f44d 100644
--- a/drivers/accel/amdxdna/amdxdna_ubuf.c
+++ b/drivers/accel/amdxdna/amdxdna_ubuf.c
@@ -7,6 +7,7 @@
 #include <drm/drm_device.h>
 #include <drm/drm_print.h>
 #include <linux/dma-buf.h>
+#include <linux/overflow.h>
 #include <linux/pagemap.h>
 #include <linux/vmalloc.h>
 
@@ -176,7 +177,10 @@ struct dma_buf *amdxdna_get_ubuf(struct drm_device *dev,
 			goto free_ent;
 		}
 
-		exp_info.size += va_ent[i].len;
+		if (check_add_overflow(exp_info.size, va_ent[i].len, &exp_info.size)) {
+			ret = -EINVAL;
+			goto free_ent;
+		}
 	}
 
 	ubuf->nr_pages = exp_info.size >> PAGE_SHIFT;

From 901ec3470994006bc8dd02399e16b675566c3416 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 19 Feb 2026 13:19:46 -0800
Subject: [PATCH 0212/1303] accel/amdxdna: Validate command buffer payload
 count

The count field in the command header is used to determine the valid
payload size. Verify that the valid payload does not exceed the remaining
buffer space.

Fixes: aac243092b70 ("accel/amdxdna: Add command execution")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260219211946.1920485-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/amdxdna_ctx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
index 5173456bbb61..263d36072540 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -104,7 +104,10 @@ void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size)
 
 	if (size) {
 		count = FIELD_GET(AMDXDNA_CMD_COUNT, cmd->header);
-		if (unlikely(count <= num_masks)) {
+		if (unlikely(count <= num_masks ||
+			     count * sizeof(u32) +
+			     offsetof(struct amdxdna_cmd, data[0]) >
+			     abo->mem.size)) {
 			*size = 0;
 			return NULL;
 		}

From 551d44200152cb26f75d2ef990aeb6185b7e37fd Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 23 Feb 2026 09:33:08 -0800
Subject: [PATCH 0213/1303] default_gfp(): avoid using the "newfangled"
 __VA_OPT__ trick

The default_gfp() helper that I added is not wrong, but it turns out
that it causes unnecessary headaches for 'sparse' which doesn't support
the use of __VA_OPT__ (introduced in C++20 and C23, and supported by gcc
and clang for a long time).

We do already use __VA_OPT__ in some other cases in the kernel (drm/xe
and btrfs), but it has been fairly limited.  Now it triggers for pretty
much everything, and sparse ends up not working at all.

We can use the traditional gcc ',##__VA_ARGS__' syntax instead: it may
not be the "C standard" way and is slightly less natural in this
context, but it is the traditional model for this and avoids the sparse
problem.

Reported-and-tested-by: Ricardo Ribalda <ribalda@chromium.org>
Reported-and-tested-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reported-by: Ben Dooks <ben.dooks@codethink.co.uk>
Fixes: e19e1b480ac7 ("add default_gfp() helper macro and use it in the new *alloc_obj() helpers")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2b30a0529d48..90536b2bc42e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -14,8 +14,8 @@ struct vm_area_struct;
 struct mempolicy;
 
 /* Helper macro to avoid gfp flags if they are the default one */
-#define __default_gfp(a,...) a
-#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL)
+#define __default_gfp(a,b,...) b
+#define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)

From a7b4bc094fbaa7dc7b7b91ae33549bbd7eefaac1 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Wed, 7 Jan 2026 13:22:57 +0100
Subject: [PATCH 0214/1303] module: Remove duplicate freeing of lockdep classes

In the error path of load_module(), under the free_module label, the
code calls lockdep_free_key_range() to release lock classes associated
with the MOD_DATA, MOD_RODATA and MOD_RO_AFTER_INIT module regions, and
subsequently invokes module_deallocate().

Since commit ac3b43283923 ("module: replace module_layout with
module_memory"), the module_deallocate() function calls free_mod_mem(),
which releases the lock classes as well and considers all module
regions.

Attempting to free these classes twice is unnecessary. Remove the
redundant code in load_module().

Fixes: ac3b43283923 ("module: replace module_layout with module_memory")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Aaron Tomlin <atomlin@atomlin.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/main.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 2bac4c7cd019..eec6c9cf8dbb 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3544,12 +3544,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_unlock(&module_mutex);
  free_module:
 	mod_stat_bump_invalid(info, flags);
-	/* Free lock-classes; relies on the preceding sync_rcu() */
-	for_class_mod_mem_type(type, core_data) {
-		lockdep_free_key_range(mod->mem[type].base,
-				       mod->mem[type].size);
-	}
-
 	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:

From 8d597ba6ec18dae2eec143d4e1c9d81441ca0dda Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Thu, 5 Feb 2026 15:37:08 +0100
Subject: [PATCH 0215/1303] module: Fix the modversions and signing submenus

The module Kconfig file contains a set of options related to "Module
versioning support" (depends on MODVERSIONS) and "Module signature
verification" (depends on MODULE_SIG). The Kconfig tool automatically
creates submenus when an entry for a symbol is followed by consecutive
items that all depend on the symbol. However, this functionality doesn't
work for the mentioned module options. The MODVERSIONS options are
interleaved with ASM_MODVERSIONS, which has no 'depends on MODVERSIONS' but
instead uses 'default HAVE_ASM_MODVERSIONS && MODVERSIONS'. Similarly, the
MODULE_SIG options are interleaved by a comment warning not to forget
signing modules with scripts/sign-file, which uses the condition 'depends
on MODULE_SIG_FORCE && !MODULE_SIG_ALL'.

The result is that the options are confusingly shown when using
a menuconfig tool, as follows:

 [*]   Module versioning support
         Module versioning implementation (genksyms (from source code))  --->
 [ ]   Extended Module Versioning Support
 [*]   Basic Module Versioning Support
 [*]   Source checksum for all modules
 [*]   Module signature verification
 [ ]     Require modules to be validly signed
 [ ]     Automatically sign all modules
       Hash algorithm to sign modules (SHA-256)  --->

Fix the issue by using if/endif to group related options together in
kernel/module/Kconfig, similarly to how the MODULE_DEBUG options are
already grouped. Note that the signing-related options depend on
'MODULE_SIG || IMA_APPRAISE_MODSIG', with the exception of
MODULE_SIG_FORCE, which is valid only for MODULE_SIG and is therefore kept
separately. For consistency, do the same for the MODULE_COMPRESS entries.
The options are then properly placed into submenus, as follows:

 [*]   Module versioning support
         Module versioning implementation (genksyms (from source code))  --->
 [ ]     Extended Module Versioning Support
 [*]     Basic Module Versioning Support
 [*]   Source checksum for all modules
 [*]   Module signature verification
 [ ]     Require modules to be validly signed
 [ ]     Automatically sign all modules
         Hash algorithm to sign modules (SHA-256)  --->

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/Kconfig | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index be74917802ad..43b1bb01fd27 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -169,9 +169,10 @@ config MODVERSIONS
 	  make them incompatible with the kernel you are running.  If
 	  unsure, say N.
 
+if MODVERSIONS
+
 choice
 	prompt "Module versioning implementation"
-	depends on MODVERSIONS
 	help
 	  Select the tool used to calculate symbol versions for modules.
 
@@ -206,7 +207,7 @@ endchoice
 
 config ASM_MODVERSIONS
 	bool
-	default HAVE_ASM_MODVERSIONS && MODVERSIONS
+	default HAVE_ASM_MODVERSIONS
 	help
 	  This enables module versioning for exported symbols also from
 	  assembly. This can be enabled only when the target architecture
@@ -214,7 +215,6 @@ config ASM_MODVERSIONS
 
 config EXTENDED_MODVERSIONS
 	bool "Extended Module Versioning Support"
-	depends on MODVERSIONS
 	help
 	  This enables extended MODVERSIONs support, allowing long symbol
 	  names to be versioned.
@@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS
 
 config BASIC_MODVERSIONS
 	bool "Basic Module Versioning Support"
-	depends on MODVERSIONS
 	default y
 	help
 	  This enables basic MODVERSIONS support, allowing older tools or
@@ -237,6 +236,8 @@ config BASIC_MODVERSIONS
 	  This is enabled by default when MODVERSIONS are enabled.
 	  If unsure, say Y.
 
+endif # MODVERSIONS
+
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
@@ -277,10 +278,11 @@ config MODULE_SIG_FORCE
 	  Reject unsigned modules or signed modules for which we don't have a
 	  key.  Without this, such modules will simply taint the kernel.
 
+if MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_SIG_ALL
 	bool "Automatically sign all modules"
 	default y
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	help
 	  Sign all modules during make modules_install. Without this option,
 	  modules must be signed manually, using the scripts/sign-file tool.
@@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file"
 
 choice
 	prompt "Hash algorithm to sign modules"
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default MODULE_SIG_SHA512
 	help
 	  This determines which sort of hashing algorithm will be used during
@@ -327,7 +328,6 @@ endchoice
 
 config MODULE_SIG_HASH
 	string
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default "sha256" if MODULE_SIG_SHA256
 	default "sha384" if MODULE_SIG_SHA384
 	default "sha512" if MODULE_SIG_SHA512
@@ -335,6 +335,8 @@ config MODULE_SIG_HASH
 	default "sha3-384" if MODULE_SIG_SHA3_384
 	default "sha3-512" if MODULE_SIG_SHA3_512
 
+endif # MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_COMPRESS
 	bool "Module compression"
 	help
@@ -350,9 +352,10 @@ config MODULE_COMPRESS
 
 	  If unsure, say N.
 
+if MODULE_COMPRESS
+
 choice
 	prompt "Module compression type"
-	depends on MODULE_COMPRESS
 	help
 	  Choose the supported algorithm for module compression.
 
@@ -379,7 +382,6 @@ endchoice
 config MODULE_COMPRESS_ALL
 	bool "Automatically compress all modules"
 	default y
-	depends on MODULE_COMPRESS
 	help
 	  Compress all modules during 'make modules_install'.
 
@@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL
 
 config MODULE_DECOMPRESS
 	bool "Support in-kernel module decompression"
-	depends on MODULE_COMPRESS
 	select ZLIB_INFLATE if MODULE_COMPRESS_GZIP
 	select XZ_DEC if MODULE_COMPRESS_XZ
 	select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD
@@ -400,6 +401,8 @@ config MODULE_DECOMPRESS
 
 	  If unsure, say N.
 
+endif # MODULE_COMPRESS
+
 config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS
 	bool "Allow loading of modules with missing namespace imports"
 	help

From 1f0638604f65dae9fc8b6ce937907daf5f0132d0 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 16:25:22 +0800
Subject: [PATCH 0216/1303] selftests/sched_ext: Fix unused-result warning for
 read()

The read() call in run_test() triggers a warn_unused_result compiler
warning, which breaks the build under -Werror.

Check the return value of read() and exit the child process on failure to
satisfy the compiler and handle pipe read errors.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/init_enable_count.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c
index 82c71653977b..44577e30e764 100644
--- a/tools/testing/selftests/sched_ext/init_enable_count.c
+++ b/tools/testing/selftests/sched_ext/init_enable_count.c
@@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global)
 			char buf;
 
 			close(pipe_fds[1]);
-			read(pipe_fds[0], &buf, 1);
+			if (read(pipe_fds[0], &buf, 1) < 0)
+				exit(1);
 			close(pipe_fds[0]);
 			exit(0);
 		}

From 0c36a6f6f0eb071379b7995ef571c18c1235adf2 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 21:08:25 +0800
Subject: [PATCH 0217/1303] tools/sched_ext: scx_central: Remove unused '-p'
 option

The '-p' option is defined in getopt() but not handled in the switch
statement or documented in the help text. Providing '-p' currently
triggers the default error path.

Remove it to sync the optstring with the actual implementation.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/scx_central.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
index 2a805f1d6c8f..710fa03376e2 100644
--- a/tools/sched_ext/scx_central.c
+++ b/tools/sched_ext/scx_central.c
@@ -66,7 +66,7 @@ int main(int argc, char **argv)
 	assert(skel->rodata->nr_cpu_ids > 0);
 	assert(skel->rodata->nr_cpu_ids <= INT32_MAX);
 
-	while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:c:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;

From cbb297323dbed4f6087b5f189585413801d1d45b Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 21:08:26 +0800
Subject: [PATCH 0218/1303] tools/sched_ext: scx_sdt: Remove unused '-f' option

The '-f' option is defined in getopt() but not handled in the switch
statement or documented in the help text. Providing '-f' currently
triggers the default error path.

Remove it to sync the optstring with the actual implementation.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/scx_sdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sched_ext/scx_sdt.c b/tools/sched_ext/scx_sdt.c
index d8ca9aa316a5..a36405d8df30 100644
--- a/tools/sched_ext/scx_sdt.c
+++ b/tools/sched_ext/scx_sdt.c
@@ -54,7 +54,7 @@ int main(int argc, char **argv)
 	optind = 1;
 	skel = SCX_OPS_OPEN(sdt_ops, scx_sdt);
 
-	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+	while ((opt = getopt(argc, argv, "vh")) != -1) {
 		switch (opt) {
 		case 'v':
 			verbose = true;

From 075e70d13edfcb309c8fdc1f444fbd1f834ca1d4 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Mon, 23 Feb 2026 02:47:09 +0800
Subject: [PATCH 0219/1303] selftests/sched_ext: Remove duplicated unistd.h
 include in rt_stall.c

The header <unistd.h> is included twice in rt_stall.c. Remove the
redundant inclusion to clean up the code.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/rt_stall.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
index ab772e336f86..81ea9b4883e5 100644
--- a/tools/testing/selftests/sched_ext/rt_stall.c
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -15,7 +15,6 @@
 #include <signal.h>
 #include <bpf/bpf.h>
 #include <scx/common.h>
-#include <unistd.h>
 #include "rt_stall.bpf.skel.h"
 #include "scx_test.h"
 #include "../kselftest.h"

From e7e222ad73d93fe54d6e6e3a15253a0ecf081a1b Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 11 Feb 2026 17:31:23 -0700
Subject: [PATCH 0220/1303] cxl: Move devm_cxl_add_nvdimm_bridge() to
 cxl_pmem.ko

Moving the symbol devm_cxl_add_nvdimm_bridge() to
drivers/cxl/cxl_pmem.c, so that cxl_pmem can export a symbol that gives
cxl_acpi a depedency on cxl_pmem kernel module. This is a prepatory patch
to resolve the issue of a race for nvdimm_bus object that is created
during cxl_acpi_probe().

No functional changes besides moving code.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Ira Weiny <ira.weiny@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com?>
Link: https://patch.msgid.link/20260205001633.1813643-2-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/pmem.c | 13 +++----------
 drivers/cxl/cxl.h       |  2 ++
 drivers/cxl/pmem.c      | 14 ++++++++++++++
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index 3c6e76721522..b652e3486038 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -115,15 +115,8 @@ static void unregister_nvb(void *_cxl_nvb)
 	device_unregister(&cxl_nvb->dev);
 }
 
-/**
- * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
- * @host: platform firmware root device
- * @port: CXL port at the root of a CXL topology
- *
- * Return: bridge device that can host cxl_nvdimm objects
- */
-struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
-						     struct cxl_port *port)
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port)
 {
 	struct cxl_nvdimm_bridge *cxl_nvb;
 	struct device *dev;
@@ -155,7 +148,7 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
 	put_device(dev);
 	return ERR_PTR(rc);
 }
-EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL");
+EXPORT_SYMBOL_FOR_MODULES(__devm_cxl_add_nvdimm_bridge, "cxl_pmem");
 
 static void cxl_nvdimm_release(struct device *dev)
 {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 04c673e7cdb0..f5850800f400 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -920,6 +920,8 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv);
 struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev);
 struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
 						     struct cxl_port *port);
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port);
 struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev);
 bool is_cxl_nvdimm(struct device *dev);
 int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index 6a97e4e490b6..c67b30b516bf 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -13,6 +13,20 @@
 
 static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
 
+/**
+ * __devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
+ * @host: platform firmware root device
+ * @port: CXL port at the root of a CXL topology
+ *
+ * Return: bridge device that can host cxl_nvdimm objects
+ */
+struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
+						     struct cxl_port *port)
+{
+	return __devm_cxl_add_nvdimm_bridge(host, port);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL");
+
 static void clear_exclusive(void *mds)
 {
 	clear_exclusive_cxl_commands(mds, exclusive_cmds);

From 43d37df67f7770d8d261fdcb64ecc8c314e91303 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 6 Feb 2026 14:30:59 -0800
Subject: [PATCH 0221/1303] drm/xe/wa: Steer RMW of MCR registers while
 building default LRC

When generating the default LRC, if a register is not masked, we apply
any save-restore programming necessary via a read-modify-write sequence
that will ensure we only update the relevant bits/fields without
clobbering the rest of the register.  However some of the registers that
need to be updated might be MCR registers which require steering to a
non-terminated instance to ensure we can read back a valid, non-zero
value. The steering of reads originating from a command streamer is
controlled by register CS_MMIO_GROUP_INSTANCE_SELECT.  Emit additional
MI_LRI commands to update the steering before any RMW of an MCR register
to ensure the reads are performed properly.

Note that needing to perform a RMW of an MCR register while building the
default LRC is pretty rare.  Most of the MCR registers that are part of
an engine's LRCs are also masked registers, so no MCR is necessary.

Fixes: f2f90989ccff ("drm/xe: Avoid reading RMW registers in emit_wa_job")
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patch.msgid.link/20260206223058.387014-2-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 6c2e331c915ba9e774aa847921262805feb00863)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h |  6 +++
 drivers/gpu/drm/xe/xe_gt.c               | 66 +++++++++++++++++++-----
 2 files changed, 60 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 68172b0248a6..dc5a4fafa70c 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -96,6 +96,12 @@
 #define   ENABLE_SEMAPHORE_POLL_BIT		REG_BIT(13)
 
 #define RING_CMD_CCTL(base)			XE_REG((base) + 0xc4, XE_REG_OPTION_MASKED)
+
+#define CS_MMIO_GROUP_INSTANCE_SELECT(base)	XE_REG((base) + 0xcc)
+#define   SELECTIVE_READ_ADDRESSING		REG_BIT(30)
+#define   SELECTIVE_READ_GROUP			REG_GENMASK(29, 23)
+#define   SELECTIVE_READ_INSTANCE		REG_GENMASK(22, 16)
+
 /*
  * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
  * The lsb of each can be considered a separate enabling bit for encryption.
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 9d090d0f2438..df6d04704823 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -210,11 +210,15 @@ static int emit_nop_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	return ret;
 }
 
+/* Dwords required to emit a RMW of a register */
+#define EMIT_RMW_DW 20
+
 static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 {
-	struct xe_reg_sr *sr = &q->hwe->reg_lrc;
+	struct xe_hw_engine *hwe = q->hwe;
+	struct xe_reg_sr *sr = &hwe->reg_lrc;
 	struct xe_reg_sr_entry *entry;
-	int count_rmw = 0, count = 0, ret;
+	int count_rmw = 0, count_rmw_mcr = 0, count = 0, ret;
 	unsigned long idx;
 	struct xe_bb *bb;
 	size_t bb_len = 0;
@@ -224,6 +228,8 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	xa_for_each(&sr->xa, idx, entry) {
 		if (entry->reg.masked || entry->clr_bits == ~0)
 			++count;
+		else if (entry->reg.mcr)
+			++count_rmw_mcr;
 		else
 			++count_rmw;
 	}
@@ -231,17 +237,35 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	if (count)
 		bb_len += count * 2 + 1;
 
-	if (count_rmw)
-		bb_len += count_rmw * 20 + 7;
+	/*
+	 * RMW of MCR registers is the same as a normal RMW, except an
+	 * additional LRI (3 dwords) is required per register to steer the read
+	 * to a nom-terminated instance.
+	 *
+	 * We could probably shorten the batch slightly by eliding the
+	 * steering for consecutive MCR registers that have the same
+	 * group/instance target, but it's not worth the extra complexity to do
+	 * so.
+	 */
+	bb_len += count_rmw * EMIT_RMW_DW;
+	bb_len += count_rmw_mcr * (EMIT_RMW_DW + 3);
 
-	if (q->hwe->class == XE_ENGINE_CLASS_RENDER)
+	/*
+	 * After doing all RMW, we need 7 trailing dwords to clean up,
+	 * plus an additional 3 dwords to reset steering if any of the
+	 * registers were MCR.
+	 */
+	if (count_rmw || count_rmw_mcr)
+		bb_len += 7 + (count_rmw_mcr ? 3 : 0);
+
+	if (hwe->class == XE_ENGINE_CLASS_RENDER)
 		/*
 		 * Big enough to emit all of the context's 3DSTATE via
 		 * xe_lrc_emit_hwe_state_instructions()
 		 */
-		bb_len += xe_gt_lrc_size(gt, q->hwe->class) / sizeof(u32);
+		bb_len += xe_gt_lrc_size(gt, hwe->class) / sizeof(u32);
 
-	xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", q->hwe->name, bb_len);
+	xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", hwe->name, bb_len);
 
 	bb = xe_bb_new(gt, bb_len, false);
 	if (IS_ERR(bb))
@@ -276,13 +300,23 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 		}
 	}
 
-	if (count_rmw) {
-		/* Emit MI_MATH for each RMW reg: 20dw per reg + 7 trailing dw */
-
+	if (count_rmw || count_rmw_mcr) {
 		xa_for_each(&sr->xa, idx, entry) {
 			if (entry->reg.masked || entry->clr_bits == ~0)
 				continue;
 
+			if (entry->reg.mcr) {
+				struct xe_reg_mcr reg = { .__reg.raw = entry->reg.raw };
+				u8 group, instance;
+
+				xe_gt_mcr_get_nonterminated_steering(gt, reg, &group, &instance);
+				*cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
+				*cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(hwe->mmio_base).addr;
+				*cs++ = SELECTIVE_READ_ADDRESSING |
+					REG_FIELD_PREP(SELECTIVE_READ_GROUP, group) |
+					REG_FIELD_PREP(SELECTIVE_READ_INSTANCE, instance);
+			}
+
 			*cs++ = MI_LOAD_REGISTER_REG | MI_LRR_DST_CS_MMIO;
 			*cs++ = entry->reg.addr;
 			*cs++ = CS_GPR_REG(0, 0).addr;
@@ -308,8 +342,9 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 			*cs++ = CS_GPR_REG(0, 0).addr;
 			*cs++ = entry->reg.addr;
 
-			xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x\n",
-				  entry->reg.addr, entry->clr_bits, entry->set_bits);
+			xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x%s\n",
+				  entry->reg.addr, entry->clr_bits, entry->set_bits,
+				  entry->reg.mcr ? " (MCR)" : "");
 		}
 
 		/* reset used GPR */
@@ -321,6 +356,13 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 		*cs++ = 0;
 		*cs++ = CS_GPR_REG(0, 2).addr;
 		*cs++ = 0;
+
+		/* reset steering */
+		if (count_rmw_mcr) {
+			*cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
+			*cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(q->hwe->mmio_base).addr;
+			*cs++ = 0;
+		}
 	}
 
 	cs = xe_lrc_emit_hwe_state_instructions(q, cs);

From 93cd0d664661f58f7e7bed7373714ab2ace41734 Mon Sep 17 00:00:00 2001
From: A1RM4X <dev@a1rm4x.com>
Date: Wed, 4 Feb 2026 14:26:48 -0500
Subject: [PATCH 0222/1303] USB: add QUIRK_NO_BOS for video capture several
 devices

Several USB capture devices also need the USB_QUIRK_NO_BOS set for them
to work properly, odds are they are all the same chip inside, just
different vendor/product ids.

This fixes up:
  - ASUS TUF 4K PRO
  - Avermedia Live Gamer Ultra 2.1 (GC553G2)
  - UGREEN 35871
to now run at full speed (10 Gbps/4K 60 fps mode.)

Link: https://lore.kernel.org/r/CACy+XB-f-51xGpNQFCSm5pE_momTQLu=BaZggHYU1DiDmFX=ug@mail.gmail.com
Cc: stable <stable@kernel.org>
Signed-off-by: A1RM4X <dev@a1rm4x.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 9e7e49712739..e347236d83e8 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -376,6 +376,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* SanDisk Extreme 55AE */
 	{ USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Avermedia Live Gamer Ultra 2.1 (GC553G2) - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* Realforce 87U Keyboard */
 	{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
 
@@ -436,6 +439,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/
 	{ USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS },
 
@@ -564,6 +570,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* APTIV AUTOMOTIVE HUB */
 	{ USB_DEVICE(0x2c48, 0x0132), .driver_info =
 			USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT },

From 7dff99b354601dd01829e1511711846e04340a69 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 23 Feb 2026 11:18:48 -0800
Subject: [PATCH 0223/1303] Remove WARN_ALL_UNSEEDED_RANDOM kernel config
 option

This config option goes way back - it used to be an internal debug
option to random.c (at that point called DEBUG_RANDOM_BOOT), then was
renamed and exposed as a config option as CONFIG_WARN_UNSEEDED_RANDOM,
and then further renamed to the current CONFIG_WARN_ALL_UNSEEDED_RANDOM.

It was all done with the best of intentions: the more limited
rate-limited reports were reporting some cases, but if you wanted to see
all the gory details, you'd enable this "ALL" option.

However, it turns out - perhaps not surprisingly - that when people
don't care about and fix the first rate-limited cases, they most
certainly don't care about any others either, and so warning about all
of them isn't actually helping anything.

And the non-ratelimited reporting causes problems, where well-meaning
people enable debug options, but the excessive flood of messages that
nobody cares about will hide actual real information when things go
wrong.

I just got a kernel bug report (which had nothing to do with randomness)
where two thirds of the the truncated dmesg was just variations of

   random: get_random_u32 called from __get_random_u32_below+0x10/0x70 with crng_init=0

and in the process early boot messages had been lost (in addition to
making the messages that _hadn't_ been lost harder to read).

The proper way to find these things for the hypothetical developer that
cares - if such a person exists - is almost certainly with boot time
tracing.  That gives you the option to get call graphs etc too, which is
likely a requirement for fixing any problems anyway.

See Documentation/trace/boottime-trace.rst for that option.

And if we for some reason do want to re-introduce actual printing of
these things, it will need to have some uniqueness filtering rather than
this "just print it all" model.

Fixes: cc1e127bfa95 ("random: remove ratelimiting for in-kernel unseeded randomness")
Acked-by: Jason Donenfeld <Jason@zx2c4.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/random.c       | 12 +-----------
 kernel/configs/debug.config |  1 -
 lib/Kconfig.debug           | 27 ---------------------------
 3 files changed, 1 insertion(+), 39 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index dcd002e1b890..7ff4d29911fd 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -96,8 +96,7 @@ static ATOMIC_NOTIFIER_HEAD(random_ready_notifier);
 /* Control how we warn userspace. */
 static struct ratelimit_state urandom_warning =
 	RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE);
-static int ratelimit_disable __read_mostly =
-	IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM);
+static int ratelimit_disable __read_mostly = 0;
 module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
 MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
 
@@ -168,12 +167,6 @@ int __cold execute_with_initialized_rng(struct notifier_block *nb)
 	return ret;
 }
 
-#define warn_unseeded_randomness() \
-	if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \
-		printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \
-				__func__, (void *)_RET_IP_, crng_init)
-
-
 /*********************************************************************
  *
  * Fast key erasure RNG, the "crng".
@@ -434,7 +427,6 @@ static void _get_random_bytes(void *buf, size_t len)
  */
 void get_random_bytes(void *buf, size_t len)
 {
-	warn_unseeded_randomness();
 	_get_random_bytes(buf, len);
 }
 EXPORT_SYMBOL(get_random_bytes);
@@ -523,8 +515,6 @@ type get_random_ ##type(void)							\
 	struct batch_ ##type *batch;						\
 	unsigned long next_gen;							\
 										\
-	warn_unseeded_randomness();						\
-										\
 	if  (!crng_ready()) {							\
 		_get_random_bytes(&ret, sizeof(ret));				\
 		return ret;							\
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index 774702591d26..307c97ac5fa9 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -29,7 +29,6 @@ CONFIG_SECTION_MISMATCH_WARN_ONLY=y
 # CONFIG_UBSAN_ALIGNMENT is not set
 # CONFIG_UBSAN_DIV_ZERO is not set
 # CONFIG_UBSAN_TRAP is not set
-# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_FS_ALLOW_ALL=y
 CONFIG_DEBUG_IRQFLAGS=y
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e2dfbbd3d78..318df4c75454 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1766,33 +1766,6 @@ config STACKTRACE
 	  It is also used by various kernel debugging features that require
 	  stack trace generation.
 
-config WARN_ALL_UNSEEDED_RANDOM
-	bool "Warn for all uses of unseeded randomness"
-	default n
-	help
-	  Some parts of the kernel contain bugs relating to their use of
-	  cryptographically secure random numbers before it's actually possible
-	  to generate those numbers securely. This setting ensures that these
-	  flaws don't go unnoticed, by enabling a message, should this ever
-	  occur. This will allow people with obscure setups to know when things
-	  are going wrong, so that they might contact developers about fixing
-	  it.
-
-	  Unfortunately, on some models of some architectures getting
-	  a fully seeded CRNG is extremely difficult, and so this can
-	  result in dmesg getting spammed for a surprisingly long
-	  time.  This is really bad from a security perspective, and
-	  so architecture maintainers really need to do what they can
-	  to get the CRNG seeded sooner after the system is booted.
-	  However, since users cannot do anything actionable to
-	  address this, by default this option is disabled.
-
-	  Say Y here if you want to receive warnings for all uses of
-	  unseeded randomness.  This will be of use primarily for
-	  those developers interested in improving the security of
-	  Linux kernels running on their architecture (or
-	  subarchitecture).
-
 config DEBUG_KOBJECT
 	bool "kobject debugging"
 	depends on DEBUG_KERNEL

From b9fde507355342a2d64225d582dc8b98ff5ecb19 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Date: Thu, 19 Feb 2026 02:38:34 +0000
Subject: [PATCH 0224/1303] usb: gadget: f_tcm: Fix NULL pointer dereferences
 in nexus handling

The `tpg->tpg_nexus` pointer in the USB Target driver is dynamically
managed and tied to userspace configuration via ConfigFS. It can be
NULL if the USB host sends requests before the nexus is fully
established or immediately after it is dropped.

Currently, functions like `bot_submit_command()` and the data
transfer paths retrieve `tv_nexus = tpg->tpg_nexus` and immediately
dereference `tv_nexus->tvn_se_sess` without any validation. If a
malicious or misconfigured USB host sends a BOT (Bulk-Only Transport)
command during this race window, it triggers a NULL pointer
dereference, leading to a kernel panic (local DoS).

This exposes an inconsistent API usage within the module, as peer
functions like `usbg_submit_command()` and `bot_send_bad_response()`
correctly implement a NULL check for `tv_nexus` before proceeding.

Fix this by bringing consistency to the nexus handling. Add the
missing `if (!tv_nexus)` checks to the vulnerable BOT command and
request processing paths, aborting the command gracefully with an
error instead of crashing the system.

Fixes: c52661d60f63 ("usb-gadget: Initial merge of target module for UASP + BOT")
Cc: stable <stable@kernel.org>
Signed-off-by: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Reviewed-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260219023834.17976-1-jiashengjiangcool@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_tcm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index ec050d8f99f1..a7853dcbb14c 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1222,6 +1222,13 @@ static void usbg_submit_cmd(struct usbg_cmd *cmd)
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		struct usb_gadget *gadget = fuas_to_gadget(cmd->fu);
+
+		dev_err(&gadget->dev, "Missing nexus, ignoring command\n");
+		return;
+	}
+
 	dir = get_cmd_dir(cmd->cmd_buf);
 	if (dir < 0)
 		goto out;
@@ -1483,6 +1490,13 @@ static void bot_cmd_work(struct work_struct *work)
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		struct usb_gadget *gadget = fuas_to_gadget(cmd->fu);
+
+		dev_err(&gadget->dev, "Missing nexus, ignoring command\n");
+		return;
+	}
+
 	dir = get_cmd_dir(cmd->cmd_buf);
 	if (dir < 0)
 		goto out;

From fde0634ad9856b3943a2d1a8cc8de174a63ac840 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Sat, 21 Feb 2026 22:48:15 +0800
Subject: [PATCH 0225/1303] usb: legacy: ncm: Fix NPE in gncm_bind

Commit 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle
with bind/unbind") deferred the allocation of the net_device. This
change leads to a NULL pointer dereference in the legacy NCM driver as
it attempts to access the net_device before it's fully instantiated.

Store the provided qmult, host_addr, and dev_addr into the struct
ncm_opts->net_opts during gncm_bind(). These values will be properly
applied to the net_device when it is allocated and configured later in
the binding process by the NCM function driver.

Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable@kernel.org
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202602181727.fd76c561-lkp@intel.com
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260221-legacy-ncm-v2-1-dfb891d76507@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/legacy/ncm.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index 0f1b45e3abd1..e8d565534053 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -15,8 +15,10 @@
 /* #define DEBUG */
 /* #define VERBOSE_DEBUG */
 
+#include <linux/hex.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
 #include <linux/usb/composite.h>
 
 #include "u_ether.h"
@@ -129,6 +131,7 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 	struct usb_gadget	*gadget = cdev->gadget;
 	struct f_ncm_opts	*ncm_opts;
 	int			status;
+	u8			mac[ETH_ALEN];
 
 	f_ncm_inst = usb_get_function_instance("ncm");
 	if (IS_ERR(f_ncm_inst))
@@ -136,11 +139,15 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 
 	ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst);
 
-	gether_set_qmult(ncm_opts->net, qmult);
-	if (!gether_set_host_addr(ncm_opts->net, host_addr))
+	ncm_opts->net_opts.qmult = qmult;
+	if (host_addr && mac_pton(host_addr, mac)) {
+		memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN);
 		pr_info("using host ethernet address: %s", host_addr);
-	if (!gether_set_dev_addr(ncm_opts->net, dev_addr))
+	}
+	if (dev_addr && mac_pton(dev_addr, mac)) {
+		memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN);
 		pr_info("using self ethernet address: %s", dev_addr);
+	}
 
 	/* Allocate string descriptor numbers ... note that string
 	 * contents can be overridden by the composite_dev glue.

From 0d6c8144ca4d93253de952a5ea0028c19ed7ab68 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Sat, 21 Feb 2026 22:48:16 +0800
Subject: [PATCH 0226/1303] usb: gadget: f_ncm: Fix atomic context locking
 issue

The ncm_set_alt function was holding a mutex to protect against races
with configfs, which invokes the might-sleep function inside an atomic
context.

Remove the struct net_device pointer from the f_ncm_opts structure to
eliminate the contention. The connection state is now managed by a new
boolean flag to preserve the use-after-free fix from
commit 6334b8e4553c ("usb: gadget: f_ncm: Fix UAF ncm object at re-bind
after usb ep transport error").

BUG: sleeping function called from invalid context
Call Trace:
 dump_stack_lvl+0x83/0xc0
 dump_stack+0x14/0x16
 __might_resched+0x389/0x4c0
 __might_sleep+0x8e/0x100
 ...
 __mutex_lock+0x6f/0x1740
 ...
 ncm_set_alt+0x209/0xa40
 set_config+0x6b6/0xb40
 composite_setup+0x734/0x2b40
 ...

Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable@kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260221-legacy-ncm-v2-2-dfb891d76507@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c           | 29 ++++++++-----------
 .../usb/gadget/function/u_ether_configfs.h    | 11 +------
 drivers/usb/gadget/function/u_ncm.h           |  1 -
 3 files changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 14fc7dce6f39..4da19864d70b 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -58,6 +58,7 @@ struct f_ncm {
 	u8				notify_state;
 	atomic_t			notify_count;
 	bool				is_open;
+	bool				is_connected;
 
 	const struct ndp_parser_opts	*parser_opts;
 	bool				is_crc;
@@ -864,7 +865,6 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,13 +887,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		scoped_guard(mutex, &opts->lock)
-			if (opts->net) {
-				DBG(cdev, "reset ncm\n");
-				opts->net = NULL;
-				gether_disconnect(&ncm->port);
-				ncm_reset_values(ncm);
-			}
+		if (ncm->is_connected) {
+			DBG(cdev, "reset ncm\n");
+			ncm->is_connected = false;
+			gether_disconnect(&ncm->port);
+			ncm_reset_values(ncm);
+		}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -926,8 +925,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			scoped_guard(mutex, &opts->lock)
-				opts->net = net;
+			ncm->is_connected = true;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1374,16 +1372,14 @@ static int ncm_unwrap_ntb(struct gether *port,
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	scoped_guard(mutex, &opts->lock)
-		if (opts->net) {
-			opts->net = NULL;
-			gether_disconnect(&ncm->port);
-		}
+	if (ncm->is_connected) {
+		ncm->is_connected = false;
+		gether_disconnect(&ncm->port);
+	}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1687,7 +1683,6 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
 
-	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
 	gether_setup_opts_default(&opts->net_opts, "usb");
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 217990a266b2..25d8fb05b598 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -327,18 +327,9 @@ out:									\
 					      char *page)			\
 	{									\
 		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		const char *name;						\
 										\
 		guard(mutex)(&opts->lock);					\
-		rtnl_lock();							\
-		if (opts->net_opts.ifname_set)					\
-			name = opts->net_opts.name;				\
-		else if (opts->net)						\
-			name = netdev_name(opts->net);				\
-		else								\
-			name = "(inactive net_device)";				\
-		rtnl_unlock();							\
-		return sysfs_emit(page, "%s\n", name);				\
+		return sysfs_emit(page, "%s\n", opts->net_opts.name);		\
 	}									\
 										\
 	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index d99330fe31e8..6d7538855744 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -19,7 +19,6 @@
 
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
-	struct net_device		*net;
 
 	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;

From 7a875c09899ba0404844abfd8f0d54cdc481c151 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 9 Feb 2026 15:37:20 +0100
Subject: [PATCH 0227/1303] usb: yurex: fix race in probe

The bbu member of the descriptor must be set to the value
standing for uninitialized values before the URB whose
completion handler sets bbu is submitted. Otherwise there is
a window during which probing can overwrite already retrieved
data.

Cc: stable <stable@kernel.org>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/20260209143720.1507500-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 9189e4bb213a..7a482cdee1e9 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -272,6 +272,7 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_
 			 dev->int_buffer, YUREX_BUF_SIZE, yurex_interrupt,
 			 dev, 1);
 	dev->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+	dev->bbu = -1;
 	if (usb_submit_urb(dev->urb, GFP_KERNEL)) {
 		retval = -EIO;
 		dev_err(&interface->dev, "Could not submitting URB\n");
@@ -280,7 +281,6 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_
 
 	/* save our data pointer in this interface device */
 	usb_set_intfdata(interface, dev);
-	dev->bbu = -1;
 
 	/* we can register the device now, as it is ready */
 	retval = usb_register_dev(interface, &yurex_class);

From f9d69d5e7bde2295eb7488a56f094ac8f5383b92 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Tue, 30 Dec 2025 10:32:08 -0800
Subject: [PATCH 0228/1303] module: Fix kernel panic when a symbol st_shndx is
 out of bounds

The module loader doesn't check for bounds of the ELF section index in
simplify_symbols():

       for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) {
		const char *name = info->strtab + sym[i].st_name;

		switch (sym[i].st_shndx) {
		case SHN_COMMON:

		[...]

		default:
			/* Divert to percpu allocation if a percpu var. */
			if (sym[i].st_shndx == info->index.pcpu)
				secbase = (unsigned long)mod_percpu(mod);
			else
  /** HERE --> **/		secbase = info->sechdrs[sym[i].st_shndx].sh_addr;
			sym[i].st_value += secbase;
			break;
		}
	}

A symbol with an out-of-bounds st_shndx value, for example 0xffff
(known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic:

  BUG: unable to handle page fault for address: ...
  RIP: 0010:simplify_symbols+0x2b2/0x480
  ...
  Kernel panic - not syncing: Fatal exception

This can happen when module ELF is legitimately using SHN_XINDEX or
when it is corrupted.

Add a bounds check in simplify_symbols() to validate that st_shndx is
within the valid range before using it.

This issue was discovered due to a bug in llvm-objcopy, see relevant
discussion for details [1].

[1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index eec6c9cf8dbb..c3ce106c70af 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 			break;
 
 		default:
+			if (sym[i].st_shndx >= info->hdr->e_shnum) {
+				pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n",
+				       mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1);
+				ret = -ENOEXEC;
+				break;
+			}
+
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == info->index.pcpu)
 				secbase = (unsigned long)mod_percpu(mod);

From 16cb1a64dce56708a1684bf755ad52fb52c41f87 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Feb 2026 13:12:00 +0100
Subject: [PATCH 0229/1303] RDMA/uverbs: select CONFIG_DMA_SHARED_BUFFER

The addition of dmabuf support in uverbs means that it is no
longer possible to build infiniband support if that is disabled:

arm-linux-gnueabi-ld: drivers/infiniband/core/ib_core_uverbs.o: in function `rdma_user_mmap_entry_remove.part.0':
ib_core_uverbs.c:(.text+0x508): undefined reference to `dma_buf_move_notify'
(dma_buf_move_notify): Unknown destination type (ARM/Thumb) in drivers/infiniband/core/ib_core_uverbs.o
ib_core_uverbs.c:(.text+0x518): undefined reference to `dma_resv_wait_timeout'
(dma_resv_wait_timeout): Unknown destination type (ARM/Thumb) in drivers/infiniband/core/ib_core_uverbs.o

Select this from Kconfig, as we do for the other users.

Fixes: 0ac6f4056c4a ("RDMA/uverbs: Add DMABUF object type and operations")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20260216121213.2088910-1-arnd@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 794b9778816b..78ac2ff5befd 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -6,6 +6,7 @@ menuconfig INFINIBAND
 	depends on INET
 	depends on m || IPV6 != m
 	depends on !ALPHA
+	select DMA_SHARED_BUFFER
 	select IRQ_POLL
 	select DIMLIB
 	help

From f9b888599418951b8229bbb28851ed4da50c58e9 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 28 Jan 2026 16:02:42 -0600
Subject: [PATCH 0230/1303] remoteproc: qcom_wcnss: Fix reserved region mapping
 failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_*
functions for "memory-region"") switched from devm_ioremap_wc() to
devm_ioremap_resource_wc(). The difference is devm_ioremap_resource_wc()
also requests the resource which fails. Testing of both fixed and
dynamic reserved regions indicates that requesting the resource should
work, so I'm not sure why it doesn't work in this case. Fix the issue by
reverting back to devm_ioremap_wc().

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reported-by: André Apitzsch <git@apitzsch.eu>
Fixes: c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_* functions for "memory-region"")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: André Apitzsch <git@apitzsch.eu> # on BQ Aquaris M5
Link: https://lore.kernel.org/r/20260128220243.3018526-1-robh@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_wcnss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index ee18bf2e8054..4add9037dbd5 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -537,7 +537,7 @@ static int wcnss_alloc_memory_region(struct qcom_wcnss *wcnss)
 
 	wcnss->mem_phys = wcnss->mem_reloc = res.start;
 	wcnss->mem_size = resource_size(&res);
-	wcnss->mem_region = devm_ioremap_resource_wc(wcnss->dev, &res);
+	wcnss->mem_region = devm_ioremap_wc(wcnss->dev, wcnss->mem_phys, wcnss->mem_size);
 	if (IS_ERR(wcnss->mem_region)) {
 		dev_err(wcnss->dev, "unable to map memory region: %pR\n", &res);
 		return PTR_ERR(wcnss->mem_region);

From 7accb1c4321acb617faf934af59d928b0b047e2b Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 3 Feb 2026 15:16:16 -0500
Subject: [PATCH 0231/1303] Bluetooth: L2CAP: Fix invalid response to
 L2CAP_ECRED_RECONF_REQ

This fixes responding with an invalid result caused by checking the
wrong size of CID which should have been (cmd_len - sizeof(*req)) and
on top of it the wrong result was use L2CAP_CR_LE_INVALID_PARAMS which
is invalid/reserved for reconf when running test like L2CAP/ECFC/BI-03-C:

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 64
        MPS: 64
        Source CID: 64
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reserved (0x000c)
         Result: Reconfiguration failed - one or more Destination CIDs invalid (0x0003)

Fiix L2CAP/ECFC/BI-04-C which expects L2CAP_RECONF_INVALID_MPS (0x0002)
when more than one channel gets its MPS reduced:

> ACL Data RX: Handle 64 flags 0x02 dlen 16
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 8
        MTU: 264
        MPS: 99
        Source CID: 64
!       Source CID: 65
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reconfiguration successful (0x0000)
         Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)

Fix L2CAP/ECFC/BI-05-C when SCID is invalid (85 unconnected):

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 65
        MPS: 64
!        Source CID: 85
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reconfiguration successful (0x0000)
         Result: Reconfiguration failed - one or more Destination CIDs invalid (0x0003)

Fix L2CAP/ECFC/BI-06-C when MPS < L2CAP_ECRED_MIN_MPS (64):

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 672
!       MPS: 63
        Source CID: 64
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!       Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)
        Result: Reconfiguration failed - other unacceptable parameters (0x0004)

Fix L2CAP/ECFC/BI-07-C when MPS reduced for more than one channel:

> ACL Data RX: Handle 64 flags 0x02 dlen 16
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 3 len 8
        MTU: 84
!       MPS: 71
        Source CID: 64
!        Source CID: 65
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!       Result: Reconfiguration successful (0x0000)
        Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)

Link: https://github.com/bluez/bluez/issues/1865
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h |  2 +
 net/bluetooth/l2cap_core.c    | 71 ++++++++++++++++++++++++-----------
 2 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ec3af01e4db9..6f9cf7a05986 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -493,6 +493,8 @@ struct l2cap_ecred_reconf_req {
 #define L2CAP_RECONF_SUCCESS		0x0000
 #define L2CAP_RECONF_INVALID_MTU	0x0001
 #define L2CAP_RECONF_INVALID_MPS	0x0002
+#define L2CAP_RECONF_INVALID_CID	0x0003
+#define L2CAP_RECONF_INVALID_PARAMS	0x0004
 
 struct l2cap_ecred_reconf_rsp {
 	__le16 result;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b628b0fa39b2..81038458be0c 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5310,14 +5310,14 @@ static inline int l2cap_ecred_reconf_req(struct l2cap_conn *conn,
 	struct l2cap_ecred_reconf_req *req = (void *) data;
 	struct l2cap_ecred_reconf_rsp rsp;
 	u16 mtu, mps, result;
-	struct l2cap_chan *chan;
+	struct l2cap_chan *chan[L2CAP_ECRED_MAX_CID] = {};
 	int i, num_scid;
 
 	if (!enable_ecred)
 		return -EINVAL;
 
-	if (cmd_len < sizeof(*req) || cmd_len - sizeof(*req) % sizeof(u16)) {
-		result = L2CAP_CR_LE_INVALID_PARAMS;
+	if (cmd_len < sizeof(*req) || (cmd_len - sizeof(*req)) % sizeof(u16)) {
+		result = L2CAP_RECONF_INVALID_CID;
 		goto respond;
 	}
 
@@ -5327,42 +5327,69 @@ static inline int l2cap_ecred_reconf_req(struct l2cap_conn *conn,
 	BT_DBG("mtu %u mps %u", mtu, mps);
 
 	if (mtu < L2CAP_ECRED_MIN_MTU) {
-		result = L2CAP_RECONF_INVALID_MTU;
+		result = L2CAP_RECONF_INVALID_PARAMS;
 		goto respond;
 	}
 
 	if (mps < L2CAP_ECRED_MIN_MPS) {
-		result = L2CAP_RECONF_INVALID_MPS;
+		result = L2CAP_RECONF_INVALID_PARAMS;
 		goto respond;
 	}
 
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
+
+	if (num_scid > L2CAP_ECRED_MAX_CID) {
+		result = L2CAP_RECONF_INVALID_PARAMS;
+		goto respond;
+	}
+
 	result = L2CAP_RECONF_SUCCESS;
 
+	/* Check if each SCID, MTU and MPS are valid */
 	for (i = 0; i < num_scid; i++) {
 		u16 scid;
 
 		scid = __le16_to_cpu(req->scid[i]);
-		if (!scid)
-			return -EPROTO;
-
-		chan = __l2cap_get_chan_by_dcid(conn, scid);
-		if (!chan)
-			continue;
-
-		/* If the MTU value is decreased for any of the included
-		 * channels, then the receiver shall disconnect all
-		 * included channels.
-		 */
-		if (chan->omtu > mtu) {
-			BT_ERR("chan %p decreased MTU %u -> %u", chan,
-			       chan->omtu, mtu);
-			result = L2CAP_RECONF_INVALID_MTU;
+		if (!scid) {
+			result = L2CAP_RECONF_INVALID_CID;
+			goto respond;
 		}
 
-		chan->omtu = mtu;
-		chan->remote_mps = mps;
+		chan[i] = __l2cap_get_chan_by_dcid(conn, scid);
+		if (!chan[i]) {
+			result = L2CAP_RECONF_INVALID_CID;
+			goto respond;
+		}
+
+		/* The MTU field shall be greater than or equal to the greatest
+		 * current MTU size of these channels.
+		 */
+		if (chan[i]->omtu > mtu) {
+			BT_ERR("chan %p decreased MTU %u -> %u", chan[i],
+			       chan[i]->omtu, mtu);
+			result = L2CAP_RECONF_INVALID_MTU;
+			goto respond;
+		}
+
+		/* If more than one channel is being configured, the MPS field
+		 * shall be greater than or equal to the current MPS size of
+		 * each of these channels. If only one channel is being
+		 * configured, the MPS field may be less than the current MPS
+		 * of that channel.
+		 */
+		if (chan[i]->remote_mps >= mps && i) {
+			BT_ERR("chan %p decreased MPS %u -> %u", chan[i],
+			       chan[i]->remote_mps, mps);
+			result = L2CAP_RECONF_INVALID_MPS;
+			goto respond;
+		}
+	}
+
+	/* Commit the new MTU and MPS values after checking they are valid */
+	for (i = 0; i < num_scid; i++) {
+		chan[i]->omtu = mtu;
+		chan[i]->remote_mps = mps;
 	}
 
 respond:

From c28d2bff70444a85b3b86aaf241ece9408c7858c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 5 Feb 2026 15:11:34 -0500
Subject: [PATCH 0232/1303] Bluetooth: L2CAP: Fix result of
 L2CAP_ECRED_CONN_RSP when MTU is too short

Test L2CAP/ECFC/BV-26-C expect the response to L2CAP_ECRED_CONN_REQ with
and MTU value < L2CAP_ECRED_MIN_MTU (64) to be L2CAP_CR_LE_INVALID_PARAMS
rather than L2CAP_CR_LE_UNACCEPT_PARAMS.

Also fix not including the correct number of CIDs in the response since
the spec requires all CIDs being rejected to be included in the
response.

Link: https://github.com/bluez/bluez/issues/1868
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h |  6 +++---
 net/bluetooth/l2cap_core.c    | 14 ++++++++------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 6f9cf7a05986..010f1a8fd15f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -284,9 +284,9 @@ struct l2cap_conn_rsp {
 #define L2CAP_CR_LE_BAD_KEY_SIZE	0x0007
 #define L2CAP_CR_LE_ENCRYPTION		0x0008
 #define L2CAP_CR_LE_INVALID_SCID	0x0009
-#define L2CAP_CR_LE_SCID_IN_USE		0X000A
-#define L2CAP_CR_LE_UNACCEPT_PARAMS	0X000B
-#define L2CAP_CR_LE_INVALID_PARAMS	0X000C
+#define L2CAP_CR_LE_SCID_IN_USE		0x000A
+#define L2CAP_CR_LE_UNACCEPT_PARAMS	0x000B
+#define L2CAP_CR_LE_INVALID_PARAMS	0x000C
 
 /* connect/create channel status */
 #define L2CAP_CS_NO_INFO	0x0000
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 81038458be0c..390d25909104 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5051,13 +5051,15 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	struct l2cap_chan *chan, *pchan;
 	u16 mtu, mps;
 	__le16 psm;
-	u8 result, len = 0;
+	u8 result, rsp_len = 0;
 	int i, num_scid;
 	bool defer = false;
 
 	if (!enable_ecred)
 		return -EINVAL;
 
+	memset(pdu, 0, sizeof(*pdu));
+
 	if (cmd_len < sizeof(*req) || (cmd_len - sizeof(*req)) % sizeof(u16)) {
 		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
@@ -5066,6 +5068,9 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
 
+	/* Always respond with the same number of scids as in the request */
+	rsp_len = cmd_len;
+
 	if (num_scid > L2CAP_ECRED_MAX_CID) {
 		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
@@ -5075,7 +5080,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	mps  = __le16_to_cpu(req->mps);
 
 	if (mtu < L2CAP_ECRED_MIN_MTU || mps < L2CAP_ECRED_MIN_MPS) {
-		result = L2CAP_CR_LE_UNACCEPT_PARAMS;
+		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
 	}
 
@@ -5095,8 +5100,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 
 	BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps);
 
-	memset(pdu, 0, sizeof(*pdu));
-
 	/* Check if we have socket listening on psm */
 	pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src,
 					 &conn->hcon->dst, LE_LINK);
@@ -5121,7 +5124,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		BT_DBG("scid[%d] 0x%4.4x", i, scid);
 
 		pdu->dcid[i] = 0x0000;
-		len += sizeof(*pdu->dcid);
 
 		/* Check for valid dynamic CID range */
 		if (scid < L2CAP_CID_DYN_START || scid > L2CAP_CID_LE_DYN_END) {
@@ -5188,7 +5190,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		return 0;
 
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_ECRED_CONN_RSP,
-		       sizeof(*pdu) + len, pdu);
+		       sizeof(*pdu) + rsp_len, pdu);
 
 	return 0;
 }

From 21e4271e65094172aadd5beb8caea95dd0fbf6d7 Mon Sep 17 00:00:00 2001
From: Heitor Alves de Siqueira <halves@igalia.com>
Date: Wed, 11 Feb 2026 15:03:35 -0300
Subject: [PATCH 0233/1303] Bluetooth: purge error queues in socket destructors

When TX timestamping is enabled via SO_TIMESTAMPING, SKBs may be queued
into sk_error_queue and will stay there until consumed. If userspace never
gets to read the timestamps, or if the controller is removed unexpectedly,
these SKBs will leak.

Fix by adding skb_queue_purge() calls for sk_error_queue in affected
bluetooth destructors. RFCOMM does not currently use sk_error_queue.

Fixes: 134f4b39df7b ("Bluetooth: add support for skb TX SND/COMPLETION timestamping")
Reported-by: syzbot+7ff4013eabad1407b70a@syzkaller.appspotmail.com
Closes: https://syzbot.org/bug?extid=7ff4013eabad1407b70a
Cc: stable@vger.kernel.org
Signed-off-by: Heitor Alves de Siqueira <halves@igalia.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sock.c   | 1 +
 net/bluetooth/iso.c        | 1 +
 net/bluetooth/l2cap_sock.c | 1 +
 net/bluetooth/sco.c        | 1 +
 4 files changed, 4 insertions(+)

diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 4e7bf63af9c5..0290dea081f6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -2166,6 +2166,7 @@ static void hci_sock_destruct(struct sock *sk)
 	mgmt_cleanup(sk);
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static const struct proto_ops hci_sock_ops = {
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 1459ab161fd2..a38d3774176d 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -746,6 +746,7 @@ static void iso_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void iso_sock_cleanup_listen(struct sock *parent)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 3ba3ce7eaa98..62ceda979f39 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1817,6 +1817,7 @@ static void l2cap_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 87ba90336e80..cccfaf560317 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -470,6 +470,7 @@ static void sco_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void sco_sock_cleanup_listen(struct sock *parent)

From 5c4e9a8b18457ad28b57069ef0f14661e3192b2e Mon Sep 17 00:00:00 2001
From: Jinwang Li <jinwang.li@oss.qualcomm.com>
Date: Thu, 5 Feb 2026 14:26:00 +0800
Subject: [PATCH 0234/1303] Bluetooth: hci_qca: Cleanup on all setup failures

The setup process previously combined error handling and retry gating
under one condition. As a result, the final failed attempt exited
without performing cleanup.

Update the failure path to always perform power and port cleanup on
setup failure, and reopen the port only when retrying.

Fixes: 9e80587aba4c ("Bluetooth: hci_qca: Enhance retry logic in qca_setup")
Signed-off-by: Jinwang Li <jinwang.li@oss.qualcomm.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index c511546f793e..c6de2602b49d 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2046,19 +2046,23 @@ static int qca_setup(struct hci_uart *hu)
 	}
 
 out:
-	if (ret && retries < MAX_INIT_RETRIES) {
-		bt_dev_warn(hdev, "Retry BT power ON:%d", retries);
+	if (ret) {
 		qca_power_shutdown(hu);
-		if (hu->serdev) {
-			serdev_device_close(hu->serdev);
-			ret = serdev_device_open(hu->serdev);
-			if (ret) {
-				bt_dev_err(hdev, "failed to open port");
-				return ret;
+
+		if (retries < MAX_INIT_RETRIES) {
+			bt_dev_warn(hdev, "Retry BT power ON:%d", retries);
+			if (hu->serdev) {
+				serdev_device_close(hu->serdev);
+				ret = serdev_device_open(hu->serdev);
+				if (ret) {
+					bt_dev_err(hdev, "failed to open port");
+					return ret;
+				}
 			}
+			retries++;
+			goto retry;
 		}
-		retries++;
-		goto retry;
+		return ret;
 	}
 
 	/* Setup bdaddr */

From 05761c2c2b5bfec85c47f60c903c461e9b56cf87 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 11 Feb 2026 15:18:03 -0500
Subject: [PATCH 0235/1303] Bluetooth: L2CAP: Fix response to
 L2CAP_ECRED_CONN_REQ

Similar to 03dba9cea72f ("Bluetooth: L2CAP: Fix not responding with
L2CAP_CR_LE_ENCRYPTION") the result code L2CAP_CR_LE_ENCRYPTION shall
be used when BT_SECURITY_MEDIUM is set since that means security mode 2
which mean it doesn't require authentication which results in
qualification test L2CAP/ECFC/BV-32-C failing.

Link: https://github.com/bluez/bluez/issues/1871
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 390d25909104..9452c6179acb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5112,7 +5112,8 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 
 	if (!smp_sufficient_security(conn->hcon, pchan->sec_level,
 				     SMP_ALLOW_STK)) {
-		result = L2CAP_CR_LE_AUTHENTICATION;
+		result = pchan->sec_level == BT_SECURITY_MEDIUM ?
+			L2CAP_CR_LE_ENCRYPTION : L2CAP_CR_LE_AUTHENTICATION;
 		goto unlock;
 	}
 

From f9a1767ce3a34bc33c3d33473f65dc13a380e379 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:11 -0500
Subject: [PATCH 0236/1303] cgroup/cpuset: Fix incorrect change to
 effective_xcpus in partition_xcpus_del()

The effective_xcpus of a cpuset can contain offline CPUs. In
partition_xcpus_del(), the xcpus parameter is incorrectly used as
a temporary cpumask to mask out offline CPUs. As xcpus can be the
effective_xcpus of a cpuset, this can result in unexpected changes
in that cpumask. Fix this problem by not making any changes to the
xcpus parameter.

Fixes: 11e5f407b64a ("cgroup/cpuset: Keep track of CPUs in isolated partitions")
Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c43efef7df71..a366ef84f982 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1221,8 +1221,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent,
 		isolated_cpus_update(old_prs, parent->partition_root_state,
 				     xcpus);
 
-	cpumask_and(xcpus, xcpus, cpu_active_mask);
 	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+	cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask);
 }
 
 /*

From 68230aac8b9aad243626fbaf3ca170012c17fec5 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:12 -0500
Subject: [PATCH 0237/1303] cgroup/cpuset: Fix incorrect use of
 cpuset_update_tasks_cpumask() in update_cpumasks_hier()

Commit e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2")
incorrectly changed the 2nd parameter of cpuset_update_tasks_cpumask()
from tmp->new_cpus to cp->effective_cpus. This second parameter is just
a temporary cpumask for internal use. The cpuset_update_tasks_cpumask()
function was originally called update_tasks_cpumask() before commit
381b53c3b549 ("cgroup/cpuset: rename functions shared between v1
and v2").

This mistake can incorrectly change the effective_cpus of the
cpuset when it is the top_cpuset or in arm64 architecture where
task_cpu_possible_mask() may differ from cpu_possible_mask.  So far
top_cpuset hasn't been passed to update_cpumasks_hier() yet, but arm64
arch can still be impacted. Fix it by reverting the incorrect change.

Fixes: e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a366ef84f982..8dfffe2dc9ed 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2157,7 +2157,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		cpuset_update_tasks_cpumask(cp, cp->effective_cpus);
+		cpuset_update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE

From 17b1860034c769c9f7669ae2612e91ef8fdde769 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:13 -0500
Subject: [PATCH 0238/1303] cgroup/cpuset: Clarify exclusion rules for cpuset
 internal variables

Clarify the locking rules associated with file level internal variables
inside the cpuset code. There is no functional change.

Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 105 ++++++++++++++++++++++++-----------------
 1 file changed, 61 insertions(+), 44 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 8dfffe2dc9ed..165e2967025b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -61,6 +61,58 @@ static const char * const perr_strings[] = {
 	[PERR_REMOTE]    = "Have remote partition underneath",
 };
 
+/*
+ * CPUSET Locking Convention
+ * -------------------------
+ *
+ * Below are the three global locks guarding cpuset structures in lock
+ * acquisition order:
+ *  - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock)
+ *  - cpuset_mutex
+ *  - callback_lock (raw spinlock)
+ *
+ * A task must hold all the three locks to modify externally visible or
+ * used fields of cpusets, though some of the internally used cpuset fields
+ * and internal variables can be modified without holding callback_lock. If only
+ * reliable read access of the externally used fields are needed, a task can
+ * hold either cpuset_mutex or callback_lock which are exposed to other
+ * external subsystems.
+ *
+ * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others,
+ * ensuring that it is the only task able to also acquire callback_lock and
+ * be able to modify cpusets.  It can perform various checks on the cpuset
+ * structure first, knowing nothing will change. It can also allocate memory
+ * without holding callback_lock. While it is performing these checks, various
+ * callback routines can briefly acquire callback_lock to query cpusets.  Once
+ * it is ready to make the changes, it takes callback_lock, blocking everyone
+ * else.
+ *
+ * Calls to the kernel memory allocator cannot be made while holding
+ * callback_lock which is a spinlock, as the memory allocator may sleep or
+ * call back into cpuset code and acquire callback_lock.
+ *
+ * Now, the task_struct fields mems_allowed and mempolicy may be changed
+ * by other task, we use alloc_lock in the task_struct fields to protect
+ * them.
+ *
+ * The cpuset_common_seq_show() handlers only hold callback_lock across
+ * small pieces of code, such as when reading out possibly multi-word
+ * cpumasks and nodemasks.
+ */
+
+static DEFINE_MUTEX(cpuset_mutex);
+
+/*
+ * File level internal variables below follow one of the following exclusion
+ * rules.
+ *
+ * RWCS: Read/write-able by holding either cpus_write_lock (and optionally
+ *	 cpuset_mutex) or both cpus_read_lock and cpuset_mutex.
+ *
+ * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable
+ *	 by holding both cpuset_mutex and callback_lock.
+ */
+
 /*
  * For local partitions, update to subpartitions_cpus & isolated_cpus is done
  * in update_parent_effective_cpumask(). For remote partitions, it is done in
@@ -70,19 +122,18 @@ static const char * const perr_strings[] = {
  * Exclusive CPUs distributed out to local or remote sub-partitions of
  * top_cpuset
  */
-static cpumask_var_t	subpartitions_cpus;
+static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 
 /*
- * Exclusive CPUs in isolated partitions
+ * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated)
  */
-static cpumask_var_t	isolated_cpus;
+static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * isolated_cpus updating flag (protected by cpuset_mutex)
- * Set if isolated_cpus is going to be updated in the current
- * cpuset_mutex crtical section.
+ * Set if isolated_cpus is being updated in the current cpuset_mutex
+ * critical section.
  */
-static bool isolated_cpus_updating;
+static bool		isolated_cpus_updating;	/* RWCS */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -98,7 +149,7 @@ static bool isolated_cpus_updating;
  * Note that update_relax_domain_level() in cpuset-v1.c can still call
  * rebuild_sched_domains_locked() directly without using this flag.
  */
-static bool force_sd_rebuild;
+static bool force_sd_rebuild;			/* RWCS */
 
 /*
  * Partition root states:
@@ -218,42 +269,6 @@ struct cpuset top_cpuset = {
 	.partition_root_state = PRS_ROOT,
 };
 
-/*
- * There are two global locks guarding cpuset structures - cpuset_mutex and
- * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel
- * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
- * structures. Note that cpuset_mutex needs to be a mutex as it is used in
- * paths that rely on priority inheritance (e.g. scheduler - on RT) for
- * correctness.
- *
- * A task must hold both locks to modify cpusets.  If a task holds
- * cpuset_mutex, it blocks others, ensuring that it is the only task able to
- * also acquire callback_lock and be able to modify cpusets.  It can perform
- * various checks on the cpuset structure first, knowing nothing will change.
- * It can also allocate memory while just holding cpuset_mutex.  While it is
- * performing these checks, various callback routines can briefly acquire
- * callback_lock to query cpusets.  Once it is ready to make the changes, it
- * takes callback_lock, blocking everyone else.
- *
- * Calls to the kernel memory allocator can not be made while holding
- * callback_lock, as that would risk double tripping on callback_lock
- * from one of the callbacks into the cpuset code from within
- * __alloc_pages().
- *
- * If a task is only holding callback_lock, then it has read-only
- * access to cpusets.
- *
- * Now, the task_struct fields mems_allowed and mempolicy may be changed
- * by other task, we use alloc_lock in the task_struct fields to protect
- * them.
- *
- * The cpuset_common_seq_show() handlers only hold callback_lock across
- * small pieces of code, such as when reading out possibly multi-word
- * cpumasks and nodemasks.
- */
-
-static DEFINE_MUTEX(cpuset_mutex);
-
 /**
  * cpuset_lock - Acquire the global cpuset mutex
  *
@@ -1163,6 +1178,8 @@ static void reset_partition_data(struct cpuset *cs)
 static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
 	WARN_ON_ONCE(old_prs == new_prs);
+	lockdep_assert_held(&callback_lock);
+	lockdep_assert_held(&cpuset_mutex);
 	if (new_prs == PRS_ISOLATED)
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
 	else

From 14713ed9e9291813849018f32edbf5f6de362088 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:14 -0500
Subject: [PATCH 0239/1303] cgroup/cpuset: Set isolated_cpus_updating only if
 isolated_cpus is changed

As cpuset is updating HK_TYPE_DOMAIN housekeeping mask when there is
a change in the set of isolated CPUs, making this change is now more
costly than before.  Right now, the isolated_cpus_updating flag can be
set even if there is no real change in isolated_cpus. Put in additional
checks to make sure that isolated_cpus_updating is set only if there
is a real change in isolated_cpus.

Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 165e2967025b..edc67c6aa553 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1180,11 +1180,15 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 	WARN_ON_ONCE(old_prs == new_prs);
 	lockdep_assert_held(&callback_lock);
 	lockdep_assert_held(&cpuset_mutex);
-	if (new_prs == PRS_ISOLATED)
+	if (new_prs == PRS_ISOLATED) {
+		if (cpumask_subset(xcpus, isolated_cpus))
+			return;
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
-	else
+	} else {
+		if (!cpumask_intersects(xcpus, isolated_cpus))
+			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
-
+	}
 	isolated_cpus_updating = true;
 }
 

From 5e6aac573cc4cc8e62aebf880b824e219a5ff557 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:15 -0500
Subject: [PATCH 0240/1303] kselftest/cgroup: Simplify test_cpuset_prs.sh by
 removing "S+" command

The "S+" command is used in the test matrix to enable the cpuset
controller. However this can be done automatically and we never use the
"S-" command to disable cpuset controller. Simplify the test matrix and
reduce clutter by removing the command and doing that automatically.
There is no functional change to the test cases.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 .../selftests/cgroup/test_cpuset_prs.sh       | 213 +++++++++---------
 1 file changed, 104 insertions(+), 109 deletions(-)

diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 5dff3ad53867..ef16f5610d0b 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -196,7 +196,6 @@ test_add_proc()
 #  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
 #  C<l> = add cpu-list to cpuset.cpus
 #  X<l> = add cpu-list to cpuset.cpus.exclusive
-#  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
 #  CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
 #  O<c>=<v> = Write <v> to CPU online file of <c>
@@ -209,44 +208,43 @@ test_add_proc()
 # sched-debug matching which includes offline CPUs and single-CPU partitions
 # while the second one is for matching cpuset.cpus.isolated.
 #
-SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
+SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1"
 TEST_MATRIX=(
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
-	"   C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .      .     0 A2:0-1"
 	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
-	"  C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
-	"  C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
+	"   C0-1     .      .    C2-3    P1   C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3    P1    C1:P1    .      .     0 "
+	"   C0-1     .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3     .     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .     P1     0 "
 	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
-	"  C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
 	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
 	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
-	"C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
-	"C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
+	"  C0-3:P1 C2-3:P1  .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
+	"  C2-3:P1  C2:P1   .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# CPU offlining cases:
-	"   C0-1     .      .    C2-3    S+    C4-5     .     O2=0   0 A1:0-1|B1:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
-	"C2-3:P1:S+  C3:P1  .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .     O2=0   0 A1:0-1|B1:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
+	"  C2-3:P1  C3:P1   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -264,88 +262,87 @@ TEST_MATRIX=(
 	#
 	# Remote partition and cpuset.cpus.exclusive tests
 	#
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
-	" C0-3:S+ C1-3:S+ C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
+	"   C0-3    C1-3  C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+	"  C4:X0-3  X1-3  X2-3     .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+	"  C4:X0-3  X1-3  X2-3     .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
 
 	# Nested remote/local partition tests
-	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+	"   C0-3    C1-3  C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P0|B1:P1"
-	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
+	"   C0-3    C1-3   C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
 								       A1:P0|A2:P2|A3:P1 2-4|2-3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
 								       A1:P0|A2:P2|A3:P1 2"
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      X5      .      .    0 A1:0-4|A2:1-4|A3:2-4 \
 								       A1:P0|A2:P-2|A3:P-1 ."
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
 								       A1:P0|A2:P2|A3:P-1 2-4"
 
 	# Remote partition offline tests
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
 
 	# An invalidated remote partition cannot self-recover from hotplug
-	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+	"   C0-3    C1-3   C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
 
 	# cpus.exclusive.effective clearing test
-	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
+	"   C0-3    C1-3   C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
 
 	# Invalid to valid remote partition transition test
-	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
-	" C0-3:S+ C1-3:X3:P2
-			    .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+	"   C0-3    C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+	"   C0-3 C1-3:X3:P2 .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
 
 	# Invalid to valid local partition direct transition tests
-	" C1-3:S+:P2 X4:P2  .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
-	" C1-3:S+:P2 X4:P2  .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
-	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
-	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+	" C1-3:P2  X4:P2    .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+	" C1-3:P2  X4:P2    .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+	" C0-3:P2    .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
+	" C0-3:P2    .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
 
 	# Local partition invalidation tests
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .      .      .      .     0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .     X4      .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .    C4:X     .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
 	# Local partition CPU change tests
-	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
-	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+	" C0-5:P2  C4-5:P1  .      .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+	" C0-5:P2  C4-5:P1  .      .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
 
 	# cpus_allowed/exclusive_cpus update tests
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .    X:C4     .      P2     .     0 A1:4|A2:4|XA2:|XA3:|A3:4 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .     X1      .      P2     .     0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .      .     X3      P2     .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .      .     X3      .      .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .     X4      .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
 								       A1:P0|A3:P-2"
 
@@ -356,37 +353,37 @@ TEST_MATRIX=(
 	#
 	# Adding CPUs to partition root that are not in parent's
 	# cpuset.cpus is allowed, but those extra CPUs are ignored.
-	"C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
+	"  C2-3:P1   C3:P1  .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
 
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
-	"C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
-	" C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+	"   C3:P1     C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
 	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# Changing a partition root to member makes child partitions invalid
-	"C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
 
 	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
 	# as they overlap.
-	"C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1   .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
 
 	# Deletion of CPUs distributed to child cgroup is allowed.
-	"C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
+	"  C0-1:P1  C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
 
 	# To become a valid partition root, cpuset.cpus must overlap parent's
 	# cpuset.cpus.
-	"  C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
+	"  C0-1:P1   .      .    C2-3     .   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
 
 	# Enabling partition with child cpusets is allowed
-	"  C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
+	"   C0-1    C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
 
 	# A partition root with non-partition root parent is invalid| but it
 	# can be made valid if its parent becomes a partition root too.
-	"  C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
-	"  C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
+	"   C0-1    C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
+	"   C0-1   C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
 
 	# A non-exclusive cpuset.cpus change will not invalidate its siblings partition.
 	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2|B1:3 A1:P1|B1:P0"
@@ -398,23 +395,23 @@ TEST_MATRIX=(
 
 	# Child partition root that try to take all CPUs from parent partition
 	# with tasks will remain invalid.
-	" C1-4:P1:S+ P1     .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
-	" C1-4:P1:S+ P1     .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
-	" C1-4:P1:S+ P1     .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
+	"  C1-4:P1  P1      .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
 
 	# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
 	# affect cpuset.cpus.exclusive.effective.
-	" C1-4:X3:S+ C1:X3  .      .       .     C      .      .     0 A2:1-4|XA2:3"
+	"  C1-4:X3 C1:X3    .      .       .     C      .      .     0 A2:1-4|XA2:3"
 
 	# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
 	# but creating a local partition out of it is not allowed. Similarly and change
 	# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
 	# invalidate it.
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
 								       A1:P0|A2:P2:B1:P1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
 
 	# When multiple partitions with conflicting cpuset.cpus are created, the
@@ -426,14 +423,14 @@ TEST_MATRIX=(
 	" C1-3:X1-3  .      .    C4-5      .     .      .     C1-2   0 A1:1-3|B1:1-2"
 
 	# cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
-	" C1-3:S+   C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
+	"   C1-3    C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
 
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	# Failure cases:
 
 	# A task cannot be added to a partition with no cpu
-	"C2-3:P1:S+  C3:P1  .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1 C3:P1    .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
 
 	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
 	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3|B1:4-5"
@@ -465,31 +462,31 @@ REMOTE_TEST_MATRIX=(
 	#  old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
 	#  new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------- ------- ------- ------- ----- ------ --------
-	" X1-3:S+ X4-6:S+ X1-2     X3     X4-5     X6 \
+	"   X1-3   X4-6  X1-2      X3     X4-5     X6 \
 	      .      .     P2      P2      P2      P2    c11:1-2|c12:3|c21:4-5|c22:6 \
 							 c11:P2|c12:P2|c21:P2|c22:P2 1-6"
-	" CX1-4:S+   .   X1-2:P2   C3      .       .  \
+	"  CX1-4     .  X1-2:P2    C3      .       .  \
 	      .      .     .      C3-4     .       .     p1:3-4|c11:1-2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P0 1-2"
-	" CX1-4:S+   .   X1-2:P2   .       .       .  \
+	"  CX1-4     .  X1-2:P2    .       .       .  \
 	    X2-4     .     .       .       .       .     p1:1,3-4|c11:2 \
 							 p1:P0|c11:P2 2"
-	" CX1-5:S+   .   X1-2:P2 X3-5:P1   .       .  \
+	"  CX1-5     .  X1-2:P2  X3-5:P1   .       .  \
 	    X2-4     .     .       .       .       .     p1:1,5|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X2      .       .       .     p1:1|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
 	# p1 as member, will get its effective CPUs from its parent rtest
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X1     CX2-4    .       .     p1:5-7|c11:1|c12:2-4 \
 							 p1:P0|c11:P2|c12:P1 1"
-	" CX1-4:S+ X5-6:P1:S+ .    .       .       .  \
-	      .      .   X1-2:P2  X4-5:P1  .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+	"  CX1-4  X5-6:P1  .       .       .       .  \
+	      .      .  X1-2:P2  X4-5:P1   .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
 							 p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
 							 1-2,4-6|1-2,5-6"
 	# c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition
-	" C1-5:P1:S+ .  C1-4:P1   C2-3     .       .  \
+	"  C1-5:P1   .  C1-4:P1   C2-3     .       .  \
 	      .      .     .       P1      .       .     p1:5|c11:1-4|c12:5 \
 							 p1:P1|c11:P1|c12:P-1"
 )
@@ -530,7 +527,6 @@ set_ctrl_state()
 	CGRP=$1
 	STATE=$2
 	SHOWERR=${3}
-	CTRL=${CTRL:=$CONTROLLER}
 	HASERR=0
 	REDIRECT="2> $TMPMSG"
 	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
@@ -540,15 +536,16 @@ set_ctrl_state()
 	for CMD in $(echo $STATE | sed -e "s/:/ /g")
 	do
 		TFILE=$CGRP/cgroup.procs
-		SFILE=$CGRP/cgroup.subtree_control
 		PFILE=$CGRP/cpuset.cpus.partition
 		CFILE=$CGRP/cpuset.cpus
 		XFILE=$CGRP/cpuset.cpus.exclusive
-		case $CMD in
-		    S*) PREFIX=${CMD#?}
-			COMM="echo ${PREFIX}${CTRL} > $SFILE"
+
+		# Enable cpuset controller if not enabled yet
+		[[ -f $CFILE ]] || {
+			COMM="echo +cpuset > $CGRP/../cgroup.subtree_control"
 			eval $COMM $REDIRECT
-			;;
+		}
+		case $CMD in
 		    X*)
 			CPUS=${CMD#?}
 			COMM="echo $CPUS > $XFILE"
@@ -947,7 +944,6 @@ check_test_results()
 run_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
 	RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
 	I=0
@@ -1003,7 +999,6 @@ run_state_test()
 run_remote_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	[[ -d rtest ]] || mkdir rtest
 	cd rtest
 	echo +cpuset > cgroup.subtree_control

From 3bfe47967191f42d17510713b31a47d9284b8c5a Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:16 -0500
Subject: [PATCH 0241/1303] cgroup/cpuset: Move
 housekeeping_update()/rebuild_sched_domains() together

With the latest changes in sched/isolation.c, rebuild_sched_domains*()
requires the HK_TYPE_DOMAIN housekeeping cpumask to be properly
updated first, if needed, before the sched domains can be
rebuilt. So the two naturally fit together. Do that by creating a new
update_hk_sched_domains() helper to house both actions.

The name of the isolated_cpus_updating flag to control the
call to housekeeping_update() is now outdated. So change it to
update_housekeeping to better reflect its purpose. Also move the call
to update_hk_sched_domains() to the end of cpuset and hotplug operations
before releasing the cpuset_mutex.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 51 ++++++++++++++++++++----------------------
 1 file changed, 24 insertions(+), 27 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index edc67c6aa553..14b07a283a2c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -130,10 +130,9 @@ static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * Set if isolated_cpus is being updated in the current cpuset_mutex
- * critical section.
+ * Set if housekeeping cpumasks are to be updated.
  */
-static bool		isolated_cpus_updating;	/* RWCS */
+static bool		update_housekeeping;	/* RWCS */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -1189,7 +1188,7 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
 	}
-	isolated_cpus_updating = true;
+	update_housekeeping = true;
 }
 
 /*
@@ -1307,22 +1306,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_isolation_cpumasks - Update external isolation related CPU masks
+ * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
  *
- * The following external CPU masks will be updated if necessary:
- * - workqueue unbound cpumask
+ * Update housekeeping cpumasks and rebuild sched domains if necessary.
+ * This should be called at the end of cpuset or hotplug actions.
  */
-static void update_isolation_cpumasks(void)
+static void update_hk_sched_domains(void)
 {
-	int ret;
-
-	if (!isolated_cpus_updating)
-		return;
-
-	ret = housekeeping_update(isolated_cpus);
-	WARN_ON_ONCE(ret < 0);
-
-	isolated_cpus_updating = false;
+	if (update_housekeeping) {
+		/* Updating HK cpumasks implies rebuild sched domains */
+		WARN_ON_ONCE(housekeeping_update(isolated_cpus));
+		update_housekeeping = false;
+		force_sd_rebuild = true;
+	}
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
 }
 
 /**
@@ -1473,7 +1472,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	cs->remote_partition = true;
 	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 	cs->prs_err = 0;
 
@@ -1518,7 +1516,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 	compute_excpus(cs, cs->effective_xcpus);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 
 	/*
@@ -1589,7 +1586,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	if (xcpus)
 		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	if (adding || deleting)
 		cpuset_force_rebuild();
 
@@ -1933,7 +1929,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		partition_xcpus_add(new_prs, parent, tmp->delmask);
 
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive_flag(cs, new_prs);
@@ -2901,7 +2896,6 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	else if (isolcpus_updated)
 		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
@@ -3191,9 +3185,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	}
 
 	free_cpuset(trialcs);
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 out_unlock:
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
@@ -3301,6 +3294,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	return retval ?: nbytes;
 }
@@ -3475,6 +3469,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 }
 
@@ -3882,10 +3877,12 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-	/* rebuild sched domains if necessary */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_cpuslocked();
 
+	if (update_housekeeping || force_sd_rebuild) {
+		mutex_lock(&cpuset_mutex);
+		update_hk_sched_domains();
+		mutex_unlock(&cpuset_mutex);
+	}
 	free_tmpmasks(ptmp);
 }
 

From 6df415aa46ec10d607da5063d88492a7c7762074 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:17 -0500
Subject: [PATCH 0242/1303] cgroup/cpuset: Defer housekeeping_update() calls
 from CPU hotplug to workqueue

The cpuset_handle_hotplug() may need to invoke housekeeping_update(),
for instance, when an isolated partition is invalidated because its
last active CPU has been put offline.

As we are going to enable dynamic update to the nozh_full housekeeping
cpumask (HK_TYPE_KERNEL_NOISE) soon with the help of CPU hotplug,
allowing the CPU hotplug path to call into housekeeping_update() directly
from update_isolation_cpumasks() will likely cause deadlock. So we
have to defer any call to housekeeping_update() after the CPU hotplug
operation has finished. This is now done via the workqueue where
the update_hk_sched_domains() function will be invoked via the
hk_sd_workfn().

An concurrent cpuset control file write may have executed the required
update_hk_sched_domains() function before the work function is called. So
the work function call may become a no-op when it is invoked.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c                        | 31 ++++++++++++++++---
 .../selftests/cgroup/test_cpuset_prs.sh       | 11 ++++++-
 2 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 14b07a283a2c..aa915e9b588f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1324,6 +1324,16 @@ static void update_hk_sched_domains(void)
 		rebuild_sched_domains_locked();
 }
 
+/*
+ * Work function to invoke update_hk_sched_domains()
+ */
+static void hk_sd_workfn(struct work_struct *work)
+{
+	cpuset_full_lock();
+	update_hk_sched_domains();
+	cpuset_full_unlock();
+}
+
 /**
  * rm_siblings_excl_cpus - Remove exclusive CPUs that are used by sibling cpusets
  * @parent: Parent cpuset containing all siblings
@@ -3796,6 +3806,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
  */
 static void cpuset_handle_hotplug(void)
 {
+	static DECLARE_WORK(hk_sd_work, hk_sd_workfn);
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
@@ -3878,11 +3889,21 @@ static void cpuset_handle_hotplug(void)
 	}
 
 
-	if (update_housekeeping || force_sd_rebuild) {
-		mutex_lock(&cpuset_mutex);
-		update_hk_sched_domains();
-		mutex_unlock(&cpuset_mutex);
-	}
+	/*
+	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
+	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
+	 * cpumask can correctly reflect what is in isolated_cpus.
+	 *
+	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
+	 * is still pending. Before the pending bit is cleared, the work data
+	 * is copied out and work item dequeued. So it is possible to queue
+	 * the work again before the hk_sd_workfn() is invoked to process the
+	 * previously queued work. Since hk_sd_workfn() doesn't use the work
+	 * item at all, this is not a problem.
+	 */
+	if (update_housekeeping || force_sd_rebuild)
+		queue_work(system_unbound_wq, &hk_sd_work);
+
 	free_tmpmasks(ptmp);
 }
 
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index ef16f5610d0b..a56f4153c64d 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -245,6 +245,9 @@ TEST_MATRIX=(
 	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
 	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P2   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-2"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0   .      .     0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0  O3=1    .     0 A1:1-2|A2:3 A1:P1|A2:P2  3"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -761,7 +764,7 @@ check_cgroup_states()
 # only CPUs in isolated partitions as well as those that are isolated at
 # boot time.
 #
-# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
 # <isolcpus1> - expected sched/domains value
 # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
 #
@@ -770,6 +773,7 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
+	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -807,6 +811,11 @@ check_isolcpus()
 	ISOLCPUS=
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
+	#
+	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
+	#
+	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
+
 	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#

From a84097e625f2b9e7f273161c004f34b7be63b348 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:18 -0500
Subject: [PATCH 0243/1303] cgroup/cpuset: Call housekeeping_update() without
 holding cpus_read_lock

The current cpuset partition code is able to dynamically update
the sched domains of a running system and the corresponding
HK_TYPE_DOMAIN housekeeping cpumask to perform what is essentially the
"isolcpus=domain,..." boot command line feature at run time.

The housekeeping cpumask update requires flushing a number of different
workqueues which may not be safe with cpus_read_lock() held as the
workqueue flushing code may acquire cpus_read_lock() or acquiring locks
which have locking dependency with cpus_read_lock() down the chain. Below
is an example of such circular locking problem.

  ======================================================
  WARNING: possible circular locking dependency detected
  6.18.0-test+ #2 Tainted: G S
  ------------------------------------------------------
  test_cpuset_prs/10971 is trying to acquire lock:
  ffff888112ba4958 ((wq_completion)sync_wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x7a/0x180

  but task is already holding lock:
  ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:
  -> #4 (cpuset_mutex){+.+.}-{4:4}:
  -> #3 (cpu_hotplug_lock){++++}-{0:0}:
  -> #2 (rtnl_mutex){+.+.}-{4:4}:
  -> #1 ((work_completion)(&arg.work)){+.+.}-{0:0}:
  -> #0 ((wq_completion)sync_wq){+.+.}-{0:0}:

  Chain exists of:
    (wq_completion)sync_wq --> cpu_hotplug_lock --> cpuset_mutex

  5 locks held by test_cpuset_prs/10971:
   #0: ffff88816810e440 (sb_writers#7){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0
   #1: ffff8891ab620890 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x260/0x5f0
   #2: ffff8890a78b83e8 (kn->active#187){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x2b6/0x5f0
   #3: ffffffffadf32900 (cpu_hotplug_lock){++++}-{0:0}, at: cpuset_partition_write+0x77/0x130
   #4: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130

  Call Trace:
   <TASK>
     :
   touch_wq_lockdep_map+0x93/0x180
   __flush_workqueue+0x111/0x10b0
   housekeeping_update+0x12d/0x2d0
   update_parent_effective_cpumask+0x595/0x2440
   update_prstate+0x89d/0xce0
   cpuset_partition_write+0xc5/0x130
   cgroup_file_write+0x1a5/0x680
   kernfs_fop_write_iter+0x3df/0x5f0
   vfs_write+0x525/0xfd0
   ksys_write+0xf9/0x1d0
   do_syscall_64+0x95/0x520
   entry_SYSCALL_64_after_hwframe+0x76/0x7e

To avoid such a circular locking dependency problem, we have to
call housekeeping_update() without holding the cpus_read_lock() and
cpuset_mutex. The current set of wq's flushed by housekeeping_update()
may not have work functions that call cpus_read_lock() directly,
but we are likely to extend the list of wq's that are flushed in the
future. Moreover, the current set of work functions may hold locks that
may have cpu_hotplug_lock down the dependency chain.

So housekeeping_update() is now called after releasing cpus_read_lock
and cpuset_mutex at the end of a cpuset operation. These two locks are
then re-acquired later before calling rebuild_sched_domains_locked().

To enable mutual exclusion between the housekeeping_update() call and
other cpuset control file write actions, a new top level cpuset_top_mutex
is introduced. This new mutex will be acquired first to allow sharing
variables used by both code paths. However, cpuset update from CPU
hotplug can still happen in parallel with the housekeeping_update()
call, though that should be rare in production environment.

As cpus_read_lock() is now no longer held when
tmigr_isolated_exclude_cpumask() is called, it needs to acquire it
directly.

The lockdep_is_cpuset_held() is also updated to return true if either
cpuset_top_mutex or cpuset_mutex is held.

Fixes: 03ff73510169 ("cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c        | 47 +++++++++++++++++++++++++++++++----
 kernel/sched/isolation.c      |  4 +--
 kernel/time/timer_migration.c |  4 +--
 3 files changed, 44 insertions(+), 11 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index aa915e9b588f..aa45351c6f38 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -65,14 +65,28 @@ static const char * const perr_strings[] = {
  * CPUSET Locking Convention
  * -------------------------
  *
- * Below are the three global locks guarding cpuset structures in lock
+ * Below are the four global/local locks guarding cpuset structures in lock
  * acquisition order:
+ *  - cpuset_top_mutex
  *  - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock)
  *  - cpuset_mutex
  *  - callback_lock (raw spinlock)
  *
- * A task must hold all the three locks to modify externally visible or
- * used fields of cpusets, though some of the internally used cpuset fields
+ * As cpuset will now indirectly flush a number of different workqueues in
+ * housekeeping_update() to update housekeeping cpumasks when the set of
+ * isolated CPUs is going to be changed, it may be vulnerable to deadlock
+ * if we hold cpus_read_lock while calling into housekeeping_update().
+ *
+ * The first cpuset_top_mutex will be held except when calling into
+ * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock
+ * and cpuset_mutex will be held instead. The main purpose of this mutex
+ * is to prevent regular cpuset control file write actions from interfering
+ * with the call to housekeeping_update(), though CPU hotplug operation can
+ * still happen in parallel. This mutex also provides protection for some
+ * internal variables.
+ *
+ * A task must hold all the remaining three locks to modify externally visible
+ * or used fields of cpusets, though some of the internally used cpuset fields
  * and internal variables can be modified without holding callback_lock. If only
  * reliable read access of the externally used fields are needed, a task can
  * hold either cpuset_mutex or callback_lock which are exposed to other
@@ -100,6 +114,7 @@ static const char * const perr_strings[] = {
  * cpumasks and nodemasks.
  */
 
+static DEFINE_MUTEX(cpuset_top_mutex);
 static DEFINE_MUTEX(cpuset_mutex);
 
 /*
@@ -111,6 +126,8 @@ static DEFINE_MUTEX(cpuset_mutex);
  *
  * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable
  *	 by holding both cpuset_mutex and callback_lock.
+ *
+ * T:	 Read/write-able by holding the cpuset_top_mutex.
  */
 
 /*
@@ -134,6 +151,11 @@ static cpumask_var_t	isolated_cpus;		/* CSCB */
  */
 static bool		update_housekeeping;	/* RWCS */
 
+/*
+ * Copy of isolated_cpus to be passed to housekeeping_update()
+ */
+static cpumask_var_t	isolated_hk_cpus;	/* T */
+
 /*
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
@@ -297,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void)
  */
 void cpuset_full_lock(void)
 {
+	mutex_lock(&cpuset_top_mutex);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 }
@@ -305,12 +328,14 @@ void cpuset_full_unlock(void)
 {
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
+	mutex_unlock(&cpuset_top_mutex);
 }
 
 #ifdef CONFIG_LOCKDEP
 bool lockdep_is_cpuset_held(void)
 {
-	return lockdep_is_held(&cpuset_mutex);
+	return lockdep_is_held(&cpuset_mutex) ||
+	       lockdep_is_held(&cpuset_top_mutex);
 }
 #endif
 
@@ -1315,9 +1340,20 @@ static void update_hk_sched_domains(void)
 {
 	if (update_housekeeping) {
 		/* Updating HK cpumasks implies rebuild sched domains */
-		WARN_ON_ONCE(housekeeping_update(isolated_cpus));
 		update_housekeeping = false;
 		force_sd_rebuild = true;
+		cpumask_copy(isolated_hk_cpus, isolated_cpus);
+
+		/*
+		 * housekeeping_update() is now called without holding
+		 * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex
+		 * is still being held for mutual exclusion.
+		 */
+		mutex_unlock(&cpuset_mutex);
+		cpus_read_unlock();
+		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
+		cpus_read_lock();
+		mutex_lock(&cpuset_mutex);
 	}
 	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
 	if (force_sd_rebuild)
@@ -3635,6 +3671,7 @@ int __init cpuset_init(void)
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 3b725d39c06e..ef152d401fe2 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask)
 	struct cpumask *trial, *old = NULL;
 	int err;
 
-	lockdep_assert_cpus_held();
-
 	trial = kmalloc(cpumask_size(), GFP_KERNEL);
 	if (!trial)
 		return -ENOMEM;
@@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask)
 	}
 
 	if (!housekeeping.flags)
-		static_branch_enable_cpuslocked(&housekeeping_overridden);
+		static_branch_enable(&housekeeping_overridden);
 
 	if (housekeeping.flags & HK_FLAG_DOMAIN)
 		old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN);
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 6da9cd562b20..83428aa03aef 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
 	int cpu;
 
-	lockdep_assert_cpus_held();
-
 	if (!works)
 		return -ENOMEM;
 	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
@@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	 * First set previously isolated CPUs as available (unisolate).
 	 * This cpumask contains only CPUs that switched to available now.
 	 */
+	guard(cpus_read_lock)();
 	cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask);
 	cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask);
 
@@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void)
 	cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 	/* Protect against RCU torture hotplug testing */
-	guard(cpus_read_lock)();
 	return tmigr_isolated_exclude_cpumask(cpumask);
 }
 late_initcall(tmigr_init_isolation);

From 7cff9a40c6b0f72ccefdaf0ffe03cfac30348f51 Mon Sep 17 00:00:00 2001
From: Mariusz Skamra <mariusz.skamra@codecoup.pl>
Date: Thu, 12 Feb 2026 14:46:46 +0100
Subject: [PATCH 0244/1303] Bluetooth: Fix CIS host feature condition

This fixes the condition for sending the LE Set Host Feature command.
The command is sent to indicate host support for Connected Isochronous
Streams in this case. It has been observed that the system could not
initialize BIS-only capable controllers because the controllers do not
support the command.

As per Core v6.2 | Vol 4, Part E, Table 3.1 the command shall be
supported if CIS Central or CIS Peripheral is supported; otherwise,
the command is optional.

Fixes: 709788b154ca ("Bluetooth: hci_core: Fix using {cis,bis}_capable for current settings")
Cc: stable@vger.kernel.org
Signed-off-by: Mariusz Skamra <mariusz.skamra@codecoup.pl>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index f04a90bce4a9..0b0dc0965f5a 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4592,7 +4592,7 @@ static int hci_le_set_host_features_sync(struct hci_dev *hdev)
 {
 	int err;
 
-	if (iso_capable(hdev)) {
+	if (cis_capable(hdev)) {
 		/* Connected Isochronous Channels (Host Support) */
 		err = hci_le_set_host_feature_sync(hdev, 32,
 						   (iso_enabled(hdev) ? 0x01 :

From a8d1d73c81d1e70d2aa49fdaf59d933bb783ffe5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 17 Feb 2026 13:29:43 -0500
Subject: [PATCH 0245/1303] Bluetooth: L2CAP: Fix not checking output MTU is
 acceptable on L2CAP_ECRED_CONN_REQ

Upon receiving L2CAP_ECRED_CONN_REQ the given MTU shall be checked
against the suggested MTU of the listening socket as that is required
by the likes of PTS L2CAP/ECFC/BV-27-C test which expects
L2CAP_CR_LE_UNACCEPT_PARAMS if the MTU is lowers than socket omtu.

In order to be able to set chan->omtu the code now allows setting
setsockopt(BT_SNDMTU), but it is only allowed when connection has not
been stablished since there is no procedure to reconfigure the output
MTU.

Link: https://github.com/bluez/bluez/issues/1895
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c |  8 ++++++++
 net/bluetooth/l2cap_sock.c | 15 +++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9452c6179acb..90676ca0e92b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5117,6 +5117,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		goto unlock;
 	}
 
+	/* Check if the listening channel has set an output MTU then the
+	 * requested MTU shall be less than or equal to that value.
+	 */
+	if (pchan->omtu && mtu < pchan->omtu) {
+		result = L2CAP_CR_LE_UNACCEPT_PARAMS;
+		goto unlock;
+	}
+
 	result = L2CAP_CR_LE_SUCCESS;
 
 	for (i = 0; i < num_scid; i++) {
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 62ceda979f39..477b4d145459 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1029,10 +1029,17 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		/* Setting is not supported as it's the remote side that
-		 * decides this.
-		 */
-		err = -EPERM;
+		/* Only allow setting output MTU when not connected */
+		if (sk->sk_state == BT_CONNECTED) {
+			err = -EISCONN;
+			break;
+		}
+
+		err = copy_safe_from_sockptr(&mtu, sizeof(mtu), optval, optlen);
+		if (err)
+			break;
+
+		chan->omtu = mtu;
 		break;
 
 	case BT_RCVMTU:

From 138d7eca445ef37a0333425d269ee59900ca1104 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 13 Feb 2026 13:33:33 -0500
Subject: [PATCH 0246/1303] Bluetooth: L2CAP: Fix missing key size check for
 L2CAP_LE_CONN_REQ

This adds a check for encryption key size upon receiving
L2CAP_LE_CONN_REQ which is required by L2CAP/LE/CFC/BV-15-C which
expects L2CAP_CR_LE_BAD_KEY_SIZE.

Link: https://lore.kernel.org/linux-bluetooth/5782243.rdbgypaU67@n9w6sw14/
Fixes: 27e2d4c8d28b ("Bluetooth: Add basic LE L2CAP connect request receiving support")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Tested-by: Christian Eggers <ceggers@arri.de>
---
 net/bluetooth/l2cap_core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 90676ca0e92b..2dcc5bb907b8 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4916,6 +4916,13 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 		goto response_unlock;
 	}
 
+	/* Check if Key Size is sufficient for the security level */
+	if (!l2cap_check_enc_key_size(conn->hcon, pchan)) {
+		result = L2CAP_CR_LE_BAD_KEY_SIZE;
+		chan = NULL;
+		goto response_unlock;
+	}
+
 	/* Check for valid dynamic CID range */
 	if (scid < L2CAP_CID_DYN_START || scid > L2CAP_CID_LE_DYN_END) {
 		result = L2CAP_CR_LE_INVALID_SCID;

From 1bfd7575092420ba5a0b944953c95b74a5646ff8 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 19 Feb 2026 23:35:18 +0000
Subject: [PATCH 0247/1303] drm/xe/sync: Cleanup partially initialized sync on
 parse failure

xe_sync_entry_parse() can allocate references (syncobj, fence, chain fence,
or user fence) before hitting a later failure path. Several of those paths
returned directly, leaving partially initialized state and leaking refs.

Route these error paths through a common free_sync label and call
xe_sync_entry_cleanup(sync) before returning the error.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260219233516.2938172-5-shuicheng.lin@intel.com
(cherry picked from commit f939bdd9207a5d1fc55cced5459858480686ce22)
Cc: stable@vger.kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sync.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index eb136390dafd..ebf6c96d7a41 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -146,8 +146,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 
 		if (!signal) {
 			sync->fence = drm_syncobj_fence_get(sync->syncobj);
-			if (XE_IOCTL_DBG(xe, !sync->fence))
-				return -EINVAL;
+			if (XE_IOCTL_DBG(xe, !sync->fence)) {
+				err = -EINVAL;
+				goto free_sync;
+			}
 		}
 		break;
 
@@ -167,17 +169,21 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 
 		if (signal) {
 			sync->chain_fence = dma_fence_chain_alloc();
-			if (!sync->chain_fence)
-				return -ENOMEM;
+			if (!sync->chain_fence) {
+				err = -ENOMEM;
+				goto free_sync;
+			}
 		} else {
 			sync->fence = drm_syncobj_fence_get(sync->syncobj);
-			if (XE_IOCTL_DBG(xe, !sync->fence))
-				return -EINVAL;
+			if (XE_IOCTL_DBG(xe, !sync->fence)) {
+				err = -EINVAL;
+				goto free_sync;
+			}
 
 			err = dma_fence_chain_find_seqno(&sync->fence,
 							 sync_in.timeline_value);
 			if (err)
-				return err;
+				goto free_sync;
 		}
 		break;
 
@@ -216,6 +222,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 	sync->timeline_value = sync_in.timeline_value;
 
 	return 0;
+
+free_sync:
+	xe_sync_entry_cleanup(sync);
+	return err;
 }
 ALLOW_ERROR_INJECTION(xe_sync_entry_parse, ERRNO);
 

From 0879c3f04f67e2a1677c25dcc24669ce21eb6a6c Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 19 Feb 2026 23:35:19 +0000
Subject: [PATCH 0248/1303] drm/xe/sync: Fix user fence leak on alloc failure

When dma_fence_chain_alloc() fails, properly release the user fence
reference to prevent a memory leak.

Fixes: 0995c2fc39b0 ("drm/xe: Enforce correct user fence signaling order using")
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260219233516.2938172-6-shuicheng.lin@intel.com
(cherry picked from commit a5d5634cde48a9fcd68c8504aa07f89f175074a0)
Cc: stable@vger.kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sync.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index ebf6c96d7a41..24d6d9af20d6 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -206,8 +206,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
 				return PTR_ERR(sync->ufence);
 			sync->ufence_chain_fence = dma_fence_chain_alloc();
-			if (!sync->ufence_chain_fence)
-				return -ENOMEM;
+			if (!sync->ufence_chain_fence) {
+				err = -ENOMEM;
+				goto free_sync;
+			}
 			sync->ufence_syncobj = ufence_syncobj;
 		}
 

From 96a7b71c4438d3b72d6c95e3efdc9e8e8aee6b78 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 23 Feb 2026 13:43:45 -0800
Subject: [PATCH 0249/1303] ubd: Use pointer-to-pointers for io_thread_req
 arrays

Having an unbounded array for irq_req_buffer and io_req_buffer doesn't
provide any bounds safety, and confuses the needed allocation type,
which is returning a pointer to pointers. Instead of the implicit cast,
switch the variable types.

Reported-by: Nathan Chancellor <nathan@kernel.org>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/all/b04b6c13-7d0e-4a89-9e68-b572b6c686ac@roeck-us.net
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Acked-by: Richard Weinberger <richard@nod.at>
Link: https://patch.msgid.link/20260223214341.work.846-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/um/drivers/ubd_kern.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 012b2bcaa8a0..20fc33300a95 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -69,11 +69,11 @@ struct io_thread_req {
 };
 
 
-static struct io_thread_req * (*irq_req_buffer)[];
+static struct io_thread_req **irq_req_buffer;
 static struct io_thread_req *irq_remainder;
 static int irq_remainder_size;
 
-static struct io_thread_req * (*io_req_buffer)[];
+static struct io_thread_req **io_req_buffer;
 static struct io_thread_req *io_remainder;
 static int io_remainder_size;
 
@@ -398,7 +398,7 @@ static int thread_fd = -1;
 
 static int bulk_req_safe_read(
 	int fd,
-	struct io_thread_req * (*request_buffer)[],
+	struct io_thread_req **request_buffer,
 	struct io_thread_req **remainder,
 	int *remainder_size,
 	int max_recs
@@ -465,7 +465,7 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 			&irq_remainder, &irq_remainder_size,
 			UBD_REQ_BUFFER_SIZE)) >= 0) {
 		for (i = 0; i < len / sizeof(struct io_thread_req *); i++)
-			ubd_end_request((*irq_req_buffer)[i]);
+			ubd_end_request(irq_req_buffer[i]);
 	}
 
 	if (len < 0 && len != -EAGAIN)
@@ -1512,7 +1512,7 @@ void *io_thread(void *arg)
 		}
 
 		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
-			struct io_thread_req *req = (*io_req_buffer)[count];
+			struct io_thread_req *req = io_req_buffer[count];
 			int i;
 
 			io_count++;

From f709859f331b8fbd7fede5769d668008fc5ba789 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 23 Feb 2026 11:23:12 -0700
Subject: [PATCH 0250/1303] init/Kconfig: Adjust fixed clang version for
 __builtin_counted_by_ref

Commit d39a1d7486d9 ("compiler_types: Disable __builtin_counted_by_ref
for Clang") used 22.0.0 as the fixed version for a compiler crash but
the fix was only merged in main (23.0.0) and release/22.x (22.1.0). With
the current fixed version number, prerelease or Android LLVM 22 builds
will still be able to hit the compiler crash when building the kernel.
This can be particularly disruptive when bisecting LLVM.

Use 21.1.0 as the fixed version number to ensure the fix for this crash
is always present.

Fixes: d39a1d7486d9 ("compiler_types: Disable __builtin_counted_by_ref for Clang")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20260223-fix-clang-version-builtin-counted-by-ref-v1-1-3ea478a24f0a@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index c25869cf59c1..b55deae9256c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -153,7 +153,7 @@ config CC_HAS_COUNTED_BY_PTR
 config CC_HAS_BROKEN_COUNTED_BY_REF
 	bool
 	# https://github.com/llvm/llvm-project/issues/182575
-	default y if CC_IS_CLANG && CLANG_VERSION < 220000
+	default y if CC_IS_CLANG && CLANG_VERSION < 220100
 
 config CC_HAS_MULTIDIMENSIONAL_NONSTRING
 	def_bool $(success,echo 'char tag[][4] __attribute__((__nonstring__)) = { };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror)

From a9dece60cc8246e5fc4c46d391272024bf1d309d Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Sat, 24 Jan 2026 06:32:56 +0530
Subject: [PATCH 0251/1303] drm/msm/adreno: Add GPU to MODULE_DEVICE_TABLE

Since it is possible to independently probe Adreno GPU, add GPU match
table to MODULE_DEVICE_TABLE to allow auto-loading of msm module.

Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/700656/
Link: https://lore.kernel.org/r/20260124-adreno-module-table-v1-1-9c2dbb2638b4@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 554d746f115b..4edfe80c5be7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -302,6 +302,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,kgsl-3d0" },
 	{}
 };
+MODULE_DEVICE_TABLE(of, dt_match);
 
 static int adreno_runtime_resume(struct device *dev)
 {

From f7bf1319739291067b2bc4b22bd56336afad8f0a Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Tue, 27 Jan 2026 11:58:49 +0100
Subject: [PATCH 0252/1303] drm/msm/dpu: Fix LM size on a number of platforms

The register space has grown with what seems to be DPU8.
Bump up the .len to match.

Fixes: e3b1f369db5a ("drm/msm/dpu: Add X1E80100 support")
Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP")
Fixes: efcd0107727c ("drm/msm/dpu: add support for SM8550")
Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450")
Fixes: 178575173472 ("drm/msm/dpu: add catalog entry for SAR2130P")
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/701063/
Link: https://lore.kernel.org/r/20260127-topic-lm_size_fix-v1-1-25f88d014dfd@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 .../gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------
 .../gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h   | 12 ++++++------
 .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h   | 12 ++++++------
 .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h | 12 ++++++------
 .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h | 12 ++++++------
 5 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
index 303d33dc7783..9f2bceca1789 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
@@ -133,7 +133,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = {
 static const struct dpu_lm_cfg sc8280xp_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -141,7 +141,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -149,7 +149,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -157,7 +157,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -165,14 +165,14 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
index b09a6af4c474..04b22167f93d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
@@ -134,7 +134,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 static const struct dpu_lm_cfg sm8450_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -142,7 +142,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -150,7 +150,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -158,7 +158,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -166,14 +166,14 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
index 465b6460f875..4c7eb55d474c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
@@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 static const struct dpu_lm_cfg sm8550_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
index 6caa7d40f368..dec83ea8167d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
@@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sar2130p_sspp[] = {
 static const struct dpu_lm_cfg sar2130p_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
index 7243eebb85f3..52ff4baa668a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
@@ -130,7 +130,7 @@ static const struct dpu_sspp_cfg x1e80100_sspp[] = {
 static const struct dpu_lm_cfg x1e80100_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -138,7 +138,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -146,7 +146,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -154,7 +154,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -162,14 +162,14 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,

From 6f6f3535192dd597c5326ea5456ae3bafc7d43b2 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 6 Feb 2026 14:21:52 -0800
Subject: [PATCH 0253/1303] drm/msm: Adjust
 msm_iommu_pagetable_prealloc_allocate() allocation type

In preparation for making the kmalloc family of allocators type aware,
we need to make sure that the returned type from the allocation matches
the type of the variable being assigned. (Before, the allocator would
always return "void *", which can be implicitly cast to any pointer type.)

The assigned type is "void **" but the returned type will be "void ***".
These are the same allocation size (pointer size), but the types do not
match. Adjust the allocation type to match the assignment.

Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/703588/
Link: https://lore.kernel.org/r/20260206222151.work.016-kees@kernel.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index d5dede4ff761..271baf4dc4e8 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -332,7 +332,7 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall
 	struct kmem_cache *pt_cache = get_pt_cache(mmu);
 	int ret;
 
-	p->pages = kvmalloc_array(p->count, sizeof(p->pages), GFP_KERNEL);
+	p->pages = kvmalloc_array(p->count, sizeof(*p->pages), GFP_KERNEL);
 	if (!p->pages)
 		return -ENOMEM;
 

From b1dcc804f4662256a3e4bd8ac182a7a2c9464723 Mon Sep 17 00:00:00 2001
From: sunliming <sunliming@kylinos.cn>
Date: Fri, 30 Jan 2026 13:36:15 +0800
Subject: [PATCH 0254/1303] drm/msm/dpu: Fix smatch warnings about variable
 dereferenced before check

Fix below smatch warnings:
drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c:161 dpu_hw_sspp_setup_pe_config_v13()
warn: variable dereferenced before check 'ctx' (see line 159)

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601252214.oEaY3UZM-lkp@intel.com/
Signed-off-by: sunliming <sunliming@kylinos.cn>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/701853/
Link: https://lore.kernel.org/r/20260130053615.24886-1-sunliming@linux.dev
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
index e65f1fc026fd..f8f96ad971d7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
@@ -156,11 +156,13 @@ static void dpu_hw_sspp_setup_pe_config_v13(struct dpu_hw_sspp *ctx,
 	u8 color;
 	u32 lr_pe[4], tb_pe[4];
 	const u32 bytemask = 0xff;
-	u32 offset = ctx->cap->sblk->sspp_rec0_blk.base;
+	u32 offset;
 
 	if (!ctx || !pe_ext)
 		return;
 
+	offset = ctx->cap->sblk->sspp_rec0_blk.base;
+
 	c = &ctx->hw;
 	/* program SW pixel extension override for all pipes*/
 	for (color = 0; color < DPU_MAX_PLANES; color++) {

From 9f593419eb42c68f31829aed3c199591190bfe5d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Sat, 14 Feb 2026 01:02:59 +0200
Subject: [PATCH 0255/1303] Revert "drm/msm/dpu: try reserving the DSPP-less LM
 first"

This reverts commit 42f62cd79578 ("drm/msm/dpu: try reserving the
DSPP-less LM first"). It seems on later DPUs using higher LMs require
some additional setup or conflicts with the hardware defaults. Val (and
other developers) reported blue screen on Hamoa (X1E80100) laptops.
Revert the offending commit until we understand, what is the issue.

Fixes: 42f62cd79578 ("drm/msm/dpu: try reserving the DSPP-less LM first")
Reported-by: Val Packett <val@packett.cool>
Closes: https://lore.kernel.org/r/33424a9d-10a6-4479-bba6-12f8ce60da1a@packett.cool
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Tested-by: Manivannan Sadhasivam <mani@kernel.org> # T14s
Patchwork: https://patchwork.freedesktop.org/patch/704814/
Link: https://lore.kernel.org/r/20260214-revert-dspp-less-v1-1-be0d636a2a6e@oss.qualcomm.com
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 52 +++++++-------------------
 1 file changed, 14 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index 451a4fcf3e65..7e77d88f8959 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -350,26 +350,28 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm,
 	return true;
 }
 
-static bool dpu_rm_find_lms(struct dpu_rm *rm,
-			    struct dpu_global_state *global_state,
-			    uint32_t crtc_id, bool skip_dspp,
-			    struct msm_display_topology *topology,
-			    int *lm_idx, int *pp_idx, int *dspp_idx)
+static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
+			       struct dpu_global_state *global_state,
+			       uint32_t crtc_id,
+			       struct msm_display_topology *topology)
 
 {
+	int lm_idx[MAX_BLOCKS];
+	int pp_idx[MAX_BLOCKS];
+	int dspp_idx[MAX_BLOCKS] = {0};
 	int i, lm_count = 0;
 
+	if (!topology->num_lm) {
+		DPU_ERROR("zero LMs in topology\n");
+		return -EINVAL;
+	}
+
 	/* Find a primary mixer */
 	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) &&
 			lm_count < topology->num_lm; i++) {
 		if (!rm->mixer_blks[i])
 			continue;
 
-		if (skip_dspp && to_dpu_hw_mixer(rm->mixer_blks[i])->cap->dspp) {
-			DPU_DEBUG("Skipping LM_%d, skipping LMs with DSPPs\n", i);
-			continue;
-		}
-
 		/*
 		 * Reset lm_count to an even index. This will drop the previous
 		 * primary mixer if failed to find its peer.
@@ -408,38 +410,12 @@ static bool dpu_rm_find_lms(struct dpu_rm *rm,
 		}
 	}
 
-	return lm_count == topology->num_lm;
-}
-
-static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
-			       struct dpu_global_state *global_state,
-			       uint32_t crtc_id,
-			       struct msm_display_topology *topology)
-
-{
-	int lm_idx[MAX_BLOCKS];
-	int pp_idx[MAX_BLOCKS];
-	int dspp_idx[MAX_BLOCKS] = {0};
-	int i;
-	bool found;
-
-	if (!topology->num_lm) {
-		DPU_ERROR("zero LMs in topology\n");
-		return -EINVAL;
-	}
-
-	/* Try using non-DSPP LM blocks first */
-	found = dpu_rm_find_lms(rm, global_state, crtc_id, !topology->num_dspp,
-				topology, lm_idx, pp_idx, dspp_idx);
-	if (!found && !topology->num_dspp)
-		found = dpu_rm_find_lms(rm, global_state, crtc_id, false,
-					topology, lm_idx, pp_idx, dspp_idx);
-	if (!found) {
+	if (lm_count != topology->num_lm) {
 		DPU_DEBUG("unable to find appropriate mixers\n");
 		return -ENAVAIL;
 	}
 
-	for (i = 0; i < topology->num_lm; i++) {
+	for (i = 0; i < lm_count; i++) {
 		global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id;
 		global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id;
 		global_state->dspp_to_crtc_id[dspp_idx[i]] =

From 5886cc8f895bf578903eb681fca9123065e1012e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 23 Feb 2026 08:16:55 +0100
Subject: [PATCH 0256/1303] drm/msm/dpu: Don't use %pK through printk (again)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past %pK was preferable to %p as it would not leak raw pointer
values into the kernel log.
Since commit ad67b74d2469 ("printk: hash addresses printed with %p")
the regular %p has been improved to avoid this issue.
Furthermore, restricted pointers ("%pK") were never meant to be used
through printk(). They can still unintentionally leak raw pointers or
acquire sleeping locks in atomic contexts.

Switch to the regular pointer formatting which is safer and
easier to reason about.

This was previously fixed in this driver in commit 1ba9fbe40337
("drm/msm: Don't use %pK through printk") but an additional usage
was reintroduced in commit 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC
driver to provide GAMMA_LUT DRM property")

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Fixes: 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC driver to provide GAMMA_LUT DRM property")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/706229/
Link: https://lore.kernel.org/r/20260223-restricted-pointers-msm-v1-1-14c0b451e372@linutronix.de
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
index 188ee0af2c90..23dcbe1ce1b8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
@@ -89,7 +89,7 @@ static void dpu_setup_dspp_gc(struct dpu_hw_dspp *ctx,
 	base = ctx->cap->sblk->gc.base;
 
 	if (!base) {
-		DRM_ERROR("invalid ctx %pK gc base\n", ctx);
+		DRM_ERROR("invalid ctx %p gc base\n", ctx);
 		return;
 	}
 

From eddb98ad9364b4e778768785d46cfab04ce52100 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 20 Feb 2026 13:43:00 +0900
Subject: [PATCH 0257/1303] ata: libata-eh: correctly handle deferred qc
 timeouts

A deferred qc may timeout while waiting for the device queue to drain
to be submitted. In such case, since the qc is not active,
ata_scsi_cmd_error_handler() ends up calling scsi_eh_finish_cmd(),
which frees the qc. But as the port deferred_qc field still references
this finished/freed qc, the deferred qc work may eventually attempt to
call ata_qc_issue() against this invalid qc, leading to errors such as
reported by UBSAN (syzbot run):

UBSAN: shift-out-of-bounds in drivers/ata/libata-core.c:5166:24
shift exponent 4210818301 is too large for 64-bit type 'long long unsigned int'
...
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x100/0x190 lib/dump_stack.c:120
 ubsan_epilogue+0xa/0x30 lib/ubsan.c:233
 __ubsan_handle_shift_out_of_bounds+0x279/0x2a0 lib/ubsan.c:494
 ata_qc_issue.cold+0x38/0x9f drivers/ata/libata-core.c:5166
 ata_scsi_deferred_qc_work+0x154/0x1f0 drivers/ata/libata-scsi.c:1679
 process_one_work+0x9d7/0x1920 kernel/workqueue.c:3275
 process_scheduled_works kernel/workqueue.c:3358 [inline]
 worker_thread+0x5da/0xe40 kernel/workqueue.c:3439
 kthread+0x370/0x450 kernel/kthread.c:467
 ret_from_fork+0x754/0xd80 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

Fix this by checking if the qc of a timed out SCSI command is a deferred
one, and in such case, clear the port deferred_qc field and finish the
SCSI command with DID_TIME_OUT.

Reported-by: syzbot+1f77b8ca15336fff21ff@syzkaller.appspotmail.com
Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
---
 drivers/ata/libata-eh.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 72a22b6c9682..b373cceb95d2 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -640,12 +640,28 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		set_host_byte(scmd, DID_OK);
 
 		ata_qc_for_each_raw(ap, qc, i) {
-			if (qc->flags & ATA_QCFLAG_ACTIVE &&
-			    qc->scsicmd == scmd)
+			if (qc->scsicmd != scmd)
+				continue;
+			if ((qc->flags & ATA_QCFLAG_ACTIVE) ||
+			    qc == ap->deferred_qc)
 				break;
 		}
 
-		if (i < ATA_MAX_QUEUE) {
+		if (qc == ap->deferred_qc) {
+			/*
+			 * This is a deferred command that timed out while
+			 * waiting for the command queue to drain. Since the qc
+			 * is not active yet (deferred_qc is still set, so the
+			 * deferred qc work has not issued the command yet),
+			 * simply signal the timeout by finishing the SCSI
+			 * command and clear the deferred qc to prevent the
+			 * deferred qc work from issuing this qc.
+			 */
+			WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE);
+			ap->deferred_qc = NULL;
+			set_host_byte(scmd, DID_TIME_OUT);
+			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
+		} else if (i < ATA_MAX_QUEUE) {
 			/* the scmd has an associated qc */
 			if (!(qc->flags & ATA_QCFLAG_EH)) {
 				/* which hasn't failed yet, timeout */

From 55db009926634b20955bd8abbee921adbc8d2cb4 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 20 Feb 2026 12:09:12 +0900
Subject: [PATCH 0258/1303] ata: libata-core: fix cancellation of a port
 deferred qc work

cancel_work_sync() is a sleeping function so it cannot be called with
the spin lock of a port being held. Move the call to this function in
ata_port_detach() after EH completes, with the port lock released,
together with other work cancellation calls.

Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
---
 drivers/ata/libata-core.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 11909417f017..ccbf320524da 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6269,10 +6269,6 @@ static void ata_port_detach(struct ata_port *ap)
 		}
 	}
 
-	/* Make sure the deferred qc work finished. */
-	cancel_work_sync(&ap->deferred_qc_work);
-	WARN_ON(ap->deferred_qc);
-
 	/* Tell EH to disable all devices */
 	ap->pflags |= ATA_PFLAG_UNLOADING;
 	ata_port_schedule_eh(ap);
@@ -6283,9 +6279,11 @@ static void ata_port_detach(struct ata_port *ap)
 	/* wait till EH commits suicide */
 	ata_port_wait_eh(ap);
 
-	/* it better be dead now */
+	/* It better be dead now and not have any remaining deferred qc. */
 	WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED));
+	WARN_ON(ap->deferred_qc);
 
+	cancel_work_sync(&ap->deferred_qc_work);
 	cancel_delayed_work_sync(&ap->hotplug_task);
 	cancel_delayed_work_sync(&ap->scsi_rescan_task);
 

From 41e09ec73d7431dffda01b1e7208a272a5c90fb9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 20 Feb 2026 17:18:58 -0800
Subject: [PATCH 0259/1303] MAINTAINERS: include all of framer under pef2256

The "framer" infrastructure only has one driver - pef2256
and is not covered by any MAINTAINERS entry of its own.
This leads to author not being CCed on patches.
Let's include all of framer/ under the pef2256 entry.
We can split it in the very unlikely event of another
driver appearing.

Link: https://lore.kernel.org/aZefB5f3EAkQQM1m@google.com
Acked-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260221011858.3403605-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c00b5f5d4203..e1a6c6cc2b7c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14410,9 +14410,9 @@ LANTIQ PEF2256 DRIVER
 M:	Herve Codina <herve.codina@bootlin.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/lantiq,pef2256.yaml
-F:	drivers/net/wan/framer/pef2256/
+F:	drivers/net/wan/framer/
 F:	drivers/pinctrl/pinctrl-pef2256.c
-F:	include/linux/framer/pef2256.h
+F:	include/linux/framer/
 
 LASI 53c700 driver for PARISC
 M:	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>

From 8a8a9fac9efa6423fd74938b940cb7d731780718 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Feb 2026 22:26:05 +0000
Subject: [PATCH 0260/1303] net: do not pass flow_id to set_rps_cpu()

Blamed commit made the assumption that the RPS table for each receive
queue would have the same size, and that it would not change.

Compute flow_id in set_rps_cpu(), do not assume we can use the value
computed by get_rps_cpu(). Otherwise we risk out-of-bound access
and/or crashes.

Fixes: 48aa30443e52 ("net: Cache hash and flow_id to avoid recalculation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Krishna Kumar <krikku@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260220222605.3468081-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 096b3ff13f6b..f3426385f1ba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4992,8 +4992,7 @@ static bool rps_flow_is_active(struct rps_dev_flow *rflow,
 
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
-	    struct rps_dev_flow *rflow, u16 next_cpu, u32 hash,
-	    u32 flow_id)
+	    struct rps_dev_flow *rflow, u16 next_cpu, u32 hash)
 {
 	if (next_cpu < nr_cpu_ids) {
 		u32 head;
@@ -5004,6 +5003,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		struct rps_dev_flow *tmp_rflow;
 		unsigned int tmp_cpu;
 		u16 rxq_index;
+		u32 flow_id;
 		int rc;
 
 		/* Should we steer this flow to a different hardware queue? */
@@ -5019,6 +5019,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (!flow_table)
 			goto out;
 
+		flow_id = rfs_slot(hash, flow_table);
 		tmp_rflow = &flow_table->flows[flow_id];
 		tmp_cpu = READ_ONCE(tmp_rflow->cpu);
 
@@ -5066,7 +5067,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_map *map;
 	int cpu = -1;
-	u32 flow_id;
 	u32 tcpu;
 	u32 hash;
 
@@ -5113,8 +5113,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		/* OK, now we know there is a match,
 		 * we can look at the local (per receive queue) flow table
 		 */
-		flow_id = rfs_slot(hash, flow_table);
-		rflow = &flow_table->flows[flow_id];
+		rflow = &flow_table->flows[rfs_slot(hash, flow_table)];
 		tcpu = rflow->cpu;
 
 		/*
@@ -5133,8 +5132,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		     ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
-			rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash,
-					    flow_id);
+			rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash);
 		}
 
 		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {

From 7bb09315f93dce6acc54bf59e5a95ba7365c2be4 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 20 Feb 2026 18:40:36 +0900
Subject: [PATCH 0261/1303] tls: Fix race condition in tls_sw_cancel_work_tx()

This issue was discovered during a code audit.

After cancel_delayed_work_sync() is called from tls_sk_proto_close(),
tx_work_handler() can still be scheduled from paths such as the
Delayed ACK handler or ksoftirqd.
As a result, the tx_work_handler() worker may dereference a freed
TLS object.

The following is a simple race scenario:

          cpu0                         cpu1

tls_sk_proto_close()
  tls_sw_cancel_work_tx()
                                 tls_write_space()
                                   tls_sw_write_space()
                                     if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
    set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
    cancel_delayed_work_sync(&ctx->tx_work.work);
                                     schedule_delayed_work(&tx_ctx->tx_work.work, 0);

To prevent this race condition, cancel_delayed_work_sync() is
replaced with disable_delayed_work_sync().

Fixes: f87e62d45e51 ("net/tls: remove close callback sock unlock/lock around TX work flush")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/aZgsFO6nfylfvLE7@v4bel
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9937d4c810f2..b1fa62de9dab 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2533,7 +2533,7 @@ void tls_sw_cancel_work_tx(struct tls_context *tls_ctx)
 
 	set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask);
 	set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
-	cancel_delayed_work_sync(&ctx->tx_work.work);
+	disable_delayed_work_sync(&ctx->tx_work.work);
 }
 
 void tls_sw_release_resources_tx(struct sock *sk)

From fb868db5f4bccd7a78219313ab2917429f715cea Mon Sep 17 00:00:00 2001
From: Ankit Garg <nktgrg@google.com>
Date: Fri, 20 Feb 2026 13:53:24 -0800
Subject: [PATCH 0262/1303] gve: fix incorrect buffer cleanup in
 gve_tx_clean_pending_packets for QPL

In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA
buffer cleanup path. It iterates num_bufs times and attempts to unmap
entries in the dma array.

This leads to two issues:
1. The dma array shares storage with tx_qpl_buf_ids (union).
 Interpreting buffer IDs as DMA addresses results in attempting to
 unmap incorrect memory locations.
2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed
 the size of the dma array, causing out-of-bounds access warnings
(trace below is how we noticed this issue).

UBSAN: array-index-out-of-bounds in
drivers/net/ethernet/drivers/net/ethernet/google/gve/gve_tx_dqo.c:178:5 index 18 is out of
range for type 'dma_addr_t[18]' (aka 'unsigned long long[18]')
Workqueue: gve gve_service_task [gve]
Call Trace:
<TASK>
dump_stack_lvl+0x33/0xa0
__ubsan_handle_out_of_bounds+0xdc/0x110
gve_tx_stop_ring_dqo+0x182/0x200 [gve]
gve_close+0x1be/0x450 [gve]
gve_reset+0x99/0x120 [gve]
gve_service_task+0x61/0x100 [gve]
process_scheduled_works+0x1e9/0x380

Fix this by properly checking for QPL mode and delegating to
gve_free_tx_qpl_bufs() to reclaim the buffers.

Cc: stable@vger.kernel.org
Fixes: a6fb8d5a8b69 ("gve: Tx path for DQO-QPL")
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Jordan Rhee <jordanrhee@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220215324.1631350-1-joshwash@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_tx_dqo.c | 54 +++++++++-----------
 1 file changed, 24 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 28e85730f785..b57e8f13cb51 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -167,6 +167,25 @@ gve_free_pending_packet(struct gve_tx_ring *tx,
 	}
 }
 
+static void gve_unmap_packet(struct device *dev,
+			     struct gve_tx_pending_packet_dqo *pkt)
+{
+	int i;
+
+	if (!pkt->num_bufs)
+		return;
+
+	/* SKB linear portion is guaranteed to be mapped */
+	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
+			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
+	for (i = 1; i < pkt->num_bufs; i++) {
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
+	}
+	pkt->num_bufs = 0;
+}
+
 /* gve_tx_free_desc - Cleans up all pending tx requests and buffers.
  */
 static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
@@ -176,21 +195,12 @@ static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
 	for (i = 0; i < tx->dqo.num_pending_packets; i++) {
 		struct gve_tx_pending_packet_dqo *cur_state =
 			&tx->dqo.pending_packets[i];
-		int j;
 
-		for (j = 0; j < cur_state->num_bufs; j++) {
-			if (j == 0) {
-				dma_unmap_single(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			} else {
-				dma_unmap_page(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			}
-		}
+		if (tx->dqo.qpl)
+			gve_free_tx_qpl_bufs(tx, cur_state);
+		else
+			gve_unmap_packet(tx->dev, cur_state);
+
 		if (cur_state->skb) {
 			dev_consume_skb_any(cur_state->skb);
 			cur_state->skb = NULL;
@@ -1157,22 +1167,6 @@ static void remove_from_list(struct gve_tx_ring *tx,
 	}
 }
 
-static void gve_unmap_packet(struct device *dev,
-			     struct gve_tx_pending_packet_dqo *pkt)
-{
-	int i;
-
-	/* SKB linear portion is guaranteed to be mapped */
-	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
-			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
-	for (i = 1; i < pkt->num_bufs; i++) {
-		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
-					    dma_unmap_len(pkt, len[i]),
-					    DMA_TO_DEVICE, 0);
-	}
-	pkt->num_bufs = 0;
-}
-
 /* Completion types and expected behavior:
  * No Miss compl + Packet compl = Packet completed normally.
  * Miss compl + Re-inject compl = Packet completed normally.

From ca220141fa8ebae09765a242076b2b77338106b0 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 19 Feb 2026 09:42:51 +0800
Subject: [PATCH 0263/1303] kcm: fix zero-frag skb in frag_list on partial
 sendmsg error

Syzkaller reported a warning in kcm_write_msgs() when processing a
message with a zero-fragment skb in the frag_list.

When kcm_sendmsg() fills MAX_SKB_FRAGS fragments in the current skb,
it allocates a new skb (tskb) and links it into the frag_list before
copying data. If the copy subsequently fails (e.g. -EFAULT from
user memory), tskb remains in the frag_list with zero fragments:

  head skb (msg being assembled, NOT yet in sk_write_queue)
  +-----------+
  | frags[17] |  (MAX_SKB_FRAGS, all filled with data)
  | frag_list-+--> tskb
  +-----------+    +----------+
                   | frags[0] |  (empty! copy failed before filling)
                   +----------+

For SOCK_SEQPACKET with partial data already copied, the error path
saves this message via partial_message for later completion. For
SOCK_SEQPACKET, sock_write_iter() automatically sets MSG_EOR, so a
subsequent zero-length write(fd, NULL, 0) completes the message and
queues it to sk_write_queue. kcm_write_msgs() then walks the
frag_list and hits:

  WARN_ON(!skb_shinfo(skb)->nr_frags)

TCP has a similar pattern where skbs are enqueued before data copy
and cleaned up on failure via tcp_remove_empty_skb(). KCM was
missing the equivalent cleanup.

Fix this by tracking the predecessor skb (frag_prev) when allocating
a new frag_list entry. On error, if the tail skb has zero frags,
use frag_prev to unlink and free it in O(1) without walking the
singly-linked frag_list. frag_prev is safe to dereference because
the entire message chain is only held locally (or in kcm->seq_skb)
and is not added to sk_write_queue until MSG_EOR, so the send path
cannot free it underneath us.

Also change the WARN_ON to WARN_ON_ONCE to avoid flooding the log
if the condition is somehow hit repeatedly.

There are currently no KCM selftests in the kernel tree; a simple
reproducer is available at [1].

[1] https://gist.github.com/mrpre/a94d431c757e8d6f168f4dd1a3749daa

Reported-by: syzbot+52624bdfbf2746d37d70@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/000000000000269a1405a12fdc77@google.com/T/
Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260219014256.370092-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/kcm/kcmsock.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 5dd7e0509a48..3912e75079f5 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -628,7 +628,7 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
 			skb = txm->frag_skb;
 		}
 
-		if (WARN_ON(!skb_shinfo(skb)->nr_frags) ||
+		if (WARN_ON_ONCE(!skb_shinfo(skb)->nr_frags) ||
 		    WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
 			ret = -EINVAL;
 			goto out;
@@ -749,7 +749,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
-	struct sk_buff *skb = NULL, *head = NULL;
+	struct sk_buff *skb = NULL, *head = NULL, *frag_prev = NULL;
 	size_t copy, copied = 0;
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	int eor = (sock->type == SOCK_DGRAM) ?
@@ -824,6 +824,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 				else
 					skb->next = tskb;
 
+				frag_prev = skb;
 				skb = tskb;
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 				continue;
@@ -933,6 +934,22 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 out_error:
 	kcm_push(kcm);
 
+	/* When MAX_SKB_FRAGS was reached, a new skb was allocated and
+	 * linked into the frag_list before data copy. If the copy
+	 * subsequently failed, this skb has zero frags. Remove it from
+	 * the frag_list to prevent kcm_write_msgs from later hitting
+	 * WARN_ON(!skb_shinfo(skb)->nr_frags).
+	 */
+	if (frag_prev && !skb_shinfo(skb)->nr_frags) {
+		if (head == frag_prev)
+			skb_shinfo(head)->frag_list = NULL;
+		else
+			frag_prev->next = NULL;
+		kfree_skb(skb);
+		/* Update skb as it may be saved in partial_message via goto */
+		skb = frag_prev;
+	}
+
 	if (sock->type == SOCK_SEQPACKET) {
 		/* Wrote some bytes before encountering an
 		 * error, return partial success.

From 4cfe066a82cdf9e83e48b16000f55280efc98325 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Fri, 20 Feb 2026 16:57:54 +0100
Subject: [PATCH 0264/1303] dpll: zl3073x: fix REF_PHASE_OFFSET_COMP register
 width for some chip IDs

The REF_PHASE_OFFSET_COMP register is 48-bit wide on most zl3073x chip
variants, but only 32-bit wide on chip IDs 0x0E30, 0x0E93..0x0E97 and
0x1F60. The driver unconditionally uses 48-bit read/write operations,
which on 32-bit variants causes reading 2 bytes past the register
boundary (corrupting the value) and writing 2 bytes into the adjacent
register.

Fix this by storing the chip ID in the device structure during probe
and adding a helper to detect the affected variants. Use the correct
register width for read/write operations and the matching sign extension
bit (31 vs 47) when interpreting the phase compensation value.

Fixes: 6287262f761e ("dpll: zl3073x: Add support to adjust phase")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220155755.448185-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/zl3073x/core.c |  1 +
 drivers/dpll/zl3073x/core.h | 28 ++++++++++++++++++++++++++++
 drivers/dpll/zl3073x/dpll.c |  7 +++++--
 drivers/dpll/zl3073x/ref.c  | 25 ++++++++++++++++++++-----
 drivers/dpll/zl3073x/regs.h |  1 +
 5 files changed, 55 insertions(+), 7 deletions(-)

diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c
index 63bd97181b9e..8c5ee28e02f4 100644
--- a/drivers/dpll/zl3073x/core.c
+++ b/drivers/dpll/zl3073x/core.c
@@ -1026,6 +1026,7 @@ int zl3073x_dev_probe(struct zl3073x_dev *zldev,
 				     "Unknown or non-match chip ID: 0x%0x\n",
 				     id);
 	}
+	zldev->chip_id = id;
 
 	/* Read revision, firmware version and custom config version */
 	rc = zl3073x_read_u16(zldev, ZL_REG_REVISION, &revision);
diff --git a/drivers/dpll/zl3073x/core.h b/drivers/dpll/zl3073x/core.h
index dddfcacea5c0..fd2af3c62a7d 100644
--- a/drivers/dpll/zl3073x/core.h
+++ b/drivers/dpll/zl3073x/core.h
@@ -35,6 +35,7 @@ struct zl3073x_dpll;
  * @dev: pointer to device
  * @regmap: regmap to access device registers
  * @multiop_lock: to serialize multiple register operations
+ * @chip_id: chip ID read from hardware
  * @ref: array of input references' invariants
  * @out: array of outs' invariants
  * @synth: array of synths' invariants
@@ -48,6 +49,7 @@ struct zl3073x_dev {
 	struct device		*dev;
 	struct regmap		*regmap;
 	struct mutex		multiop_lock;
+	u16			chip_id;
 
 	/* Invariants */
 	struct zl3073x_ref	ref[ZL3073X_NUM_REFS];
@@ -144,6 +146,32 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev,
 
 int zl3073x_ref_phase_offsets_update(struct zl3073x_dev *zldev, int channel);
 
+/**
+ * zl3073x_dev_is_ref_phase_comp_32bit - check ref phase comp register size
+ * @zldev: pointer to zl3073x device
+ *
+ * Some chip IDs have a 32-bit wide ref_phase_offset_comp register instead
+ * of the default 48-bit.
+ *
+ * Return: true if the register is 32-bit, false if 48-bit
+ */
+static inline bool
+zl3073x_dev_is_ref_phase_comp_32bit(struct zl3073x_dev *zldev)
+{
+	switch (zldev->chip_id) {
+	case 0x0E30:
+	case 0x0E93:
+	case 0x0E94:
+	case 0x0E95:
+	case 0x0E96:
+	case 0x0E97:
+	case 0x1F60:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline bool
 zl3073x_is_n_pin(u8 id)
 {
diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c
index 78edc36b17fb..8ffbede117c6 100644
--- a/drivers/dpll/zl3073x/dpll.c
+++ b/drivers/dpll/zl3073x/dpll.c
@@ -475,8 +475,11 @@ zl3073x_dpll_input_pin_phase_adjust_get(const struct dpll_pin *dpll_pin,
 	ref_id = zl3073x_input_pin_ref_get(pin->id);
 	ref = zl3073x_ref_state_get(zldev, ref_id);
 
-	/* Perform sign extension for 48bit signed value */
-	phase_comp = sign_extend64(ref->phase_comp, 47);
+	/* Perform sign extension based on register width */
+	if (zl3073x_dev_is_ref_phase_comp_32bit(zldev))
+		phase_comp = sign_extend64(ref->phase_comp, 31);
+	else
+		phase_comp = sign_extend64(ref->phase_comp, 47);
 
 	/* Reverse two's complement negation applied during set and convert
 	 * to 32bit signed int
diff --git a/drivers/dpll/zl3073x/ref.c b/drivers/dpll/zl3073x/ref.c
index aa2de13effa8..6b65e6103999 100644
--- a/drivers/dpll/zl3073x/ref.c
+++ b/drivers/dpll/zl3073x/ref.c
@@ -121,8 +121,16 @@ int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index)
 		return rc;
 
 	/* Read phase compensation register */
-	rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
-			      &ref->phase_comp);
+	if (zl3073x_dev_is_ref_phase_comp_32bit(zldev)) {
+		u32 val;
+
+		rc = zl3073x_read_u32(zldev, ZL_REG_REF_PHASE_OFFSET_COMP_32,
+				      &val);
+		ref->phase_comp = val;
+	} else {
+		rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
+				      &ref->phase_comp);
+	}
 	if (rc)
 		return rc;
 
@@ -179,9 +187,16 @@ int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index,
 	if (!rc && dref->sync_ctrl != ref->sync_ctrl)
 		rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL,
 				      ref->sync_ctrl);
-	if (!rc && dref->phase_comp != ref->phase_comp)
-		rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
-				       ref->phase_comp);
+	if (!rc && dref->phase_comp != ref->phase_comp) {
+		if (zl3073x_dev_is_ref_phase_comp_32bit(zldev))
+			rc = zl3073x_write_u32(zldev,
+					       ZL_REG_REF_PHASE_OFFSET_COMP_32,
+					       ref->phase_comp);
+		else
+			rc = zl3073x_write_u48(zldev,
+					       ZL_REG_REF_PHASE_OFFSET_COMP,
+					       ref->phase_comp);
+	}
 	if (rc)
 		return rc;
 
diff --git a/drivers/dpll/zl3073x/regs.h b/drivers/dpll/zl3073x/regs.h
index d837bee72b17..5573d7188406 100644
--- a/drivers/dpll/zl3073x/regs.h
+++ b/drivers/dpll/zl3073x/regs.h
@@ -194,6 +194,7 @@
 #define ZL_REF_CONFIG_DIFF_EN			BIT(2)
 
 #define ZL_REG_REF_PHASE_OFFSET_COMP		ZL_REG(10, 0x28, 6)
+#define ZL_REG_REF_PHASE_OFFSET_COMP_32	ZL_REG(10, 0x28, 4)
 
 #define ZL_REG_REF_SYNC_CTRL			ZL_REG(10, 0x2e, 1)
 #define ZL_REF_SYNC_CTRL_MODE			GENMASK(2, 0)

From 3aa677625c8fad39989496c51bcff3872c1f16f1 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.quang.nguyen@est.tech>
Date: Fri, 20 Feb 2026 05:05:41 +0000
Subject: [PATCH 0265/1303] tipc: fix duplicate publication key in
 tipc_service_insert_publ()

TIPC uses named table to store TIPC services represented by type and
instance. Each time an application calls TIPC API bind() to bind a
type/instance to a socket, an entry is created and inserted into the
named table. It looks like this:

named table:
key1, entry1 (type, instance ...)
key2, entry2 (type, instance ...)

In the above table, each entry represents a route for sending data
from one socket to the other. For all publications originated from
the same node, the key is UNIQUE to identify each entry.
It is calculated by this formula:
key = socket portid + number of bindings + 1 (1)

where:
 - socket portid: unique and calculated by using linux kernel function
                  get_random_u32_below(). So, the value is randomized.
 - number of bindings: the number of times a type/instance pair is bound
                       to a socket. This number is linearly increased,
                       starting from 0.

While the socket portid is unique and randomized by linux kernel, the
linear increment of "number of bindings" in formula (1) makes "key" not
unique anymore. For example:
- Socket 1 is created with its associated port number 20062001. Type 1000,
instance 1 is bound to socket 1:
key1: 20062001 + 0 + 1 = 20062002

Then, bind() is called a second time on Socket 1 to by the same type 1000,
instance 1:
key2: 20062001 + 1 + 1 = 20062003

Named table:
key1 (20062002), entry1 (1000, 1 ...)
key2 (20062003), entry2 (1000, 1 ...)

- Socket 2 is created with its associated port number 20062002. Type 1000,
instance 1 is bound to socket 2:
key3: 20062002 + 0 + 1 = 20062003

TIPC looks up the named table and finds out that key2 with the same value
already exists and rejects the insertion into the named table.
This leads to failure of bind() call from application on Socket 2 with error
message EINVAL "Invalid argument".

This commit fixes this issue by adding more port id checking to make sure
that the key is unique to publications originated from the same port id
and node.

Fixes: 218527fe27ad ("tipc: replace name table service range array with rb tree")
Signed-off-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220050541.237962-1-tung.quang.nguyen@est.tech
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/name_table.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index e74940eab3a4..7f42fb6a8481 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -348,7 +348,8 @@ static bool tipc_service_insert_publ(struct net *net,
 
 	/* Return if the publication already exists */
 	list_for_each_entry(_p, &sr->all_publ, all_publ) {
-		if (_p->key == key && (!_p->sk.node || _p->sk.node == node)) {
+		if (_p->key == key && _p->sk.ref == p->sk.ref &&
+		    (!_p->sk.node || _p->sk.node == node)) {
 			pr_debug("Failed to bind duplicate %u,%u,%u/%u:%u/%u\n",
 				 p->sr.type, p->sr.lower, p->sr.upper,
 				 node, p->sk.ref, key);
@@ -388,7 +389,8 @@ static struct publication *tipc_service_remove_publ(struct service_range *r,
 	u32 node = sk->node;
 
 	list_for_each_entry(p, &r->all_publ, all_publ) {
-		if (p->key != key || (node && node != p->sk.node))
+		if (p->key != key || p->sk.ref != sk->ref ||
+		    (node && node != p->sk.node))
 			continue;
 		list_del(&p->all_publ);
 		list_del(&p->local_publ);

From 63c49efc987afefc6b9bb7de083eb8748e0b1789 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:17 -0800
Subject: [PATCH 0266/1303] selftests/bpf: Add simple strscpy() implementation

Replace bpf_strlcpy() in bpf_util.h with a sized_strscpy(), which is a
simplified sized_strscpy() from the kernel (lib/string.c [1]). It:
  * takes a count (destination size) parameter
  * guarantees NULL-termination
  * returns the number of characters copied or -E2BIG

Re-define strscpy macro similar to in-kernel implementation [2]: allow
the count parameter to be optional.

Add #ifdef-s to tools/include/linux/args.h, as they may be defined in
other system headers (for example, __CONCAT in sys/cdefs.h).

Fixup the single existing bpf_strlcpy() call in cgroup_helpers.c

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/lib/string.c?h=v6.19#n113
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/linux/string.h?h=v6.19#n91

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-2-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/linux/args.h                   |  4 ++
 tools/testing/selftests/bpf/bpf_util.h       | 45 ++++++++++++++------
 tools/testing/selftests/bpf/cgroup_helpers.c |  2 +-
 3 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h
index 2e8e65d975c7..14b268f2389a 100644
--- a/tools/include/linux/args.h
+++ b/tools/include/linux/args.h
@@ -22,7 +22,11 @@
 #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 
 /* Concatenate two parameters, but allow them to be expanded beforehand. */
+#ifndef __CONCAT
 #define __CONCAT(a, b) a ## b
+#endif
+#ifndef CONCATENATE
 #define CONCATENATE(a, b) __CONCAT(a, b)
+#endif
 
 #endif	/* _LINUX_ARGS_H */
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 4bc2d25f33e1..6cb56501a505 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <syscall.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
+#include <linux/args.h>
 
 static inline unsigned int bpf_num_possible_cpus(void)
 {
@@ -21,25 +22,43 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	return possible_cpus;
 }
 
-/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
- * is zero-terminated string no matter what (unless sz == 0, in which case
- * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
- * in what is returned. Given this is internal helper, it's trivial to extend
- * this, when necessary. Use this instead of strncpy inside libbpf source code.
+/*
+ * Simplified strscpy() implementation. The kernel one is in lib/string.c
  */
-static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
+static inline ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 {
-	size_t i;
+	long res = 0;
 
-	if (sz == 0)
-		return;
+	if (count == 0)
+		return -E2BIG;
 
-	sz--;
-	for (i = 0; i < sz && src[i]; i++)
-		dst[i] = src[i];
-	dst[i] = '\0';
+	while (count > 1) {
+		char c;
+
+		c = src[res];
+		dest[res] = c;
+		if (!c)
+			return res;
+		res++;
+		count--;
+	}
+
+	/* Force NUL-termination. */
+	dest[res] = '\0';
+
+	/* Return E2BIG if the source didn't stop */
+	return src[res] ? -E2BIG : res;
 }
 
+#define __strscpy0(dst, src, ...)	\
+	sized_strscpy(dst, src, sizeof(dst))
+#define __strscpy1(dst, src, size)	\
+	sized_strscpy(dst, src, size)
+
+#undef strscpy /* Redefine the placeholder from tools/include/linux/string.h */
+#define strscpy(dst, src, ...)	\
+	CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__)
+
 #define __bpf_percpu_val_align	__attribute__((__aligned__(8)))
 
 #define BPF_DECLARE_PERCPU(type, name)				\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 20cede4db3ce..45cd0b479fe3 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -86,7 +86,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers
 		enable[len] = 0;
 		close(fd);
 	} else {
-		bpf_strlcpy(enable, controllers, sizeof(enable));
+		strscpy(enable, controllers);
 	}
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);

From 6a087ac23f5b6619033ad08e60c355b00bb8ce51 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:18 -0800
Subject: [PATCH 0267/1303] selftests/bpf: Replace strcpy() calls with
 strscpy()

strcpy() does not perform bounds checking and is considered deprecated
[1]. Replace strcpy() calls with strscpy() defined in bpf_util.h.

[1] https://docs.kernel.org/process/deprecated.html#strcpy

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-3-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c           | 2 +-
 tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c     | 2 +-
 tools/testing/selftests/bpf/prog_tests/setget_sockopt.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/sockopt_sk.c     | 2 +-
 tools/testing/selftests/bpf/prog_tests/test_veristat.c  | 4 ++--
 tools/testing/selftests/bpf/xdp_features.c              | 3 ++-
 6 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 0a6a5561bed3..5374b7e16d53 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -432,7 +432,7 @@ int make_sockaddr(int family, const char *addr_str, __u16 port,
 		memset(addr, 0, sizeof(*sun));
 		sun->sun_family = family;
 		sun->sun_path[0] = 0;
-		strcpy(sun->sun_path + 1, addr_str);
+		strscpy(sun->sun_path + 1, addr_str, sizeof(sun->sun_path) - 1);
 		if (len)
 			*len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str);
 		return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index b7d1b52309d0..f829b6f09bc9 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -281,7 +281,7 @@ static void test_dctcp_fallback(void)
 	dctcp_skel = bpf_dctcp__open();
 	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
 		return;
-	strcpy(dctcp_skel->rodata->fallback_cc, "cubic");
+	strscpy(dctcp_skel->rodata->fallback_cc, "cubic");
 	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
 		goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index e4dac529d424..77fe1bfb7504 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -212,7 +212,7 @@ void test_setget_sockopt(void)
 	if (!ASSERT_OK_PTR(skel, "open skel"))
 		goto done;
 
-	strcpy(skel->rodata->veth, "binddevtest1");
+	strscpy(skel->rodata->veth, "binddevtest1");
 	skel->rodata->veth_ifindex = if_nametoindex("binddevtest1");
 	if (!ASSERT_GT(skel->rodata->veth_ifindex, 0, "if_nametoindex"))
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index ba6b3ec1156a..53637431ec5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -142,7 +142,7 @@ static int getsetsockopt(void)
 
 	/* TCP_CONGESTION can extend the string */
 
-	strcpy(buf.cc, "nv");
+	strscpy(buf.cc, "nv");
 	err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv"));
 	if (err) {
 		log_err("Failed to call setsockopt(TCP_CONGESTION)");
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
index b38c16b4247f..9aff08ac55c0 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -24,9 +24,9 @@ static struct fixture *init_fixture(void)
 
 	/* for no_alu32 and cpuv4 veristat is in parent folder */
 	if (access("./veristat", F_OK) == 0)
-		strcpy(fix->veristat, "./veristat");
+		strscpy(fix->veristat, "./veristat");
 	else if (access("../veristat", F_OK) == 0)
-		strcpy(fix->veristat, "../veristat");
+		strscpy(fix->veristat, "../veristat");
 	else
 		PRINT_FAIL("Can't find veristat binary");
 
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
index 595c79141cf3..a27ed663967c 100644
--- a/tools/testing/selftests/bpf/xdp_features.c
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -16,6 +16,7 @@
 
 #include <network_helpers.h>
 
+#include "bpf_util.h"
 #include "xdp_features.skel.h"
 #include "xdp_features.h"
 
@@ -212,7 +213,7 @@ static void set_env_default(void)
 	env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
 	env.feature.action = -EINVAL;
 	env.ifindex = -ENODEV;
-	strcpy(env.ifname, "unknown");
+	strscpy(env.ifname, "unknown");
 	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT,
 		      &env.dut_ctrl_addr, NULL);
 	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT,

From ac47870fd795549f03d57e0879fc730c79119f4b Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Sat, 14 Feb 2026 18:51:28 +0800
Subject: [PATCH 0268/1303] drm/msm/dsi: fix hdisplay calculation when
 programming dsi registers

Recently, the hdisplay calculation is working for 3:1 compressed ratio
only. If we have a video panel with DSC BPP = 8, and BPC = 10, we still
use the default bits_per_pclk = 24, then we get the wrong hdisplay. We
can draw the conclusion by cross-comparing the calculation with the
calculation in dsi_adjust_pclk_for_compression().

Since CMD mode does not use this, we can remove
!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) safely.

Fixes: efcbd6f9cdeb ("drm/msm/dsi: Enable widebus for DSI")
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/704822/
Link: https://lore.kernel.org/r/20260214105145.105308-1-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index e0de545d4077..e8e83ee61eb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -993,7 +993,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 	if (msm_host->dsc) {
 		struct drm_dsc_config *dsc = msm_host->dsc;
-		u32 bytes_per_pclk;
+		u32 bits_per_pclk;
 
 		/* update dsc params with timing params */
 		if (!dsc || !mode->hdisplay || !mode->vdisplay) {
@@ -1015,7 +1015,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 		/*
 		 * DPU sends 3 bytes per pclk cycle to DSI. If widebus is
-		 * enabled, bus width is extended to 6 bytes.
+		 * enabled, MDP always sends out 48-bit compressed data per
+		 * pclk and on average, DSI consumes an amount of compressed
+		 * data equivalent to the uncompressed pixel depth per pclk.
 		 *
 		 * Calculate the number of pclks needed to transmit one line of
 		 * the compressed data.
@@ -1027,12 +1029,12 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 		 * unused anyway.
 		 */
 		h_total -= hdisplay;
-		if (wide_bus_enabled && !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
-			bytes_per_pclk = 6;
+		if (wide_bus_enabled)
+			bits_per_pclk = mipi_dsi_pixel_format_to_bpp(msm_host->format);
 		else
-			bytes_per_pclk = 3;
+			bits_per_pclk = 24;
 
-		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), bytes_per_pclk);
+		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc) * 8, bits_per_pclk);
 
 		h_total += hdisplay;
 		ha_end = ha_start + hdisplay;

From 5f3518d77419255f8b12bb23c8ec22acbeb6bc5b Mon Sep 17 00:00:00 2001
From: Julius Lehmann <lehmanju@devpi.de>
Date: Sat, 14 Feb 2026 20:34:21 +0100
Subject: [PATCH 0269/1303] HID: magicmouse: fix battery reporting for Apple
 Magic Trackpad 2

Battery reporting does not work for the Apple Magic Trackpad 2 if it is
connected via USB. The current hid descriptor fixup code checks for a
hid descriptor length of exactly 83 bytes. If the hid descriptor is
larger, which is the case for newer apple mice, the fixup is not
applied.

This fix checks for hid descriptor sizes greater/equal 83 bytes which
applies the fixup for newer devices as well.

Signed-off-by: Julius Lehmann <lehmanju@devpi.de>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-magicmouse.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 17908d52c027..9eadf3252d0d 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -990,7 +990,7 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	 */
 	if ((is_usb_magicmouse2(hdev->vendor, hdev->product) ||
 	     is_usb_magictrackpad2(hdev->vendor, hdev->product)) &&
-	    *rsize == 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
+	    *rsize >= 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
 		hid_info(hdev,
 			 "fixing up magicmouse battery report descriptor\n");
 		*rsize = *rsize - 1;

From a2e70a89fa58133521b2deae4427d35776bda935 Mon Sep 17 00:00:00 2001
From: Ian Ray <ian.ray@gehealthcare.com>
Date: Tue, 17 Feb 2026 13:51:51 +0200
Subject: [PATCH 0270/1303] HID: multitouch: new class MT_CLS_EGALAX_P80H84

Fixes: f9e82295eec1 ("HID: multitouch: add eGalaxTouch P80H84 support")
Signed-off-by: Ian Ray <ian.ray@gehealthcare.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-multitouch.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 7daa8f6d8187..8052b35bfd7d 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -233,6 +233,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_SMART_TECH			0x0113
 #define MT_CLS_APPLE_TOUCHBAR			0x0114
 #define MT_CLS_YOGABOOK9I			0x0115
+#define MT_CLS_EGALAX_P80H84			0x0116
 #define MT_CLS_SIS				0x0457
 
 #define MT_DEFAULT_MAXCONTACT	10
@@ -438,6 +439,11 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_YOGABOOK9I,
 		.export_all_inputs = true
 	},
+	{ .name = MT_CLS_EGALAX_P80H84,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_CONTACT_CNT_ACCURATE,
+	},
 	{ }
 };
 
@@ -2215,8 +2221,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_EGALAX_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C000) },
-	{ .driver_data = MT_CLS_EGALAX,
-		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+	{ .driver_data = MT_CLS_EGALAX_P80H84,
+		HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },
 
 	/* Elan devices */

From b4f4fd947a2a6df7cf1f530dd1028d9f3849eff5 Mon Sep 17 00:00:00 2001
From: Alex Tran <alex.t.tran@gmail.com>
Date: Sat, 31 Jan 2026 15:57:43 -0800
Subject: [PATCH 0271/1303] selftests: hid: tests: test_wacom_generic: add
 tests for display devices and opaque devices

Verify Wacom devices set INPUT_PROP_DIRECT on display devices and
INPUT_PROP_POINTER on opaque devices. Verify INPUT_PROP_POINTER
is not set on display devices and INPUT_PROP_DIRECT is not set
on opaque devices.

Moved test_prop_pointer into TestOpaqueTablet. Created a
DirectTabletTest mixin class for test_prop_direct that can be
inherited by display tablet test classes.Used DirectTabletTest
for TestDTH2452Tablet case.

Signed-off-by: Alex Tran <alex.t.tran@gmail.com>
Tested-by: Erin Skomra <erin.skomra@wacom.com>
Reviewed-by: Erin Skomra <erin.skomra@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 .../selftests/hid/tests/test_wacom_generic.py | 34 ++++++++++++-------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py
index 2d6d04f0ff80..3903f479b15b 100644
--- a/tools/testing/selftests/hid/tests/test_wacom_generic.py
+++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py
@@ -598,18 +598,6 @@ class BaseTest:
                 if unit_set:
                     assert required[usage].contains(field)
 
-        def test_prop_direct(self):
-            """
-            Todo: Verify that INPUT_PROP_DIRECT is set on display devices.
-            """
-            pass
-
-        def test_prop_pointer(self):
-            """
-            Todo: Verify that INPUT_PROP_POINTER is set on opaque devices.
-            """
-            pass
-
 
 class PenTabletTest(BaseTest.TestTablet):
     def assertName(self, uhdev):
@@ -677,6 +665,15 @@ class TestOpaqueTablet(PenTabletTest):
             uhdev.event(130, 240, pressure=0), [], auto_syn=False, strict=True
         )
 
+    def test_prop_pointer(self):
+        """
+        Verify that INPUT_PROP_POINTER is set and INPUT_PROP_DIRECT
+        is not set on opaque devices.
+        """
+        evdev = self.uhdev.get_evdev()
+        assert libevdev.INPUT_PROP_POINTER in evdev.properties
+        assert libevdev.INPUT_PROP_DIRECT not in evdev.properties
+
 
 class TestOpaqueCTLTablet(TestOpaqueTablet):
     def create_device(self):
@@ -862,7 +859,18 @@ class TestPTHX60_Pen(TestOpaqueCTLTablet):
         )
 
 
-class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest):
+class DirectTabletTest():
+    def test_prop_direct(self):
+        """
+        Verify that INPUT_PROP_DIRECT is set and INPUT_PROP_POINTER
+        is not set on display devices.
+        """
+        evdev = self.uhdev.get_evdev()
+        assert libevdev.INPUT_PROP_DIRECT in evdev.properties
+        assert libevdev.INPUT_PROP_POINTER not in evdev.properties
+
+
+class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest, DirectTabletTest):
     ContactIds = namedtuple("ContactIds", "contact_id, tracking_id, slot_num")
 
     def create_device(self):

From 9af0feae8016ba58ad7ff784a903404986b395b1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 27 Jan 2026 10:38:39 +0100
Subject: [PATCH 0272/1303] RDMA/core: Fix stale RoCE GIDs during netdev events
 at registration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RoCE GID entries become stale when netdev properties change during the
IB device registration window. This is reproducible with a udev rule
that sets a MAC address when a VF netdev appears:

  ACTION=="add", SUBSYSTEM=="net", KERNEL=="eth4", \
    RUN+="/sbin/ip link set eth4 address 88:22:33:44:55:66"

After VF creation, show_gids displays GIDs derived from the original
random MAC rather than the configured one.

The root cause is a race between netdev event processing and device
registration:

  CPU 0 (driver)                    CPU 1 (udev/workqueue)
  ──────────────                    ──────────────────────
  ib_register_device()
    ib_cache_setup_one()
      gid_table_setup_one()
        _gid_table_setup_one()
          ← GID table allocated
        rdma_roce_rescan_device()
          ← GIDs populated with
            OLD MAC
                                    ip link set eth4 addr NEW_MAC
                                    NETDEV_CHANGEADDR queued
                                    netdevice_event_work_handler()
                                      ib_enum_all_roce_netdevs()
                                        ← Iterates DEVICE_REGISTERED
                                        ← Device NOT marked yet, SKIP!
    enable_device_and_get()
      xa_set_mark(DEVICE_REGISTERED)
          ← Too late, event was lost

The netdev event handler uses ib_enum_all_roce_netdevs() which only
iterates devices marked DEVICE_REGISTERED. However, this mark is set
late in the registration process, after the GID cache is already
populated. Events arriving in this window are silently dropped.

Fix this by introducing a new xarray mark DEVICE_GID_UPDATES that is
set immediately after the GID table is allocated and initialized. Use
the new mark in ib_enum_all_roce_netdevs() function to iterate devices
instead of DEVICE_REGISTERED.

This is safe because:
- After _gid_table_setup_one(), all required structures exist (port_data,
  immutable, cache.gid)
- The GID table mutex serializes concurrent access between the initial
  rescan and event handlers
- Event handlers correctly update stale GIDs even when racing with rescan
- The mark is cleared in ib_cache_cleanup_one() before teardown

This also fixes similar races for IP address events (inetaddr_event,
inet6addr_event) which use the same enumeration path.

Fixes: 0df91bb67334 ("RDMA/devices: Use xarray to store the client_data")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20260127093839.126291-1-jiri@resnulli.us
Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/cache.c     | 13 +++++++++++
 drivers/infiniband/core/core_priv.h |  3 +++
 drivers/infiniband/core/device.c    | 34 ++++++++++++++++++++++++++++-
 3 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index b415d4aad04f..ee4a2bc68fb2 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -926,6 +926,13 @@ static int gid_table_setup_one(struct ib_device *ib_dev)
 	if (err)
 		return err;
 
+	/*
+	 * Mark the device as ready for GID cache updates. This allows netdev
+	 * event handlers to update the GID cache even before the device is
+	 * fully registered.
+	 */
+	ib_device_enable_gid_updates(ib_dev);
+
 	rdma_roce_rescan_device(ib_dev);
 
 	return err;
@@ -1637,6 +1644,12 @@ void ib_cache_release_one(struct ib_device *device)
 
 void ib_cache_cleanup_one(struct ib_device *device)
 {
+	/*
+	 * Clear the GID updates mark first to prevent event handlers from
+	 * accessing the device while it's being torn down.
+	 */
+	ib_device_disable_gid_updates(device);
+
 	/* The cleanup function waits for all in-progress workqueue
 	 * elements and cleans up the GID cache. This function should be
 	 * called after the device was removed from the devices list and
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 05102769a918..a2c36666e6fc 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -100,6 +100,9 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+void ib_device_enable_gid_updates(struct ib_device *device);
+void ib_device_disable_gid_updates(struct ib_device *device);
+
 typedef int (*nldev_callback)(struct ib_device *device,
 			      struct sk_buff *skb,
 			      struct netlink_callback *cb,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 1b5f1ee0a557..558b73940d66 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -93,6 +93,7 @@ static struct workqueue_struct *ib_unreg_wq;
 static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC);
 static DECLARE_RWSEM(devices_rwsem);
 #define DEVICE_REGISTERED XA_MARK_1
+#define DEVICE_GID_UPDATES XA_MARK_2
 
 static u32 highest_client_id;
 #define CLIENT_REGISTERED XA_MARK_1
@@ -2412,11 +2413,42 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 	unsigned long index;
 
 	down_read(&devices_rwsem);
-	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED)
+	xa_for_each_marked(&devices, index, dev, DEVICE_GID_UPDATES)
 		ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie);
 	up_read(&devices_rwsem);
 }
 
+/**
+ * ib_device_enable_gid_updates - Mark device as ready for GID cache updates
+ * @device: Device to mark
+ *
+ * Called after GID table is allocated and initialized. After this mark is set,
+ * netdevice event handlers can update the device's GID cache. This allows
+ * events that arrive during device registration to be processed, avoiding
+ * stale GID entries when netdev properties change during the device
+ * registration process.
+ */
+void ib_device_enable_gid_updates(struct ib_device *device)
+{
+	down_write(&devices_rwsem);
+	xa_set_mark(&devices, device->index, DEVICE_GID_UPDATES);
+	up_write(&devices_rwsem);
+}
+
+/**
+ * ib_device_disable_gid_updates - Clear the GID updates mark
+ * @device: Device to unmark
+ *
+ * Called before GID table cleanup to prevent event handlers from accessing
+ * the device while it's being torn down.
+ */
+void ib_device_disable_gid_updates(struct ib_device *device)
+{
+	down_write(&devices_rwsem);
+	xa_clear_mark(&devices, device->index, DEVICE_GID_UPDATES);
+	up_write(&devices_rwsem);
+}
+
 /*
  * ib_enum_all_devs - enumerate all ib_devices
  * @cb: Callback to call for each found ib_device

From 7a23af417d9dd57b4382356b2e7442e5d2bf5bea Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 18 Feb 2026 09:12:45 +0000
Subject: [PATCH 0273/1303] RDMA/bng_re: Remove unnessary validity checks

Fix below smatch warning:
drivers/infiniband/hw/bng_re/bng_dev.c:113
bng_re_net_ring_free() warn: variable dereferenced before check 'rdev'
(see line 107)

current driver has unnessary validity checks. So, removing these
unnessary validity checks.

Fixes: 4f830cd8d7fe ("RDMA/bng_re: Add infrastructure for enabling Firmware channel")
Fixes: 745065770c2d ("RDMA/bng_re: Register and get the resources from bnge driver")
Fixes: 04e031ff6e60 ("RDMA/bng_re: Initialize the Firmware and Hardware")
Fixes: d0da769c19d0 ("RDMA/bng_re: Add Auxiliary interface")
Reported-by: Simon Horman <horms@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601010413.sWadrQel-lkp@intel.com/
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20260218091246.1764808-2-siva.kallam@broadcom.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/bng_re/bng_dev.c | 27 ++++----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c
index cf3bf08e5f26..b8df807c3a64 100644
--- a/drivers/infiniband/hw/bng_re/bng_dev.c
+++ b/drivers/infiniband/hw/bng_re/bng_dev.c
@@ -54,9 +54,6 @@ static void bng_re_destroy_chip_ctx(struct bng_re_dev *rdev)
 {
 	struct bng_re_chip_ctx *chip_ctx;
 
-	if (!rdev->chip_ctx)
-		return;
-
 	kfree(rdev->dev_attr);
 	rdev->dev_attr = NULL;
 
@@ -124,12 +121,6 @@ static int bng_re_net_ring_free(struct bng_re_dev *rdev,
 	struct bnge_fw_msg fw_msg = {};
 	int rc = -EINVAL;
 
-	if (!rdev)
-		return rc;
-
-	if (!aux_dev)
-		return rc;
-
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_FREE);
 	req.ring_type = type;
 	req.ring_id = cpu_to_le16(fw_ring_id);
@@ -150,10 +141,7 @@ static int bng_re_net_ring_alloc(struct bng_re_dev *rdev,
 	struct hwrm_ring_alloc_input req = {};
 	struct hwrm_ring_alloc_output resp;
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
-
-	if (!aux_dev)
-		return rc;
+	int rc;
 
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_ALLOC);
 	req.enables = 0;
@@ -184,10 +172,7 @@ static int bng_re_stats_ctx_free(struct bng_re_dev *rdev)
 	struct hwrm_stat_ctx_free_input req = {};
 	struct hwrm_stat_ctx_free_output resp = {};
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
-
-	if (!aux_dev)
-		return rc;
+	int rc;
 
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_FREE);
 	req.stat_ctx_id = cpu_to_le32(rdev->stats_ctx.fw_id);
@@ -208,13 +193,10 @@ static int bng_re_stats_ctx_alloc(struct bng_re_dev *rdev)
 	struct hwrm_stat_ctx_alloc_output resp = {};
 	struct hwrm_stat_ctx_alloc_input req = {};
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
+	int rc;
 
 	stats->fw_id = BNGE_INVALID_STATS_CTX_ID;
 
-	if (!aux_dev)
-		return rc;
-
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_ALLOC);
 	req.update_period_ms = cpu_to_le32(1000);
 	req.stats_dma_addr = cpu_to_le64(stats->dma_map);
@@ -486,8 +468,7 @@ static void bng_re_remove(struct auxiliary_device *adev)
 
 	rdev = dev_info->rdev;
 
-	if (rdev)
-		bng_re_remove_device(rdev, adev);
+	bng_re_remove_device(rdev, adev);
 	kfree(dev_info);
 }
 

From 3d2e5d12a2eef0ca8a629a422aa593673235c77c Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 18 Feb 2026 09:12:46 +0000
Subject: [PATCH 0274/1303] RDMA/bng_re: Unwind bng_re_dev_init properly

Fix below smatch warning:
drivers/infiniband/hw/bng_re/bng_dev.c:270
bng_re_dev_init() warn: missing unwind goto?

Current bng_re_dev_init function is not having clear unwinding code.
So, added proper unwinding with ladder.

Fixes: 4f830cd8d7fe ("RDMA/bng_re: Add infrastructure for enabling Firmware channel")
Reported-by: Simon Horman <horms@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601010413.sWadrQel-lkp@intel.com/
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20260218091246.1764808-3-siva.kallam@broadcom.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/bng_re/bng_dev.c | 29 +++++++++++++-------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c
index b8df807c3a64..d34b5f88cd40 100644
--- a/drivers/infiniband/hw/bng_re/bng_dev.c
+++ b/drivers/infiniband/hw/bng_re/bng_dev.c
@@ -285,7 +285,7 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 				"Failed to register with netedev: %#x\n", rc);
-		return -EINVAL;
+		goto reg_netdev_fail;
 	}
 
 	set_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
@@ -294,19 +294,16 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 		ibdev_err(&rdev->ibdev,
 			  "RoCE requires minimum 2 MSI-X vectors, but only %d reserved\n",
 			  rdev->aux_dev->auxr_info->msix_requested);
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto msix_ctx_fail;
 	}
 	ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n",
 		  rdev->aux_dev->auxr_info->msix_requested);
 
 	rc = bng_re_setup_chip_ctx(rdev);
 	if (rc) {
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
 		ibdev_err(&rdev->ibdev, "Failed to get chip context\n");
-		return -EINVAL;
+		goto msix_ctx_fail;
 	}
 
 	bng_re_query_hwrm_version(rdev);
@@ -315,16 +312,14 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 			  "Failed to allocate RCFW Channel: %#x\n", rc);
-		goto fail;
+		goto alloc_fw_chl_fail;
 	}
 
 	/* Allocate nq record memory */
 	rdev->nqr = kzalloc_obj(*rdev->nqr);
 	if (!rdev->nqr) {
-		bng_re_destroy_chip_ctx(rdev);
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto nq_alloc_fail;
 	}
 
 	rdev->nqr->num_msix = rdev->aux_dev->auxr_info->msix_requested;
@@ -393,9 +388,15 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 free_ring:
 	bng_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type);
 free_rcfw:
+	kfree(rdev->nqr);
+nq_alloc_fail:
 	bng_re_free_rcfw_channel(&rdev->rcfw);
-fail:
-	bng_re_dev_uninit(rdev);
+alloc_fw_chl_fail:
+	bng_re_destroy_chip_ctx(rdev);
+msix_ctx_fail:
+	bnge_unregister_dev(rdev->aux_dev);
+	clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+reg_netdev_fail:
 	return rc;
 }
 

From 017c1792525064a723971f0216e6ef86a8c7af11 Mon Sep 17 00:00:00 2001
From: Vahagn Vardanian <vahagn@redrays.io>
Date: Mon, 23 Feb 2026 00:00:00 +0000
Subject: [PATCH 0275/1303] wifi: mac80211: fix NULL pointer dereference in
 mesh_rx_csa_frame()

In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced
at lines 1638 and 1642 without a prior NULL check:

    ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
    ...
    pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value);

The mesh_matches_local() check above only validates the Mesh ID,
Mesh Configuration, and Supported Rates IEs.  It does not verify the
presence of the Mesh Channel Switch Parameters IE (element ID 118).
When a received CSA action frame omits that IE, ieee802_11_parse_elems()
leaves elems->mesh_chansw_params_ie as NULL, and the unconditional
dereference causes a kernel NULL pointer dereference.

A remote mesh peer with an established peer link (PLINK_ESTAB) can
trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame
that includes a matching Mesh ID and Mesh Configuration IE but omits the
Mesh Channel Switch Parameters IE.  No authentication beyond the default
open mesh peering is required.

Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  Oops: Oops: 0000 [#1] SMP NOPTI
  RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211]
  CR2: 0000000000000000

Fix by adding a NULL check for mesh_chansw_params_ie after
mesh_matches_local() returns, consistent with how other optional IEs
are guarded throughout the mesh code.

The bug has been present since v3.13 (released 2014-01-19).

Fixes: 8f2535b92d68 ("mac80211: process the CSA frame for mesh accordingly")
Cc: stable@vger.kernel.org
Signed-off-by: Vahagn Vardanian <vahagn@redrays.io>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 68901f1def0d..129e814abe76 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1636,6 +1636,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 	if (!mesh_matches_local(sdata, elems))
 		goto free;
 
+	if (!elems->mesh_chansw_params_ie)
+		goto free;
+
 	ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
 	if (!--ifmsh->chsw_ttl)
 		fwd_csa = false;

From 021fd0f87004e949cba6f27199b9925bc24ec3a0 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Thu, 19 Feb 2026 08:57:38 +0100
Subject: [PATCH 0276/1303] net/rds: fix recursive lock in
 rds_tcp_conn_slots_available

syzbot reported a recursive lock warning in rds_tcp_get_peer_sport() as
it calls inet6_getname() which acquires the socket lock that was already
held by __release_sock().

 kworker/u8:6/2985 is trying to acquire lock:
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1709 [inline]
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: inet6_getname+0x15d/0x650 net/ipv6/af_inet6.c:533

 but task is already holding lock:
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1709 [inline]
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_sock_set_cork+0x2c/0x2e0 net/ipv4/tcp.c:3694
   lock_sock_nested+0x48/0x100 net/core/sock.c:3780
   lock_sock include/net/sock.h:1709 [inline]
   inet6_getname+0x15d/0x650 net/ipv6/af_inet6.c:533
   rds_tcp_get_peer_sport net/rds/tcp_listen.c:70 [inline]
   rds_tcp_conn_slots_available+0x288/0x470 net/rds/tcp_listen.c:149
   rds_recv_hs_exthdrs+0x60f/0x7c0 net/rds/recv.c:265
   rds_recv_incoming+0x9f6/0x12d0 net/rds/recv.c:389
   rds_tcp_data_recv+0x7f1/0xa40 net/rds/tcp_recv.c:243
   __tcp_read_sock+0x196/0x970 net/ipv4/tcp.c:1702
   rds_tcp_read_sock net/rds/tcp_recv.c:277 [inline]
   rds_tcp_data_ready+0x369/0x950 net/rds/tcp_recv.c:331
   tcp_rcv_established+0x19e9/0x2670 net/ipv4/tcp_input.c:6675
   tcp_v6_do_rcv+0x8eb/0x1ba0 net/ipv6/tcp_ipv6.c:1609
   sk_backlog_rcv include/net/sock.h:1185 [inline]
   __release_sock+0x1b8/0x3a0 net/core/sock.c:3213

Reading from the socket struct directly is safe from possible paths. For
rds_tcp_accept_one(), the socket has just been accepted and is not yet
exposed to concurrent access. For rds_tcp_conn_slots_available(), direct
access avoids the recursive deadlock seen during backlog processing
where the socket lock is already held from the __release_sock().

However, rds_tcp_conn_slots_available() is also called from the normal
softirq path via tcp_data_ready() where the lock is not held. This is
also safe because inet_dport is a stable 16 bits field. A READ_ONCE()
annotation as the value might be accessed lockless in a concurrent
access context.

Note that it is also safe to call rds_tcp_conn_slots_available() from
rds_conn_shutdown() because the fan-out is disabled.

Fixes: 9d27a0fb122f ("net/rds: Trigger rds_send_ping() more than once")
Reported-by: syzbot+5efae91f60932839f0a5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5efae91f60932839f0a5
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260219075738.4403-1-fmancera@suse.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rds/connection.c |  3 +++
 net/rds/tcp_listen.c | 26 ++++----------------------
 2 files changed, 7 insertions(+), 22 deletions(-)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 185f73b01694..a542f94c0214 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -455,6 +455,9 @@ void rds_conn_shutdown(struct rds_conn_path *cp)
 		rcu_read_unlock();
 	}
 
+	/* we do not hold the socket lock here but it is safe because
+	 * fan-out is disabled when calling conn_slots_available()
+	 */
 	if (conn->c_trans->conn_slots_available)
 		conn->c_trans->conn_slots_available(conn, false);
 }
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index b4ab68a1da6d..08a506aa7ce7 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -59,30 +59,12 @@ void rds_tcp_keepalive(struct socket *sock)
 static int
 rds_tcp_get_peer_sport(struct socket *sock)
 {
-	union {
-		struct sockaddr_storage storage;
-		struct sockaddr addr;
-		struct sockaddr_in sin;
-		struct sockaddr_in6 sin6;
-	} saddr;
-	int sport;
+	struct sock *sk = sock->sk;
 
-	if (kernel_getpeername(sock, &saddr.addr) >= 0) {
-		switch (saddr.addr.sa_family) {
-		case AF_INET:
-			sport = ntohs(saddr.sin.sin_port);
-			break;
-		case AF_INET6:
-			sport = ntohs(saddr.sin6.sin6_port);
-			break;
-		default:
-			sport = -1;
-		}
-	} else {
-		sport = -1;
-	}
+	if (!sk)
+		return -1;
 
-	return sport;
+	return ntohs(READ_ONCE(inet_sk(sk)->inet_dport));
 }
 
 /* rds_tcp_accept_one_path(): if accepting on cp_index > 0, make sure the

From fdcfce93073d990ed4b71752e31ad1c1d6e9d58b Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Mon, 23 Feb 2026 20:59:33 +0100
Subject: [PATCH 0277/1303] eventpoll: Fix integer overflow in
 ep_loop_check_proc()

If a recursive call to ep_loop_check_proc() hits the `result = INT_MAX`,
an integer overflow will occur in the calling ep_loop_check_proc() at
`result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1)`,
breaking the recursion depth check.

Fix it by using a different placeholder value that can't lead to an
overflow.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: f2e467a48287 ("eventpoll: Fix semi-unbounded recursion")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Link: https://patch.msgid.link/20260223-epoll-int-overflow-v1-1-452f35132224@google.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventpoll.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 6c36d9dc6926..d20917b03161 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -2061,7 +2061,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
  * @ep: the &struct eventpoll to be currently checked.
  * @depth: Current depth of the path being checked.
  *
- * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep.
+ * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found
+ * a loop or went too deep.
  */
 static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 {
@@ -2080,7 +2081,7 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			struct eventpoll *ep_tovisit;
 			ep_tovisit = epi->ffd.file->private_data;
 			if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
-				result = INT_MAX;
+				result = EP_MAX_NESTS+1;
 			else
 				result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1);
 			if (result > EP_MAX_NESTS)

From bae8a5d2e759da2e0cba33ab2080deee96a09373 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Thu, 19 Feb 2026 20:46:37 +0800
Subject: [PATCH 0278/1303] net: wan: farsync: Fix use-after-free bugs caused
 by unfinished tasklets

When the FarSync T-series card is being detached, the fst_card_info is
deallocated in fst_remove_one(). However, the fst_tx_task or fst_int_task
may still be running or pending, leading to use-after-free bugs when the
already freed fst_card_info is accessed in fst_process_tx_work_q() or
fst_process_int_work_q().

A typical race condition is depicted below:

CPU 0 (cleanup)           | CPU 1 (tasklet)
                          | fst_start_xmit()
fst_remove_one()          |   tasklet_schedule()
  unregister_hdlc_device()|
                          | fst_process_tx_work_q() //handler
  kfree(card) //free      |   do_bottom_half_tx()
                          |     card-> //use

The following KASAN trace was captured:

==================================================================
 BUG: KASAN: slab-use-after-free in do_bottom_half_tx+0xb88/0xd00
 Read of size 4 at addr ffff88800aad101c by task ksoftirqd/3/32
 ...
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x55/0x70
  print_report+0xcb/0x5d0
  ? do_bottom_half_tx+0xb88/0xd00
  kasan_report+0xb8/0xf0
  ? do_bottom_half_tx+0xb88/0xd00
  do_bottom_half_tx+0xb88/0xd00
  ? _raw_spin_lock_irqsave+0x85/0xe0
  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  ? __pfx___hrtimer_run_queues+0x10/0x10
  fst_process_tx_work_q+0x67/0x90
  tasklet_action_common+0x1fa/0x720
  ? hrtimer_interrupt+0x31f/0x780
  handle_softirqs+0x176/0x530
  __irq_exit_rcu+0xab/0xe0
  sysvec_apic_timer_interrupt+0x70/0x80
 ...

 Allocated by task 41 on cpu 3 at 72.330843s:
  kasan_save_stack+0x24/0x50
  kasan_save_track+0x17/0x60
  __kasan_kmalloc+0x7f/0x90
  fst_add_one+0x1a5/0x1cd0
  local_pci_probe+0xdd/0x190
  pci_device_probe+0x341/0x480
  really_probe+0x1c6/0x6a0
  __driver_probe_device+0x248/0x310
  driver_probe_device+0x48/0x210
  __device_attach_driver+0x160/0x320
  bus_for_each_drv+0x101/0x190
  __device_attach+0x198/0x3a0
  device_initial_probe+0x78/0xa0
  pci_bus_add_device+0x81/0xc0
  pci_bus_add_devices+0x7e/0x190
  enable_slot+0x9b9/0x1130
  acpiphp_check_bridge.part.0+0x2e1/0x460
  acpiphp_hotplug_notify+0x36c/0x3c0
  acpi_device_hotplug+0x203/0xb10
  acpi_hotplug_work_fn+0x59/0x80
 ...

 Freed by task 41 on cpu 1 at 75.138639s:
  kasan_save_stack+0x24/0x50
  kasan_save_track+0x17/0x60
  kasan_save_free_info+0x3b/0x60
  __kasan_slab_free+0x43/0x70
  kfree+0x135/0x410
  fst_remove_one+0x2ca/0x540
  pci_device_remove+0xa6/0x1d0
  device_release_driver_internal+0x364/0x530
  pci_stop_bus_device+0x105/0x150
  pci_stop_and_remove_bus_device+0xd/0x20
  disable_slot+0x116/0x260
  acpiphp_disable_and_eject_slot+0x4b/0x190
  acpiphp_hotplug_notify+0x230/0x3c0
  acpi_device_hotplug+0x203/0xb10
  acpi_hotplug_work_fn+0x59/0x80
 ...

 The buggy address belongs to the object at ffff88800aad1000
  which belongs to the cache kmalloc-1k of size 1024
 The buggy address is located 28 bytes inside of
  freed 1024-byte region
 The buggy address belongs to the physical page:
 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xaad0
 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
 flags: 0x100000000000040(head|node=0|zone=1)
 page_type: f5(slab)
 raw: 0100000000000040 ffff888007042dc0 dead000000000122 0000000000000000
 raw: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
 head: 0100000000000040 ffff888007042dc0 dead000000000122 0000000000000000
 head: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
 head: 0100000000000003 ffffea00002ab401 00000000ffffffff 00000000ffffffff
 head: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffff88800aad0f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff88800aad0f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 >ffff88800aad1000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                             ^
  ffff88800aad1080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  ffff88800aad1100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ==================================================================

Fix this by ensuring that both fst_tx_task and fst_int_task are properly
canceled before the fst_card_info is released. Add tasklet_kill() in
fst_remove_one() to synchronize with any pending or running tasklets.
Since unregister_hdlc_device() stops data transmission and reception,
and fst_disable_intr() prevents further interrupts, it is appropriate
to place tasklet_kill() after these calls.

The bugs were identified through static analysis. To reproduce the issue
and validate the fix, a FarSync T-series card was simulated in QEMU and
delays(e.g., mdelay()) were introduced within the tasklet handler to
increase the likelihood of triggering the race condition.

Fixes: 2f623aaf9f31 ("net: farsync: Fix kmemleak when rmmods farsync")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Reviewed-by: Jijie Shao <shaojijie@huawei.com>
Link: https://patch.msgid.link/20260219124637.72578-1-duoming@zju.edu.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/wan/farsync.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 5b01642ca44e..6b2d1e63855e 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2550,6 +2550,8 @@ fst_remove_one(struct pci_dev *pdev)
 
 	fst_disable_intr(card);
 	free_irq(card->irq, card);
+	tasklet_kill(&fst_tx_task);
+	tasklet_kill(&fst_int_task);
 
 	iounmap(card->ctlmem);
 	iounmap(card->mem);

From 82aec772fca2223bc5774bd9af486fd95766e578 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 19 Feb 2026 11:50:21 -0800
Subject: [PATCH 0279/1303] netconsole: avoid OOB reads, msg is not
 nul-terminated

msg passed to netconsole from the console subsystem is not guaranteed
to be nul-terminated. Before recent
commit 7eab73b18630 ("netconsole: convert to NBCON console infrastructure")
the message would be placed in printk_shared_pbufs, a static global
buffer, so KASAN had harder time catching OOB accesses. Now we see:

    printk: console [netcon_ext0] enabled
    BUG: KASAN: slab-out-of-bounds in string+0x1f7/0x240
    Read of size 1 at addr ffff88813b6d4c00 by task pr/netcon_ext0/594

    CPU: 65 UID: 0 PID: 594 Comm: pr/netcon_ext0 Not tainted 6.19.0-11754-g4246fd6547c9
    Call Trace:
     kasan_report+0xe4/0x120
     string+0x1f7/0x240
     vsnprintf+0x655/0xba0
     scnprintf+0xba/0x120
     netconsole_write+0x3fe/0xa10
     nbcon_emit_next_record+0x46e/0x860
     nbcon_kthread_func+0x623/0x750

    Allocated by task 1:
     nbcon_alloc+0x1ea/0x450
     register_console+0x26b/0xe10
     init_netconsole+0xbb0/0xda0

    The buggy address belongs to the object at ffff88813b6d4000
                which belongs to the cache kmalloc-4k of size 4096
    The buggy address is located 0 bytes to the right of
                allocated 3072-byte region [ffff88813b6d4000, ffff88813b6d4c00)

Fixes: c62c0a17f9b7 ("netconsole: Append kernel version to message")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260219195021.2099699-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index d144787b2947..1b6a4135ec08 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1679,7 +1679,8 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 	if (release_len) {
 		release = init_utsname()->release;
 
-		scnprintf(nt->buf, MAX_PRINT_CHUNK, "%s,%s", release, msg);
+		scnprintf(nt->buf, MAX_PRINT_CHUNK, "%s,%.*s", release,
+			  msg_len, msg);
 		msg_len += release_len;
 	} else {
 		memcpy(nt->buf, msg, msg_len);

From 7a648d598cb8e8c62af3f0e020a25820a3f3a9a7 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sat, 14 Feb 2026 23:14:51 +0800
Subject: [PATCH 0280/1303] pinctrl: pinconf-generic: Fix memory leak in
 pinconf_generic_parse_dt_config()

In pinconf_generic_parse_dt_config(), if parse_dt_cfg() fails, it returns
directly. This bypasses the cleanup logic and results in a memory leak of
the cfg buffer.

Fix this by jumping to the out label on failure, ensuring kfree(cfg) is
called before returning.

Fixes: 90a18c512884 ("pinctrl: pinconf-generic: Handle string values for generic properties")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Antonio Borneo <antonio.borneo@foss.st.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinconf-generic.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 94b1d057197c..2b030bd0e6ad 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -351,13 +351,13 @@ int pinconf_generic_parse_dt_config(struct device_node *np,
 
 	ret = parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg);
 	if (ret)
-		return ret;
+		goto out;
 	if (pctldev && pctldev->desc->num_custom_params &&
 		pctldev->desc->custom_params) {
 		ret = parse_dt_cfg(np, pctldev->desc->custom_params,
 				   pctldev->desc->num_custom_params, cfg, &ncfg);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* no configs found at all */

From a48150d05190b41b5eec19f74b751a75a15a456a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:58:39 +0100
Subject: [PATCH 0281/1303] pinctrl: amdisp: Make amdisp_pinctrl_ops variable
 static

File-scope 'amdisp_pinctrl_ops' is not used outside of this unit, so
make it static to silence sparse warning:

  pinctrl-amdisp.c:83:26: warning: symbol 'amdisp_pinctrl_ops' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-amdisp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c
index efbf40c776ea..e0874cc086a7 100644
--- a/drivers/pinctrl/pinctrl-amdisp.c
+++ b/drivers/pinctrl/pinctrl-amdisp.c
@@ -80,7 +80,7 @@ static int amdisp_get_group_pins(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-const struct pinctrl_ops amdisp_pinctrl_ops = {
+static const struct pinctrl_ops amdisp_pinctrl_ops = {
 	.get_groups_count	= amdisp_get_groups_count,
 	.get_group_name		= amdisp_get_group_name,
 	.get_group_pins		= amdisp_get_group_pins,

From c2e174994c9e98956a85dee9af6fbb293f5ad673 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:58:40 +0100
Subject: [PATCH 0282/1303] pinctrl: cix: sky1: Unexport sky1_pinctrl_pm_ops

File-scope 'sky1_pinctrl_pm_ops' is not used outside of this unit (and
it should not be!), so unexport it and make it static to silence sparse
warning:

  pinctrl-sky1.c:525:25: warning: symbol 'sky1_pinctrl_pm_ops' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/cix/pinctrl-sky1.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pinctrl/cix/pinctrl-sky1.c b/drivers/pinctrl/cix/pinctrl-sky1.c
index 5d0d8be815b2..938894058d86 100644
--- a/drivers/pinctrl/cix/pinctrl-sky1.c
+++ b/drivers/pinctrl/cix/pinctrl-sky1.c
@@ -522,11 +522,10 @@ static int __maybe_unused sky1_pinctrl_resume(struct device *dev)
 	return pinctrl_force_default(spctl->pctl);
 }
 
-const struct dev_pm_ops sky1_pinctrl_pm_ops = {
+static const struct dev_pm_ops sky1_pinctrl_pm_ops = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(sky1_pinctrl_suspend,
 					sky1_pinctrl_resume)
 };
-EXPORT_SYMBOL_GPL(sky1_pinctrl_pm_ops);
 
 static int sky1_pinctrl_probe(struct platform_device *pdev)
 {

From e9e268ea9df102abef34d7afba59ef4d5868d5d7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:25:50 +0100
Subject: [PATCH 0283/1303] pinctrl: qcom: sdm660-lpass-lpi: Make groups and
 functions variables static

File-scope 'sdm660_lpi_pinctrl_groups' and
'sdm660_lpi_pinctrl_functions' are not used outside of this unit, so
make them static to silence sparse warnings:

  pinctrl-sdm660-lpass-lpi.c:79:27: warning: symbol 'sdm660_lpi_pinctrl_groups' was not declared. Should it be static?
  pinctrl-sdm660-lpass-lpi.c:116:27: warning: symbol 'sdm660_lpi_pinctrl_functions' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
index d93af5f0e8d3..65411abfbfac 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
@@ -76,7 +76,7 @@ static const char * const pdm_clk_groups[] = { "gpio18" };
 static const char * const pdm_rx_groups[] = { "gpio21", "gpio23", "gpio25" };
 static const char * const pdm_sync_groups[] = { "gpio19" };
 
-const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
+static const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(0, LPI_NO_SLEW, _, _, _, _, 0x0000),
 	LPI_PINGROUP_OFFSET(1, LPI_NO_SLEW, _, _, _, _, 0x1000),
 	LPI_PINGROUP_OFFSET(2, LPI_NO_SLEW, _, _, _, _, 0x2000),
@@ -113,7 +113,7 @@ const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(31, LPI_NO_SLEW, _, _, _, _, 0xb010),
 };
 
-const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
+static const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
 	LPI_FUNCTION(comp_rx),
 	LPI_FUNCTION(dmic1_clk),
 	LPI_FUNCTION(dmic1_data),

From a2539b92e4b791c1ba482930b5e51b1591975461 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 19 Feb 2026 00:51:22 +0800
Subject: [PATCH 0284/1303] pinctrl: meson: amlogic-a4: Fix device node
 reference leak in aml_dt_node_to_map_pinmux()

The of_get_parent() function returns a device_node with an incremented
reference count.

Use the __free(device_node) cleanup attribute to ensure of_node_put()
is automatically called when pnode goes out of scope, fixing a
reference leak.

Fixes: 6e9be3abb78c ("pinctrl: Add driver support for Amlogic SoCs")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
index dfa32b11555c..e2293a872dcb 100644
--- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
+++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
@@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 				     unsigned int *num_maps)
 {
 	struct device *dev = pctldev->dev;
-	struct device_node *pnode;
 	unsigned long *configs = NULL;
 	unsigned int num_configs = 0;
 	struct property *prop;
@@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 		return -ENOENT;
 	}
 
-	pnode = of_get_parent(np);
+	struct device_node *pnode __free(device_node) = of_get_parent(np);
 	if (!pnode) {
 		dev_info(dev, "Missing function node\n");
 		return -EINVAL;

From fd5bed798f45eb3a178ad527b43ab92705faaf8a Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Feb 2026 17:39:07 +0800
Subject: [PATCH 0285/1303] pinctrl: cirrus: cs42l43: Fix double-put in
 cs42l43_pin_probe()

devm_add_action_or_reset() already invokes the action on failure,
so the explicit put causes a double-put.

Fixes: 9b07cdf86a0b ("pinctrl: cirrus: Fix fwnode leak in cs42l43_pin_probe()")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
index a8f82104a384..227c37c360e1 100644
--- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
+++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
@@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 		if (child) {
 			ret = devm_add_action_or_reset(&pdev->dev,
 				cs42l43_fwnode_put, child);
-			if (ret) {
-				fwnode_handle_put(child);
+			if (ret)
 				return ret;
-			}
+
 			if (!child->dev)
 				child->dev = priv->dev;
 			fwnode = child;

From 45fe4592454368df24d18352be700ff40e7df0c0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 23 Feb 2026 11:57:18 +0100
Subject: [PATCH 0286/1303] pinctrl: rockchip: Fix configuring a deferred pin

Commit e2c58cbe3aff ("pinctrl: rockchip: Simplify locking with
scoped_guard()") added a scoped_guard() over existing code containing a
"break" instruction.  That "break" was for the outer (existing)
for-loop, which now exits inner, scoped_guard() loop.  If GPIO driver
did not probe, then driver will not bail out, but instead continue to
configure the pin.

Fix the issue by simplifying the code - the break in original code was
leading directly to end of the function returning 0, thus we can simply
return here rockchip_pinconf_defer_pin status.

Reported-by: David Lechner <dlechner@baylibre.com>
Closes: https://lore.kernel.org/r/f5b38942-a584-4e78-a893-de4a219070b2@baylibre.com/
Fixes: e2c58cbe3aff ("pinctrl: rockchip: Simplify locking with scoped_guard()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-rockchip.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index d87c0b1de616..f15b18f334ee 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3640,14 +3640,10 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			 * or the gpio driver hasn't probed yet.
 			 */
 			scoped_guard(mutex, &bank->deferred_lock) {
-				if (!gpio || !gpio->direction_output) {
-					rc = rockchip_pinconf_defer_pin(bank,
-									pin - bank->pin_base,
-									param, arg);
-					if (rc)
-						return rc;
-					break;
-				}
+				if (!gpio || !gpio->direction_output)
+					return rockchip_pinconf_defer_pin(bank,
+									  pin - bank->pin_base,
+									  param, arg);
 			}
 		}
 

From 01e10d0272b932f908b4f9b6609a10cb1f35fafe Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@kernel.org>
Date: Tue, 24 Feb 2026 17:24:18 +0800
Subject: [PATCH 0287/1303] pinctrl: sunxi: Implement gpiochip::get_direction()

After commit 471e998c0e31 ("gpiolib: remove redundant callback check"),
a warning will be printed if the gpio driver does not implement this
callback. The warning was added in commit e623c4303ed1 ("gpiolib:
sanitize the return value of gpio_chip::get_direction()"), but was
masked by the "redundant" check.

The warning can be triggered by any action that calls the callback,
such as dumping the GPIO state from /sys/kernel/debug/gpio.

Implement it for the sunxi driver. This is simply a matter of reading
out the mux value from the registers, then checking if it is one of
the GPIO functions and which direction it is.

Signed-off-by: Chen-Yu Tsai <wens@kernel.org>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/sunxi/pinctrl-sunxi.c | 51 +++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 48434292a39b..c990b6118172 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -204,6 +204,32 @@ sunxi_pinctrl_desc_find_function_by_pin(struct sunxi_pinctrl *pctl,
 	return NULL;
 }
 
+static struct sunxi_desc_function *
+sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl,
+						const u16 pin_num,
+						const u8 muxval)
+{
+	for (unsigned int i = 0; i < pctl->desc->npins; i++) {
+		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
+		struct sunxi_desc_function *func = pin->functions;
+
+		if (pin->pin.number != pin_num)
+			continue;
+
+		if (pin->variant && !(pctl->variant & pin->variant))
+			continue;
+
+		while (func->name) {
+			if (func->muxval == muxval)
+				return func;
+
+			func++;
+		}
+	}
+
+	return NULL;
+}
+
 static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
 {
 	struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
@@ -930,6 +956,30 @@ static const struct pinmux_ops sunxi_pmx_ops = {
 	.strict			= true,
 };
 
+static int sunxi_pinctrl_gpio_get_direction(struct gpio_chip *chip,
+					    unsigned int offset)
+{
+	struct sunxi_pinctrl *pctl = gpiochip_get_data(chip);
+	const struct sunxi_desc_function *func;
+	u32 pin = offset + chip->base;
+	u32 reg, shift, mask;
+	u8 muxval;
+
+	sunxi_mux_reg(pctl, offset, &reg, &shift, &mask);
+
+	muxval = (readl(pctl->membase + reg) & mask) >> shift;
+
+	func = sunxi_pinctrl_desc_find_function_by_pin_and_mux(pctl, pin, muxval);
+	if (!func)
+		return -ENODEV;
+
+	if (!strcmp(func->name, "gpio_out"))
+		return GPIO_LINE_DIRECTION_OUT;
+	if (!strcmp(func->name, "gpio_in") || !strcmp(func->name, "irq"))
+		return GPIO_LINE_DIRECTION_IN;
+	return -EINVAL;
+}
+
 static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip,
 					unsigned offset)
 {
@@ -1599,6 +1649,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 	pctl->chip->request = gpiochip_generic_request;
 	pctl->chip->free = gpiochip_generic_free;
 	pctl->chip->set_config = gpiochip_generic_config;
+	pctl->chip->get_direction = sunxi_pinctrl_gpio_get_direction;
 	pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input;
 	pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output;
 	pctl->chip->get = sunxi_pinctrl_gpio_get;

From fd80bd7105f88189f47d465ca8cb7d115570de30 Mon Sep 17 00:00:00 2001
From: Kamal Heib <kheib@redhat.com>
Date: Fri, 20 Feb 2026 17:21:26 -0500
Subject: [PATCH 0288/1303] RDMA/ionic: Fix potential NULL pointer dereference
 in ionic_query_port

The function ionic_query_port() calls ib_device_get_netdev() without
checking the return value which could lead to NULL pointer dereference,
Fix it by checking the return value and return -ENODEV if the 'ndev' is
NULL.

Fixes: 2075bbe8ef03 ("RDMA/ionic: Register device ops for miscellaneous functionality")
Signed-off-by: Kamal Heib <kheib@redhat.com>
Link: https://patch.msgid.link/20260220222125.16973-2-kheib@redhat.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/ionic/ionic_ibdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/ionic/ionic_ibdev.c b/drivers/infiniband/hw/ionic/ionic_ibdev.c
index 164046d00e5d..bd4c73e530d0 100644
--- a/drivers/infiniband/hw/ionic/ionic_ibdev.c
+++ b/drivers/infiniband/hw/ionic/ionic_ibdev.c
@@ -81,6 +81,8 @@ static int ionic_query_port(struct ib_device *ibdev, u32 port,
 		return -EINVAL;
 
 	ndev = ib_device_get_netdev(ibdev, port);
+	if (!ndev)
+		return -ENODEV;
 
 	if (netif_running(ndev) && netif_carrier_ok(ndev)) {
 		attr->state = IB_PORT_ACTIVE;

From f22c77ce49db0589103d96487dca56f5b2136362 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:47 -0400
Subject: [PATCH 0289/1303] RDMA/efa: Fix typo in efa_alloc_mr()

The pattern is to check the entire driver request space, not just
sizeof something unrelated.

Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/1-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Acked-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/efa/efa_verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index b5b93b42e6c4..b0aa7c0238ed 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1661,7 +1661,7 @@ static struct efa_mr *efa_alloc_mr(struct ib_pd *ibpd, int access_flags,
 	struct efa_mr *mr;
 
 	if (udata && udata->inlen &&
-	    !ib_is_udata_cleared(udata, 0, sizeof(udata->inlen))) {
+	    !ib_is_udata_cleared(udata, 0, udata->inlen)) {
 		ibdev_dbg(&dev->ibdev,
 			  "Incompatible ABI params, udata not cleared\n");
 		return ERR_PTR(-EINVAL);

From 117942ca43e2e3c3d121faae530989931b7f67e1 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:48 -0400
Subject: [PATCH 0290/1303] IB/mthca: Add missed mthca_unmap_user_db() for
 mthca_create_srq()

Fix a user triggerable leak on the system call failure path.

Cc: stable@vger.kernel.org
Fixes: ec34a922d243 ("[PATCH] IB/mthca: Add SRQ implementation")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/2-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mthca/mthca_provider.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index ef0635064fba..5c182ae4fc2f 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -428,6 +428,8 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 	if (context && ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) {
 		mthca_free_srq(to_mdev(ibsrq->device), srq);
+		mthca_unmap_user_db(to_mdev(ibsrq->device), &context->uar,
+				    context->db_tab, ucmd.db_index);
 		return -EFAULT;
 	}
 
@@ -436,6 +438,7 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
+	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	if (udata) {
 		struct mthca_ucontext *context =
 			rdma_udata_to_drv_context(
@@ -446,8 +449,6 @@ static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 		mthca_unmap_user_db(to_mdev(srq->device), &context->uar,
 				    context->db_tab, to_msrq(srq)->db_index);
 	}
-
-	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	return 0;
 }
 

From 74586c6da9ea222a61c98394f2fc0a604748438c Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:49 -0400
Subject: [PATCH 0291/1303] RDMA/irdma: Fix kernel stack leak in
 irdma_create_user_ah()

struct irdma_create_ah_resp {  // 8 bytes, no padding
    __u32 ah_id;               // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx)
    __u8  rsvd[4];             // offset 4 - NEVER SET <- LEAK
};

rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata().

The reserved members of the structure were not zeroed.

Cc: stable@vger.kernel.org
Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/3-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 15af53237217..7251cd7a2147 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -5212,7 +5212,7 @@ static int irdma_create_user_ah(struct ib_ah *ibah,
 #define IRDMA_CREATE_AH_MIN_RESP_LEN offsetofend(struct irdma_create_ah_resp, rsvd)
 	struct irdma_ah *ah = container_of(ibah, struct irdma_ah, ibah);
 	struct irdma_device *iwdev = to_iwdev(ibah->pd->device);
-	struct irdma_create_ah_resp uresp;
+	struct irdma_create_ah_resp uresp = {};
 	struct irdma_ah *parent_ah;
 	int err;
 

From faa72102b178c7ae6c6afea23879e7c84fc59b4e Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:50 -0400
Subject: [PATCH 0292/1303] RDMA/ionic: Fix kernel stack leak in
 ionic_create_cq()

struct ionic_cq_resp resp {
    __u32 cqid[2];         // offset 0 - PARTIALLY SET (see below)
    __u8  udma_mask;       // offset 8 - SET (resp.udma_mask = vcq->udma_mask)
    __u8  rsvd[7];         // offset 9 - NEVER SET <- LEAK
};

rsvd[7]: 7 bytes of stack memory leaked unconditionally.

cqid[2]: The loop at line 1256 iterates over udma_idx but skips indices
where !(vcq->udma_mask & BIT(udma_idx)). The array has 2 entries but
udma_count could be 1, meaning cqid[1] might never be written via
ionic_create_cq_common(). If udma_mask only has bit 0 set, cqid[1] (4
bytes) is also leaked. So potentially 11 bytes leaked.

Cc: stable@vger.kernel.org
Fixes: e8521822c733 ("RDMA/ionic: Register device ops for control path")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/4-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Acked-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/ionic/ionic_controlpath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/ionic/ionic_controlpath.c b/drivers/infiniband/hw/ionic/ionic_controlpath.c
index 5b3f40bd98d8..4842931f5316 100644
--- a/drivers/infiniband/hw/ionic/ionic_controlpath.c
+++ b/drivers/infiniband/hw/ionic/ionic_controlpath.c
@@ -1218,7 +1218,7 @@ int ionic_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		rdma_udata_to_drv_context(udata, struct ionic_ctx, ibctx);
 	struct ionic_vcq *vcq = to_ionic_vcq(ibcq);
 	struct ionic_tbl_buf buf = {};
-	struct ionic_cq_resp resp;
+	struct ionic_cq_resp resp = {};
 	struct ionic_cq_req req;
 	int udma_idx = 0, rc;
 

From 983512f3a87fd8dc4c94dfa6b596b6e57df5aad7 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 20 Feb 2026 19:38:58 +0100
Subject: [PATCH 0293/1303] net: Drop the lock in skb_may_tx_timestamp()

skb_may_tx_timestamp() may acquire sock::sk_callback_lock. The lock must
not be taken in IRQ context, only softirq is okay. A few drivers receive
the timestamp via a dedicated interrupt and complete the TX timestamp
from that handler. This will lead to a deadlock if the lock is already
write-locked on the same CPU.

Taking the lock can be avoided. The socket (pointed by the skb) will
remain valid until the skb is released. The ->sk_socket and ->file
member will be set to NULL once the user closes the socket which may
happen before the timestamp arrives.
If we happen to observe the pointer while the socket is closing but
before the pointer is set to NULL then we may use it because both
pointer (and the file's cred member) are RCU freed.

Drop the lock. Use READ_ONCE() to obtain the individual pointer. Add a
matching WRITE_ONCE() where the pointer are cleared.

Link: https://lore.kernel.org/all/20260205145104.iWinkXHv@linutronix.de
Fixes: b245be1f4db1a ("net-timestamp: no-payload only sysctl")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260220183858.N4ERjFW6@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sock.h |  2 +-
 net/core/skbuff.c  | 23 ++++++++++++++++++-----
 net/socket.c       |  2 +-
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 66b56288c1d3..6c9a83016e95 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2098,7 +2098,7 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk->sk_socket = sock;
+	WRITE_ONCE(sk->sk_socket, sock);
 	if (sock) {
 		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
 		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dc47d3efc72e..0e217041958a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5590,15 +5590,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 
 static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
-	bool ret;
+	struct socket *sock;
+	struct file *file;
+	bool ret = false;
 
 	if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data)))
 		return true;
 
-	read_lock_bh(&sk->sk_callback_lock);
-	ret = sk->sk_socket && sk->sk_socket->file &&
-	      file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
-	read_unlock_bh(&sk->sk_callback_lock);
+	/* The sk pointer remains valid as long as the skb is. The sk_socket and
+	 * file pointer may become NULL if the socket is closed. Both structures
+	 * (including file->cred) are RCU freed which means they can be accessed
+	 * within a RCU read section.
+	 */
+	rcu_read_lock();
+	sock = READ_ONCE(sk->sk_socket);
+	if (!sock)
+		goto out;
+	file = READ_ONCE(sock->file);
+	if (!file)
+		goto out;
+	ret = file_ns_capable(file, &init_user_ns, CAP_NET_RAW);
+out:
+	rcu_read_unlock();
 	return ret;
 }
 
diff --git a/net/socket.c b/net/socket.c
index 136b98c54fb3..05952188127f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -674,7 +674,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		iput(SOCK_INODE(sock));
 		return;
 	}
-	sock->file = NULL;
+	WRITE_ONCE(sock->file, NULL);
 }
 
 /**

From bf4fde7db4a8e2613cba36d81ac271f3d66c28f7 Mon Sep 17 00:00:00 2001
From: Ferry Meng <mengferry@linux.alibaba.com>
Date: Tue, 24 Feb 2026 14:02:07 +0800
Subject: [PATCH 0294/1303] erofs: remove more unnecessary #ifdefs

Many #ifdefs can be replaced with IS_ENABLED() to improve code
readability.  No functional changes.

Signed-off-by: Ferry Meng <mengferry@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/super.c | 83 ++++++++++++++++++++----------------------------
 1 file changed, 35 insertions(+), 48 deletions(-)

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index d4995686ac6c..972a0c82198d 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -424,26 +424,23 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 
 static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
 {
-#ifdef CONFIG_FS_DAX
-	struct erofs_sb_info *sbi = fc->s_fs_info;
+	if (IS_ENABLED(CONFIG_FS_DAX)) {
+		struct erofs_sb_info *sbi = fc->s_fs_info;
 
-	switch (mode) {
-	case EROFS_MOUNT_DAX_ALWAYS:
-		set_opt(&sbi->opt, DAX_ALWAYS);
-		clear_opt(&sbi->opt, DAX_NEVER);
-		return true;
-	case EROFS_MOUNT_DAX_NEVER:
-		set_opt(&sbi->opt, DAX_NEVER);
-		clear_opt(&sbi->opt, DAX_ALWAYS);
-		return true;
-	default:
+		if (mode == EROFS_MOUNT_DAX_ALWAYS) {
+			set_opt(&sbi->opt, DAX_ALWAYS);
+			clear_opt(&sbi->opt, DAX_NEVER);
+			return true;
+		} else if (mode == EROFS_MOUNT_DAX_NEVER) {
+			set_opt(&sbi->opt, DAX_NEVER);
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+			return true;
+		}
 		DBG_BUGON(1);
 		return false;
 	}
-#else
 	errorfc(fc, "dax options not supported");
 	return false;
-#endif
 }
 
 static int erofs_fc_parse_param(struct fs_context *fc,
@@ -460,31 +457,26 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 
 	switch (opt) {
 	case Opt_user_xattr:
-#ifdef CONFIG_EROFS_FS_XATTR
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_XATTR))
+			errorfc(fc, "{,no}user_xattr options not supported");
+		else if (result.boolean)
 			set_opt(&sbi->opt, XATTR_USER);
 		else
 			clear_opt(&sbi->opt, XATTR_USER);
-#else
-		errorfc(fc, "{,no}user_xattr options not supported");
-#endif
 		break;
 	case Opt_acl:
-#ifdef CONFIG_EROFS_FS_POSIX_ACL
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL))
+			errorfc(fc, "{,no}acl options not supported");
+		else if (result.boolean)
 			set_opt(&sbi->opt, POSIX_ACL);
 		else
 			clear_opt(&sbi->opt, POSIX_ACL);
-#else
-		errorfc(fc, "{,no}acl options not supported");
-#endif
 		break;
 	case Opt_cache_strategy:
-#ifdef CONFIG_EROFS_FS_ZIP
-		sbi->opt.cache_strategy = result.uint_32;
-#else
-		errorfc(fc, "compression not supported, cache_strategy ignored");
-#endif
+		if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP))
+			errorfc(fc, "compression not supported, cache_strategy ignored");
+		else
+			sbi->opt.cache_strategy = result.uint_32;
 		break;
 	case Opt_dax:
 		if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS))
@@ -533,24 +525,21 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		break;
 #endif
 	case Opt_directio:
-#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE))
+			errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		else if (result.boolean)
 			set_opt(&sbi->opt, DIRECT_IO);
 		else
 			clear_opt(&sbi->opt, DIRECT_IO);
-#else
-		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
-#endif
 		break;
 	case Opt_fsoffset:
 		sbi->dif0.fsoff = result.uint_64;
 		break;
 	case Opt_inode_share:
-#ifdef CONFIG_EROFS_FS_PAGE_CACHE_SHARE
-		set_opt(&sbi->opt, INODE_SHARE);
-#else
-		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
-#endif
+		if (!IS_ENABLED(CONFIG_EROFS_FS_PAGE_CACHE_SHARE))
+			errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		else
+			set_opt(&sbi->opt, INODE_SHARE);
 		break;
 	}
 	return 0;
@@ -809,8 +798,7 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 	ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
 		IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ?
 			GET_TREE_BDEV_QUIET_LOOKUP : 0);
-#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
-	if (ret == -ENOTBLK) {
+	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && ret == -ENOTBLK) {
 		struct file *file;
 
 		if (!fc->source)
@@ -824,7 +812,6 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 		    sbi->dif0.file->f_mapping->a_ops->read_folio)
 			return get_tree_nodev(fc, erofs_fc_fill_super);
 	}
-#endif
 	return ret;
 }
 
@@ -1108,12 +1095,12 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",dax=never");
 	if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
 		seq_puts(seq, ",directio");
-#ifdef CONFIG_EROFS_FS_ONDEMAND
-	if (sbi->fsid)
-		seq_printf(seq, ",fsid=%s", sbi->fsid);
-	if (sbi->domain_id)
-		seq_printf(seq, ",domain_id=%s", sbi->domain_id);
-#endif
+	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND)) {
+		if (sbi->fsid)
+			seq_printf(seq, ",fsid=%s", sbi->fsid);
+		if (sbi->domain_id)
+			seq_printf(seq, ",domain_id=%s", sbi->domain_id);
+	}
 	if (sbi->dif0.fsoff)
 		seq_printf(seq, ",fsoffset=%llu", sbi->dif0.fsoff);
 	if (test_opt(opt, INODE_SHARE))

From 3d7e6ce34f4fcc7083510c28b17a7c36462a25d4 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Sun, 22 Feb 2026 05:06:33 +0000
Subject: [PATCH 0295/1303] net: usb: pegasus: enable basic endpoint checking

pegasus_probe() fills URBs with hardcoded endpoint pipes without
verifying the endpoint descriptors:

  - usb_rcvbulkpipe(dev, 1) for RX data
  - usb_sndbulkpipe(dev, 2) for TX data
  - usb_rcvintpipe(dev, 3)  for status interrupts

A malformed USB device can present these endpoints with transfer types
that differ from what the driver assumes.

Add a pegasus_usb_ep enum for endpoint numbers, replacing magic
constants throughout. Add usb_check_bulk_endpoints() and
usb_check_int_endpoints() calls before any resource allocation to
verify endpoint types before use, rejecting devices with mismatched
descriptors at probe time, and avoid triggering assertion.

Similar fix to
- commit 90b7f2961798 ("net: usb: rtl8150: enable basic endpoint checking")
- commit 9e7021d2aeae ("net: usb: catc: enable basic endpoint checking")

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260222050633.410165-1-n7l8m4@u.northwestern.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/pegasus.c | 35 ++++++++++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 7b6d6eb60709..b84968c5f074 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -28,6 +28,17 @@ static const char driver_name[] = "pegasus";
 			BMSR_100FULL | BMSR_ANEGCAPABLE)
 #define CARRIER_CHECK_DELAY (2 * HZ)
 
+/*
+ * USB endpoints.
+ */
+
+enum pegasus_usb_ep {
+	PEGASUS_USB_EP_CONTROL	= 0,
+	PEGASUS_USB_EP_BULK_IN	= 1,
+	PEGASUS_USB_EP_BULK_OUT	= 2,
+	PEGASUS_USB_EP_INT_IN	= 3,
+};
+
 static bool loopback;
 static bool mii_mode;
 static char *devid;
@@ -542,7 +553,7 @@ static void read_bulk_callback(struct urb *urb)
 		goto tl_sched;
 goon:
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 	rx_status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC);
@@ -582,7 +593,7 @@ static void rx_fixup(struct tasklet_struct *t)
 		return;
 	}
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 try_again:
@@ -710,7 +721,7 @@ static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
 	((__le16 *) pegasus->tx_buff)[0] = cpu_to_le16(l16);
 	skb_copy_from_linear_data(skb, pegasus->tx_buff + 2, skb->len);
 	usb_fill_bulk_urb(pegasus->tx_urb, pegasus->usb,
-			  usb_sndbulkpipe(pegasus->usb, 2),
+			  usb_sndbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_OUT),
 			  pegasus->tx_buff, count,
 			  write_bulk_callback, pegasus);
 	if ((res = usb_submit_urb(pegasus->tx_urb, GFP_ATOMIC))) {
@@ -837,7 +848,7 @@ static int pegasus_open(struct net_device *net)
 	set_registers(pegasus, EthID, 6, net->dev_addr);
 
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 	if ((res = usb_submit_urb(pegasus->rx_urb, GFP_KERNEL))) {
@@ -848,7 +859,7 @@ static int pegasus_open(struct net_device *net)
 	}
 
 	usb_fill_int_urb(pegasus->intr_urb, pegasus->usb,
-			 usb_rcvintpipe(pegasus->usb, 3),
+			 usb_rcvintpipe(pegasus->usb, PEGASUS_USB_EP_INT_IN),
 			 pegasus->intr_buff, sizeof(pegasus->intr_buff),
 			 intr_callback, pegasus, pegasus->intr_interval);
 	if ((res = usb_submit_urb(pegasus->intr_urb, GFP_KERNEL))) {
@@ -1133,10 +1144,24 @@ static int pegasus_probe(struct usb_interface *intf,
 	pegasus_t *pegasus;
 	int dev_index = id - pegasus_ids;
 	int res = -ENOMEM;
+	static const u8 bulk_ep_addr[] = {
+		PEGASUS_USB_EP_BULK_IN | USB_DIR_IN,
+		PEGASUS_USB_EP_BULK_OUT | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		PEGASUS_USB_EP_INT_IN | USB_DIR_IN,
+		0};
 
 	if (pegasus_blacklisted(dev))
 		return -ENODEV;
 
+	/* Verify that all required endpoints are present */
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(&intf->dev, "Missing or invalid endpoints\n");
+		return -ENODEV;
+	}
+
 	net = alloc_etherdev(sizeof(struct pegasus));
 	if (!net)
 		goto out;

From 4a1ddb0f1c48c2b56f21d8b5200e2e29adf4c1df Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Feb 2026 12:09:00 +0100
Subject: [PATCH 0296/1303] pidfs: avoid misleading break

The break would only break out of the scoped_guard() loop, not the
switch statement. It still works correct as is ofc but let's avoid the
confusion.

Reported-by: David Lechner <dlechner@baylibre.com>
Link:: https://lore.kernel.org/cd2153f1-098b-463c-bbc1-5c6ca9ef1f12@baylibre.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 1e20e36e0ed5..21f9f011a957 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -577,9 +577,8 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			struct user_namespace *user_ns;
 
 			user_ns = task_cred_xxx(task, user_ns);
-			if (!ns_ref_get(user_ns))
-				break;
-			ns_common = to_ns_common(user_ns);
+			if (ns_ref_get(user_ns))
+				ns_common = to_ns_common(user_ns);
 		}
 #endif
 		break;
@@ -589,9 +588,8 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			struct pid_namespace *pid_ns;
 
 			pid_ns = task_active_pid_ns(task);
-			if (!ns_ref_get(pid_ns))
-				break;
-			ns_common = to_ns_common(pid_ns);
+			if (ns_ref_get(pid_ns))
+				ns_common = to_ns_common(pid_ns);
 		}
 #endif
 		break;

From c8dbdc6e380e7e96a51706db3e4b7870d8a9402d Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 22 Feb 2026 16:26:01 +0100
Subject: [PATCH 0297/1303] net: phy: register phy led_triggers during probe to
 avoid AB-BA deadlock

There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and
LED_TRIGGER_PHY are enabled:

[ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc             <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock);
[ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234
[ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c
[ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c
[ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0
[ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0
[ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c
[ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78
[ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654                       <-- Hold lock "rtnl_mutex" by calling rtnl_lock();
[ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0
[ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c
[ 1362.104022] [<80014504>] syscall_common+0x34/0x58

Here LED_TRIGGER_PHY is registering LED triggers during phy_attach
while holding RTNL and then taking triggers_list_lock.

[ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168      <-- Trying to get lock "rtnl_mutex" via rtnl_lock();
[ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4
[ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360                 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock);
[ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c
[ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc
[ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c
[ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4
[ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c
[ 1362.232164] [<80014504>] syscall_common+0x34/0x58

Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes
triggers_list_lock and then RTNL. A classical AB-BA deadlock.

phy_led_triggers_registers() does not require the RTNL, it does not
make any calls into the network stack which require protection. There
is also no requirement the PHY has been attached to a MAC, the
triggers only make use of phydev state. This allows the call to
phy_led_triggers_registers() to be placed elsewhere. PHY probe() and
release() don't hold RTNL, so solving the AB-BA deadlock.

Reported-by: Shiji Yang <yangshiji66@outlook.com>
Closes: https://lore.kernel.org/all/OS7PR01MB13602B128BA1AD3FA38B6D1FFBC69A@OS7PR01MB13602.jpnprd01.prod.outlook.com/
Fixes: 06f502f57d0d ("leds: trigger: Introduce a NETDEV trigger")
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Shiji Yang <yangshiji66@outlook.com>
Link: https://patch.msgid.link/20260222152601.1978655-1-andrew@lunn.ch
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy_device.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9b8eaac63b90..cbb4af604aa5 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1866,8 +1866,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error;
 
 	phy_resume(phydev);
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_register(phydev);
 
 	/**
 	 * If the external phy used by current mac interface is managed by
@@ -1982,9 +1980,6 @@ void phy_detach(struct phy_device *phydev)
 	phydev->phy_link_change = NULL;
 	phydev->phylink = NULL;
 
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_unregister(phydev);
-
 	if (phydev->mdio.dev.driver)
 		module_put(phydev->mdio.dev.driver->owner);
 
@@ -3778,16 +3773,27 @@ static int phy_probe(struct device *dev)
 	/* Set the state to READY by default */
 	phydev->state = PHY_READY;
 
+	/* Register the PHY LED triggers */
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_register(phydev);
+
 	/* Get the LEDs from the device tree, and instantiate standard
 	 * LEDs for them.
 	 */
-	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
+	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev)) {
 		err = of_phy_leds(phydev);
+		if (err)
+			goto out;
+	}
+
+	return 0;
 
 out:
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	/* Re-assert the reset signal on error */
-	if (err)
-		phy_device_reset(phydev, 1);
+	phy_device_reset(phydev, 1);
 
 	return err;
 }
@@ -3801,6 +3807,9 @@ static int phy_remove(struct device *dev)
 	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
 		phy_leds_unregister(phydev);
 
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	phydev->state = PHY_DOWN;
 
 	phy_cleanup_ports(phydev);

From 78437ab3b769f80526416570f60173c89858dd84 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 13 Feb 2026 00:58:11 +0100
Subject: [PATCH 0298/1303] clk: scu/imx8qxp: do not register driver in probe()

imx_clk_scu_init() registers the imx_clk_scu_driver while commonly being
called from IMX driver's probe() callbacks.

However, it neither makes sense to register drivers from probe()
callbacks of other drivers, nor does the driver core allow registering
drivers with a device lock already being held.

The latter was revealed by commit dc23806a7c47 ("driver core: enforce
device_lock for driver_match_device()") leading to a deadlock condition
described in [1].

Besides that, nothing seems to unregister the imx_clk_scu_driver once
the corresponding driver module is unloaded, which leaves the
driver-core with a dangling pointer.

Also, if there are multiple matching devices for the imx8qxp_clk_driver,
imx8qxp_clk_probe() calls imx_clk_scu_init() multiple times.  However,
any subsequent call after the first one will fail, since the driver-core
does not allow to register the same struct platform_driver multiple
times.

Hence, register the imx_clk_scu_driver from module_init() and unregister
it in module_exit().

Note that we first register the imx8qxp_clk_driver and then call
imx_clk_scu_module_init() to avoid having to call
imx_clk_scu_module_exit() in the unwind path of imx8qxp_clk_init().

Fixes: dc23806a7c47 ("driver core: enforce device_lock for driver_match_device()")
Fixes: 220175cd3979 ("clk: imx: scu: fix build break when compiled as modules")
Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Closes: https://lore.kernel.org/lkml/13955113.uLZWGnKmhe@steina-w/
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com> # TQMa8x/MBa8x
Link: https://lore.kernel.org/lkml/DFU7CEPUSG9A.1KKGVW4HIPMSH@kernel.org/ [1]
Acked-by: Abel Vesa <abelvesa@kernel.org>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://patch.msgid.link/20260212235842.85934-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/clk/imx/clk-imx8qxp.c | 24 +++++++++++++++++++++++-
 drivers/clk/imx/clk-scu.c     | 12 +++++++++++-
 drivers/clk/imx/clk-scu.h     |  2 ++
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
index 3ae162625bb1..c781425a005e 100644
--- a/drivers/clk/imx/clk-imx8qxp.c
+++ b/drivers/clk/imx/clk-imx8qxp.c
@@ -346,7 +346,29 @@ static struct platform_driver imx8qxp_clk_driver = {
 	},
 	.probe = imx8qxp_clk_probe,
 };
-module_platform_driver(imx8qxp_clk_driver);
+
+static int __init imx8qxp_clk_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&imx8qxp_clk_driver);
+	if (ret)
+		return ret;
+
+	ret = imx_clk_scu_module_init();
+	if (ret)
+		platform_driver_unregister(&imx8qxp_clk_driver);
+
+	return ret;
+}
+module_init(imx8qxp_clk_init);
+
+static void __exit imx8qxp_clk_exit(void)
+{
+	imx_clk_scu_module_exit();
+	platform_driver_unregister(&imx8qxp_clk_driver);
+}
+module_exit(imx8qxp_clk_exit);
 
 MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
 MODULE_DESCRIPTION("NXP i.MX8QXP clock driver");
diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c
index 33e637ad3579..a85ec48a798b 100644
--- a/drivers/clk/imx/clk-scu.c
+++ b/drivers/clk/imx/clk-scu.c
@@ -191,6 +191,16 @@ static bool imx_scu_clk_is_valid(u32 rsrc_id)
 	return p != NULL;
 }
 
+int __init imx_clk_scu_module_init(void)
+{
+	return platform_driver_register(&imx_clk_scu_driver);
+}
+
+void __exit imx_clk_scu_module_exit(void)
+{
+	return platform_driver_unregister(&imx_clk_scu_driver);
+}
+
 int imx_clk_scu_init(struct device_node *np,
 		     const struct imx_clk_scu_rsrc_table *data)
 {
@@ -215,7 +225,7 @@ int imx_clk_scu_init(struct device_node *np,
 		rsrc_table = data;
 	}
 
-	return platform_driver_register(&imx_clk_scu_driver);
+	return 0;
 }
 
 /*
diff --git a/drivers/clk/imx/clk-scu.h b/drivers/clk/imx/clk-scu.h
index af7b697f51ca..ca82f2cce897 100644
--- a/drivers/clk/imx/clk-scu.h
+++ b/drivers/clk/imx/clk-scu.h
@@ -25,6 +25,8 @@ extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8dxl;
 extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qxp;
 extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qm;
 
+int __init imx_clk_scu_module_init(void);
+void __exit imx_clk_scu_module_exit(void);
 int imx_clk_scu_init(struct device_node *np,
 		     const struct imx_clk_scu_rsrc_table *data);
 struct clk_hw *imx_scu_of_clk_src_get(struct of_phandle_args *clkspec,

From fb73d0e19f12b793bfe013171d931587f37e3552 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Mon, 23 Feb 2026 13:10:20 +0530
Subject: [PATCH 0299/1303] MAINTAINERS: Update AMD XGBE driver maintainers

Due to additional responsibilities, Shyam Sundar S K will no longer be
supporting the AMD XGBE driver. Maintenance will be handled by
Raju Rangoju going forward.

Cc: Raju Rangoju <Raju.Rangoju@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://patch.msgid.link/20260223074020.1987884-1-Shyam-sundar.S-k@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e1a6c6cc2b7c..cf0313ca6039 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1292,7 +1292,6 @@ F:	include/trace/events/amdxdna.h
 F:	include/uapi/drm/amdxdna_accel.h
 
 AMD XGBE DRIVER
-M:	"Shyam Sundar S K" <Shyam-sundar.S-k@amd.com>
 M:	Raju Rangoju <Raju.Rangoju@amd.com>
 L:	netdev@vger.kernel.org
 S:	Maintained

From ab39cc4cb8ceecdc2b61747433e7237f1ac2b789 Mon Sep 17 00:00:00 2001
From: David Arcari <darcari@redhat.com>
Date: Tue, 24 Feb 2026 07:21:06 -0500
Subject: [PATCH 0300/1303] cpufreq: intel_pstate: Fix NULL pointer dereference
 in update_cpu_qos_request()

The update_cpu_qos_request() function attempts to initialize the 'freq'
variable by dereferencing 'cpudata' before verifying if the 'policy'
is valid.

This issue occurs on systems booted with the "nosmt" parameter, where
all_cpu_data[cpu] is NULL for the SMT sibling threads. As a result,
any call to update_qos_requests() will result in a NULL pointer
dereference as the code will attempt to access pstate.turbo_freq using
the NULL cpudata pointer.

Also, pstate.turbo_freq may be updated by intel_pstate_get_hwp_cap()
after initializing the 'freq' variable, so it is better to defer the
'freq' until intel_pstate_get_hwp_cap() has been called.

Fix this by deferring the 'freq' assignment until after the policy and
driver_data have been validated.

Fixes: ae1bdd23b99f ("cpufreq: intel_pstate: Adjust frequency percentage computations")
Reported-by: Jirka Hladky <jhladky@redhat.com>
Closes: https://lore.kernel.org/all/CAE4VaGDfiPvz3AzrwrwM4kWB3SCkMci25nPO8W1JmTBd=xHzZg@mail.gmail.com/
Signed-off-by: David Arcari <darcari@redhat.com>
Cc: 6.18+ <stable@vger.kernel.org> # 6.18+
[ rjw: Added one paragraph to the changelog ]
Link: https://patch.msgid.link/20260224122106.228116-1-darcari@redhat.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a48af3540c74..bdc37080d319 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1647,8 +1647,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type)
 {
 	struct cpudata *cpudata = all_cpu_data[cpu];
-	unsigned int freq = cpudata->pstate.turbo_freq;
 	struct freq_qos_request *req;
+	unsigned int freq;
 
 	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	if (!policy)
@@ -1661,6 +1661,8 @@ static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type)
 	if (hwp_active)
 		intel_pstate_get_hwp_cap(cpudata);
 
+	freq = cpudata->pstate.turbo_freq;
+
 	if (type == FREQ_QOS_MIN) {
 		freq = DIV_ROUND_UP(freq * global.min_perf_pct, 100);
 	} else {

From 5ede90206273ff156a778254f0f972a55e973c89 Mon Sep 17 00:00:00 2001
From: Sofia Schneider <sofia@schn.dev>
Date: Sun, 22 Feb 2026 23:52:40 -0300
Subject: [PATCH 0301/1303] ACPI: OSI: Add DMI quirk for Acer Aspire One D255

The screen backlight turns off during boot (specifically during udev device
initialization) when returning true for _OSI("Windows 2009").

Analyzing the device's DSDT reveals that the firmware takes a different
code path when Windows 7 is reported, which leads to the backlight shutoff.
Add a DMI quirk to invoke dmi_disable_osi_win7 for this model.

Signed-off-by: Sofia Schneider <sofia@schn.dev>
Link: https://patch.msgid.link/20260223025240.518509-1-sofia@schn.dev
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osi.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index f2c943b934be..9470f1830ff5 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -389,6 +389,19 @@ static const struct dmi_system_id acpi_osi_dmi_table[] __initconst = {
 		},
 	},
 
+	/*
+	 * The screen backlight turns off during udev device creation
+	 * when returning true for _OSI("Windows 2009")
+	 */
+	{
+	.callback = dmi_disable_osi_win7,
+	.ident = "Acer Aspire One D255",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "AOD255"),
+		},
+	},
+
 	/*
 	 * The wireless hotkey does not work on those machines when
 	 * returning true for _OSI("Windows 2012")

From e710b2283725f0db9e5b99c2483df3f4a7feadbd Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Mon, 23 Feb 2026 11:04:48 +0100
Subject: [PATCH 0302/1303] Revert "hwmon: add SMARC-sAM67 support"

This reverts commit 443b39c82c322c9f3c38bea0389fe927ba00b3b4.

I was just informed that this product is discontinued (without being
ever released to the market). Pull the plug and let's not waste any more
maintainers time.

Signed-off-by: Michael Walle <mwalle@kernel.org>
Link: https://lore.kernel.org/r/20260223100459.844967-4-mwalle@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/index.rst |   1 -
 Documentation/hwmon/sa67.rst  |  41 ---------
 MAINTAINERS                   |   1 -
 drivers/hwmon/Kconfig         |  10 ---
 drivers/hwmon/Makefile        |   1 -
 drivers/hwmon/sa67mcu-hwmon.c | 161 ----------------------------------
 6 files changed, 215 deletions(-)
 delete mode 100644 Documentation/hwmon/sa67.rst
 delete mode 100644 drivers/hwmon/sa67mcu-hwmon.c

diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index d91dbb20c7dc..b2ca8513cfcd 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -220,7 +220,6 @@ Hardware Monitoring Kernel Drivers
    q54sj108a2
    qnap-mcu-hwmon
    raspberrypi-hwmon
-   sa67
    sbrmi
    sbtsi_temp
    sch5627
diff --git a/Documentation/hwmon/sa67.rst b/Documentation/hwmon/sa67.rst
deleted file mode 100644
index 029c7c169b7f..000000000000
--- a/Documentation/hwmon/sa67.rst
+++ /dev/null
@@ -1,41 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0-only
-
-Kernel driver sa67mcu
-=====================
-
-Supported chips:
-
-   * Kontron sa67mcu
-
-     Prefix: 'sa67mcu'
-
-     Datasheet: not available
-
-Authors: Michael Walle <mwalle@kernel.org>
-
-Description
------------
-
-The sa67mcu is a board management controller which also exposes a hardware
-monitoring controller.
-
-The controller has two voltage and one temperature sensor. The values are
-hold in two 8 bit registers to form one 16 bit value. Reading the lower byte
-will also capture the high byte to make the access atomic. The unit of the
-volatge sensors are 1mV and the unit of the temperature sensor is 0.1degC.
-
-Sysfs entries
--------------
-
-The following attributes are supported.
-
-======================= ========================================================
-in0_label		"VDDIN"
-in0_input		Measured VDDIN voltage.
-
-in1_label		"VDD_RTC"
-in1_input		Measured VDD_RTC voltage.
-
-temp1_input		MCU temperature. Roughly the board temperature.
-======================= ========================================================
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..d5a2078a6717 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24337,7 +24337,6 @@ F:	Documentation/devicetree/bindings/interrupt-controller/kontron,sl28cpld-intc.
 F:	Documentation/devicetree/bindings/pwm/kontron,sl28cpld-pwm.yaml
 F:	Documentation/devicetree/bindings/watchdog/kontron,sl28cpld-wdt.yaml
 F:	drivers/gpio/gpio-sl28cpld.c
-F:	drivers/hwmon/sa67mcu-hwmon.c
 F:	drivers/hwmon/sl28cpld-hwmon.c
 F:	drivers/irqchip/irq-sl28cpld.c
 F:	drivers/pwm/pwm-sl28cpld.c
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 41c381764c2b..486152a8ea77 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1927,16 +1927,6 @@ config SENSORS_RASPBERRYPI_HWMON
 	  This driver can also be built as a module. If so, the module
 	  will be called raspberrypi-hwmon.
 
-config SENSORS_SA67MCU
-	tristate "Kontron sa67mcu hardware monitoring driver"
-	depends on MFD_SL28CPLD || COMPILE_TEST
-	help
-	  If you say yes here you get support for the voltage and temperature
-	  monitor of the sa67 board management controller.
-
-	  This driver can also be built as a module.  If so, the module
-	  will be called sa67mcu-hwmon.
-
 config SENSORS_SL28CPLD
 	tristate "Kontron sl28cpld hardware monitoring driver"
 	depends on MFD_SL28CPLD || COMPILE_TEST
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index eade8e3b1bde..5833c807c688 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -199,7 +199,6 @@ obj-$(CONFIG_SENSORS_PT5161L)	+= pt5161l.o
 obj-$(CONFIG_SENSORS_PWM_FAN)	+= pwm-fan.o
 obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON)	+= qnap-mcu-hwmon.o
 obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON)	+= raspberrypi-hwmon.o
-obj-$(CONFIG_SENSORS_SA67MCU)	+= sa67mcu-hwmon.o
 obj-$(CONFIG_SENSORS_SBTSI)	+= sbtsi_temp.o
 obj-$(CONFIG_SENSORS_SBRMI)	+= sbrmi.o
 obj-$(CONFIG_SENSORS_SCH56XX_COMMON)+= sch56xx-common.o
diff --git a/drivers/hwmon/sa67mcu-hwmon.c b/drivers/hwmon/sa67mcu-hwmon.c
deleted file mode 100644
index 22f703b7b256..000000000000
--- a/drivers/hwmon/sa67mcu-hwmon.c
+++ /dev/null
@@ -1,161 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sl67mcu hardware monitoring driver
- *
- * Copyright 2025 Kontron Europe GmbH
- */
-
-#include <linux/bitfield.h>
-#include <linux/hwmon.h>
-#include <linux/kernel.h>
-#include <linux/mod_devicetable.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/property.h>
-#include <linux/regmap.h>
-
-#define SA67MCU_VOLTAGE(n)	(0x00 + ((n) * 2))
-#define SA67MCU_TEMP(n)		(0x04 + ((n) * 2))
-
-struct sa67mcu_hwmon {
-	struct regmap *regmap;
-	u32 offset;
-};
-
-static int sa67mcu_hwmon_read(struct device *dev,
-			      enum hwmon_sensor_types type, u32 attr,
-			      int channel, long *input)
-{
-	struct sa67mcu_hwmon *hwmon = dev_get_drvdata(dev);
-	unsigned int offset;
-	u8 reg[2];
-	int ret;
-
-	switch (type) {
-	case hwmon_in:
-		switch (attr) {
-		case hwmon_in_input:
-			offset = hwmon->offset + SA67MCU_VOLTAGE(channel);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		break;
-	case hwmon_temp:
-		switch (attr) {
-		case hwmon_temp_input:
-			offset = hwmon->offset + SA67MCU_TEMP(channel);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	/* Reading the low byte will capture the value */
-	ret = regmap_bulk_read(hwmon->regmap, offset, reg, ARRAY_SIZE(reg));
-	if (ret)
-		return ret;
-
-	*input = reg[1] << 8 | reg[0];
-
-	/* Temperatures are s16 and in 0.1degC steps. */
-	if (type == hwmon_temp)
-		*input = sign_extend32(*input, 15) * 100;
-
-	return 0;
-}
-
-static const struct hwmon_channel_info * const sa67mcu_hwmon_info[] = {
-	HWMON_CHANNEL_INFO(in,
-			   HWMON_I_INPUT | HWMON_I_LABEL,
-			   HWMON_I_INPUT | HWMON_I_LABEL),
-	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
-	NULL
-};
-
-static const char *const sa67mcu_hwmon_in_labels[] = {
-	"VDDIN",
-	"VDD_RTC",
-};
-
-static int sa67mcu_hwmon_read_string(struct device *dev,
-				     enum hwmon_sensor_types type, u32 attr,
-				     int channel, const char **str)
-{
-	switch (type) {
-	case hwmon_in:
-		switch (attr) {
-		case hwmon_in_label:
-			*str = sa67mcu_hwmon_in_labels[channel];
-			return 0;
-		default:
-			return -EOPNOTSUPP;
-		}
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static const struct hwmon_ops sa67mcu_hwmon_ops = {
-	.visible = 0444,
-	.read = sa67mcu_hwmon_read,
-	.read_string = sa67mcu_hwmon_read_string,
-};
-
-static const struct hwmon_chip_info sa67mcu_hwmon_chip_info = {
-	.ops = &sa67mcu_hwmon_ops,
-	.info = sa67mcu_hwmon_info,
-};
-
-static int sa67mcu_hwmon_probe(struct platform_device *pdev)
-{
-	struct sa67mcu_hwmon *hwmon;
-	struct device *hwmon_dev;
-	int ret;
-
-	if (!pdev->dev.parent)
-		return -ENODEV;
-
-	hwmon = devm_kzalloc(&pdev->dev, sizeof(*hwmon), GFP_KERNEL);
-	if (!hwmon)
-		return -ENOMEM;
-
-	hwmon->regmap = dev_get_regmap(pdev->dev.parent, NULL);
-	if (!hwmon->regmap)
-		return -ENODEV;
-
-	ret = device_property_read_u32(&pdev->dev, "reg", &hwmon->offset);
-	if (ret)
-		return -EINVAL;
-
-	hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev,
-							 "sa67mcu_hwmon", hwmon,
-							 &sa67mcu_hwmon_chip_info,
-							 NULL);
-	if (IS_ERR(hwmon_dev))
-		dev_err(&pdev->dev, "failed to register as hwmon device");
-
-	return PTR_ERR_OR_ZERO(hwmon_dev);
-}
-
-static const struct of_device_id sa67mcu_hwmon_of_match[] = {
-	{ .compatible = "kontron,sa67mcu-hwmon", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, sa67mcu_hwmon_of_match);
-
-static struct platform_driver sa67mcu_hwmon_driver = {
-	.probe = sa67mcu_hwmon_probe,
-	.driver = {
-		.name = "sa67mcu-hwmon",
-		.of_match_table = sa67mcu_hwmon_of_match,
-	},
-};
-module_platform_driver(sa67mcu_hwmon_driver);
-
-MODULE_DESCRIPTION("sa67mcu Hardware Monitoring Driver");
-MODULE_AUTHOR("Michael Walle <mwalle@kernel.org>");
-MODULE_LICENSE("GPL");

From 364410170ab33f6e7ef0eb2afb12bf89b0feb3a6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 5 Feb 2026 07:59:20 -0500
Subject: [PATCH 0303/1303] nfsd: report the requested maximum number of
 threads instead of number running

The current netlink and /proc interfaces deviate from their traditional
values when dynamic threading is enabled, and there is currently no way
to know what the current setting is. This patch brings the reporting
back in line with traditional behavior.

Make these interfaces report the requested maximum number of threads
instead of the number currently running. Also, update documentation and
comments to reflect that this value represents a maximum and not the
number currently running.

Fixes: d8316b837c2c ("nfsd: add controls to set the minimum number of threads per pool")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 Documentation/netlink/specs/nfsd.yaml |  4 ++--
 fs/nfsd/nfsctl.c                      | 18 +++++++++---------
 fs/nfsd/nfssvc.c                      |  7 ++++---
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml
index badb2fe57c98..f87b5a05e5e9 100644
--- a/Documentation/netlink/specs/nfsd.yaml
+++ b/Documentation/netlink/specs/nfsd.yaml
@@ -152,7 +152,7 @@ operations:
             - compound-ops
     -
       name: threads-set
-      doc: set the number of running threads
+      doc: set the maximum number of running threads
       attribute-set: server
       flags: [admin-perm]
       do:
@@ -165,7 +165,7 @@ operations:
             - min-threads
     -
       name: threads-get
-      doc: get the number of running threads
+      doc: get the maximum number of running threads
       attribute-set: server
       do:
         reply:
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b06adb5d5a2e..369da69d5efe 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -377,15 +377,15 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_threads - Start NFSD, or report the current number of running threads
+ * write_threads - Start NFSD, or report the configured number of threads
  *
  * Input:
  *			buf:		ignored
  *			size:		zero
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero
  *
@@ -399,8 +399,8 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	NFS service is started;
  *			passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -430,7 +430,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_pool_threads - Set or report the current number of threads per pool
+ * write_pool_threads - Set or report the configured number of threads per pool
  *
  * Input:
  *			buf:		ignored
@@ -447,7 +447,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
  *			string containing integer values representing the
- *			number of NFSD threads in each pool;
+ *			configured number of NFSD threads in each pool;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -1657,7 +1657,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 /**
- * nfsd_nl_threads_get_doit - get the number of running threads
+ * nfsd_nl_threads_get_doit - get the maximum number of running threads
  * @skb: reply buffer
  * @info: netlink metadata and command arguments
  *
@@ -1700,7 +1700,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
 			struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
 
 			err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
-					  sp->sp_nrthreads);
+					  sp->sp_nrthrmax);
 			if (err)
 				goto err_unlock;
 		}
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 0887ee601d3c..4a04208393b8 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -239,12 +239,13 @@ static void nfsd_net_free(struct percpu_ref *ref)
 
 int nfsd_nrthreads(struct net *net)
 {
-	int rv = 0;
+	int i, rv = 0;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	mutex_lock(&nfsd_mutex);
 	if (nn->nfsd_serv)
-		rv = nn->nfsd_serv->sv_nrthreads;
+		for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i)
+			rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax;
 	mutex_unlock(&nfsd_mutex);
 	return rv;
 }
@@ -659,7 +660,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 
 	if (serv)
 		for (i = 0; i < serv->sv_nrpools && i < n; i++)
-			nthreads[i] = serv->sv_pools[i].sp_nrthreads;
+			nthreads[i] = serv->sv_pools[i].sp_nrthrmax;
 	return 0;
 }
 

From 297318a1c26dabb5a2d8540fdf436c22094eb2d7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 24 Feb 2026 12:52:18 +0100
Subject: [PATCH 0304/1303] spi: dt-bindings: snps,dw-abp-ssi: Remove unused
 bindings

As stated in the da0a672268b3 ("spi: dw: Remove not-going-to-be-supported
code for Baikal SoC") the Baikal platforms are not supported and
the respective driver code was removed. Remove the currently unused bindings.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20260224115218.3499222-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/spi/snps,dw-apb-ssi.yaml         | 31 +------------------
 1 file changed, 1 insertion(+), 30 deletions(-)

diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index 81838577cf9c..8ebebcebca16 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -22,21 +22,6 @@ allOf:
       properties:
         reg:
           minItems: 2
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - baikal,bt1-sys-ssi
-    then:
-      properties:
-        mux-controls:
-          maxItems: 1
-      required:
-        - mux-controls
-    else:
-      required:
-        - interrupts
   - if:
       properties:
         compatible:
@@ -75,10 +60,6 @@ properties:
         const: intel,mountevans-imc-ssi
       - description: AMD Pensando Elba SoC SPI Controller
         const: amd,pensando-elba-spi
-      - description: Baikal-T1 SPI Controller
-        const: baikal,bt1-ssi
-      - description: Baikal-T1 System Boot SPI Controller
-        const: baikal,bt1-sys-ssi
       - description: Canaan Kendryte K210 SoS SPI Controller
         const: canaan,k210-spi
       - description: Renesas RZ/N1 SPI Controller
@@ -170,6 +151,7 @@ required:
   - "#address-cells"
   - "#size-cells"
   - clocks
+  - interrupts
 
 examples:
   - |
@@ -190,15 +172,4 @@ examples:
         rx-sample-delay-ns = <7>;
       };
     };
-  - |
-    spi@1f040100 {
-      compatible = "baikal,bt1-sys-ssi";
-      reg = <0x1f040100 0x900>,
-            <0x1c000000 0x1000000>;
-      #address-cells = <1>;
-      #size-cells = <0>;
-      mux-controls = <&boot_mux>;
-      clocks = <&ccu_sys>;
-      clock-names = "ssi_clk";
-    };
 ...

From 07ed4f05bbfd2bc014974dcc4297fd3aa1cb88c0 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:14 -0800
Subject: [PATCH 0305/1303] hwmon: (it87) Check the it87_lock() return value

Return early in it87_resume() if it87_lock() fails instead of ignoring the
return value of that function. This patch suppresses a Clang thread-safety
warning.

Cc: Frank Crawford <frank@crawford.emu.id.au>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Jean Delvare <jdelvare@suse.com>
Cc: linux-hwmon@vger.kernel.org
Fixes: 376e1a937b30 ("hwmon: (it87) Add calls to smbus_enable/smbus_disable as required")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20260223220102.2158611-15-bart.vanassche@linux.dev
[groeck: Declare 'ret' at the beginning of it87_resume()]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/it87.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index e233aafa8856..5cfb98a0512f 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -3590,10 +3590,13 @@ static int it87_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct it87_data *data = dev_get_drvdata(dev);
+	int err;
 
 	it87_resume_sio(pdev);
 
-	it87_lock(data);
+	err = it87_lock(data);
+	if (err)
+		return err;
 
 	it87_check_pwm(dev);
 	it87_check_limit_regs(data);

From 96a1fd0d84b17360840f344826897fa71049870e Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 12 Feb 2026 14:50:38 -0700
Subject: [PATCH 0306/1303] cxl: Fix race of nvdimm_bus object when creating
 nvdimm objects

Found issue during running of cxl-translate.sh unit test. Adding a 3s
sleep right before the test seems to make the issue reproduce fairly
consistently. The cxl_translate module has dependency on cxl_acpi and
causes orphaned nvdimm objects to reprobe after cxl_acpi is removed.
The nvdimm_bus object is registered by the cxl_nvb object when
cxl_acpi_probe() is called. With the nvdimm_bus object missing,
__nd_device_register() will trigger NULL pointer dereference when
accessing the dev->parent that points to &nvdimm_bus->dev.

[  192.884510] BUG: kernel NULL pointer dereference, address: 000000000000006c
[  192.895383] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20250812-19.fc42 08/12/2025
[  192.897721] Workqueue: cxl_port cxl_bus_rescan_queue [cxl_core]
[  192.899459] RIP: 0010:kobject_get+0xc/0x90
[  192.924871] Call Trace:
[  192.925959]  <TASK>
[  192.926976]  ? pm_runtime_init+0xb9/0xe0
[  192.929712]  __nd_device_register.part.0+0x4d/0xc0 [libnvdimm]
[  192.933314]  __nvdimm_create+0x206/0x290 [libnvdimm]
[  192.936662]  cxl_nvdimm_probe+0x119/0x1d0 [cxl_pmem]
[  192.940245]  cxl_bus_probe+0x1a/0x60 [cxl_core]
[  192.943349]  really_probe+0xde/0x380

This patch also relies on the previous change where
devm_cxl_add_nvdimm_bridge() is called from drivers/cxl/pmem.c instead
of drivers/cxl/core.c to ensure the dependency of cxl_acpi on cxl_pmem.

1. Set probe_type of cxl_nvb to PROBE_FORCE_SYNCHRONOUS to ensure the
   driver is probed synchronously when add_device() is called.
2. Add a check in __devm_cxl_add_nvdimm_bridge() to ensure that the
   cxl_nvb driver is attached during cxl_acpi_probe().
3. Take the cxl_root uport_dev lock and the cxl_nvb->dev lock in
   devm_cxl_add_nvdimm() before checking nvdimm_bus is valid.
4. Set cxl_nvdimm flag to CXL_NVD_F_INVALIDATED so cxl_nvdimm_probe()
   will exit with -EBUSY.

The removal of cxl_nvdimm devices should prevent any orphaned devices
from probing once the nvdimm_bus is gone.

[ dj: Fixed 0-day reported kdoc issue. ]
[ dj: Fix cxl_nvb reference leak on error. Gregory (kreview-0811365) ]

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Fixes: 8fdcb1704f61 ("cxl/pmem: Add initial infrastructure for pmem support")
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com?>
Link: https://patch.msgid.link/20260205001633.1813643-3-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/pmem.c | 29 +++++++++++++++++++++++++++++
 drivers/cxl/cxl.h       |  5 +++++
 drivers/cxl/pmem.c      | 10 ++++++++--
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index b652e3486038..68462e38a977 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -115,6 +115,15 @@ static void unregister_nvb(void *_cxl_nvb)
 	device_unregister(&cxl_nvb->dev);
 }
 
+static bool cxl_nvdimm_bridge_failed_attach(struct cxl_nvdimm_bridge *cxl_nvb)
+{
+	struct device *dev = &cxl_nvb->dev;
+
+	guard(device)(dev);
+	/* If the device has no driver, then it failed to attach. */
+	return dev->driver == NULL;
+}
+
 struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
 						       struct cxl_port *port)
 {
@@ -138,6 +147,11 @@ struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
 	if (rc)
 		goto err;
 
+	if (cxl_nvdimm_bridge_failed_attach(cxl_nvb)) {
+		unregister_nvb(cxl_nvb);
+		return ERR_PTR(-ENODEV);
+	}
+
 	rc = devm_add_action_or_reset(host, unregister_nvb, cxl_nvb);
 	if (rc)
 		return ERR_PTR(rc);
@@ -248,6 +262,21 @@ int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
 	if (!cxl_nvb)
 		return -ENODEV;
 
+	/*
+	 * Take the uport_dev lock to guard against race of nvdimm_bus object.
+	 * cxl_acpi_probe() registers the nvdimm_bus and is done under the
+	 * root port uport_dev lock.
+	 *
+	 * Take the cxl_nvb device lock to ensure that cxl_nvb driver is in a
+	 * consistent state. And the driver registers nvdimm_bus.
+	 */
+	guard(device)(cxl_nvb->port->uport_dev);
+	guard(device)(&cxl_nvb->dev);
+	if (!cxl_nvb->nvdimm_bus) {
+		rc = -ENODEV;
+		goto err_alloc;
+	}
+
 	cxl_nvd = cxl_nvdimm_alloc(cxl_nvb, cxlmd);
 	if (IS_ERR(cxl_nvd)) {
 		rc = PTR_ERR(cxl_nvd);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index f5850800f400..9b947286eb9b 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -574,11 +574,16 @@ struct cxl_nvdimm_bridge {
 
 #define CXL_DEV_ID_LEN 19
 
+enum {
+	CXL_NVD_F_INVALIDATED = 0,
+};
+
 struct cxl_nvdimm {
 	struct device dev;
 	struct cxl_memdev *cxlmd;
 	u8 dev_id[CXL_DEV_ID_LEN]; /* for nvdimm, string of 'serial' */
 	u64 dirty_shutdowns;
+	unsigned long flags;
 };
 
 struct cxl_pmem_region_mapping {
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index c67b30b516bf..082ec0f1c3a0 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -14,7 +14,7 @@
 static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
 
 /**
- * __devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
+ * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
  * @host: platform firmware root device
  * @port: CXL port at the root of a CXL topology
  *
@@ -143,6 +143,9 @@ static int cxl_nvdimm_probe(struct device *dev)
 	struct nvdimm *nvdimm;
 	int rc;
 
+	if (test_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags))
+		return -EBUSY;
+
 	set_exclusive_cxl_commands(mds, exclusive_cmds);
 	rc = devm_add_action_or_reset(dev, clear_exclusive, mds);
 	if (rc)
@@ -323,8 +326,10 @@ static int detach_nvdimm(struct device *dev, void *data)
 	scoped_guard(device, dev) {
 		if (dev->driver) {
 			cxl_nvd = to_cxl_nvdimm(dev);
-			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
+			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) {
 				release = true;
+				set_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags);
+			}
 		}
 	}
 	if (release)
@@ -367,6 +372,7 @@ static struct cxl_driver cxl_nvdimm_bridge_driver = {
 	.probe = cxl_nvdimm_bridge_probe,
 	.id = CXL_DEVICE_NVDIMM_BRIDGE,
 	.drv = {
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
 		.suppress_bind_attrs = true,
 	},
 };

From 60b5d1f68338aff2c5af0113f04aefa7169c50c2 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Thu, 19 Feb 2026 16:16:17 -0800
Subject: [PATCH 0307/1303] cxl/mbox: validate payload size before accessing
 contents in cxl_payload_from_user_allowed()

cxl_payload_from_user_allowed() casts and dereferences the input
payload without first verifying its size. When a raw mailbox command
is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG,
which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer,
triggering a KASAN splat:

BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683
Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258

CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0xab/0xe0 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xce/0x650 mm/kasan/report.c:482
 kasan_report+0xce/0x100 mm/kasan/report.c:595
 memcmp+0x176/0x1d0 lib/string.c:683
 uuid_equal include/linux/uuid.h:73 [inline]
 cxl_payload_from_user_allowed drivers/cxl/core/mbox.c:345 [inline]
 cxl_mbox_cmd_ctor drivers/cxl/core/mbox.c:368 [inline]
 cxl_validate_cmd_from_user drivers/cxl/core/mbox.c:522 [inline]
 cxl_send_cmd+0x9c0/0xb50 drivers/cxl/core/mbox.c:643
 __cxl_memdev_ioctl drivers/cxl/core/memdev.c:698 [inline]
 cxl_memdev_ioctl+0x14f/0x190 drivers/cxl/core/memdev.c:713
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xa8/0x330 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fdaf331ba79
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fdaf1d77038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fdaf3585fa0 RCX: 00007fdaf331ba79
RDX: 00002000000001c0 RSI: 00000000c030ce02 RDI: 0000000000000003
RBP: 00007fdaf33749df R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fdaf3586038 R14: 00007fdaf3585fa0 R15: 00007ffced2af768
 </TASK>

Add 'in_size' parameter to cxl_payload_from_user_allowed() and validate
the payload is large enough.

Fixes: 6179045ccc0c ("cxl/mbox: Block immediate mode in SET_PARTITION_INFO command")
Fixes: 206f9fa9d555 ("cxl/mbox: Add Clear Log mailbox command")
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260220001618.963490-2-dave@stgolabs.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/mbox.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index fa6dd0c94656..e7a6452bf544 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -311,6 +311,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode)
  * cxl_payload_from_user_allowed() - Check contents of in_payload.
  * @opcode: The mailbox command opcode.
  * @payload_in: Pointer to the input payload passed in from user space.
+ * @in_size: Size of @payload_in in bytes.
  *
  * Return:
  *  * true	- payload_in passes check for @opcode.
@@ -325,12 +326,15 @@ static bool cxl_mem_raw_command_allowed(u16 opcode)
  *
  * The specific checks are determined by the opcode.
  */
-static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in)
+static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in,
+					  size_t in_size)
 {
 	switch (opcode) {
 	case CXL_MBOX_OP_SET_PARTITION_INFO: {
 		struct cxl_mbox_set_partition_info *pi = payload_in;
 
+		if (in_size < sizeof(*pi))
+			return false;
 		if (pi->flags & CXL_SET_PARTITION_IMMEDIATE_FLAG)
 			return false;
 		break;
@@ -338,6 +342,8 @@ static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in)
 	case CXL_MBOX_OP_CLEAR_LOG: {
 		const uuid_t *uuid = (uuid_t *)payload_in;
 
+		if (in_size < sizeof(uuid_t))
+			return false;
 		/*
 		 * Restrict the ‘Clear log’ action to only apply to
 		 * Vendor debug logs.
@@ -365,7 +371,8 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox_cmd,
 		if (IS_ERR(mbox_cmd->payload_in))
 			return PTR_ERR(mbox_cmd->payload_in);
 
-		if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in)) {
+		if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in,
+						  in_size)) {
 			dev_dbg(cxl_mbox->host, "%s: input payload not allowed\n",
 				cxl_mem_opcode_to_name(opcode));
 			kvfree(mbox_cmd->payload_in);

From 0a70b7cd397e545e926c93715ff6366b67c716f6 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Mon, 23 Feb 2026 11:13:39 -0800
Subject: [PATCH 0308/1303] cxl: Test CXL_DECODER_F_LOCK as a bitmask

The CXL decoder flags are defined as bitmasks, not bit indices.
Using test_bit() to check them interprets the mask value as a bit
index, which is the wrong test.

For CXL_DECODER_F_LOCK the test reads beyond the defined bits, causing
the test to always return false and allowing resets that should have
been blocked.

Replace test_bit() with a bitmask check.

Fixes: 2230c4bdc412 ("cxl: Add handling of locked CXL decoder")
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Tested-by: Gregory Price <gourry@gourry.net>
Link: https://patch.msgid.link/98851c4770e4631753cf9f75b58a3a6daeca2ea2.1771873256.git.alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/hdm.c    | 2 +-
 drivers/cxl/core/region.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index e3f0c39e6812..c222e98ae736 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -904,7 +904,7 @@ static void cxl_decoder_reset(struct cxl_decoder *cxld)
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
 		return;
 
-	if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags))
+	if (cxld->flags & CXL_DECODER_F_LOCK)
 		return;
 
 	if (port->commit_end == id)
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index fec37af1dfbf..780ec947ecf2 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1100,7 +1100,7 @@ static int cxl_rr_assign_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 static void cxl_region_setup_flags(struct cxl_region *cxlr,
 				   struct cxl_decoder *cxld)
 {
-	if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags)) {
+	if (cxld->flags & CXL_DECODER_F_LOCK) {
 		set_bit(CXL_REGION_F_LOCK, &cxlr->flags);
 		clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}

From e46f25f5a81f6f1a9ab93bcda80d5dfaea9f4897 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Mon, 23 Feb 2026 11:13:40 -0800
Subject: [PATCH 0309/1303] cxl/region: Test
 CXL_DECODER_F_NORMALIZED_ADDRESSING as a bitmask

The CXL decoder flags are defined as bitmasks, not bit indices.
Using test_bit() to check them interprets the mask value as a bit
index, which is the wrong test.

For CXL_DECODER_F_NORMALIZED_ADDRESSING the test reads beyond the
flags word, making the flag sometimes appear set and blocking creation
of CXL region debugfs attributes that support poison operations.

Replace test_bit() with a bitmask check.

Found with cxl-test.

Fixes: 208f432406b7 ("cxl: Disable HPA/SPA translation handlers for Normalized Addressing")
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Tested-by: Gregory Price <gourry@gourry.net>
Link: https://patch.msgid.link/63fe4a6203e40e404347f1cdc7a1c55cb4959b86.1771873256.git.alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/region.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 780ec947ecf2..42874948b589 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1105,7 +1105,7 @@ static void cxl_region_setup_flags(struct cxl_region *cxlr,
 		clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}
 
-	if (test_bit(CXL_DECODER_F_NORMALIZED_ADDRESSING, &cxld->flags))
+	if (cxld->flags & CXL_DECODER_F_NORMALIZED_ADDRESSING)
 		set_bit(CXL_REGION_F_NORMALIZED_ADDRESSING, &cxlr->flags);
 }
 

From 43277d8f57b490550d33f6f4cb73c28ec6024696 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:19 -0800
Subject: [PATCH 0310/1303] selftests/bpf: Replace strncpy() with strscpy()

strncpy() does not guarantee NULL-termination and is considered
deprecated [1]. Replace strncpy() calls with strscpy().

[1] https://docs.kernel.org/process/deprecated.html#strncpy-on-nul-terminated-strings

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-4-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c             | 3 +--
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c         | 3 +--
 tools/testing/selftests/bpf/prog_tests/flow_dissector.c   | 4 ++--
 tools/testing/selftests/bpf/prog_tests/queue_stack_map.c  | 4 ++--
 tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/task_local_data.h  | 2 +-
 tools/testing/selftests/bpf/prog_tests/tc_redirect.c      | 2 +-
 tools/testing/selftests/bpf/test_progs.c                  | 2 +-
 tools/testing/selftests/bpf/xdp_hw_metadata.c             | 4 ++--
 9 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 5374b7e16d53..b82f572641b7 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -581,8 +581,7 @@ int open_tuntap(const char *dev_name, bool need_mac)
 		return -1;
 
 	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
-	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+	strscpy(ifr.ifr_name, dev_name);
 
 	err = ioctl(fd, TUNSETIFF, &ifr);
 	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 5225d69bf79b..c69080ca14f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -346,8 +346,7 @@ static void test_task_sleepable(void)
 		close(finish_pipe[1]);
 
 		test_data = malloc(sizeof(char) * 10);
-		strncpy(test_data, "test_data", 10);
-		test_data[9] = '\0';
+		strscpy(test_data, "test_data", 10);
 
 		test_data_long = malloc(sizeof(char) * 5000);
 		for (int i = 0; i < 5000; ++i) {
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 08bae13248c4..fb4892681464 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -570,7 +570,7 @@ static int create_tap(const char *ifname)
 	};
 	int fd, ret;
 
-	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	strscpy(ifr.ifr_name, ifname);
 
 	fd = open("/dev/net/tun", O_RDWR);
 	if (fd < 0)
@@ -599,7 +599,7 @@ static int ifup(const char *ifname)
 	struct ifreq ifr = {};
 	int sk, ret;
 
-	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	strscpy(ifr.ifr_name, ifname);
 
 	sk = socket(PF_INET, SOCK_DGRAM, 0);
 	if (sk < 0)
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index a043af9cd6d9..41441325e179 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -28,9 +28,9 @@ static void test_queue_stack_map_by_type(int type)
 		vals[i] = rand();
 
 	if (type == QUEUE)
-		strncpy(file, "./test_queue_map.bpf.o", sizeof(file));
+		strscpy(file, "./test_queue_map.bpf.o");
 	else if (type == STACK)
-		strncpy(file, "./test_stack_map.bpf.o", sizeof(file));
+		strscpy(file, "./test_stack_map.bpf.o");
 	else
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
index 3eefdfed1db9..657d897958b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
@@ -34,7 +34,7 @@ void test_skc_to_unix_sock(void)
 
 	memset(&sockaddr, 0, sizeof(sockaddr));
 	sockaddr.sun_family = AF_UNIX;
-	strncpy(sockaddr.sun_path, sock_path, strlen(sock_path));
+	strscpy(sockaddr.sun_path, sock_path);
 	sockaddr.sun_path[0] = '\0';
 
 	err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr));
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
index 0f86b9275cf9..8342e2fe5260 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_data.h
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -262,7 +262,7 @@ static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data)
 		if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1))
 			goto retry;
 
-		strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN);
+		strscpy(tld_meta_p->metadata[i].name, name);
 		atomic_store(&tld_meta_p->metadata[i].size, size);
 		return (tld_key_t){(__s16)off};
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 76d72a59365e..64fbda082309 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -1095,7 +1095,7 @@ static int tun_open(char *name)
 
 	ifr.ifr_flags = IFF_TUN | IFF_NO_PI;
 	if (*name)
-		strncpy(ifr.ifr_name, name, IFNAMSIZ);
+		strscpy(ifr.ifr_name, name);
 
 	err = ioctl(fd, TUNSETIFF, &ifr);
 	if (!ASSERT_OK(err, "ioctl TUNSETIFF"))
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 02a85dda30e6..d1418ec1f351 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1799,7 +1799,7 @@ static int worker_main_send_subtests(int sock, struct test_state *state)
 
 		msg.subtest_done.num = i;
 
-		strncpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME);
+		strscpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME);
 
 		msg.subtest_done.error_cnt = subtest_state->error_cnt;
 		msg.subtest_done.skipped = subtest_state->skipped;
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 3d8de0d4c96a..6db3b5555a22 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -550,7 +550,7 @@ static int rxq_num(const char *ifname)
 	struct ifreq ifr = {
 		.ifr_data = (void *)&ch,
 	};
-	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	strscpy(ifr.ifr_name, ifname);
 	int fd, ret;
 
 	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
@@ -571,7 +571,7 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c
 	struct ifreq ifr = {
 		.ifr_data = (void *)cfg,
 	};
-	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	strscpy(ifr.ifr_name, ifname);
 	int fd, ret;
 
 	fd = socket(AF_UNIX, SOCK_DGRAM, 0);

From 3ed0bc2d4994c718fb5476b45d4aafec42a1d040 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:20 -0800
Subject: [PATCH 0311/1303] selftests/bpf: Use strscpy in bpftool_helpers.c

Replace strncpy() calls in bpftool_helpers.c with strscpy().

Pass the destination buffer size to detect_bpftool_path() instead of
hardcoding BPFTOOL_PATH_MAX_LEN.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-5-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpftool_helpers.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c
index a5824945a4a5..595a636fa13b 100644
--- a/tools/testing/selftests/bpf/bpftool_helpers.c
+++ b/tools/testing/selftests/bpf/bpftool_helpers.c
@@ -1,15 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include "bpftool_helpers.h"
 #include <unistd.h>
 #include <string.h>
 #include <stdbool.h>
 
+#include "bpf_util.h"
+#include "bpftool_helpers.h"
+
 #define BPFTOOL_PATH_MAX_LEN		64
 #define BPFTOOL_FULL_CMD_MAX_LEN	512
 
 #define BPFTOOL_DEFAULT_PATH		"tools/sbin/bpftool"
 
-static int detect_bpftool_path(char *buffer)
+static int detect_bpftool_path(char *buffer, size_t size)
 {
 	char tmp[BPFTOOL_PATH_MAX_LEN];
 
@@ -18,7 +20,7 @@ static int detect_bpftool_path(char *buffer)
 	 */
 	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "./%s", BPFTOOL_DEFAULT_PATH);
 	if (access(tmp, X_OK) == 0) {
-		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		strscpy(buffer, tmp, size);
 		return 0;
 	}
 
@@ -27,7 +29,7 @@ static int detect_bpftool_path(char *buffer)
 	 */
 	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "../%s", BPFTOOL_DEFAULT_PATH);
 	if (access(tmp, X_OK) == 0) {
-		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		strscpy(buffer, tmp, size);
 		return 0;
 	}
 
@@ -44,7 +46,7 @@ static int run_command(char *args, char *output_buf, size_t output_max_len)
 	int ret;
 
 	/* Detect and cache bpftool binary location */
-	if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path))
+	if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path, sizeof(bpftool_path)))
 		return 1;
 
 	ret = snprintf(command, BPFTOOL_FULL_CMD_MAX_LEN, "%s %s%s",

From 9d8685239e85ba5a4899b5b3534c732e3ae5f2aa Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:21 -0800
Subject: [PATCH 0312/1303] selftests/bpf: Use memcpy() for bounded
 non-NULL-terminated copies

Replace strncpy() with memcpy() in cases where the source is
non-NULL-terminated and the copy length is known.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-6-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c | 6 ++++--
 tools/testing/selftests/bpf/test_verifier.c          | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index dd75ccb03770..469e92869523 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -308,8 +308,10 @@ static int find_field_offset(struct btf *btf, char *pattern, regmatch_t *matches
 		return -1;
 	}
 
-	strncpy(type_str, type, type_sz);
-	strncpy(field_str, field, field_sz);
+	memcpy(type_str, type, type_sz);
+	type_str[type_sz] = '\0';
+	memcpy(field_str, field, field_sz);
+	field_str[field_sz] = '\0';
 	btf_id = btf__find_by_name(btf, type_str);
 	if (btf_id < 0) {
 		PRINT_FAIL("No BTF info for type %s\n", type_str);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 27db34ecf3f5..a8ae03c57bba 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1320,7 +1320,7 @@ static bool cmp_str_seq(const char *log, const char *exp)
 			printf("FAIL\nTestcase bug\n");
 			return false;
 		}
-		strncpy(needle, exp, len);
+		memcpy(needle, exp, len);
 		needle[len] = 0;
 		q = strstr(log, needle);
 		if (!q) {

From 4021848a903e65f74cf88997c12b96d6bc2453e6 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:22 -0800
Subject: [PATCH 0313/1303] selftests/bpf: Pass through build flags to bpftool
 and resolve_btfids

EXTRA_* and SAN_* build flags were not correctly propagated to bpftool
and resolve_btids when building selftests/bpf. This led to various
build errors on attempt to build with SAN_CFLAGS="-fsanitize=address",
for example.

Fix the makefiles to address this:
  - Pass SAN_CFLAGS/SAN_LDFLAGS to bpftool and resolve_btfids build
  - Propagate EXTRA_LDFLAGS to resolve_btfids link command
  - Use pkg-config to detect zlib and zstd for resolve_btfids, similar
    libelf handling

Also check for ASAN flag in selftests/bpf/Makefile for convenience.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-7-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/Makefile    |  7 +++++--
 tools/testing/selftests/bpf/Makefile | 13 +++++++++----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 1733a6e93a07..ef083602b73a 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -65,6 +65,9 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU
 LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
 LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
 
+ZLIB_LIBS  := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz)
+ZSTD_LIBS  := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd)
+
 HOSTCFLAGS_resolve_btfids += -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
@@ -73,7 +76,7 @@ HOSTCFLAGS_resolve_btfids += -g \
           $(LIBELF_FLAGS) \
           -Wall -Werror
 
-LIBS = $(LIBELF_LIBS) -lz
+LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS)
 
 export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR
 include $(srctree)/tools/build/Makefile.include
@@ -83,7 +86,7 @@ $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT)
 
 $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
 	$(call msg,LINK,$@)
-	$(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
+	$(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) $(EXTRA_LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
 
 clean_objects := $(wildcard $(OUTPUT)/*.o                \
                             $(OUTPUT)/.*.o.cmd           \
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6776158f1f3e..72a9ba41f95e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -27,7 +27,11 @@ ifneq ($(wildcard $(GENHDR)),)
 endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
+ifdef ASAN
+SAN_CFLAGS 	?= -fsanitize=address -fno-omit-frame-pointer
+else
 SAN_CFLAGS	?=
+endif
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
 RELEASE		?=
 OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
@@ -326,8 +330,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" 	       \
-		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'	       \
-		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'			       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)'			       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
 		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
@@ -338,8 +342,8 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
 		    $(BPFOBJ) | $(BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
 		    ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE)			\
-		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'		\
-		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'				\
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)'			       \
 		    OUTPUT=$(BUILD_DIR)/bpftool/				\
 		    LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/				\
 		    LIBBPF_DESTDIR=$(SCRATCH_DIR)/				\
@@ -404,6 +408,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids	\
 		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
+		EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by

From c5c1e313493cd836863bb673bb2b8beaa915cad9 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:23 -0800
Subject: [PATCH 0314/1303] resolve_btfids: Fix memory leaks reported by ASAN

Running resolve_btfids with ASAN reveals memory leaks in btf_id
handling.

- Change get_id() to use a local buffer
- Make btf_id__add() strdup the name internally
- Add btf_id__free_all() that frees all nodese of a tree
- Call the cleanup function on exit for every tree

Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-8-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/main.c | 81 ++++++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 27 deletions(-)

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index ca7fcd03efb6..5208f650080f 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -226,7 +226,7 @@ static struct btf_id *btf_id__find(struct rb_root *root, const char *name)
 }
 
 static struct btf_id *__btf_id__add(struct rb_root *root,
-				    char *name,
+				    const char *name,
 				    enum btf_id_kind kind,
 				    bool unique)
 {
@@ -250,7 +250,11 @@ static struct btf_id *__btf_id__add(struct rb_root *root,
 	id = zalloc(sizeof(*id));
 	if (id) {
 		pr_debug("adding symbol %s\n", name);
-		id->name = name;
+		id->name = strdup(name);
+		if (!id->name) {
+			free(id);
+			return NULL;
+		}
 		id->kind = kind;
 		rb_link_node(&id->rb_node, parent, p);
 		rb_insert_color(&id->rb_node, root);
@@ -258,17 +262,21 @@ static struct btf_id *__btf_id__add(struct rb_root *root,
 	return id;
 }
 
-static inline struct btf_id *btf_id__add(struct rb_root *root, char *name, enum btf_id_kind kind)
+static inline struct btf_id *btf_id__add(struct rb_root *root,
+					 const char *name,
+					 enum btf_id_kind kind)
 {
 	return __btf_id__add(root, name, kind, false);
 }
 
-static inline struct btf_id *btf_id__add_unique(struct rb_root *root, char *name, enum btf_id_kind kind)
+static inline struct btf_id *btf_id__add_unique(struct rb_root *root,
+						const char *name,
+						enum btf_id_kind kind)
 {
 	return __btf_id__add(root, name, kind, true);
 }
 
-static char *get_id(const char *prefix_end)
+static int get_id(const char *prefix_end, char *buf, size_t buf_sz)
 {
 	/*
 	 * __BTF_ID__func__vfs_truncate__0
@@ -277,28 +285,28 @@ static char *get_id(const char *prefix_end)
 	 */
 	int len = strlen(prefix_end);
 	int pos = sizeof("__") - 1;
-	char *p, *id;
+	char *p;
 
 	if (pos >= len)
-		return NULL;
+		return -1;
 
-	id = strdup(prefix_end + pos);
-	if (id) {
-		/*
-		 * __BTF_ID__func__vfs_truncate__0
-		 * id =            ^
-		 *
-		 * cut the unique id part
-		 */
-		p = strrchr(id, '_');
-		p--;
-		if (*p != '_') {
-			free(id);
-			return NULL;
-		}
-		*p = '\0';
-	}
-	return id;
+	if (len - pos >= buf_sz)
+		return -1;
+
+	strcpy(buf, prefix_end + pos);
+	/*
+	 * __BTF_ID__func__vfs_truncate__0
+	 * buf =           ^
+	 *
+	 * cut the unique id part
+	 */
+	p = strrchr(buf, '_');
+	p--;
+	if (*p != '_')
+		return -1;
+	*p = '\0';
+
+	return 0;
 }
 
 static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind kind)
@@ -335,10 +343,9 @@ static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind k
 
 static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 {
-	char *id;
+	char id[KSYM_NAME_LEN];
 
-	id = get_id(name + size);
-	if (!id) {
+	if (get_id(name + size, id, sizeof(id))) {
 		pr_err("FAILED to parse symbol name: %s\n", name);
 		return NULL;
 	}
@@ -346,6 +353,21 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, BTF_ID_KIND_SYM);
 }
 
+static void btf_id__free_all(struct rb_root *root)
+{
+	struct rb_node *next;
+	struct btf_id *id;
+
+	next = rb_first(root);
+	while (next) {
+		id = rb_entry(next, struct btf_id, rb_node);
+		next = rb_next(&id->rb_node);
+		rb_erase(&id->rb_node, root);
+		free(id->name);
+		free(id);
+	}
+}
+
 static void bswap_32_data(void *data, u32 nr_bytes)
 {
 	u32 cnt, i;
@@ -1547,6 +1569,11 @@ int main(int argc, const char **argv)
 out:
 	btf__free(obj.base_btf);
 	btf__free(obj.btf);
+	btf_id__free_all(&obj.structs);
+	btf_id__free_all(&obj.unions);
+	btf_id__free_all(&obj.typedefs);
+	btf_id__free_all(&obj.funcs);
+	btf_id__free_all(&obj.sets);
 	if (obj.efile.elf) {
 		elf_end(obj.efile.elf);
 		close(obj.efile.fd);

From 45897ced3c1d3940fb5b68fe48c9e144143ae0ae Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:24 -0800
Subject: [PATCH 0315/1303] selftests/bpf: Add DENYLIST.asan

Add a denylist file for tests that should be skipped when built with
userspace ASAN:

    $ make ... SAN_CFLAGS="-fsanitize=address -fno-omit-frame-pointer"

Skip the following tests:

- *arena*: userspace ASAN does not understand BPF arena maps and gets
  confused particularly when map_extra is non-zero
  - non-zero map_extra leads to mmap with MAP_FIXED, and ASAN treats
    this as an unknown memory region
- task_local_data: ASAN complains about "incorrect" aligned_alloc()
  usage, but it's intentional in the test
- uprobe_multi_test: very slow with ASAN enabled

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-9-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/DENYLIST.asan | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/DENYLIST.asan

diff --git a/tools/testing/selftests/bpf/DENYLIST.asan b/tools/testing/selftests/bpf/DENYLIST.asan
new file mode 100644
index 000000000000..d7fe372a2293
--- /dev/null
+++ b/tools/testing/selftests/bpf/DENYLIST.asan
@@ -0,0 +1,3 @@
+*arena*
+task_local_data
+uprobe_multi_test

From a1a771bd649212ef32cf9b0bcc63213a762d354a Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:25 -0800
Subject: [PATCH 0316/1303] selftests/bpf: Refactor bpf_get_ksyms() trace
 helper

ASAN reported a memory leak in bpf_get_ksyms(): it allocates a struct
ksyms internally and never frees it.

Move struct ksyms to trace_helpers.h and return it from the
bpf_get_ksyms(), giving ownership to the caller. Add filtered_syms and
filtered_cnt fields to the ksyms to hold the filtered array of
symbols, previously returned by bpf_get_ksyms().

Fixup the call sites: kprobe_multi_test and bench_trigger.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260223190736.649171-10-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/benchs/bench_trigger.c      | 14 ++++++-----
 .../bpf/prog_tests/kprobe_multi_test.c        | 12 ++++------
 tools/testing/selftests/bpf/trace_helpers.c   | 23 ++++++++++---------
 tools/testing/selftests/bpf/trace_helpers.h   | 11 +++++++--
 4 files changed, 34 insertions(+), 26 deletions(-)

diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index aeec9edd3851..f74b313d6ae4 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -230,8 +230,8 @@ static void trigger_fentry_setup(void)
 static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
-	char **syms = NULL;
-	size_t cnt = 0;
+	struct bpf_link *link = NULL;
+	struct ksyms *ksyms = NULL;
 
 	/* Some recursive functions will be skipped in
 	 * bpf_get_ksyms -> skip_entry, as they can introduce sufficient
@@ -241,16 +241,18 @@ static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
 	 * So, don't run the kprobe-multi-all and kretprobe-multi-all on
 	 * a debug kernel.
 	 */
-	if (bpf_get_ksyms(&syms, &cnt, true)) {
+	if (bpf_get_ksyms(&ksyms, true)) {
 		fprintf(stderr, "failed to get ksyms\n");
 		exit(1);
 	}
 
-	opts.syms = (const char **) syms;
-	opts.cnt = cnt;
+	opts.syms = (const char **)ksyms->filtered_syms;
+	opts.cnt = ksyms->filtered_cnt;
 	opts.retprobe = kretprobe;
 	/* attach empty to all the kernel functions except bpf_get_numa_node_id. */
-	if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) {
+	link = bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts);
+	free_kallsyms_local(ksyms);
+	if (!link) {
 		fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 9caef222e528..f81dcd609ee9 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -456,25 +456,23 @@ static void test_kprobe_multi_bench_attach(bool kernel)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	struct kprobe_multi_empty *skel = NULL;
-	char **syms = NULL;
-	size_t cnt = 0;
+	struct ksyms *ksyms = NULL;
 
-	if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms"))
+	if (!ASSERT_OK(bpf_get_ksyms(&ksyms, kernel), "bpf_get_ksyms"))
 		return;
 
 	skel = kprobe_multi_empty__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
 		goto cleanup;
 
-	opts.syms = (const char **) syms;
-	opts.cnt = cnt;
+	opts.syms = (const char **)ksyms->filtered_syms;
+	opts.cnt = ksyms->filtered_cnt;
 
 	do_bench_test(skel, &opts);
 
 cleanup:
 	kprobe_multi_empty__destroy(skel);
-	if (syms)
-		free(syms);
+	free_kallsyms_local(ksyms);
 }
 
 static void test_kprobe_multi_bench_attach_addr(bool kernel)
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index eeaab7013ca2..0e63daf83ed5 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -24,12 +24,6 @@
 #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
 #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
 
-struct ksyms {
-	struct ksym *syms;
-	size_t sym_cap;
-	size_t sym_cnt;
-};
-
 static struct ksyms *ksyms;
 static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
 
@@ -54,6 +48,8 @@ void free_kallsyms_local(struct ksyms *ksyms)
 	if (!ksyms)
 		return;
 
+	free(ksyms->filtered_syms);
+
 	if (!ksyms->syms) {
 		free(ksyms);
 		return;
@@ -610,7 +606,7 @@ static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
 	return compare_name(p1, p2->name);
 }
 
-int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
+int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel)
 {
 	size_t cap = 0, cnt = 0;
 	char *name = NULL, *ksym_name, **syms = NULL;
@@ -637,8 +633,10 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
 	else
 		f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
 
-	if (!f)
+	if (!f) {
+		free_kallsyms_local(ksyms);
 		return -EINVAL;
+	}
 
 	map = hashmap__new(symbol_hash, symbol_equal, NULL);
 	if (IS_ERR(map)) {
@@ -679,15 +677,18 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
 		syms[cnt++] = ksym_name;
 	}
 
-	*symsp = syms;
-	*cntp = cnt;
+	ksyms->filtered_syms = syms;
+	ksyms->filtered_cnt = cnt;
+	*ksymsp = ksyms;
 
 error:
 	free(name);
 	fclose(f);
 	hashmap__free(map);
-	if (err)
+	if (err) {
 		free(syms);
+		free_kallsyms_local(ksyms);
+	}
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index a5576b2dfc26..d5bf1433675d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -23,7 +23,14 @@ struct ksym {
 	long addr;
 	char *name;
 };
-struct ksyms;
+
+struct ksyms {
+	struct ksym *syms;
+	size_t sym_cap;
+	size_t sym_cnt;
+	char **filtered_syms;
+	size_t filtered_cnt;
+};
 
 typedef int (*ksym_cmp_t)(const void *p1, const void *p2);
 typedef int (*ksym_search_cmp_t)(const void *p1, const struct ksym *p2);
@@ -53,7 +60,7 @@ ssize_t get_rel_offset(uintptr_t addr);
 
 int read_build_id(const char *path, char *build_id, size_t size);
 
-int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel);
+int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel);
 int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel);
 
 #endif

From 9d0272c91fbc3ae86f2c3b6ba0a0b0ee77d862e3 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:26 -0800
Subject: [PATCH 0317/1303] selftests/bpf: Fix memory leaks in tests

Fix trivial memory leaks detected by userspace ASAN:
  - htab_update: free value buffer in test_reenter_update cleanup
  - test_xsk: inline pkt_stream_replace() in testapp_stats_rx_full()
    and testapp_stats_fill_empty()
  - testing_helpers: free buffer allocated by getline() in
    parse_test_list_file

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-11-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/htab_update.c    |  1 +
 .../selftests/bpf/prog_tests/test_xsk.c       | 24 +++++++++++++++----
 tools/testing/selftests/bpf/testing_helpers.c |  1 +
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c
index d0b405eb2966..ea1a6766fbe9 100644
--- a/tools/testing/selftests/bpf/prog_tests/htab_update.c
+++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c
@@ -61,6 +61,7 @@ static void test_reenter_update(void)
 
 	ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy");
 out:
+	free(value);
 	htab_update__destroy(skel);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index bab4a31621c7..7e38ec6e656b 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -2003,9 +2003,17 @@ int testapp_stats_tx_invalid_descs(struct test_spec *test)
 
 int testapp_stats_rx_full(struct test_spec *test)
 {
-	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+	struct pkt_stream *tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
+	if (!tmp)
 		return TEST_FAILURE;
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_tx->xsk->pkt_stream = tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	if (!tmp)
+		return TEST_FAILURE;
+	test->ifobj_rx->xsk->pkt_stream = tmp;
 
 	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
 	test->ifobj_rx->release_rx = false;
@@ -2015,9 +2023,17 @@ int testapp_stats_rx_full(struct test_spec *test)
 
 int testapp_stats_fill_empty(struct test_spec *test)
 {
-	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+	struct pkt_stream *tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
+	if (!tmp)
 		return TEST_FAILURE;
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_tx->xsk->pkt_stream = tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	if (!tmp)
+		return TEST_FAILURE;
+	test->ifobj_rx->xsk->pkt_stream = tmp;
 
 	test->ifobj_rx->use_fill_ring = false;
 	test->ifobj_rx->validation_func = validate_fill_empty;
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 16eb37e5bad6..66af0d13751a 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -212,6 +212,7 @@ int parse_test_list_file(const char *path,
 			break;
 	}
 
+	free(buf);
 	fclose(f);
 	return err;
 }

From 3eb4a2e399c6766ea0c8291e2adb5e6dc42b6e68 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:27 -0800
Subject: [PATCH 0318/1303] selftests/bpf: Fix cleanup in
 check_fd_array_cnt__fd_array_too_big()

The Close() macro uses the passed in expression three times, which
leads to repeated execution in case it has side effects. That is,
Close(i--) would decrement i three times.

ASAN caught a stack-buffer-undeflow error at a point where this was
overlooked. Fix it.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-12-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/fd_array.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index c534b4d5f9da..3078d8264deb 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -412,8 +412,8 @@ static void check_fd_array_cnt__fd_array_too_big(void)
 	ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG");
 
 cleanup_fds:
-	while (i > 0)
-		Close(extra_fds[--i]);
+	while (i-- > 0)
+		Close(extra_fds[i]);
 }
 
 void test_fd_array_cnt(void)

From ff9511410d5fbdec21a3bbfaa477aa1f56735b33 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:28 -0800
Subject: [PATCH 0319/1303] veristat: Fix a memory leak for preset ENUMERATOR

ASAN detected a memory leak in veristat. The cleanup code handling
ENUMERATOR value missed freeing strdup-ed svalue. Fix it.

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-13-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/veristat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 1be1e353d40a..75f85e0362f5 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -3378,6 +3378,8 @@ int main(int argc, char **argv)
 			}
 		}
 		free(env.presets[i].atoms);
+		if (env.presets[i].value.type == ENUMERATOR)
+			free(env.presets[i].value.svalue);
 	}
 	free(env.presets);
 	return -err;

From f7ac552be7f13e834a942f64b1ac87e7755b32f4 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:29 -0800
Subject: [PATCH 0320/1303] selftests/bpf: Fix use-after-free in xdp_metadata
 test

ASAN reported a use-after-free in close_xsk().

The xsk->socket internally references xsk->umem via socket->ctx->umem,
so the socket must be deleted before the umem. Fix the order of
operations in close_xsk().

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-14-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 19f92affc2da..5c31054ad4a4 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -126,10 +126,10 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 
 static void close_xsk(struct xsk *xsk)
 {
-	if (xsk->umem)
-		xsk_umem__delete(xsk->umem);
 	if (xsk->socket)
 		xsk_socket__delete(xsk->socket);
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
 	munmap(xsk->umem_area, UMEM_SIZE);
 }
 

From 68b8bea1eec392aa50736a859b8f1418067a3bc4 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:30 -0800
Subject: [PATCH 0321/1303] selftests/bpf: Fix double thread join in
 uprobe_multi_test

ASAN reported a "joining already joined thread" error. The
release_child() may be called multiple times for the same struct
child.

Fix by resetting child->thread to 0 after pthread_join.

Also memset(0) static child variable in test_attach_api().

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-15-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 2ee17ef1dae2..56cbea280fbd 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -62,8 +62,10 @@ static void release_child(struct child *child)
 		return;
 	close(child->go[1]);
 	close(child->go[0]);
-	if (child->thread)
+	if (child->thread) {
 		pthread_join(child->thread, NULL);
+		child->thread = 0;
+	}
 	close(child->c2p[0]);
 	close(child->c2p[1]);
 	if (child->pid > 0)
@@ -331,6 +333,8 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi
 {
 	static struct child child;
 
+	memset(&child, 0, sizeof(child));
+
 	/* no pid filter */
 	__test_attach_api(binary, pattern, opts, NULL);
 

From 71dca2950fe9abf8e6fd3d9f5e6342da6634b898 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:31 -0800
Subject: [PATCH 0322/1303] selftests/bpf: Fix resource leaks caused by missing
 cleanups

ASAN reported a number of resource leaks:
  - Add missing  *__destroy(skel) calls
  - Replace bpf_link__detach() with bpf_link__destroy() where appropriate
  - cgrp_local_storage: Add bpf_link__destroy() when bpf_iter_create fails
  - dynptr: Add missing bpf_object__close()

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-16-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/prog_tests/cgrp_local_storage.c       |  4 ++-
 .../testing/selftests/bpf/prog_tests/dynptr.c |  5 +++-
 .../selftests/bpf/prog_tests/sockmap_basic.c  | 28 +++++++++----------
 .../selftests/bpf/prog_tests/sockmap_listen.c |  2 +-
 .../bpf/prog_tests/struct_ops_private_stack.c |  4 +--
 .../selftests/bpf/prog_tests/tc_opts.c        |  6 ++--
 .../selftests/bpf/prog_tests/test_tc_tunnel.c |  5 +++-
 7 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
index 9015e2c2ab12..478a77cb67e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -202,7 +202,7 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
 	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
-		goto out;
+		goto out_link;
 
 	/* trigger the program run */
 	(void)read(iter_fd, buf, sizeof(buf));
@@ -210,6 +210,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 	ASSERT_EQ(skel->bss->cgroup_id, cgroup_id, "cgroup_id");
 
 	close(iter_fd);
+out_link:
+	bpf_link__destroy(link);
 out:
 	cgrp_ls_sleepable__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index b9f86cb91e81..5fda11590708 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -137,11 +137,14 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 		);
 
 		link = bpf_program__attach(prog);
-		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach")) {
+			bpf_object__close(obj);
 			goto cleanup;
+		}
 
 		err = bpf_prog_test_run_opts(aux_prog_fd, &topts);
 		bpf_link__destroy(link);
+		bpf_object__close(obj);
 
 		if (!ASSERT_OK(err, "test_run"))
 			goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 256707e7d20d..dd3c757859f6 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -204,7 +204,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type)
 	/* Fail since bpf_link for the same prog type has been created. */
 	link2 = bpf_program__attach_sockmap(prog_clone, map);
 	if (!ASSERT_ERR_PTR(link2, "bpf_program__attach_sockmap")) {
-		bpf_link__detach(link2);
+		bpf_link__destroy(link2);
 		goto out;
 	}
 
@@ -230,7 +230,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type)
 	if (!ASSERT_OK(err, "bpf_link_update"))
 		goto out;
 out:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 	test_skmsg_load_helpers__destroy(skel);
 }
 
@@ -417,7 +417,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
 		goto out;
 
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 
 	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
@@ -426,7 +426,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void)
 	/* Fail since attaching with the same prog/map has been done. */
 	link = bpf_program__attach_sockmap(prog, map);
 	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_sockmap"))
-		bpf_link__detach(link);
+		bpf_link__destroy(link);
 
 	err = bpf_prog_detach2(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT);
 	if (!ASSERT_OK(err, "bpf_prog_detach2"))
@@ -747,13 +747,13 @@ static void test_sockmap_skb_verdict_peek_with_link(void)
 	test_sockmap_skb_verdict_peek_helper(map);
 	ASSERT_EQ(pass->bss->clone_called, 1, "clone_called");
 out:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 	test_sockmap_pass_prog__destroy(pass);
 }
 
 static void test_sockmap_unconnected_unix(void)
 {
-	int err, map, stream = 0, dgram = 0, zero = 0;
+	int err, map, stream = -1, dgram = -1, zero = 0;
 	struct test_sockmap_pass_prog *skel;
 
 	skel = test_sockmap_pass_prog__open_and_load();
@@ -764,22 +764,22 @@ static void test_sockmap_unconnected_unix(void)
 
 	stream = xsocket(AF_UNIX, SOCK_STREAM, 0);
 	if (stream < 0)
-		return;
+		goto out;
 
 	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
-	if (dgram < 0) {
-		close(stream);
-		return;
-	}
+	if (dgram < 0)
+		goto out;
 
 	err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY);
-	ASSERT_ERR(err, "bpf_map_update_elem(stream)");
+	if (!ASSERT_ERR(err, "bpf_map_update_elem(stream)"))
+		goto out;
 
 	err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
 	ASSERT_OK(err, "bpf_map_update_elem(dgram)");
-
+out:
 	close(stream);
 	close(dgram);
+	test_sockmap_pass_prog__destroy(skel);
 }
 
 static void test_sockmap_many_socket(void)
@@ -1027,7 +1027,7 @@ static void test_sockmap_skb_verdict_vsock_poll(void)
 	if (xrecv_nonblock(conn, &buf, 1, 0) != 1)
 		FAIL("xrecv_nonblock");
 detach:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 close:
 	xclose(conn);
 	xclose(peer);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index f1bdccc7e4e7..cc0c68bab907 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -899,7 +899,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk
 
 	redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
 
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 }
 
 static void redir_partial(int family, int sotype, int sock_map, int parser_map)
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
index 4006879ca3fe..d42123a0fb16 100644
--- a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
@@ -54,9 +54,7 @@ static void test_private_stack_fail(void)
 	}
 
 	err = struct_ops_private_stack_fail__load(skel);
-	if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load"))
-		goto cleanup;
-	return;
+	ASSERT_ERR(err, "struct_ops_private_stack_fail__load");
 
 cleanup:
 	struct_ops_private_stack_fail__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index dd7a138d8c3d..2955750ddada 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -1360,10 +1360,8 @@ static void test_tc_opts_dev_cleanup_target(int target)
 
 	assert_mprog_count_ifindex(ifindex, target, 4);
 
-	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
-	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
-	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
-	return;
+	goto cleanup;
+
 cleanup3:
 	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
 	ASSERT_OK(err, "prog_detach");
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
index 0fe0a8f62486..7fc4d7dd70ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
@@ -699,7 +699,7 @@ void test_tc_tunnel(void)
 		return;
 
 	if (!ASSERT_OK(setup(), "global setup"))
-		return;
+		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) {
 		cfg = &subtests_cfg[i];
@@ -711,4 +711,7 @@ void test_tc_tunnel(void)
 		subtest_cleanup(cfg);
 	}
 	cleanup();
+
+out:
+	test_tc_tunnel__destroy(skel);
 }

From 2bb270a0ac68990648c5e84abf73bb7493230ea6 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:32 -0800
Subject: [PATCH 0323/1303] selftests/bpf: Free bpf_object in test_sysctl

ASAN reported a resource leak due to the bpf_object not being tracked
in test_sysctl. Add obj field to struct sysctl_test to properly clean
it up.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-17-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/test_sysctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
index 273dd41ca09e..2a1ff821bc97 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -27,6 +27,7 @@ struct sysctl_test {
 		OP_EPERM,
 		SUCCESS,
 	} result;
+	struct bpf_object *obj;
 };
 
 static struct sysctl_test tests[] = {
@@ -1471,6 +1472,7 @@ static int load_sysctl_prog_file(struct sysctl_test *test)
 		return -1;
 	}
 
+	test->obj = obj;
 	return prog_fd;
 }
 
@@ -1573,6 +1575,7 @@ static int run_test_case(int cgfd, struct sysctl_test *test)
 	/* Detaching w/o checking return code: best effort attempt. */
 	if (progfd != -1)
 		bpf_prog_detach(cgfd, atype);
+	bpf_object__close(test->obj);
 	close(progfd);
 	printf("[%s]\n", err ? "FAIL" : "PASS");
 	return err;

From 3e711c8e4707c46cc45d9775b50204d0f2790d77 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:33 -0800
Subject: [PATCH 0324/1303] selftests/bpf: Fix array bounds warning in
 jit_disasm_helpers

Compiler cannot infer upper bound for labels.cnt and warns about
potential buffer overflow in snprintf. Add an explicit bounds
check (... && i < MAX_LOCAL_LABELS) in the loop condition to fix the
warning.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-18-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/jit_disasm_helpers.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
index febd6b12e372..364c557c5115 100644
--- a/tools/testing/selftests/bpf/jit_disasm_helpers.c
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -122,15 +122,15 @@ static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len)
 		pc += cnt;
 	}
 	qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
-	for (i = 0; i < labels.cnt; ++i)
-		/* gcc is unable to infer upper bound for labels.cnt and assumes
-		 * it to be U32_MAX. U32_MAX takes 10 decimal digits.
-		 * snprintf below prints into labels.names[*],
-		 * which has space only for two digits and a letter.
-		 * To avoid truncation warning use (i % MAX_LOCAL_LABELS),
-		 * which informs gcc about printed value upper bound.
-		 */
-		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS);
+	/* gcc is unable to infer upper bound for labels.cnt and
+	 * assumes it to be U32_MAX. U32_MAX takes 10 decimal digits.
+	 * snprintf below prints into labels.names[*], which has space
+	 * only for two digits and a letter.  To avoid truncation
+	 * warning use (i < MAX_LOCAL_LABELS), which informs gcc about
+	 * printed value upper bound.
+	 */
+	for (i = 0; i < labels.cnt && i < MAX_LOCAL_LABELS; ++i)
+		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i);
 
 	/* now print with labels */
 	labels.print_phase = true;

From ad90ecedad755e2f3e31364ec3130e5bb2f4b64a Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:16 -0800
Subject: [PATCH 0325/1303] selftests/bpf: Fix out-of-bounds array access bugs
 reported by ASAN

- kmem_cache_iter: remove unnecessary debug output
- lwt_seg6local: change the type of foobar to char[]
  - the sizeof(foobar) returned the pointer size and not a string
    length as intended
- verifier_log: increase prog_name buffer size in verif_log_subtest()
  - compiler has a conservative estimate of fixed_log_sz value, making
    ASAN complain on snprint() call

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c | 7 ++-----
 tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c   | 2 +-
 tools/testing/selftests/bpf/prog_tests/verifier_log.c    | 2 +-
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
index 6e35e13c2022..399fe9103f83 100644
--- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
@@ -104,11 +104,8 @@ void test_kmem_cache_iter(void)
 	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
 		goto destroy;
 
-	memset(buf, 0, sizeof(buf));
-	while (read(iter_fd, buf, sizeof(buf)) > 0) {
-		/* Read out all contents */
-		printf("%s", buf);
-	}
+	while (read(iter_fd, buf, sizeof(buf)) > 0)
+		; /* Read out all contents */
 
 	/* Next reads should return 0 */
 	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
index 3bc730b7c7fa..1b25d5c5f8fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
@@ -117,7 +117,7 @@ void test_lwt_seg6local(void)
 	const char *ns1 = NETNS_BASE "1";
 	const char *ns6 = NETNS_BASE "6";
 	struct nstoken *nstoken = NULL;
-	const char *foobar = "foobar";
+	const char foobar[] = "foobar";
 	ssize_t bytes;
 	int sfd, cfd;
 	char buf[7];
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
index 8337c6bc5b95..aaa2854974c0 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier_log.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
@@ -47,7 +47,7 @@ static int load_prog(struct bpf_prog_load_opts *opts, bool expect_load_error)
 static void verif_log_subtest(const char *name, bool expect_load_error, int log_level)
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	char *exp_log, prog_name[16], op_name[32];
+	char *exp_log, prog_name[24], op_name[32];
 	struct test_log_buf *skel;
 	struct bpf_program *prog;
 	size_t fixed_log_sz;

From a2714e730304c79bf85d2178387255ef8348b897 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:17 -0800
Subject: [PATCH 0326/1303] selftests/bpf: Check BPFTOOL env var in
 detect_bpftool_path()

The bpftool_maps_access and bpftool_metadata tests may fail on BPF CI
with "command not found", depending on a workflow.
This happens because detect_bpftool_path() only checks two hardcoded
relative paths:
  - ./tools/sbin/bpftool
  - ../tools/sbin/bpftool

Add support for a BPFTOOL environment variable that allows specifying
the exact path to the bpftool binary.

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-2-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpftool_helpers.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c
index 595a636fa13b..929fc257f431 100644
--- a/tools/testing/selftests/bpf/bpftool_helpers.c
+++ b/tools/testing/selftests/bpf/bpftool_helpers.c
@@ -14,6 +14,17 @@
 static int detect_bpftool_path(char *buffer, size_t size)
 {
 	char tmp[BPFTOOL_PATH_MAX_LEN];
+	const char *env_path;
+
+	/* First, check if BPFTOOL environment variable is set */
+	env_path = getenv("BPFTOOL");
+	if (env_path && access(env_path, X_OK) == 0) {
+		strscpy(buffer, env_path, size);
+		return 0;
+	} else if (env_path) {
+		fprintf(stderr, "bpftool '%s' doesn't exist or is not executable\n", env_path);
+		return 1;
+	}
 
 	/* Check default bpftool location (will work if we are running the
 	 * default flavor of test_progs)
@@ -33,7 +44,7 @@ static int detect_bpftool_path(char *buffer, size_t size)
 		return 0;
 	}
 
-	/* Failed to find bpftool binary */
+	fprintf(stderr, "Failed to detect bpftool path, use BPFTOOL env var to override\n");
 	return 1;
 }
 

From 4c9d07865c06bb9b9faff1ecf6c4b7cc8f7d67a9 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:18 -0800
Subject: [PATCH 0327/1303] selftests/bpf: Don't override SIGSEGV handler with
 ASAN

test_progs has custom SIGSEGV handler, which interferes with the
address sanitizer [1]. Add an #ifndef to avoid this.

Additionally, declare an __asan_on_error() to dump the test logs in
the same way it happens in the custom SIGSEGV handler.

[1] https://lore.kernel.org/bpf/73d832948b01dbc0ebc60d85574bdf8537f3a810.camel@gmail.com/

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-3-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 36 +++++++++++++++++-------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index d1418ec1f351..0929f4a7bda4 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1261,14 +1261,8 @@ int get_bpf_max_tramp_links(void)
 	return ret;
 }
 
-#define MAX_BACKTRACE_SZ 128
-void crash_handler(int signum)
+static void dump_crash_log(void)
 {
-	void *bt[MAX_BACKTRACE_SZ];
-	size_t sz;
-
-	sz = backtrace(bt, ARRAY_SIZE(bt));
-
 	fflush(stdout);
 	stdout = env.stdout_saved;
 	stderr = env.stderr_saved;
@@ -1277,12 +1271,32 @@ void crash_handler(int signum)
 		env.test_state->error_cnt++;
 		dump_test_log(env.test, env.test_state, true, false, NULL);
 	}
+}
+
+#define MAX_BACKTRACE_SZ 128
+
+void crash_handler(int signum)
+{
+	void *bt[MAX_BACKTRACE_SZ];
+	size_t sz;
+
+	sz = backtrace(bt, ARRAY_SIZE(bt));
+
+	dump_crash_log();
+
 	if (env.worker_id != -1)
 		fprintf(stderr, "[%d]: ", env.worker_id);
 	fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
 	backtrace_symbols_fd(bt, sz, STDERR_FILENO);
 }
 
+#ifdef __SANITIZE_ADDRESS__
+void __asan_on_error(void)
+{
+	dump_crash_log();
+}
+#endif
+
 void hexdump(const char *prefix, const void *buf, size_t len)
 {
 	for (int i = 0; i < len; i++) {
@@ -1944,13 +1958,15 @@ int main(int argc, char **argv)
 		.parser = parse_arg,
 		.doc = argp_program_doc,
 	};
+	int err, i;
+
+#ifndef __SANITIZE_ADDRESS__
 	struct sigaction sigact = {
 		.sa_handler = crash_handler,
 		.sa_flags = SA_RESETHAND,
-		};
-	int err, i;
-
+	};
 	sigaction(SIGSEGV, &sigact, NULL);
+#endif
 
 	env.stdout_saved = stdout;
 	env.stderr_saved = stderr;

From 56e0a838277b12d48477b9c7478ceb5ae528ae2c Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawnguo@kernel.org>
Date: Tue, 24 Feb 2026 15:57:53 +0800
Subject: [PATCH 0328/1303] MAINTAINERS: Update Shawn Guo's address for
 HiSilicon PCIe controller driver

Shawn is no longer with Linaro.  Use his korg email address instead.

Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260224075753.122091-1-shawnguo@kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..f02f50c9d695 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20509,7 +20509,7 @@ F:	Documentation/devicetree/bindings/pci/hisilicon,kirin-pcie.yaml
 F:	drivers/pci/controller/dwc/pcie-kirin.c
 
 PCIE DRIVER FOR HISILICON STB
-M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Shawn Guo <shawnguo@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/hisilicon-histb-pcie.txt

From 30df81f2228d65bddf492db3929d9fcaffd38fc5 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Mon, 23 Feb 2026 14:56:09 +0800
Subject: [PATCH 0329/1303] scsi: ufs: core: Fix possible NULL pointer
 dereference in ufshcd_add_command_trace()

The kernel log indicates a crash in ufshcd_add_command_trace, due to a NULL
pointer dereference when accessing hwq->id.  This can happen if
ufshcd_mcq_req_to_hwq() returns NULL.

This patch adds a NULL check for hwq before accessing its id field to
prevent a kernel crash.

Kernel log excerpt:
[<ffffffd5d192dc4c>] notify_die+0x4c/0x8c
[<ffffffd5d1814e58>] __die+0x60/0xb0
[<ffffffd5d1814d64>] die+0x4c/0xe0
[<ffffffd5d181575c>] die_kernel_fault+0x74/0x88
[<ffffffd5d1864db4>] __do_kernel_fault+0x314/0x318
[<ffffffd5d2a3cdf8>] do_page_fault+0xa4/0x5f8
[<ffffffd5d2a3cd34>] do_translation_fault+0x34/0x54
[<ffffffd5d1864524>] do_mem_abort+0x50/0xa8
[<ffffffd5d2a297dc>] el1_abort+0x3c/0x64
[<ffffffd5d2a29718>] el1h_64_sync_handler+0x44/0xcc
[<ffffffd5d181133c>] el1h_64_sync+0x80/0x88
[<ffffffd5d255c1dc>] ufshcd_add_command_trace+0x23c/0x320
[<ffffffd5d255bad8>] ufshcd_compl_one_cqe+0xa4/0x404
[<ffffffd5d2572968>] ufshcd_mcq_poll_cqe_lock+0xac/0x104
[<ffffffd5d11c7460>] ufs_mtk_mcq_intr+0x54/0x74 [ufs_mediatek_mod]
[<ffffffd5d19ab92c>] __handle_irq_event_percpu+0xc8/0x348
[<ffffffd5d19abca8>] handle_irq_event+0x3c/0xa8
[<ffffffd5d19b1f0c>] handle_fasteoi_irq+0xf8/0x294
[<ffffffd5d19aa778>] generic_handle_domain_irq+0x54/0x80
[<ffffffd5d18102bc>] gic_handle_irq+0x1d4/0x330
[<ffffffd5d1838210>] call_on_irq_stack+0x44/0x68
[<ffffffd5d183af30>] do_interrupt_handler+0x78/0xd8
[<ffffffd5d2a29c00>] el1_interrupt+0x48/0xa8
[<ffffffd5d2a29ba8>] el1h_64_irq_handler+0x14/0x24
[<ffffffd5d18113c4>] el1h_64_irq+0x80/0x88
[<ffffffd5d2527fb4>] arch_local_irq_enable+0x4/0x1c
[<ffffffd5d25282e4>] cpuidle_enter+0x34/0x54
[<ffffffd5d195a678>] do_idle+0x1dc/0x2f8
[<ffffffd5d195a7c4>] cpu_startup_entry+0x30/0x3c
[<ffffffd5d18155c4>] secondary_start_kernel+0x134/0x1ac
[<ffffffd5d18640bc>] __secondary_switched+0xc4/0xcc

Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223065657.2432447-1-peter.wang@mediatek.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 571a73860561..4dc7fbc2a6db 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -518,8 +518,8 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, struct scsi_cmnd *cmd,
 
 	if (hba->mcq_enabled) {
 		struct ufs_hw_queue *hwq = ufshcd_mcq_req_to_hwq(hba, rq);
-
-		hwq_id = hwq->id;
+		if (hwq)
+			hwq_id = hwq->id;
 	} else {
 		doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	}

From 62c015373e1cdb1cdca824bd2dbce2dac0819467 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Mon, 23 Feb 2026 18:37:57 +0800
Subject: [PATCH 0330/1303] scsi: ufs: core: Move link recovery for hibern8
 exit failure to wl_resume

Move the link recovery trigger from ufshcd_uic_pwr_ctrl() to
__ufshcd_wl_resume(). Ensure link recovery is only attempted when hibern8
exit fails during resume, not during hibern8 enter in suspend. Improve
error handling and prevent unnecessary link recovery attempts.

Fixes: 35dabf4503b9 ("scsi: ufs: core: Use link recovery when h8 exit fails during runtime resume")
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223103906.2533654-1-peter.wang@mediatek.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4dc7fbc2a6db..85987373b961 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4390,14 +4390,6 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
-	/*
-	 * If the h8 exit fails during the runtime resume process, it becomes
-	 * stuck and cannot be recovered through the error handler.  To fix
-	 * this, use link recovery instead of the error handler.
-	 */
-	if (ret && hba->pm_op_in_progress)
-		ret = ufshcd_link_recovery(hba);
-
 	return ret;
 }
 
@@ -10200,7 +10192,15 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		} else {
 			dev_err(hba->dev, "%s: hibern8 exit failed %d\n",
 					__func__, ret);
-			goto vendor_suspend;
+			/*
+			 * If the h8 exit fails during the runtime resume
+			 * process, it becomes stuck and cannot be recovered
+			 * through the error handler. To fix this, use link
+			 * recovery instead of the error handler.
+			 */
+			ret = ufshcd_link_recovery(hba);
+			if (ret)
+				goto vendor_suspend;
 		}
 	} else if (ufshcd_is_link_off(hba)) {
 		/*

From 74b6e83942dcc9f3cca9e561b205a5b19940a344 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 19 Feb 2026 12:50:29 -0800
Subject: [PATCH 0331/1303] drm/gpusvm: Fix drm_gpusvm_pages_valid_unlocked()
 kernel-doc

The kernel-doc for drm_gpusvm_pages_valid_unlocked() was stale and still
referenced old range-based arguments and naming. Update the documentation
to match the current function arguments and signature.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/20260219205029.1011336-1-matthew.brost@intel.com
---
 drivers/gpu/drm/drm_gpusvm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 24180bfdf5a2..9ef9e52c0547 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1338,14 +1338,14 @@ bool drm_gpusvm_range_pages_valid(struct drm_gpusvm *gpusvm,
 EXPORT_SYMBOL_GPL(drm_gpusvm_range_pages_valid);
 
 /**
- * drm_gpusvm_range_pages_valid_unlocked() - GPU SVM range pages valid unlocked
+ * drm_gpusvm_pages_valid_unlocked() - GPU SVM pages valid unlocked
  * @gpusvm: Pointer to the GPU SVM structure
- * @range: Pointer to the GPU SVM range structure
+ * @svm_pages: Pointer to the GPU SVM pages structure
  *
- * This function determines if a GPU SVM range pages are valid. Expected be
- * called without holding gpusvm->notifier_lock.
+ * This function determines if a GPU SVM pages are valid. Expected be called
+ * without holding gpusvm->notifier_lock.
  *
- * Return: True if GPU SVM range has valid pages, False otherwise
+ * Return: True if GPU SVM pages are valid, False otherwise
  */
 static bool drm_gpusvm_pages_valid_unlocked(struct drm_gpusvm *gpusvm,
 					    struct drm_gpusvm_pages *svm_pages)

From 0902010c8d163f7b62e655efda1a843529152c7c Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 18:07:59 +0800
Subject: [PATCH 0332/1303] regulator: fp9931: Fix PM runtime reference leak in
 fp9931_hwmon_read()

In fp9931_hwmon_read(), if regmap_read() failed, the function returned
the error code without calling pm_runtime_put_autosuspend(), causing
a PM reference leak.

Fixes: 12d821bd13d4 ("regulator: Add FP9931/JD9930 driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Andreas Kemnade <andreas@kemnade.info>
Link: https://patch.msgid.link/20260224-fp9931-v1-1-1cf05cabef4a@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/fp9931.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/regulator/fp9931.c b/drivers/regulator/fp9931.c
index 7fbcc6327cc6..abea3b69d8a0 100644
--- a/drivers/regulator/fp9931.c
+++ b/drivers/regulator/fp9931.c
@@ -144,13 +144,12 @@ static int fp9931_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 		return ret;
 
 	ret = regmap_read(data->regmap, FP9931_REG_TMST_VALUE, &val);
-	if (ret)
-		return ret;
+	if (!ret)
+		*temp = (s8)val * 1000;
 
 	pm_runtime_put_autosuspend(data->dev);
-	*temp = (s8)val * 1000;
 
-	return 0;
+	return ret;
 }
 
 static umode_t fp9931_hwmon_is_visible(const void *data,

From 4baaddaa44af01cd4ce239493060738fd0881835 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 19:19:03 +0800
Subject: [PATCH 0333/1303] regulator: bq257xx: Fix device node reference leak
 in bq257xx_reg_dt_parse_gpio()

In bq257xx_reg_dt_parse_gpio(), if fails to get subchild, it returns
without calling of_node_put(child), causing the device node reference
leak.

Fixes: 981dd162b635 ("regulator: bq257xx: Add bq257xx boost regulator driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-bq257-v1-1-8ebbc731c1c3@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bq257xx-regulator.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/regulator/bq257xx-regulator.c b/drivers/regulator/bq257xx-regulator.c
index fc1ccede4468..dab8f1ab4450 100644
--- a/drivers/regulator/bq257xx-regulator.c
+++ b/drivers/regulator/bq257xx-regulator.c
@@ -115,11 +115,10 @@ static void bq257xx_reg_dt_parse_gpio(struct platform_device *pdev)
 		return;
 
 	subchild = of_get_child_by_name(child, pdata->desc.of_match);
+	of_node_put(child);
 	if (!subchild)
 		return;
 
-	of_node_put(child);
-
 	pdata->otg_en_gpio = devm_fwnode_gpiod_get_index(&pdev->dev,
 							 of_fwnode_handle(subchild),
 							 "enable", 0,

From bfd7db781e2e7a99b086d645a104d16e368f58ff Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 20:23:30 +0800
Subject: [PATCH 0334/1303] regulator: Kconfig: fix a typo

Fixes a typo in Kconfig, HWWON -> HWMON

Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-kconfig-v1-1-b0c5459ed7a0@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index a708fc63f581..d10b6f9243d5 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -508,7 +508,7 @@ config REGULATOR_FP9931
 	  This driver supports the FP9931/JD9930 voltage regulator chip
 	  which is used to provide power to Electronic Paper Displays
 	  so it is found in E-Book readers.
-	  If HWWON is enabled, it also provides temperature measurement.
+	  If HWMON is enabled, it also provides temperature measurement.
 
 config REGULATOR_LM363X
 	tristate "TI LM363X voltage regulators"

From e08f2adcf990b8cf272e90898401a9e481c1c667 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 24 Feb 2026 13:36:09 +0200
Subject: [PATCH 0335/1303] Revert "irqchip/ls-extirq: Use
 for_each_of_imap_item iterator"

This reverts commit 3ac6dfe3d7a2396602b67667249b146504dfbd2a.

The ls-extirq uses interrupt-map but it's a non-standard use documented
in fsl,ls-extirq.yaml:

        # The driver(drivers/irqchip/irq-ls-extirq.c) have not use standard DT
        # function to parser interrupt-map. So it doesn't consider '#address-size'
        # in parent interrupt controller, such as GIC.
        #
        # When dt-binding verify interrupt-map, item data matrix is spitted at
        # incorrect position. Remove interrupt-map restriction because it always
        # wrong.

This means that by using for_each_of_imap_item and the underlying
of_irq_parse_imap_parent() on its interrupt-map property will effectively
break its functionality

Revert the patch making use of for_each_of_imap_item() in ls-extirq.

Fixes: 3ac6dfe3d7a2 ("irqchip/ls-extirq: Use for_each_of_imap_item iterator")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Acked-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260224113610.1129022-2-ioana.ciornei@nxp.com
---
 drivers/irqchip/irq-ls-extirq.c | 47 +++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c
index a7e9c3885b09..96f9c20621cf 100644
--- a/drivers/irqchip/irq-ls-extirq.c
+++ b/drivers/irqchip/irq-ls-extirq.c
@@ -125,32 +125,45 @@ static const struct irq_domain_ops extirq_domain_ops = {
 static int
 ls_extirq_parse_map(struct ls_extirq_data *priv, struct device_node *node)
 {
-	struct of_imap_parser imap_parser;
-	struct of_imap_item imap_item;
+	const __be32 *map;
+	u32 mapsize;
 	int ret;
 
-	ret = of_imap_parser_init(&imap_parser, node, &imap_item);
-	if (ret)
-		return ret;
+	map = of_get_property(node, "interrupt-map", &mapsize);
+	if (!map)
+		return -ENOENT;
+	if (mapsize % sizeof(*map))
+		return -EINVAL;
+	mapsize /= sizeof(*map);
 
-	for_each_of_imap_item(&imap_parser, &imap_item) {
+	while (mapsize) {
 		struct device_node *ipar;
-		u32 hwirq;
-		int i;
+		u32 hwirq, intsize, j;
 
-		hwirq = imap_item.child_imap[0];
-		if (hwirq >= MAXIRQ) {
-			of_node_put(imap_item.parent_args.np);
+		if (mapsize < 3)
+			return -EINVAL;
+		hwirq = be32_to_cpup(map);
+		if (hwirq >= MAXIRQ)
 			return -EINVAL;
-		}
 		priv->nirq = max(priv->nirq, hwirq + 1);
 
-		ipar = of_node_get(imap_item.parent_args.np);
-		priv->map[hwirq].fwnode = of_fwnode_handle(ipar);
+		ipar = of_find_node_by_phandle(be32_to_cpup(map + 2));
+		map += 3;
+		mapsize -= 3;
+		if (!ipar)
+			return -EINVAL;
+		priv->map[hwirq].fwnode = &ipar->fwnode;
+		ret = of_property_read_u32(ipar, "#interrupt-cells", &intsize);
+		if (ret)
+			return ret;
 
-		priv->map[hwirq].param_count = imap_item.parent_args.args_count;
-		for (i = 0; i < priv->map[hwirq].param_count; i++)
-			priv->map[hwirq].param[i] = imap_item.parent_args.args[i];
+		if (intsize > mapsize)
+			return -EINVAL;
+
+		priv->map[hwirq].param_count = intsize;
+		for (j = 0; j < intsize; ++j)
+			priv->map[hwirq].param[j] = be32_to_cpup(map++);
+		mapsize -= intsize;
 	}
 	return 0;
 }

From fe5669e363b129cde285bfb4d45abb72d1d77cfc Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 24 Feb 2026 13:36:10 +0200
Subject: [PATCH 0336/1303] irqchip/ls-extirq: Fix devm_of_iomap() error check

The devm_of_iomap() function returns an ERR_PTR() encoded error code on
failure. Replace the incorrect check against NULL with IS_ERR().

Fixes: 05cd654829dd ("irqchip/ls-extirq: Convert to a platform driver to make it work again")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260224113610.1129022-3-ioana.ciornei@nxp.com
Closes: https://lore.kernel.org/all/aYXvfbfT6w0TMsXS@stanley.mountain/
---
 drivers/irqchip/irq-ls-extirq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c
index 96f9c20621cf..d724fe843980 100644
--- a/drivers/irqchip/irq-ls-extirq.c
+++ b/drivers/irqchip/irq-ls-extirq.c
@@ -190,8 +190,10 @@ static int ls_extirq_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, -ENOMEM, "Failed to allocate memory\n");
 
 	priv->intpcr = devm_of_iomap(dev, node, 0, NULL);
-	if (!priv->intpcr)
-		return dev_err_probe(dev, -ENOMEM, "Cannot ioremap OF node %pOF\n", node);
+	if (IS_ERR(priv->intpcr)) {
+		return dev_err_probe(dev, PTR_ERR(priv->intpcr),
+				     "Cannot ioremap OF node %pOF\n", node);
+	}
 
 	ret = ls_extirq_parse_map(priv, node);
 	if (ret)

From 095f5693329221ffd9dfe5fcd0079263d462e441 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 17 Feb 2026 15:25:59 +0800
Subject: [PATCH 0337/1303] tools/sched_ext: Sync README.md Kconfig with
 upstream scx

Sync the documentation with the upstream scx repository to
reflect the current recommended configuration.

Ref: https://github.com/sched-ext/scx/blob/main/README.md#build--install

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/README.md | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md
index 56a9d1557ac4..6e282bce453c 100644
--- a/tools/sched_ext/README.md
+++ b/tools/sched_ext/README.md
@@ -58,14 +58,8 @@ CONFIG_SCHED_CLASS_EXT=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_DEBUG_INFO_BTF=y
-```
-
-It's also recommended that you also include the following Kconfig options:
-
-```
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
-CONFIG_PAHOLE_HAS_BTF_TAG=y
 ```
 
 There is a `Kconfig` file in this directory whose contents you can append to

From ee0ff6690f2641b8f6ba8026ec17f6bc48f86649 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 17 Feb 2026 15:26:00 +0800
Subject: [PATCH 0338/1303] tools/sched_ext: Add Kconfig to sync with upstream

Add the missing Kconfig file to tools/sched_ext/ as referenced in
the README.

Ref: https://github.com/sched-ext/scx/blob/main/kernel.config

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/Kconfig | 61 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 tools/sched_ext/Kconfig

diff --git a/tools/sched_ext/Kconfig b/tools/sched_ext/Kconfig
new file mode 100644
index 000000000000..275bd97ae62b
--- /dev/null
+++ b/tools/sched_ext/Kconfig
@@ -0,0 +1,61 @@
+# sched-ext mandatory options
+#
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_SCHED_CLASS_EXT=y
+
+# Required by some rust schedulers (e.g. scx_p2dq)
+#
+CONFIG_KALLSYMS_ALL=y
+
+# Required on arm64
+#
+# CONFIG_DEBUG_INFO_REDUCED is not set
+
+# LAVD tracks futex to give an additional time slice for futex holder
+# (i.e., avoiding lock holder preemption) for better system-wide progress.
+# LAVD first tries to use ftrace to trace futex function calls.
+# If that is not available, it tries to use a tracepoint.
+CONFIG_FUNCTION_TRACER=y
+
+# Enable scheduling debugging
+#
+CONFIG_SCHED_DEBUG=y
+
+# Enable extra scheduling features (for a better code coverage while testing
+# the schedulers)
+#
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_SCHED_CORE=y
+CONFIG_SCHED_MC=y
+
+# Enable fully preemptible kernel for a better test coverage of the schedulers
+#
+# CONFIG_PREEMPT_NONE is not set
+# CONFIG_PREEMPT_VOLUNTARY is not set
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+
+# Additional debugging information (useful to catch potential locking issues)
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_PROVE_LOCKING=y
+
+# Bpftrace headers (for additional debug info)
+CONFIG_BPF_EVENTS=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_KPROBES=y
+CONFIG_KPROBE_EVENTS=y
+CONFIG_UPROBES=y
+CONFIG_UPROBE_EVENTS=y
+CONFIG_DEBUG_FS=y
+
+# Enable access to kernel configuration and headers at runtime
+CONFIG_IKHEADERS=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_IKCONFIG=y

From a75281626fc8fa6dc6c9cc314ee423e8bc45203b Mon Sep 17 00:00:00 2001
From: Luka Gejak <luka.gejak@linux.dev>
Date: Tue, 24 Feb 2026 14:26:47 +0100
Subject: [PATCH 0339/1303] staging: rtl8723bs: fix potential out-of-bounds
 read in rtw_restruct_wmm_ie

The current code checks 'i + 5 < in_len' at the end of the if statement.
However, it accesses 'in_ie[i + 5]' before that check, which can lead
to an out-of-bounds read. Move the length check to the beginning of the
conditional to ensure the index is within bounds before accessing the
array.

Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Luka Gejak <luka.gejak@linux.dev>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/20260224132647.11642-2-luka.gejak@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8723bs/core/rtw_mlme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c
index 7df651708381..1ef48bf6581c 100644
--- a/drivers/staging/rtl8723bs/core/rtw_mlme.c
+++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c
@@ -1988,7 +1988,10 @@ int rtw_restruct_wmm_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_
 	while (i < in_len) {
 		ielength = initial_out_len;
 
-		if (in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && in_ie[i + 3] == 0x50  && in_ie[i + 4] == 0xF2 && in_ie[i + 5] == 0x02 && i + 5 < in_len) { /* WMM element ID and OUI */
+		if (i + 5 < in_len &&
+		    in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 &&
+		    in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 &&
+		    in_ie[i + 5] == 0x02) {
 			for (j = i; j < i + 9; j++) {
 				out_ie[ielength] = in_ie[j];
 				ielength++;

From a46435537a844d0f7b4b620baf962cad136422de Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 24 Feb 2026 11:36:09 -0700
Subject: [PATCH 0340/1303] io_uring/cmd_net: use READ_ONCE() for ->addr3 read

Any SQE read should use READ_ONCE(), to ensure the result is read once
and only once. Doesn't really matter for this case, but it's better to
keep these 100% consistent and always use READ_ONCE() for the prep side
of SQE handling.

Fixes: 5d24321e4c15 ("io_uring: Introduce getsockname io_uring cmd")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/cmd_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c
index 57ddaf874611..125a81c520a6 100644
--- a/io_uring/cmd_net.c
+++ b/io_uring/cmd_net.c
@@ -146,7 +146,7 @@ static int io_uring_cmd_getsockname(struct socket *sock,
 		return -EINVAL;
 
 	uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
-	ulen = u64_to_user_ptr(sqe->addr3);
+	ulen = u64_to_user_ptr(READ_ONCE(sqe->addr3));
 	peer = READ_ONCE(sqe->optlen);
 	if (peer > 1)
 		return -EINVAL;

From 09833d99db36d74456a4d13eb29c32d56ff8f2b6 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 13 Feb 2026 10:54:10 +0100
Subject: [PATCH 0341/1303] mm/kfence: disable KFENCE upon KASAN HW tags
 enablement

KFENCE does not currently support KASAN hardware tags.  As a result, the
two features are incompatible when enabled simultaneously.

Given that MTE provides deterministic protection and KFENCE is a
sampling-based debugging tool, prioritize the stronger hardware
protections.  Disable KFENCE initialization and free the pre-allocated
pool if KASAN hardware tags are detected to ensure the system maintains
the security guarantees provided by MTE.

Link: https://lkml.kernel.org/r/20260213095410.1862978-1-glider@google.com
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Alexander Potapenko <glider@google.com>
Suggested-by: Marco Elver <elver@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ernesto Martinez Garcia <ernesto.martinezgarcia@tugraz.at>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Kees Cook <kees@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kfence/core.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index b4ea3262c925..b5aedf505cec 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -13,6 +13,7 @@
 #include <linux/hash.h>
 #include <linux/irq_work.h>
 #include <linux/jhash.h>
+#include <linux/kasan-enabled.h>
 #include <linux/kcsan-checks.h>
 #include <linux/kfence.h>
 #include <linux/kmemleak.h>
@@ -916,6 +917,20 @@ void __init kfence_alloc_pool_and_metadata(void)
 	if (!kfence_sample_interval)
 		return;
 
+	/*
+	 * If KASAN hardware tags are enabled, disable KFENCE, because it
+	 * does not support MTE yet.
+	 */
+	if (kasan_hw_tags_enabled()) {
+		pr_info("disabled as KASAN HW tags are enabled\n");
+		if (__kfence_pool) {
+			memblock_free(__kfence_pool, KFENCE_POOL_SIZE);
+			__kfence_pool = NULL;
+		}
+		kfence_sample_interval = 0;
+		return;
+	}
+
 	/*
 	 * If the pool has already been initialized by arch, there is no need to
 	 * re-allocate the memory pool.

From eb9549346f7578eda3755683ac2cfb4d94c0675f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Feb 2026 13:17:44 +0100
Subject: [PATCH 0342/1303] mm: change vma_alloc_folio_noprof() macro to inline
 function

In a few rare configurations with extra warnings eanbled, the new
drm_pagemap_migrate_populate_ram_pfn() calls vma_alloc_folio_noprof() but
that does not use all the arguments, leading to a harmless warning:

drivers/gpu/drm/drm_pagemap.c: In function 'drm_pagemap_migrate_populate_ram_pfn':
drivers/gpu/drm/drm_pagemap.c:701:63: error: parameter 'addr' set but not used [-Werror=unused-but-set-parameter=]
  701 |                                                 unsigned long addr)
      |                                                 ~~~~~~~~~~~~~~^~~~

Replace the macro with an inline function so the compiler can see how the
argument would be used, but is still able to optimize out the assignments.

Link: https://lkml.kernel.org/r/20260216121751.2378374-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2b30a0529d48..f82d74a77cad 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde
 {
 	return folio_alloc_noprof(gfp, order);
 }
-#define vma_alloc_folio_noprof(gfp, order, vma, addr)		\
-	folio_alloc_noprof(gfp, order)
+static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	return folio_alloc_noprof(gfp, order);
+}
 #endif
 
 #define alloc_pages(...)			alloc_hooks(alloc_pages_noprof(__VA_ARGS__))

From dd085fe9a8ebfc5d10314c60452db38d2b75e609 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Sat, 14 Feb 2026 05:45:35 +0530
Subject: [PATCH 0343/1303] mm: thp: deny THP for files on anonymous inodes

file_thp_enabled() incorrectly allows THP for files on anonymous inodes
(e.g. guest_memfd and secretmem). These files are created via
alloc_file_pseudo(), which does not call get_write_access() and leaves
inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being
true, they appear as read-only regular files when
CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP
collapse.

Anonymous inodes can never pass the inode_is_open_for_write() check
since their i_writecount is never incremented through the normal VFS
open path. The right thing to do is to exclude them from THP eligibility
altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real
filesystem files (e.g. shared libraries), not for pseudo-filesystem
inodes.

For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create
large folios in the page cache via the collapse path, but the
guest_memfd fault handler does not support large folios. This triggers
WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping().

For secretmem, collapse_file() tries to copy page contents through the
direct map, but secretmem pages are removed from the direct map. This
can result in a kernel crash:

    BUG: unable to handle page fault for address: ffff88810284d000
    RIP: 0010:memcpy_orig+0x16/0x130
    Call Trace:
     collapse_file
     hpage_collapse_scan_file
     madvise_collapse

Secretmem is not affected by the crash on upstream as the memory failure
recovery handles the failed copy gracefully, but it still triggers
confusing false memory failure reports:

    Memory failure: 0x106d96f: recovery action for clean unevictable
    LRU page: Recovered

Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all
anonymous inode files.

Link: https://syzkaller.appspot.com/bug?extid=33a04338019ac7e43a44
Link: https://lore.kernel.org/linux-mm/CAEvNRgHegcz3ro35ixkDw39ES8=U6rs6S7iP0gkR9enr7HoGtA@mail.gmail.com
Link: https://lkml.kernel.org/r/20260214001535.435626-1-kartikey406@gmail.com
Fixes: 7fbb5e188248 ("mm: remove VM_EXEC requirement for THP eligibility")
Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
Reported-by: syzbot+33a04338019ac7e43a44@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33a04338019ac7e43a44
Tested-by: syzbot+33a04338019ac7e43a44@syzkaller.appspotmail.com
Tested-by: Lance Yang <lance.yang@linux.dev>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Ackerley Tng <ackerleytng@google.com>
Tested-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Fangrui Song <i@maskray.me>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d4ca8cfd7f9d..8e2746ea74ad 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -94,6 +94,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
+	if (IS_ANON_FILE(inode))
+		return false;
+
 	return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 

From f85b1c6af5bc3872f994df0a5688c1162de07a62 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 16 Feb 2026 14:22:19 +0100
Subject: [PATCH 0344/1303] liveupdate: luo_file: remember retrieve() status

LUO keeps track of successful retrieve attempts on a LUO file.  It does so
to avoid multiple retrievals of the same file.  Multiple retrievals cause
problems because once the file is retrieved, the serialized data
structures are likely freed and the file is likely in a very different
state from what the code expects.

The retrieve boolean in struct luo_file keeps track of this, and is passed
to the finish callback so it knows what work was already done and what it
has left to do.

All this works well when retrieve succeeds.  When it fails,
luo_retrieve_file() returns the error immediately, without ever storing
anywhere that a retrieve was attempted or what its error code was.  This
results in an errored LIVEUPDATE_SESSION_RETRIEVE_FD ioctl to userspace,
but nothing prevents it from trying this again.

The retry is problematic for much of the same reasons listed above.  The
file is likely in a very different state than what the retrieve logic
normally expects, and it might even have freed some serialization data
structures.  Attempting to access them or free them again is going to
break things.

For example, if memfd managed to restore 8 of its 10 folios, but fails on
the 9th, a subsequent retrieve attempt will try to call
kho_restore_folio() on the first folio again, and that will fail with a
warning since it is an invalid operation.

Apart from the retry, finish() also breaks.  Since on failure the
retrieved bool in luo_file is never touched, the finish() call on session
close will tell the file handler that retrieve was never attempted, and it
will try to access or free the data structures that might not exist, much
in the same way as the retry attempt.

There is no sane way of attempting the retrieve again.  Remember the error
retrieve returned and directly return it on a retry.  Also pass this
status code to finish() so it can make the right decision on the work it
needs to do.

This is done by changing the bool to an integer.  A value of 0 means
retrieve was never attempted, a positive value means it succeeded, and a
negative value means it failed and the error code is the value.

Link: https://lkml.kernel.org/r/20260216132221.987987-1-pratyush@kernel.org
Fixes: 7c722a7f44e0 ("liveupdate: luo_file: implement file systems callbacks")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/liveupdate.h   |  9 +++++---
 kernel/liveupdate/luo_file.c | 41 ++++++++++++++++++++++--------------
 mm/memfd_luo.c               |  7 +++++-
 3 files changed, 37 insertions(+), 20 deletions(-)

diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index fe82a6c3005f..dd11fdc76a5f 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -23,8 +23,11 @@ struct file;
 /**
  * struct liveupdate_file_op_args - Arguments for file operation callbacks.
  * @handler:          The file handler being called.
- * @retrieved:        The retrieve status for the 'can_finish / finish'
- *                    operation.
+ * @retrieve_status:  The retrieve status for the 'can_finish / finish'
+ *                    operation. A value of 0 means the retrieve has not been
+ *                    attempted, a positive value means the retrieve was
+ *                    successful, and a negative value means the retrieve failed,
+ *                    and the value is the error code of the call.
  * @file:             The file object. For retrieve: [OUT] The callback sets
  *                    this to the new file. For other ops: [IN] The caller sets
  *                    this to the file being operated on.
@@ -40,7 +43,7 @@ struct file;
  */
 struct liveupdate_file_op_args {
 	struct liveupdate_file_handler *handler;
-	bool retrieved;
+	int retrieve_status;
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c
index 8c79058253e1..5acee4174bf0 100644
--- a/kernel/liveupdate/luo_file.c
+++ b/kernel/liveupdate/luo_file.c
@@ -134,9 +134,12 @@ static LIST_HEAD(luo_file_handler_list);
  *                 state that is not preserved. Set by the handler's .preserve()
  *                 callback, and must be freed in the handler's .unpreserve()
  *                 callback.
- * @retrieved:     A flag indicating whether a user/kernel in the new kernel has
+ * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has
  *                 successfully called retrieve() on this file. This prevents
- *                 multiple retrieval attempts.
+ *                 multiple retrieval attempts. A value of 0 means a retrieve()
+ *                 has not been attempted, a positive value means the retrieve()
+ *                 was successful, and a negative value means the retrieve()
+ *                 failed, and the value is the error code of the call.
  * @mutex:         A mutex that protects the fields of this specific instance
  *                 (e.g., @retrieved, @file), ensuring that operations like
  *                 retrieving or finishing a file are atomic.
@@ -161,7 +164,7 @@ struct luo_file {
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
-	bool retrieved;
+	int retrieve_status;
 	struct mutex mutex;
 	struct list_head list;
 	u64 token;
@@ -298,7 +301,6 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd)
 	luo_file->file = file;
 	luo_file->fh = fh;
 	luo_file->token = token;
-	luo_file->retrieved = false;
 	mutex_init(&luo_file->mutex);
 
 	args.handler = fh;
@@ -577,7 +579,12 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 		return -ENOENT;
 
 	guard(mutex)(&luo_file->mutex);
-	if (luo_file->retrieved) {
+	if (luo_file->retrieve_status < 0) {
+		/* Retrieve was attempted and it failed. Return the error code. */
+		return luo_file->retrieve_status;
+	}
+
+	if (luo_file->retrieve_status > 0) {
 		/*
 		 * Someone is asking for this file again, so get a reference
 		 * for them.
@@ -590,16 +597,19 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 	args.handler = luo_file->fh;
 	args.serialized_data = luo_file->serialized_data;
 	err = luo_file->fh->ops->retrieve(&args);
-	if (!err) {
-		luo_file->file = args.file;
-
-		/* Get reference so we can keep this file in LUO until finish */
-		get_file(luo_file->file);
-		*filep = luo_file->file;
-		luo_file->retrieved = true;
+	if (err) {
+		/* Keep the error code for later use. */
+		luo_file->retrieve_status = err;
+		return err;
 	}
 
-	return err;
+	luo_file->file = args.file;
+	/* Get reference so we can keep this file in LUO until finish */
+	get_file(luo_file->file);
+	*filep = luo_file->file;
+	luo_file->retrieve_status = 1;
+
+	return 0;
 }
 
 static int luo_file_can_finish_one(struct luo_file_set *file_set,
@@ -615,7 +625,7 @@ static int luo_file_can_finish_one(struct luo_file_set *file_set,
 		args.handler = luo_file->fh;
 		args.file = luo_file->file;
 		args.serialized_data = luo_file->serialized_data;
-		args.retrieved = luo_file->retrieved;
+		args.retrieve_status = luo_file->retrieve_status;
 		can_finish = luo_file->fh->ops->can_finish(&args);
 	}
 
@@ -632,7 +642,7 @@ static void luo_file_finish_one(struct luo_file_set *file_set,
 	args.handler = luo_file->fh;
 	args.file = luo_file->file;
 	args.serialized_data = luo_file->serialized_data;
-	args.retrieved = luo_file->retrieved;
+	args.retrieve_status = luo_file->retrieve_status;
 
 	luo_file->fh->ops->finish(&args);
 	luo_flb_file_finish(luo_file->fh);
@@ -788,7 +798,6 @@ int luo_file_deserialize(struct luo_file_set *file_set,
 		luo_file->file = NULL;
 		luo_file->serialized_data = file_ser[i].data;
 		luo_file->token = file_ser[i].token;
-		luo_file->retrieved = false;
 		mutex_init(&luo_file->mutex);
 		list_add_tail(&luo_file->list, &file_set->files_list);
 	}
diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index 5c17da3880c5..e485b828d173 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -326,7 +326,12 @@ static void memfd_luo_finish(struct liveupdate_file_op_args *args)
 	struct memfd_luo_folio_ser *folios_ser;
 	struct memfd_luo_ser *ser;
 
-	if (args->retrieved)
+	/*
+	 * If retrieve was successful, nothing to do. If it failed, retrieve()
+	 * already cleaned up everything it could. So nothing to do there
+	 * either. Only need to clean up when retrieve was not called.
+	 */
+	if (args->retrieve_status)
 		return;
 
 	ser = phys_to_virt(args->serialized_data);

From 319d0bff22f3dd7a982c289e8336da69f0581299 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Tue, 17 Feb 2026 11:21:52 +0100
Subject: [PATCH 0345/1303] MAINTAINERS, mailmap: update e-mail address for
 Vlastimil Babka

Hopefully improve e-mail performance.

Link: https://lkml.kernel.org/r/20260217102151.10425-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    |  1 +
 MAINTAINERS | 18 +++++++++---------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..b3785362f73f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -876,6 +876,7 @@ Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+Vlastimil Babka <vbabka@kernel.org> <vbabka@suse.cz>
 WangYuli <wangyuli@aosc.io> <wangyl5933@chinaunicom.cn>
 WangYuli <wangyuli@aosc.io> <wangyuli@deepin.org>
 Weiwen Hu <huweiwen@linux.alibaba.com> <sehuww@mail.scut.edu.cn>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..02fe14782533 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16656,7 +16656,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
@@ -16786,7 +16786,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
@@ -16841,7 +16841,7 @@ F:	mm/oom_kill.c
 
 MEMORY MANAGEMENT - PAGE ALLOCATOR
 M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Vlastimil Babka <vbabka@suse.cz>
+M:	Vlastimil Babka <vbabka@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
 R:	Brendan Jackman <jackmanb@google.com>
@@ -16887,7 +16887,7 @@ M:	David Hildenbrand <david@kernel.org>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Harry Yoo <harry.yoo@oracle.com>
 R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
@@ -16986,7 +16986,7 @@ MEMORY MAPPING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 R:	Pedro Falcato <pfalcato@suse.de>
 L:	linux-mm@kvack.org
@@ -17016,7 +17016,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Suren Baghdasaryan <surenb@google.com>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -17032,7 +17032,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 M:	David Hildenbrand <david@kernel.org>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -23174,7 +23174,7 @@ K:	\b(?i:rust)\b
 RUST [ALLOC]
 M:	Danilo Krummrich <dakr@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Uladzislau Rezki <urezki@gmail.com>
 L:	rust-for-linux@vger.kernel.org
@@ -24350,7 +24350,7 @@ F:	Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml
 F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
-M:	Vlastimil Babka <vbabka@suse.cz>
+M:	Vlastimil Babka <vbabka@kernel.org>
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Christoph Lameter <cl@gentwo.org>
 R:	David Rientjes <rientjes@google.com>

From fdb24a820a5832ec4532273282cbd4f22c291a0d Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@squashfs.org.uk>
Date: Tue, 17 Feb 2026 05:09:55 +0000
Subject: [PATCH 0346/1303] Squashfs: check metadata block offset is within
 range

Syzkaller reports a "general protection fault in squashfs_copy_data"

This is ultimately caused by a corrupted index look-up table, which
produces a negative metadata block offset.

This is subsequently passed to squashfs_copy_data (via
squashfs_read_metadata) where the negative offset causes an out of bounds
access.

The fix is to check that the offset is within range in
squashfs_read_metadata.  This will trap this and other cases.

Link: https://lkml.kernel.org/r/20260217050955.138351-1-phillip@squashfs.org.uk
Fixes: f400e12656ab ("Squashfs: cache operations")
Reported-by: syzbot+a9747fe1c35a5b115d3f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/699234e2.a70a0220.2c38d7.00e2.GAE@google.com/
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/squashfs/cache.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 8e958db5f786..67abd4dff222 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -344,6 +344,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 	if (unlikely(length < 0))
 		return -EIO;
 
+	if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {

From c80f46ac228b48403866d65391ad09bdf0e8562a Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 14 Feb 2026 13:41:21 -0800
Subject: [PATCH 0347/1303] mm/damon/core: disallow non-power of two
 min_region_sz

DAMON core uses min_region_sz parameter value as the DAMON region
alignment.  The alignment is made using ALIGN() and ALIGN_DOWN(), which
support only the power of two alignments.  But DAMON core API callers can
set min_region_sz to an arbitrary number.  Users can also set it
indirectly, using addr_unit.

When the alignment is not properly set, DAMON behavior becomes difficult
to expect and understand, makes it effectively broken.  It doesn't cause a
kernel crash-like significant issue, though.

Fix the issue by disallowing min_region_sz input that is not a power of
two.  Add the check to damon_commit_ctx(), as all DAMON API callers who
set min_region_sz uses the function.

This can be a sort of behavioral change, but it does not break users, for
the following reasons.  As the symptom is making DAMON effectively broken,
it is not reasonable to believe there are real use cases of non-power of
two min_region_sz.  There is no known use case or issue reports from the
setup, either.

In future, if we find real use cases of non-power of two alignments and we
can support it with low enough overhead, we can consider moving the
restriction.  But, for now, simply disallowing the corner case should be
good enough as a hot fix.

Link: https://lkml.kernel.org/r/20260214214124.87689-1-sj@kernel.org
Fixes: d8f867fa0825 ("mm/damon: add damon_ctx->min_sz_region")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Quanmin Yan <yanquanmin1@huawei.com>
Cc: <stable@vger.kernel.org>	[6.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 01eba1a547d4..adfc52fee9dc 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1252,6 +1252,9 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 {
 	int err;
 
+	if (!is_power_of_2(src->min_region_sz))
+		return -EINVAL;
+
 	err = damon_commit_schemes(dst, src);
 	if (err)
 		return err;

From d155aab90fffa00f93cea1f107aef0a3d548b2ff Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 20 Feb 2026 15:49:40 +0100
Subject: [PATCH 0348/1303] mm/kfence: fix KASAN hardware tag faults during
 late enablement

When KASAN hardware tags are enabled, re-enabling KFENCE late (via
/sys/module/kfence/parameters/sample_interval) causes KASAN faults.

This happens because the KFENCE pool and metadata are allocated via the
page allocator, which tags the memory, while KFENCE continues to access it
using untagged pointers during initialization.

Use __GFP_SKIP_KASAN for late KFENCE pool and metadata allocations to
ensure the memory remains untagged, consistent with early allocations from
memblock.  To support this, add __GFP_SKIP_KASAN to the allowlist in
__alloc_contig_verify_gfp_mask().

Link: https://lkml.kernel.org/r/20260220144940.2779209-1-glider@google.com
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Alexander Potapenko <glider@google.com>
Suggested-by: Ernesto Martinez Garcia <ernesto.martinezgarcia@tugraz.at>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kfence/core.c | 14 ++++++++------
 mm/page_alloc.c  |  3 ++-
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index b5aedf505cec..7393957f9a20 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -1004,14 +1004,14 @@ static int kfence_init_late(void)
 #ifdef CONFIG_CONTIG_ALLOC
 	struct page *pages;
 
-	pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL, first_online_node,
-				   NULL);
+	pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL | __GFP_SKIP_KASAN,
+				   first_online_node, NULL);
 	if (!pages)
 		return -ENOMEM;
 
 	__kfence_pool = page_to_virt(pages);
-	pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL, first_online_node,
-				   NULL);
+	pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL | __GFP_SKIP_KASAN,
+				   first_online_node, NULL);
 	if (pages)
 		kfence_metadata_init = page_to_virt(pages);
 #else
@@ -1021,11 +1021,13 @@ static int kfence_init_late(void)
 		return -EINVAL;
 	}
 
-	__kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, GFP_KERNEL);
+	__kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE,
+					  GFP_KERNEL | __GFP_SKIP_KASAN);
 	if (!__kfence_pool)
 		return -ENOMEM;
 
-	kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE, GFP_KERNEL);
+	kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE,
+						 GFP_KERNEL | __GFP_SKIP_KASAN);
 #endif
 
 	if (!kfence_metadata_init)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fcc32737f451..2d4b6f1a554e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6928,7 +6928,8 @@ static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask)
 {
 	const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM;
 	const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN |
-				  __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO;
+				  __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO |
+				  __GFP_SKIP_KASAN;
 	const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
 
 	/*

From 079c24d5690262e83ee476e2a548e416f3237511 Mon Sep 17 00:00:00 2001
From: Kalesh Singh <kaleshsingh@google.com>
Date: Thu, 19 Feb 2026 15:36:56 -0800
Subject: [PATCH 0349/1303] mm/tracing: rss_stat: ensure curr is false from
 kthread context

The rss_stat trace event allows userspace tools, like Perfetto [1], to
inspect per-process RSS metric changes over time.

The curr field was introduced to rss_stat in commit e4dcad204d3a
("rss_stat: add support to detect RSS updates of external mm").  Its
intent is to indicate whether the RSS update is for the mm_struct of the
current execution context; and is set to false when operating on a remote
mm_struct (e.g., via kswapd or a direct reclaimer).

However, an issue arises when a kernel thread temporarily adopts a user
process's mm_struct.  Kernel threads do not have their own mm_struct and
normally have current->mm set to NULL.  To operate on user memory, they
can "borrow" a memory context using kthread_use_mm(), which sets
current->mm to the user process's mm.

This can be observed, for example, in the USB Function Filesystem (FFS)
driver.  The ffs_user_copy_worker() handles AIO completions and uses
kthread_use_mm() to copy data to a user-space buffer.  If a page fault
occurs during this copy, the fault handler executes in the kthread's
context.

At this point, current is the kthread, but current->mm points to the user
process's mm.  Since the rss_stat event (from the page fault) is for that
same mm, the condition current->mm == mm becomes true, causing curr to be
incorrectly set to true when the trace event is emitted.

This is misleading because it suggests the mm belongs to the kthread,
confusing userspace tools that track per-process RSS changes and
corrupting their mm_id-to-process association.

Fix this by ensuring curr is always false when the trace event is emitted
from a kthread context by checking for the PF_KTHREAD flag.

Link: https://lkml.kernel.org/r/20260219233708.1971199-1-kaleshsingh@google.com
Link: https://perfetto.dev/ [1]
Fixes: e4dcad204d3a ("rss_stat: add support to detect RSS updates of external mm")
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Cc: "David Hildenbrand (Arm)" <david@kernel.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>	[5.10+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/trace/events/kmem.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 7f93e754da5c..cd7920c81f85 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat,
 
 	TP_fast_assign(
 		__entry->mm_id = mm_ptr_to_hash(mm);
-		__entry->curr = !!(current->mm == mm);
+		/*
+		 * curr is true if the mm matches the current task's mm_struct.
+		 * Since kthreads (PF_KTHREAD) have no mm_struct of their own
+		 * but can borrow one via kthread_use_mm(), we must filter them
+		 * out to avoid incorrectly attributing the RSS update to them.
+		 */
+		__entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD);
 		__entry->member = member;
 		__entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member])
 							    << PAGE_SHIFT);

From a4ab97e34bb687a2ca63fc70b47e8762e689797f Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 22 Feb 2026 19:57:02 +0800
Subject: [PATCH 0350/1303] mm: fix NULL NODE_DATA dereference for memoryless
 nodes on boot

Commit d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones
and memory map") moved free_area_init() from setup_arch() to
mm_core_init_early(), which runs after setup_arch() returns.

This changed the ordering relative to init_cpu_to_node() on x86.  Before
the commit, free_area_init() ran during paging_init() (called from
setup_arch()) *before* init_cpu_to_node().  After the commit, it runs
*after* init_cpu_to_node().

On machines with memoryless NUMA nodes (e.g., node 0 has CPUs but no
memory), this causes a NULL pointer dereference:

 1. numa_register_nodes() skips memoryless nodes: no alloc_node_data()
    and no node_set_online() for them.
 2. init_cpu_to_node() sets memoryless nodes online (they have CPUs)
    but does not allocate NODE_DATA.
 3. free_area_init() checks "if (!node_online(nid))" to decide whether
    to call alloc_offline_node_data(). Since the memoryless node is now
    online, the allocation is skipped, leaving NODE_DATA(nid) == NULL.
 4. The immediate "pgdat = NODE_DATA(nid)" dereferences NULL.

The crash happens before console_init(), so no output is visible without
earlyprintk.  With earlyprintk enabled, the following panic is observed:

 BUG: unable to handle page fault for address: 000000000002a1e0
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:free_area_init_node+0x3a/0x540
 Call Trace:
  <TASK>
  free_area_init+0x331/0x4e0
  start_kernel+0x69/0x4a0
  x86_64_start_reservations+0x24/0x30
  x86_64_start_kernel+0x125/0x130
  common_startup_64+0x13e/0x148
  </TASK>
 Kernel panic - not syncing: Attempted to kill the idle task!

Fix this by checking "if (!NODE_DATA(nid))" instead of "if
(!node_online(nid))".  This directly tests whether the per-node data
structure needs to be allocated, regardless of the node's online status.
This change is also safe for non-x86 architectures as they all allocate
NODE_DATA for every node including memoryless ones, so the check simply
evaluates to false with no change in behavior.

Link: https://lkml.kernel.org/r/20260222115702.3659-1-ming.lei@redhat.com
Fixes: d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones and memory map")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mm_init.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 61d983d23f55..df34797691bd 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1896,7 +1896,11 @@ static void __init free_area_init(void)
 	for_each_node(nid) {
 		pg_data_t *pgdat;
 
-		if (!node_online(nid))
+		/*
+		 * If an architecture has not allocated node data for
+		 * this node, presume the node is memoryless or offline.
+		 */
+		if (!NODE_DATA(nid))
 			alloc_offline_node_data(nid);
 
 		pgdat = NODE_DATA(nid);

From 37a012c5c10c3364c5cba5def30dd7a17a6b587a Mon Sep 17 00:00:00 2001
From: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Date: Mon, 23 Feb 2026 17:09:05 +0000
Subject: [PATCH 0351/1303] mailmap: add entry for Daniele Alessandrelli

My Intel email is going to bounce soon.  Map it to my personal Gmail
address.

Link: https://lkml.kernel.org/r/20260223170905.278956-1-daniele.alessandrelli@intel.com
Signed-off-by: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Cc: Daniele Alessandrelli <daniele.alessandrelli@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index b3785362f73f..cd09bc545586 100644
--- a/.mailmap
+++ b/.mailmap
@@ -211,6 +211,7 @@ Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
+Daniele Alessandrelli <daniele.alessandrelli@gmail.com> <daniele.alessandrelli@intel.com>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
 David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>

From 410aed670cddac1de4f0c2865f30ec623fd20f78 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry@kernel.org>
Date: Mon, 23 Feb 2026 16:00:26 +0000
Subject: [PATCH 0352/1303] MAINTAINERS: update Yosry Ahmed's email address

Use my kernel.org email address.

Link: https://lkml.kernel.org/r/20260223160027.122307-1-yosry@kernel.org
Signed-off-by: Yosry Ahmed <yosry@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 3 ++-
 MAINTAINERS | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/.mailmap b/.mailmap
index cd09bc545586..c124a1306d26 100644
--- a/.mailmap
+++ b/.mailmap
@@ -892,7 +892,8 @@ Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn>
 Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com>
 Yixun Lan <dlan@kernel.org> <dlan@gentoo.org>
 Yixun Lan <dlan@kernel.org> <yixun.lan@amlogic.com>
-Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com>
+Yosry Ahmed <yosry@kernel.org> <yosryahmed@google.com>
+Yosry Ahmed <yosry@kernel.org> <yosry.ahmed@linux.dev>
 Yu-Chun Lin <eleanor.lin@realtek.com> <eleanor15x@gmail.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 02fe14782533..e4572a36afd2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -29186,7 +29186,7 @@ K:	zstd
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Yosry Ahmed <yosry.ahmed@linux.dev>
+M:	Yosry Ahmed <yosry@kernel.org>
 M:	Nhat Pham <nphamcs@gmail.com>
 R:	Chengming Zhou <chengming.zhou@linux.dev>
 L:	linux-mm@kvack.org

From 2f38fd99c0004676d835ae96ac4f3b54edc02c82 Mon Sep 17 00:00:00 2001
From: wangshuaiwei <wangshuaiwei1@xiaomi.com>
Date: Tue, 24 Feb 2026 14:32:28 +0800
Subject: [PATCH 0353/1303] scsi: ufs: core: Fix shift out of bounds when
 MAXQ=32

According to JESD223F, the maximum number of queues (MAXQ) is 32. When MCQ
is enabled and ESI is disabled, nr_hw_queues=32 causes a shift overflow
problem.

Fix this by using 64-bit intermediate values to handle the nr_hw_queues=32
case safely.

Signed-off-by: wangshuaiwei <wangshuaiwei1@xiaomi.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260224063228.50112-1-wangshuaiwei1@xiaomi.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 85987373b961..899e663fea6e 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7110,7 +7110,7 @@ static irqreturn_t ufshcd_handle_mcq_cq_events(struct ufs_hba *hba)
 
 	ret = ufshcd_vops_get_outstanding_cqs(hba, &outstanding_cqs);
 	if (ret)
-		outstanding_cqs = (1U << hba->nr_hw_queues) - 1;
+		outstanding_cqs = (1ULL << hba->nr_hw_queues) - 1;
 
 	/* Exclude the poll queues */
 	nr_queues = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL];

From bfbc0b5b32a8f28ce284add619bf226716a59bc0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 24 Feb 2026 11:51:16 -0700
Subject: [PATCH 0354/1303] media: dvb-core: fix wrong reinitialization of
 ringbuffer on reopen

dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the
DVR device.  dvb_ringbuffer_init() calls init_waitqueue_head(), which
reinitializes the waitqueue list head to empty.

Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the
same DVR device share it), this orphans any existing waitqueue entries
from io_uring poll or epoll, leaving them with stale prev/next pointers
while the list head is reset to {self, self}.

The waitqueue and spinlock in dvr_buffer are already properly
initialized once in dvb_dmxdev_init().  The open path only needs to
reset the buffer data pointer, size, and read/write positions.

Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct
assignment of data/size and a call to dvb_ringbuffer_reset(), which
properly resets pread, pwrite, and error with correct memory ordering
without touching the waitqueue or spinlock.

Cc: stable@vger.kernel.org
Fixes: 34731df288a5f ("V4L/DVB (3501): Dmxdev: use dvb_ringbuffer")
Reported-by: syzbot+ab12f0c08dd7ab8d057c@syzkaller.appspotmail.com
Tested-by: syzbot+ab12f0c08dd7ab8d057c@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/698a26d3.050a0220.3b3015.007d.GAE@google.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/media/dvb-core/dmxdev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index 7cfed24054d0..3c8bc75e4d6c 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -168,7 +168,9 @@ static int dvb_dvr_open(struct inode *inode, struct file *file)
 			mutex_unlock(&dmxdev->mutex);
 			return -ENOMEM;
 		}
-		dvb_ringbuffer_init(&dmxdev->dvr_buffer, mem, DVR_BUFFER_SIZE);
+		dmxdev->dvr_buffer.data = mem;
+		dmxdev->dvr_buffer.size = DVR_BUFFER_SIZE;
+		dvb_ringbuffer_reset(&dmxdev->dvr_buffer);
 		if (dmxdev->may_do_mmap)
 			dvb_vb2_init(&dmxdev->dvr_vb2_ctx, "dvr",
 				     &dmxdev->mutex,

From 6acf7860dcc79ed045cc9e6a79c8a8bb6959dba7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Feb 2026 06:21:44 -0800
Subject: [PATCH 0355/1303] zloop: advertise a volatile write cache

Zloop is file system backed and thus needs to sync the underlying file
system to persist data.  Set BLK_FEAT_WRITE_CACHE so that the block
layer actually send flush commands, and fix the flush implementation
as sync_filesystem requires s_umount to be held and the code currently
misses that.

Fixes: eb0570c7df23 ("block: new zoned loop block device driver")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/zloop.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index 8e334f5025fc..ae9bf2a85c21 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -542,6 +542,21 @@ static void zloop_rw(struct zloop_cmd *cmd)
 	zloop_put_cmd(cmd);
 }
 
+/*
+ * Sync the entire FS containing the zone files instead of walking all files.
+ */
+static int zloop_flush(struct zloop_device *zlo)
+{
+	struct super_block *sb = file_inode(zlo->data_dir)->i_sb;
+	int ret;
+
+	down_read(&sb->s_umount);
+	ret = sync_filesystem(sb);
+	up_read(&sb->s_umount);
+
+	return ret;
+}
+
 static void zloop_handle_cmd(struct zloop_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
@@ -562,11 +577,7 @@ static void zloop_handle_cmd(struct zloop_cmd *cmd)
 		zloop_rw(cmd);
 		return;
 	case REQ_OP_FLUSH:
-		/*
-		 * Sync the entire FS containing the zone files instead of
-		 * walking all files
-		 */
-		cmd->ret = sync_filesystem(file_inode(zlo->data_dir)->i_sb);
+		cmd->ret = zloop_flush(zlo);
 		break;
 	case REQ_OP_ZONE_RESET:
 		cmd->ret = zloop_reset_zone(zlo, rq_zone_no(rq));
@@ -981,7 +992,8 @@ static int zloop_ctl_add(struct zloop_options *opts)
 	struct queue_limits lim = {
 		.max_hw_sectors		= SZ_1M >> SECTOR_SHIFT,
 		.chunk_sectors		= opts->zone_size,
-		.features		= BLK_FEAT_ZONED,
+		.features		= BLK_FEAT_ZONED | BLK_FEAT_WRITE_CACHE,
+
 	};
 	unsigned int nr_zones, i, j;
 	struct zloop_device *zlo;

From 3c4617117a2b7682cf037be5e5533e379707f050 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Feb 2026 06:21:45 -0800
Subject: [PATCH 0356/1303] zloop: check for spurious options passed to remove

Zloop uses a command option parser for all control commands,
but most options are only valid for adding a new device.  Check
for incorrectly specified options in the remove handler.

Fixes: eb0570c7df23 ("block: new zoned loop block device driver")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/zloop.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index ae9bf2a85c21..9e3bb538d5fc 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -1174,7 +1174,12 @@ static int zloop_ctl_remove(struct zloop_options *opts)
 	int ret;
 
 	if (!(opts->mask & ZLOOP_OPT_ID)) {
-		pr_err("No ID specified\n");
+		pr_err("No ID specified for remove\n");
+		return -EINVAL;
+	}
+
+	if (opts->mask & ~ZLOOP_OPT_ID) {
+		pr_err("Invalid option specified for remove\n");
 		return -EINVAL;
 	}
 

From 201ceb94aa1def0024a7c18ce643e5f65026be06 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 23 Feb 2026 19:37:51 -0800
Subject: [PATCH 0357/1303] kunit: irq: Ensure timer doesn't fire too
 frequently

Fix a bug where kunit_run_irq_test() could hang if the system is too
slow.  This was noticed with the crypto library tests in certain VMs.

Specifically, if kunit_irq_test_timer_func() and the associated hrtimer
code took over 5us to run, then the CPU would spend all its time
executing that code in hardirq context.  As a result, the task executing
kunit_run_irq_test() never had a chance to run, exit the loop, and
cancel the timer.

To fix it, make kunit_irq_test_timer_func() increase the timer interval
when the other contexts aren't having a chance to run.

Fixes: 950a81224e8b ("lib/crypto: tests: Add hash-test-template.h and gen-hash-testvecs.py")
Cc: stable@vger.kernel.org
Reviewed-by: David Gow <david@davidgow.net>
Link: https://lore.kernel.org/r/20260224033751.97615-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 include/kunit/run-in-irq-context.h | 44 +++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 16 deletions(-)

diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h
index c89b1b1b12dd..bfe60d6cf28d 100644
--- a/include/kunit/run-in-irq-context.h
+++ b/include/kunit/run-in-irq-context.h
@@ -12,16 +12,16 @@
 #include <linux/hrtimer.h>
 #include <linux/workqueue.h>
 
-#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5)
-
 struct kunit_irq_test_state {
 	bool (*func)(void *test_specific_state);
 	void *test_specific_state;
 	bool task_func_reported_failure;
 	bool hardirq_func_reported_failure;
 	bool softirq_func_reported_failure;
+	atomic_t task_func_calls;
 	atomic_t hardirq_func_calls;
 	atomic_t softirq_func_calls;
+	ktime_t interval;
 	struct hrtimer timer;
 	struct work_struct bh_work;
 };
@@ -30,14 +30,25 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer)
 {
 	struct kunit_irq_test_state *state =
 		container_of(timer, typeof(*state), timer);
+	int task_calls, hardirq_calls, softirq_calls;
 
 	WARN_ON_ONCE(!in_hardirq());
-	atomic_inc(&state->hardirq_func_calls);
+	task_calls = atomic_read(&state->task_func_calls);
+	hardirq_calls = atomic_inc_return(&state->hardirq_func_calls);
+	softirq_calls = atomic_read(&state->softirq_func_calls);
+
+	/*
+	 * If the timer is firing too often for the softirq or task to ever have
+	 * a chance to run, increase the timer interval.  This is needed on very
+	 * slow systems.
+	 */
+	if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0))
+		state->interval = ktime_add_ns(state->interval, 250);
 
 	if (!state->func(state->test_specific_state))
 		state->hardirq_func_reported_failure = true;
 
-	hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL);
+	hrtimer_forward_now(&state->timer, state->interval);
 	queue_work(system_bh_wq, &state->bh_work);
 	return HRTIMER_RESTART;
 }
@@ -86,10 +97,14 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	struct kunit_irq_test_state state = {
 		.func = func,
 		.test_specific_state = test_specific_state,
+		/*
+		 * Start with a 5us timer interval.  If the system can't keep
+		 * up, kunit_irq_test_timer_func() will increase it.
+		 */
+		.interval = us_to_ktime(5),
 	};
 	unsigned long end_jiffies;
-	int hardirq_calls, softirq_calls;
-	bool allctx = false;
+	int task_calls, hardirq_calls, softirq_calls;
 
 	/*
 	 * Set up a hrtimer (the way we access hardirq context) and a work
@@ -104,21 +119,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	 * and hardirq), or 1 second, whichever comes first.
 	 */
 	end_jiffies = jiffies + HZ;
-	hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL,
-		      HRTIMER_MODE_REL_HARD);
-	for (int task_calls = 0, calls = 0;
-	     ((calls < max_iterations) || !allctx) &&
-	     !time_after(jiffies, end_jiffies);
-	     task_calls++) {
+	hrtimer_start(&state.timer, state.interval, HRTIMER_MODE_REL_HARD);
+	do {
 		if (!func(test_specific_state))
 			state.task_func_reported_failure = true;
 
+		task_calls = atomic_inc_return(&state.task_func_calls);
 		hardirq_calls = atomic_read(&state.hardirq_func_calls);
 		softirq_calls = atomic_read(&state.softirq_func_calls);
-		calls = task_calls + hardirq_calls + softirq_calls;
-		allctx = (task_calls > 0) && (hardirq_calls > 0) &&
-			 (softirq_calls > 0);
-	}
+	} while ((task_calls + hardirq_calls + softirq_calls < max_iterations ||
+		  (task_calls == 0 || hardirq_calls == 0 ||
+		   softirq_calls == 0)) &&
+		 !time_after(jiffies, end_jiffies));
 
 	/* Cancel the timer and work. */
 	hrtimer_cancel(&state.timer);

From 4b44cbb264d0ed3f2f2bc2659db6ce45882f4670 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 24 Feb 2026 15:24:52 -0800
Subject: [PATCH 0358/1303] overflow: Make sure size helpers are always inlined

With kmalloc_obj() performing implicit size calculations, the embedded
size_mul() calls, while marked inline, were not always being inlined.
I noticed a couple places where allocations were making a call out for
things that would otherwise be compile-time calculated. Force the
compilers to always inline these calculations.

Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/20260224232451.work.614-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/overflow.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index eddd987a8513..a8cb6319b4fb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -42,7 +42,7 @@
  * both the type-agnostic benefits of the macros while also being able to
  * enforce that the return value is, in fact, checked.
  */
-static inline bool __must_check __must_check_overflow(bool overflow)
+static __always_inline bool __must_check __must_check_overflow(bool overflow)
 {
 	return unlikely(overflow);
 }
@@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
+static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2)
 {
 	size_t bytes;
 
@@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_add(size_t addend1, size_t addend2)
+static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2)
 {
 	size_t bytes;
 
@@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2)
  * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX).
  * The lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
+static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
 {
 	size_t bytes;
 

From 2f61f38a217462411fed950e843b82bc119884cf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 23 Feb 2026 12:19:08 +0000
Subject: [PATCH 0359/1303] net: stmmac: fix timestamping configuration after
 suspend/resume

When stmmac_init_timestamping() is called, it clears the receive and
transmit path booleans that allow timestamps to be read. These are
never re-initialised until after userspace requests timestamping
features to be enabled.

However, our copy of the timestamp configuration is not cleared, which
means we return the old configuration to userspace when requested.
This is inconsistent. Fix this by clearing the timestamp configuration.

Fixes: d6228b7cdd6e ("net: stmmac: implement the SIOCGHWTSTAMP ioctl")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/E1vuUu4-0000000Afea-0j9B@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 82375d34ad57..91f638ce132e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -853,6 +853,7 @@ static int stmmac_init_timestamping(struct stmmac_priv *priv)
 		netdev_info(priv->dev,
 			    "IEEE 1588-2008 Advanced Timestamp supported\n");
 
+	memset(&priv->tstamp_config, 0, sizeof(priv->tstamp_config));
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 

From c45f7263100cece247dd3fa5fe277bd97fdb5687 Mon Sep 17 00:00:00 2001
From: Liwei Song <liwei.song@windriver.com>
Date: Thu, 12 Feb 2026 12:00:35 +0800
Subject: [PATCH 0360/1303] firmware: stratix10-rsu: Fix NULL pointer
 dereference when RSU is disabled

When the Remote System Update (RSU) isn't enabled in the First Stage
Boot Loader (FSBL), the driver encounters a NULL pointer dereference when
excute svc_normal_to_secure_thread() thread, resulting in a kernel panic:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
Mem abort info:
...
Data abort info:
...
[0000000000000008] user address but active_mm is swapper
Internal error: Oops: 0000000096000004 [#1]  SMP
Modules linked in:
CPU: 0 UID: 0 PID: 79 Comm: svc_smc_hvc_thr Not tainted 6.19.0-rc8-yocto-standard+ #59 PREEMPT
Hardware name: SoCFPGA Stratix 10 SoCDK (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : svc_normal_to_secure_thread+0x38c/0x990
lr : svc_normal_to_secure_thread+0x144/0x990
...
Call trace:
 svc_normal_to_secure_thread+0x38c/0x990 (P)
 kthread+0x150/0x210
 ret_from_fork+0x10/0x20
Code: 97cfc113 f9400260 aa1403e1 f9400400 (f9400402)
---[ end trace 0000000000000000 ]---

The issue occurs because rsu_send_async_msg() fails when RSU is not enabled
in firmware, causing the channel to be freed via stratix10_svc_free_channel().
However, the probe function continues execution and registers
svc_normal_to_secure_thread(), which subsequently attempts to access the
already-freed channel, triggering the NULL pointer dereference.

Fix this by properly cleaning up the async client and returning early on
failure, preventing the thread from being used with an invalid channel.

Fixes: 15847537b623 ("firmware: stratix10-rsu: Migrate RSU driver to use stratix10 asynchronous framework.")
Cc: stable@kernel.org
Signed-off-by: Liwei Song <liwei.song@windriver.com>
Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
---
 drivers/firmware/stratix10-rsu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c
index 41da07c445a6..e1912108a0fe 100644
--- a/drivers/firmware/stratix10-rsu.c
+++ b/drivers/firmware/stratix10-rsu.c
@@ -768,7 +768,9 @@ static int stratix10_rsu_probe(struct platform_device *pdev)
 				 rsu_async_status_callback);
 	if (ret) {
 		dev_err(dev, "Error, getting RSU status %i\n", ret);
+		stratix10_svc_remove_async_client(priv->chan);
 		stratix10_svc_free_channel(priv->chan);
+		return ret;
 	}
 
 	/* get DCMF version from firmware */

From c601fd5414315fc515f746b499110e46272e7243 Mon Sep 17 00:00:00 2001
From: Jonathan Cavitt <jonathan.cavitt@intel.com>
Date: Tue, 24 Feb 2026 22:12:28 +0000
Subject: [PATCH 0361/1303] drm/client: Do not destroy NULL modes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'modes' in drm_client_modeset_probe may fail to kcalloc.  If this
occurs, we jump to 'out', calling modes_destroy on it, which
dereferences it.  This may result in a NULL pointer dereference in the
error case.  Prevent that.

Fixes: 3039cc0c0653 ("drm/client: Make copies of modes")
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260224221227.69126-2-jonathan.cavitt@intel.com
---
 drivers/gpu/drm/drm_client_modeset.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 262b1b8773c5..bb49b8361271 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -930,7 +930,8 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
 	mutex_unlock(&client->modeset_mutex);
 out:
 	kfree(crtcs);
-	modes_destroy(dev, modes, connector_count);
+	if (modes)
+		modes_destroy(dev, modes, connector_count);
 	kfree(modes);
 	kfree(offsets);
 	kfree(enabled);

From 83236b2e43dba00bee5b82eb5758816b1a674f6a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 24 Feb 2026 21:39:58 -1000
Subject: [PATCH 0362/1303] sched_ext: Disable preemption between
 scx_claim_exit() and kicking helper work

scx_claim_exit() atomically sets exit_kind, which prevents scx_error() from
triggering further error handling. After claiming exit, the caller must kick
the helper kthread work which initiates bypass mode and teardown.

If the calling task gets preempted between claiming exit and kicking the
helper work, and the BPF scheduler fails to schedule it back (since error
handling is now disabled), the helper work is never queued, bypass mode
never activates, tasks stop being dispatched, and the system wedges.

Disable preemption across scx_claim_exit() and the subsequent work kicking
in all callers - scx_disable() and scx_vexit(). Add
lockdep_assert_preemption_disabled() to scx_claim_exit() to enforce the
requirement.

Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index c18e81e8ef51..9280381f8923 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4423,10 +4423,19 @@ static void scx_disable_workfn(struct kthread_work *work)
 	scx_bypass(false);
 }
 
+/*
+ * Claim the exit on @sch. The caller must ensure that the helper kthread work
+ * is kicked before the current task can be preempted. Once exit_kind is
+ * claimed, scx_error() can no longer trigger, so if the current task gets
+ * preempted and the BPF scheduler fails to schedule it back, the helper work
+ * will never be kicked and the whole system can wedge.
+ */
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind)
 {
 	int none = SCX_EXIT_NONE;
 
+	lockdep_assert_preemption_disabled();
+
 	if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind))
 		return false;
 
@@ -4449,6 +4458,7 @@ static void scx_disable(enum scx_exit_kind kind)
 	rcu_read_lock();
 	sch = rcu_dereference(scx_root);
 	if (sch) {
+		guard(preempt)();
 		scx_claim_exit(sch, kind);
 		kthread_queue_work(sch->helper, &sch->disable_work);
 	}
@@ -4771,6 +4781,8 @@ static bool scx_vexit(struct scx_sched *sch,
 {
 	struct scx_exit_info *ei = sch->exit_info;
 
+	guard(preempt)();
+
 	if (!scx_claim_exit(sch, kind))
 		return false;
 

From 29c8b85adb47daefc213381bc1831787f512d89b Mon Sep 17 00:00:00 2001
From: Sascha Bischoff <Sascha.Bischoff@arm.com>
Date: Wed, 25 Feb 2026 08:31:40 +0000
Subject: [PATCH 0363/1303] irqchip/gic-v5: Fix inversion of IRS_IDR0.virt flag

It appears that a !! became ! during a cleanup, resulting in inverted
logic when detecting if a host GICv5 implementation is capable of
virtualization.

Re-add the missing !, fixing the behaviour.

Fixes: 3227c3a89d65f ("irqchip/gic-v5: Check if impl is virt capable")
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Link: https://patch.msgid.link/20260225083130.3378490-1-sascha.bischoff@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/irqchip/irq-gic-v5-irs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index eeeb40fb0eaa..4ed2bfa17c01 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -744,7 +744,7 @@ static int __init gicv5_irs_init(struct device_node *node)
 	 */
 	if (list_empty(&irs_nodes)) {
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR0);
-		gicv5_global_data.virt_capable = !FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
+		gicv5_global_data.virt_capable = !!FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
 
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1);
 		irs_setup_pri_bits(idr);

From 7fe8dec3f628e9779f1631576f8e693370050348 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:28 +0100
Subject: [PATCH 0364/1303] ALSA: usb-audio: Cap the packet size
 pre-calculations

We calculate the possible packet sizes beforehand for adaptive and
synchronous endpoints, but we didn't take care of the max frame size
for those pre-calculated values.  When a device or a bus limits the
packet size, a high sample rate or a high number of channels may lead
to the packet sizes that are larger than the given limit, which
results in an error from the USB core at submitting URBs.

As a simple workaround, just add the sanity checks of pre-calculated
packet sizes to have the upper boundary of ep->maxframesize.

Fixes: f0bd62b64016 ("ALSA: usb-audio: Improve frames size computation")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 73bce9712dbd..c887c2f5b25d 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -1378,6 +1378,9 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
 		return -EINVAL;
 	}
 
+	ep->packsize[0] = min(ep->packsize[0], ep->maxframesize);
+	ep->packsize[1] = min(ep->packsize[1], ep->maxframesize);
+
 	/* calculate the frequency in 16.16 format */
 	ep->freqm = ep->freqn;
 	ep->freqshift = INT_MIN;

From 7cb2a5422f5bbdf1cf32eae0eda41000485b9346 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:29 +0100
Subject: [PATCH 0365/1303] ALSA: usb-audio: Check max frame size for implicit
 feedback mode, too

When the packet sizes are taken from the capture stream in the
implicit feedback mode, the sizes might be larger than the upper
boundary defined by the descriptor.  As already done for other
transfer modes, we have to cap the sizes accordingly at sending,
otherwise this would lead to an error in USB core at submission of
URBs.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index c887c2f5b25d..2e70dbc479b4 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -221,6 +221,7 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
 
 	packet = ctx->packet_size[idx];
 	if (packet) {
+		packet = min(packet, ep->maxframesize);
 		if (avail && packet >= avail)
 			return -EAGAIN;
 		return packet;

From c5bf24c8aba1ff711226ee0f039ff01a5754692b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:30 +0100
Subject: [PATCH 0366/1303] ALSA: usb-audio: Avoid implicit feedback mode on
 DIYINHK USB Audio 2.0

Although DIYINHK USB Audio 2.0 (ID 20b1:2009) shows the implicit
feedback source for the capture stream, this would cause several
problems for the playback.  Namely, the device can get wMaxPackSize
1024 for 24/32 bit format with 6 channels, and when a high sample rate
like 352.8kHz or 384kHz is played, the packet size overflows the max
limit.  Also, the device has another two playback altsets, and those
aren't properly handled with the implicit feedback.

Since the device has been working well even before introducing the
implicit feedback, we can assume that it works fine in the async mode.
This patch adds the explicit skip of the implicit fb detection to make
the playback running in the async mode.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index fbceed8e8d36..c6a78efbcaa3 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2365,6 +2365,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x2040, 0x7281, /* Hauppauge HVR-950Q-MXL */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x20b1, 0x2009, /* XMOS Ltd DIYINHK USB Audio 2.0 */
+		   QUIRK_FLAG_SKIP_IMPLICIT_FB | QUIRK_FLAG_DSD_RAW),
 	DEVICE_FLG(0x2040, 0x8200, /* Hauppauge Woodbury */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */

From 4e9113c533acee2ba1f72fd68ee6ecd36b64484e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:31 +0100
Subject: [PATCH 0367/1303] ALSA: usb-audio: Use inclusive terms

Replace the remaining with inclusive terms; it's only this function
name we overlooked at the previous conversion.

Fixes: 53837b4ac2bd ("ALSA: usb-audio: Replace slave/master terms")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-5-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 2e70dbc479b4..bf4401aba76c 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -160,8 +160,8 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep)
  * This won't be used for implicit feedback which takes the packet size
  * returned from the sync source
  */
-static int slave_next_packet_size(struct snd_usb_endpoint *ep,
-				  unsigned int avail)
+static int synced_next_packet_size(struct snd_usb_endpoint *ep,
+				   unsigned int avail)
 {
 	unsigned int phase;
 	int ret;
@@ -228,7 +228,7 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
 	}
 
 	if (ep->sync_source)
-		return slave_next_packet_size(ep, avail);
+		return synced_next_packet_size(ep, avail);
 	else
 		return next_packet_size(ep, avail);
 }

From 4a2d046e4b13202a6301a993961f5b30ae4d7119 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 24 Feb 2026 18:31:25 +0800
Subject: [PATCH 0368/1303] erofs: fix interlaced plain identification for
 encoded extents

Only plain data whose start position and on-disk physical length are
both aligned to the block size should be classified as interlaced
plain extents. Otherwise, it must be treated as shifted plain extents.

This issue was found by syzbot using a crafted compressed image
containing plain extents with unaligned physical lengths, which can
cause OOB read in z_erofs_transform_plain().

Reported-and-tested-by: syzbot+d988dc155e740d76a331@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/699d5714.050a0220.cdd3c.03e7.GAE@google.com
Fixes: 1d191b4ca51d ("erofs: implement encoded extent metadata")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/zmap.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index c8d8e129eb4b..30775502b56d 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -513,6 +513,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 	unsigned int recsz = z_erofs_extent_recsize(vi->z_advise);
 	erofs_off_t pos = round_up(Z_EROFS_MAP_HEADER_END(erofs_iloc(inode) +
 				   vi->inode_isize + vi->xattr_isize), recsz);
+	unsigned int bmask = sb->s_blocksize - 1;
 	bool in_mbox = erofs_inode_in_metabox(inode);
 	erofs_off_t lend = inode->i_size;
 	erofs_off_t l, r, mid, pa, la, lstart;
@@ -596,17 +597,17 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 			map->m_flags |= EROFS_MAP_MAPPED |
 				EROFS_MAP_FULL_MAPPED | EROFS_MAP_ENCODED;
 			fmt = map->m_plen >> Z_EROFS_EXTENT_PLEN_FMT_BIT;
+			if (map->m_plen & Z_EROFS_EXTENT_PLEN_PARTIAL)
+				map->m_flags |= EROFS_MAP_PARTIAL_REF;
+			map->m_plen &= Z_EROFS_EXTENT_PLEN_MASK;
 			if (fmt)
 				map->m_algorithmformat = fmt - 1;
-			else if (interlaced && !erofs_blkoff(sb, map->m_pa))
+			else if (interlaced && !((map->m_pa | map->m_plen) & bmask))
 				map->m_algorithmformat =
 					Z_EROFS_COMPRESSION_INTERLACED;
 			else
 				map->m_algorithmformat =
 					Z_EROFS_COMPRESSION_SHIFTED;
-			if (map->m_plen & Z_EROFS_EXTENT_PLEN_PARTIAL)
-				map->m_flags |= EROFS_MAP_PARTIAL_REF;
-			map->m_plen &= Z_EROFS_EXTENT_PLEN_MASK;
 		}
 	}
 	map->m_llen = lend - map->m_la;

From a4b0bf6a40f3c107c67a24fbc614510ef5719980 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Wed, 25 Feb 2026 08:55:55 +0200
Subject: [PATCH 0369/1303] x86/efi: defer freeing of boot services memory

efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE
and EFI_BOOT_SERVICES_DATA using memblock_free_late().

There are two issue with that: memblock_free_late() should be used for
memory allocated with memblock_alloc() while the memory reserved with
memblock_reserve() should be freed with free_reserved_area().

More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
efi_free_boot_services() is called before deferred initialization of the
memory map is complete.

Benjamin Herrenschmidt reports that this causes a leak of ~140MB of
RAM on EC2 t3a.nano instances which only have 512MB or RAM.

If the freed memory resides in the areas that memory map for them is
still uninitialized, they won't be actually freed because
memblock_free_late() calls memblock_free_pages() and the latter skips
uninitialized pages.

Using free_reserved_area() at this point is also problematic because
__free_page() accesses the buddy of the freed page and that again might
end up in uninitialized part of the memory map.

Delaying the entire efi_free_boot_services() could be problematic
because in addition to freeing boot services memory it updates
efi.memmap without any synchronization and that's undesirable late in
boot when there is concurrency.

More robust approach is to only defer freeing of the EFI boot services
memory.

Split efi_free_boot_services() in two. First efi_unmap_boot_services()
collects ranges that should be freed into an array then
efi_free_boot_services() later frees them after deferred init is complete.

Link: https://lore.kernel.org/all/ec2aaef14783869b3be6e3c253b2dcbf67dbc12a.camel@kernel.crashing.org
Fixes: 916f676f8dc0 ("x86, efi: Retain boot service code until after switching to virtual mode")
Cc: <stable@vger.kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/include/asm/efi.h          |  2 +-
 arch/x86/platform/efi/efi.c         |  2 +-
 arch/x86/platform/efi/quirks.c      | 55 +++++++++++++++++++++++++++--
 drivers/firmware/efi/mokvar-table.c |  2 +-
 4 files changed, 55 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index f227a70ac91f..51b4cdbea061 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -138,7 +138,7 @@ extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);
 extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
-extern void efi_free_boot_services(void);
+extern void efi_unmap_boot_services(void);
 
 void arch_efi_call_virt_setup(void);
 void arch_efi_call_virt_teardown(void);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d00c6de7f3b7..d84c6020dda1 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -836,7 +836,7 @@ static void __init __efi_enter_virtual_mode(void)
 	}
 
 	efi_check_for_embedded_firmwares();
-	efi_free_boot_services();
+	efi_unmap_boot_services();
 
 	if (!efi_is_mixed())
 		efi_native_runtime_setup();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 553f330198f2..35caa5746115 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -341,7 +341,7 @@ void __init efi_reserve_boot_services(void)
 
 		/*
 		 * Because the following memblock_reserve() is paired
-		 * with memblock_free_late() for this region in
+		 * with free_reserved_area() for this region in
 		 * efi_free_boot_services(), we must be extremely
 		 * careful not to reserve, and subsequently free,
 		 * critical regions of memory (like the kernel image) or
@@ -404,17 +404,33 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 		pr_err("Failed to unmap VA mapping for 0x%llx\n", va);
 }
 
-void __init efi_free_boot_services(void)
+struct efi_freeable_range {
+	u64 start;
+	u64 end;
+};
+
+static struct efi_freeable_range *ranges_to_free;
+
+void __init efi_unmap_boot_services(void)
 {
 	struct efi_memory_map_data data = { 0 };
 	efi_memory_desc_t *md;
 	int num_entries = 0;
+	int idx = 0;
+	size_t sz;
 	void *new, *new_md;
 
 	/* Keep all regions for /sys/kernel/debug/efi */
 	if (efi_enabled(EFI_DBG))
 		return;
 
+	sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1;
+	ranges_to_free = kzalloc(sz, GFP_KERNEL);
+	if (!ranges_to_free) {
+		pr_err("Failed to allocate storage for freeable EFI regions\n");
+		return;
+	}
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -471,7 +487,15 @@ void __init efi_free_boot_services(void)
 			start = SZ_1M;
 		}
 
-		memblock_free_late(start, size);
+		/*
+		 * With CONFIG_DEFERRED_STRUCT_PAGE_INIT parts of the memory
+		 * map are still not initialized and we can't reliably free
+		 * memory here.
+		 * Queue the ranges to free at a later point.
+		 */
+		ranges_to_free[idx].start = start;
+		ranges_to_free[idx].end = start + size;
+		idx++;
 	}
 
 	if (!num_entries)
@@ -512,6 +536,31 @@ void __init efi_free_boot_services(void)
 	}
 }
 
+static int __init efi_free_boot_services(void)
+{
+	struct efi_freeable_range *range = ranges_to_free;
+	unsigned long freed = 0;
+
+	if (!ranges_to_free)
+		return 0;
+
+	while (range->start) {
+		void *start = phys_to_virt(range->start);
+		void *end = phys_to_virt(range->end);
+
+		free_reserved_area(start, end, -1, NULL);
+		freed += (end - start);
+		range++;
+	}
+	kfree(ranges_to_free);
+
+	if (freed)
+		pr_info("Freeing EFI boot services memory: %ldK\n", freed / SZ_1K);
+
+	return 0;
+}
+arch_initcall(efi_free_boot_services);
+
 /*
  * A number of config table entries get remapped to virtual addresses
  * after entering EFI virtual mode. However, the kexec kernel requires
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 4ff0c2926097..6842aa96d704 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -85,7 +85,7 @@ static struct kobject *mokvar_kobj;
  * as an alternative to ordinary EFI variables, due to platform-dependent
  * limitations. The memory occupied by this table is marked as reserved.
  *
- * This routine must be called before efi_free_boot_services() in order
+ * This routine must be called before efi_unmap_boot_services() in order
  * to guarantee that it can mark the table as reserved.
  *
  * Implicit inputs:

From 54e367cb94d6bef941bbc1132d9959dc73bd4b6f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 25 Feb 2026 10:47:18 +0000
Subject: [PATCH 0370/1303] KVM: arm64: Deduplicate ASID retrieval code

We currently have three versions of the ASID retrieval code, one
in the S1 walker, and two in the VNCR handling (although the last
two are limited to the EL2&0 translation regime).

Make this code common, and take this opportunity to also simplify
the code a bit while switching over to the TTBRx_EL1_ASID macro.

Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260225104718.14209-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  2 +
 arch/arm64/kvm/at.c                 | 27 +------------
 arch/arm64/kvm/nested.c             | 60 +++++++++++++++--------------
 3 files changed, 35 insertions(+), 54 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 905c658057a4..091544e6af44 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -397,6 +397,8 @@ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu);
 int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu);
 void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val);
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime);
+
 #define vncr_fixmap(c)						\
 	({							\
 		u32 __c = (c);					\
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 885bd5bb2f41..6588ea251ed7 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -540,31 +540,8 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
 	wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0);
 
 	wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG);
-	if (wr->nG) {
-		u64 asid_ttbr, tcr;
-
-		switch (wi->regime) {
-		case TR_EL10:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL1) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL1));
-			break;
-		case TR_EL20:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-			break;
-		default:
-			BUG();
-		}
-
-		wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			wr->asid &= GENMASK(7, 0);
-	}
+	if (wr->nG)
+		wr->asid = get_asid_by_regime(vcpu, wi->regime);
 
 	return 0;
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7f1ea85dc67a..787776aaf4ad 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -854,6 +854,33 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
 	return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime)
+{
+	enum vcpu_sysreg ttbr_elx;
+	u64 tcr;
+	u16 asid;
+
+	switch (regime) {
+	case TR_EL10:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1;
+		break;
+	case TR_EL20:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2;
+		break;
+	default:
+		BUG();
+	}
+
+	asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx));
+	if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+	    !(tcr & TCR_ASID16))
+		asid &= GENMASK(7, 0);
+
+	return asid;
+}
+
 static void invalidate_vncr(struct vncr_tlb *vt)
 {
 	vt->valid = false;
@@ -1333,20 +1360,8 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return false;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		return asid == vt->wr.asid;
-	}
+	if (vt->wr.nG)
+		return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid;
 
 	return true;
 }
@@ -1449,21 +1464,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		if (asid != vt->wr.asid)
-			return;
-	}
+	if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid)
+		return;
 
 	vt->cpu = smp_processor_id();
 

From 93a4a9b732fbb479f95d327aa867d094aed3f712 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Tue, 24 Feb 2026 17:59:52 +0100
Subject: [PATCH 0371/1303] RDMA/core: Check id_priv->restricted_node_type in
 cma_listen_on_dev()

When listening on wildcard addresses we have a global list for the application
layer rdma_cm_id and for any existing device or any device added in future we
try to listen on any wildcard listener.

When the listener has a restricted_node_type we should prevent listening on
devices with a different node type.

While there fix the documentation comment of rdma_restrict_node_type()
to include rdma_resolve_addr() instead of having rdma_bind_addr() twice.

Fixes: a760e80e90f5 ("RDMA/core: introduce rdma_restrict_node_type()")
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Steve French <smfrench@gmail.com>
Cc: Namjae Jeon <linkinjeon@kernel.org>
Cc: Tom Talpey <tom@talpey.com>
Cc: Long Li <longli@microsoft.com>
Cc: linux-rdma@vger.kernel.org
Cc: linux-cifs@vger.kernel.org
Cc: samba-technical@lists.samba.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Link: https://patch.msgid.link/20260224165951.3582093-2-metze@samba.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/cma.c | 6 +++++-
 include/rdma/rdma_cm.h        | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e54c07c74575..9480d1a51c11 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2729,6 +2729,9 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
 	*to_destroy = NULL;
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return 0;
+	if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED &&
+	    id_priv->restricted_node_type != cma_dev->device->node_type)
+		return 0;
 
 	dev_id_priv =
 		__rdma_create_id(net, cma_listen_handler, id_priv,
@@ -2736,6 +2739,7 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
 	if (IS_ERR(dev_id_priv))
 		return PTR_ERR(dev_id_priv);
 
+	dev_id_priv->restricted_node_type = id_priv->restricted_node_type;
 	dev_id_priv->state = RDMA_CM_ADDR_BOUND;
 	memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv),
 	       rdma_addr_size(cma_src_addr(id_priv)));
@@ -4194,7 +4198,7 @@ int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type)
 	}
 
 	mutex_lock(&lock);
-	if (id_priv->cma_dev)
+	if (READ_ONCE(id_priv->state) != RDMA_CM_IDLE)
 		ret = -EALREADY;
 	else
 		id_priv->restricted_node_type = node_type;
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 6de6fd8bd15e..d639ff889e64 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -181,7 +181,7 @@ void rdma_destroy_id(struct rdma_cm_id *id);
  *
  * It needs to be called before the RDMA identifier is bound
  * to an device, which mean it should be called before
- * rdma_bind_addr(), rdma_bind_addr() and rdma_listen().
+ * rdma_bind_addr(), rdma_resolve_addr() and rdma_listen().
  */
 int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type);
 

From 104016eb671e19709721c1b0048dd912dc2e96be Mon Sep 17 00:00:00 2001
From: Jacob Moroni <jmoroni@google.com>
Date: Tue, 24 Feb 2026 23:41:53 +0000
Subject: [PATCH 0372/1303] RDMA/umem: Fix double dma_buf_unpin in failure path

In ib_umem_dmabuf_get_pinned_with_dma_device(), the call to
ib_umem_dmabuf_map_pages() can fail. If this occurs, the dmabuf
is immediately unpinned but the umem_dmabuf->pinned flag is still
set. Then, when ib_umem_release() is called, it calls
ib_umem_dmabuf_revoke() which will call dma_buf_unpin() again.

Fix this by removing the immediate unpin upon failure and just let
the ib_umem_release/revoke path handle it. This also ensures the
proper unmap-unpin unwind ordering if the dmabuf_map_pages call
happened to fail due to dma_resv_wait_timeout (and therefore has
a non-NULL umem_dmabuf->sgt).

Fixes: 1e4df4a21c5a ("RDMA/umem: Allow pinned dmabuf umem usage")
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Link: https://patch.msgid.link/20260224234153.1207849-1-jmoroni@google.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/umem_dmabuf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
index f5298c33e581..d30f24b90bca 100644
--- a/drivers/infiniband/core/umem_dmabuf.c
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -218,13 +218,11 @@ ib_umem_dmabuf_get_pinned_with_dma_device(struct ib_device *device,
 
 	err = ib_umem_dmabuf_map_pages(umem_dmabuf);
 	if (err)
-		goto err_unpin;
+		goto err_release;
 	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
 
 	return umem_dmabuf;
 
-err_unpin:
-	dma_buf_unpin(umem_dmabuf->attach);
 err_release:
 	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
 	ib_umem_release(&umem_dmabuf->umem);

From 18c16f602a67782f5eb4b5ab9ba73350b9f711ec Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 4 Feb 2026 20:36:26 +0530
Subject: [PATCH 0373/1303] xfs: Replace ASSERT with XFS_IS_CORRUPT in
 xfs_rtcopy_summary()

Replace ASSERT(sum > 0) with an XFS_IS_CORRUPT() and place it just
after the call to xfs_rtget_summary() so that we don't end up using
an illegal value of sum.

Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 90a94a5b6f7e..aab59f66384e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -112,6 +112,10 @@ xfs_rtcopy_summary(
 			error = xfs_rtget_summary(oargs, log, bbno, &sum);
 			if (error)
 				goto out;
+			if (XFS_IS_CORRUPT(oargs->mp, sum < 0)) {
+				error = -EFSCORRUPTED;
+				goto out;
+			}
 			if (sum == 0)
 				continue;
 			error = xfs_rtmodify_summary(oargs, log, bbno, -sum);
@@ -120,7 +124,6 @@ xfs_rtcopy_summary(
 			error = xfs_rtmodify_summary(nargs, log, bbno, sum);
 			if (error)
 				goto out;
-			ASSERT(sum > 0);
 		}
 	}
 	error = 0;

From a49b7ff63f98ba1c4503869c568c99ecffa478f2 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 11 Feb 2026 19:25:13 +0530
Subject: [PATCH 0374/1303] xfs: Refactoring the nagcount and delta calculation

Introduce xfs_growfs_compute_delta() to calculate the nagcount
and delta blocks and refactor the code from xfs_growfs_data_private().
No functional changes.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c | 28 ++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_ag.h |  3 +++
 fs/xfs/xfs_fsops.c     | 17 ++---------------
 3 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9c6765cc2d44..bd8fbb40b49e 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -872,6 +872,34 @@ xfs_ag_shrink_space(
 	return err2;
 }
 
+void
+xfs_growfs_compute_deltas(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		nb,
+	int64_t			*deltap,
+	xfs_agnumber_t		*nagcountp)
+{
+	xfs_rfsblock_t	nb_div, nb_mod;
+	int64_t		delta;
+	xfs_agnumber_t	nagcount;
+
+	nb_div = nb;
+	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
+	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
+		nb_div++;
+	else if (nb_mod)
+		nb = nb_div * mp->m_sb.sb_agblocks;
+
+	if (nb_div > XFS_MAX_AGNUMBER + 1) {
+		nb_div = XFS_MAX_AGNUMBER + 1;
+		nb = nb_div * mp->m_sb.sb_agblocks;
+	}
+	nagcount = nb_div;
+	delta = nb - mp->m_sb.sb_dblocks;
+	*deltap = delta;
+	*nagcountp = nagcount;
+}
+
 /*
  * Extent the AG indicated by the @id by the length passed in
  */
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 1f24cfa27321..3cd4790768ff 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -331,6 +331,9 @@ struct aghdr_init_data {
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
 int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp,
 			xfs_extlen_t delta);
+void
+xfs_growfs_compute_deltas(struct xfs_mount *mp, xfs_rfsblock_t nb,
+			int64_t *deltap, xfs_agnumber_t *nagcountp);
 int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp,
 			xfs_extlen_t len);
 int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 17255c41786b..8d64d904d73c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -95,18 +95,17 @@ xfs_growfs_data_private(
 	struct xfs_growfs_data	*in)		/* growfs data input struct */
 {
 	xfs_agnumber_t		oagcount = mp->m_sb.sb_agcount;
+	xfs_rfsblock_t		nb = in->newblocks;
 	struct xfs_buf		*bp;
 	int			error;
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
-	xfs_rfsblock_t		nb, nb_div, nb_mod;
 	int64_t			delta;
 	bool			lastag_extended = false;
 	struct xfs_trans	*tp;
 	struct aghdr_init_data	id = {};
 	struct xfs_perag	*last_pag;
 
-	nb = in->newblocks;
 	error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
 	if (error)
 		return error;
@@ -125,20 +124,8 @@ xfs_growfs_data_private(
 			mp->m_sb.sb_rextsize);
 	if (error)
 		return error;
+	xfs_growfs_compute_deltas(mp, nb, &delta, &nagcount);
 
-	nb_div = nb;
-	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
-	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
-		nb_div++;
-	else if (nb_mod)
-		nb = nb_div * mp->m_sb.sb_agblocks;
-
-	if (nb_div > XFS_MAX_AGNUMBER + 1) {
-		nb_div = XFS_MAX_AGNUMBER + 1;
-		nb = nb_div * mp->m_sb.sb_agblocks;
-	}
-	nagcount = nb_div;
-	delta = nb - mp->m_sb.sb_dblocks;
 	/*
 	 * Reject filesystems with a single AG because they are not
 	 * supported, and reject a shrink operation that would cause a

From 4ad85e633bc576a5cc8c8310aab141af7ed20efa Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 11 Feb 2026 19:25:14 +0530
Subject: [PATCH 0375/1303] xfs: Replace &rtg->rtg_group with rtg_group()

Use the already existing rtg_group() wrapper instead of directly
accessing the struct xfs_group member in struct xfs_rtgroup.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
[cem: Conflict resolution against 06873dbd940d]
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_alloc.c |  6 +++---
 fs/xfs/xfs_zone_gc.c    | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 67e0c8f5800f..e3d19b6dc64a 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -78,7 +78,7 @@ xfs_zone_account_reclaimable(
 	struct xfs_rtgroup	*rtg,
 	uint32_t		freed)
 {
-	struct xfs_group	*xg = &rtg->rtg_group;
+	struct xfs_group	*xg = rtg_group(rtg);
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_zone_info	*zi = mp->m_zone_info;
 	uint32_t		used = rtg_rmap(rtg)->i_used_blocks;
@@ -759,7 +759,7 @@ xfs_zone_alloc_blocks(
 
 	trace_xfs_zone_alloc_blocks(oz, allocated, count_fsb);
 
-	*sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	*sector = xfs_gbno_to_daddr(rtg_group(rtg), 0);
 	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector);
 	if (!*is_seq)
 		*sector += XFS_FSB_TO_BB(mp, allocated);
@@ -1080,7 +1080,7 @@ xfs_init_zone(
 	if (write_pointer == 0) {
 		/* zone is empty */
 		atomic_inc(&zi->zi_nr_free_zones);
-		xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+		xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE);
 		iz->available += rtg_blocks(rtg);
 	} else if (write_pointer < rtg_blocks(rtg)) {
 		/* zone is open */
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 48c6cf584447..7efeecd2d85f 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -627,7 +627,7 @@ xfs_zone_gc_alloc_blocks(
 	if (!*count_fsb)
 		return NULL;
 
-	*daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0);
+	*daddr = xfs_gbno_to_daddr(rtg_group(oz->oz_rtg), 0);
 	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr);
 	if (!*is_seq)
 		*daddr += XFS_FSB_TO_BB(mp, oz->oz_allocated);
@@ -702,7 +702,7 @@ xfs_zone_gc_start_chunk(
 	chunk->data = data;
 	chunk->oz = oz;
 	chunk->victim_rtg = iter->victim_rtg;
-	atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+	atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref);
 	atomic_inc(&chunk->victim_rtg->rtg_gccount);
 
 	bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock);
@@ -788,7 +788,7 @@ xfs_zone_gc_split_write(
 	atomic_inc(&chunk->oz->oz_ref);
 
 	split_chunk->victim_rtg = chunk->victim_rtg;
-	atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+	atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref);
 	atomic_inc(&chunk->victim_rtg->rtg_gccount);
 
 	chunk->offset += split_len;
@@ -888,7 +888,7 @@ xfs_zone_gc_finish_reset(
 		goto out;
 	}
 
-	xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+	xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE);
 	atomic_inc(&zi->zi_nr_free_zones);
 
 	xfs_zoned_add_available(mp, rtg_blocks(rtg));
@@ -917,7 +917,7 @@ xfs_submit_zone_reset_bio(
 
 	XFS_STATS_INC(mp, xs_gc_zone_reset_calls);
 
-	bio->bi_iter.bi_sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	bio->bi_iter.bi_sector = xfs_gbno_to_daddr(rtg_group(rtg), 0);
 	if (!bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) {
 		/*
 		 * Also use the bio to drive the state machine when neither

From fd81d3fd01a5ee4bd26a7dc440e7a2209277d14b Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Fri, 13 Feb 2026 08:50:06 +1000
Subject: [PATCH 0376/1303] xfs: fix code alignment issues in xfs_ondisk.c

Fixup some code alignment issues in xfs_ondisk.c

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 2e9715cc1641..70605019383c 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -73,7 +73,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry,	8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr,		32);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local,	4);
@@ -116,7 +116,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,	4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
 	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag,	0);
 	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length,	2);

From 03a6d6c4c85d2758534638fb2bb5f72e0f8877d0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2026 15:14:31 +0100
Subject: [PATCH 0377/1303] xfs: cleanup inode counter stats

Most of them are unused, so mark them as such.  Give the remaining ones
names that match their use instead of the historic IRIX ones based on
vnodes.  Note that the names are purely internal to the XFS code, the
user interface is based on section names and arrays of counters.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_icache.c |  6 +++---
 fs/xfs/xfs_stats.c  | 10 +++++-----
 fs/xfs/xfs_stats.h  | 16 ++++++++--------
 fs/xfs/xfs_super.c  |  4 ++--
 4 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index dbaab4ae709f..f76c6decdaa3 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -106,7 +106,7 @@ xfs_inode_alloc(
 	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
 				    M_IGEO(mp)->min_folio_order);
 
-	XFS_STATS_INC(mp, vn_active);
+	XFS_STATS_INC(mp, xs_inodes_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(ip->i_ino == 0);
 
@@ -172,7 +172,7 @@ __xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
-	XFS_STATS_DEC(ip->i_mount, vn_active);
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
@@ -2234,7 +2234,7 @@ xfs_inode_mark_reclaimable(
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			need_inactive;
 
-	XFS_STATS_INC(mp, vn_reclaim);
+	XFS_STATS_INC(mp, xs_inode_mark_reclaimable);
 
 	/*
 	 * We should never get here with any of the reclaim flags already set.
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index 017db0361cd8..bc4a5d6dc795 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -42,7 +42,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		{ "xstrat",		xfsstats_offset(xs_write_calls)	},
 		{ "rw",			xfsstats_offset(xs_attr_get)	},
 		{ "attr",		xfsstats_offset(xs_iflush_count)},
-		{ "icluster",		xfsstats_offset(vn_active)	},
+		{ "icluster",		xfsstats_offset(xs_inodes_active) },
 		{ "vnodes",		xfsstats_offset(xb_get)		},
 		{ "buf",		xfsstats_offset(xs_abtb_2)	},
 		{ "abtb2",		xfsstats_offset(xs_abtc_2)	},
@@ -100,15 +100,15 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
 	int		c;
-	uint32_t	vn_active;
+	uint32_t	xs_inodes_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
 		preempt_disable();
-		/* save vn_active, it's a universal truth! */
-		vn_active = per_cpu_ptr(stats, c)->s.vn_active;
+		/* save xs_inodes_active, it's a universal truth! */
+		xs_inodes_active = per_cpu_ptr(stats, c)->s.xs_inodes_active;
 		memset(per_cpu_ptr(stats, c), 0, sizeof(*stats));
-		per_cpu_ptr(stats, c)->s.vn_active = vn_active;
+		per_cpu_ptr(stats, c)->s.xs_inodes_active = xs_inodes_active;
 		preempt_enable();
 	}
 }
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 153d2381d0a8..64bc0cc18126 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -100,14 +100,14 @@ struct __xfsstats {
 	uint32_t		xs_iflush_count;
 	uint32_t		xs_icluster_flushcnt;
 	uint32_t		xs_icluster_flushinode;
-	uint32_t		vn_active;	/* # vnodes not on free lists */
-	uint32_t		vn_alloc;	/* # times vn_alloc called */
-	uint32_t		vn_get;		/* # times vn_get called */
-	uint32_t		vn_hold;	/* # times vn_hold called */
-	uint32_t		vn_rele;	/* # times vn_rele called */
-	uint32_t		vn_reclaim;	/* # times vn_reclaim called */
-	uint32_t		vn_remove;	/* # times vn_remove called */
-	uint32_t		vn_free;	/* # times vn_free called */
+	uint32_t		xs_inodes_active;
+	uint32_t		__unused_vn_alloc;
+	uint32_t		__unused_vn_get;
+	uint32_t		__unused_vn_hold;
+	uint32_t		xs_inode_destroy;
+	uint32_t		xs_inode_destroy2; /* same as xs_inode_destroy */
+	uint32_t		xs_inode_mark_reclaimable;
+	uint32_t		__unused_vn_free;
 	uint32_t		xb_get;
 	uint32_t		xb_create;
 	uint32_t		xb_get_locked;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index abc45f860a73..f8de44443e81 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -712,8 +712,8 @@ xfs_fs_destroy_inode(
 	trace_xfs_destroy_inode(ip);
 
 	ASSERT(!rwsem_is_locked(&inode->i_rwsem));
-	XFS_STATS_INC(ip->i_mount, vn_rele);
-	XFS_STATS_INC(ip->i_mount, vn_remove);
+	XFS_STATS_INC(ip->i_mount, xs_inode_destroy);
+	XFS_STATS_INC(ip->i_mount, xs_inode_destroy2);
 	xfs_inode_mark_reclaimable(ip);
 }
 

From 47553dd60b1da88df2354f841a4f71dd4de6478a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2026 15:14:32 +0100
Subject: [PATCH 0378/1303] xfs: remove metafile inodes from the active inode
 stat

The active inode (or active vnode until recently) stat can get much larger
than expected on file systems with a lot of metafile inodes like zoned
file systems on SMR hard disks with 10.000s of rtg rmap inodes.

Remove all metafile inodes from the active counter to make it more useful
to track actual workloads and add a separate counter for active metafile
inodes.

This fixes xfs/177 on SMR hard drives.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c |  4 ++++
 fs/xfs/libxfs/xfs_metafile.c  |  5 +++++
 fs/xfs/xfs_icache.c           |  5 ++++-
 fs/xfs/xfs_stats.c            | 11 ++++++++---
 fs/xfs/xfs_stats.h            |  3 ++-
 5 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index a017016e9075..3794e5412eba 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -268,6 +268,10 @@ xfs_inode_from_disk(
 	}
 	if (xfs_is_reflink_inode(ip))
 		xfs_ifork_init_cow(ip);
+	if (xfs_is_metadir_inode(ip)) {
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+		XFS_STATS_INC(ip->i_mount, xs_inodes_meta);
+	}
 	return 0;
 
 out_destroy_data_fork:
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
index cf239f862212..71f004e9dc64 100644
--- a/fs/xfs/libxfs/xfs_metafile.c
+++ b/fs/xfs/libxfs/xfs_metafile.c
@@ -61,6 +61,9 @@ xfs_metafile_set_iflag(
 	ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
 	ip->i_metatype = metafile_type;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+	XFS_STATS_INC(ip->i_mount, xs_inodes_meta);
 }
 
 /* Clear the metadata directory inode flag. */
@@ -74,6 +77,8 @@ xfs_metafile_clear_iflag(
 
 	ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	XFS_STATS_INC(ip->i_mount, xs_inodes_active);
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_meta);
 }
 
 /*
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f76c6decdaa3..f2d4294efd37 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -172,7 +172,10 @@ __xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
-	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+	if (xfs_is_metadir_inode(ip))
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_meta);
+	else
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index bc4a5d6dc795..c13d600732c9 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -59,7 +59,8 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		{ "rtrefcntbt",		xfsstats_offset(xs_qm_dqreclaims)},
 		/* we print both series of quota information together */
 		{ "qm",			xfsstats_offset(xs_gc_read_calls)},
-		{ "zoned",		xfsstats_offset(__pad1)},
+		{ "zoned",		xfsstats_offset(xs_inodes_meta)},
+		{ "metafile",		xfsstats_offset(xs_xstrat_bytes)},
 	};
 
 	/* Loop over all stats groups */
@@ -99,16 +100,20 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
+	uint32_t	xs_inodes_active, xs_inodes_meta;
 	int		c;
-	uint32_t	xs_inodes_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
 		preempt_disable();
-		/* save xs_inodes_active, it's a universal truth! */
+		/*
+		 * Save the active / meta inode counters, as they are stateful.
+		 */
 		xs_inodes_active = per_cpu_ptr(stats, c)->s.xs_inodes_active;
+		xs_inodes_meta = per_cpu_ptr(stats, c)->s.xs_inodes_meta;
 		memset(per_cpu_ptr(stats, c), 0, sizeof(*stats));
 		per_cpu_ptr(stats, c)->s.xs_inodes_active = xs_inodes_active;
+		per_cpu_ptr(stats, c)->s.xs_inodes_meta = xs_inodes_meta;
 		preempt_enable();
 	}
 }
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 64bc0cc18126..57c32b86c358 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -142,7 +142,8 @@ struct __xfsstats {
 	uint32_t		xs_gc_read_calls;
 	uint32_t		xs_gc_write_calls;
 	uint32_t		xs_gc_zone_reset_calls;
-	uint32_t		__pad1;
+/* Metafile counters */
+	uint32_t		xs_inodes_meta;
 /* Extra precision counters */
 	uint64_t		xs_xstrat_bytes;
 	uint64_t		xs_write_bytes;

From cddfa648f1ab99e30e91455be19cd5ade26338c2 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Thu, 19 Feb 2026 21:38:25 -0600
Subject: [PATCH 0379/1303] xfs: Fix error pointer dereference

The function try_lookup_noperm() can return an error pointer and is not
checked for one.

Add checks for error pointer in xrep_adoption_check_dcache() and
xrep_adoption_zap_dcache().

Detected by Smatch:
fs/xfs/scrub/orphanage.c:449 xrep_adoption_check_dcache() error:
'd_child' dereferencing possible ERR_PTR()

fs/xfs/scrub/orphanage.c:485 xrep_adoption_zap_dcache() error:
'd_child' dereferencing possible ERR_PTR()

Fixes: 73597e3e42b4 ("xfs: ensure dentry consistency when the orphanage adopts a file")
Cc: stable@vger.kernel.org # v6.16
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/orphanage.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 52a108f6d5f4..33c6db6b4498 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c
@@ -442,6 +442,11 @@ xrep_adoption_check_dcache(
 		return 0;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
+	if (IS_ERR(d_child)) {
+		dput(d_orphanage);
+		return PTR_ERR(d_child);
+	}
+
 	if (d_child) {
 		trace_xrep_adoption_check_child(sc->mp, d_child);
 
@@ -479,7 +484,7 @@ xrep_adoption_zap_dcache(
 		return;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
-	while (d_child != NULL) {
+	while (!IS_ERR_OR_NULL(d_child)) {
 		trace_xrep_adoption_invalidate_child(sc->mp, d_child);
 
 		ASSERT(d_is_negative(d_child));

From e764dd439d68cfc16724e469db390d779ab49521 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:35 -0800
Subject: [PATCH 0380/1303] xfs: fix copy-paste error in previous fix

Chris Mason noticed that there is a copy-paste error in a recent change
to xrep_dir_teardown that nulls out pointers after freeing the
resources.

Fixes: ba408d299a3bb3c ("xfs: only call xf{array,blob}_destroy if we have a valid pointer")
Link: https://lore.kernel.org/linux-xfs/20260205194211.2307232-1-clm@meta.com/
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/dir_repair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 9dc55c918c78..23b80c54aa60 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -177,7 +177,7 @@ xrep_dir_teardown(
 	rd->dir_names = NULL;
 	if (rd->dir_entries)
 		xfarray_destroy(rd->dir_entries);
-	rd->dir_names = NULL;
+	rd->dir_entries = NULL;
 }
 
 /* Set up for a directory repair. */

From 161456987a1fe4ad73c3f36dec1f684316ac9bdd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:35 -0800
Subject: [PATCH 0381/1303] xfs: fix xfs_group release bug in
 xfs_verify_report_losses

Chris Mason reports that his AI tools noticed that we were using
xfs_perag_put and xfs_group_put to release the group reference returned
by xfs_group_next_range.  However, the iterator function returns an
object with an active refcount, which means that we must use the correct
function to release the active refcount, which is _rele.

Fixes: b8accfd65d31f2 ("xfs: add media verification ioctl")
Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-xfs/20260206030527.2506821-1-clm@meta.com/
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_verify_media.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c
index 069cd371619d..8bbd4ec567f8 100644
--- a/fs/xfs/xfs_verify_media.c
+++ b/fs/xfs/xfs_verify_media.c
@@ -122,7 +122,7 @@ xfs_verify_report_losses(
 
 			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
 			if (error) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 
@@ -158,7 +158,7 @@ xfs_verify_report_losses(
 		if (rtg)
 			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 		if (error) {
-			xfs_group_put(xg);
+			xfs_group_rele(xg);
 			break;
 		}
 	}

From eb8550fb75a875657dc29e3925a40244ec6b6bd6 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:36 -0800
Subject: [PATCH 0382/1303] xfs: fix xfs_group release bug in
 xfs_dax_notify_dev_failure

Chris Mason reports that his AI tools noticed that we were using
xfs_perag_put and xfs_group_put to release the group reference returned
by xfs_group_next_range.  However, the iterator function returns an
object with an active refcount, which means that we must use the correct
function to release the active refcount, which is _rele.

Cc: <stable@vger.kernel.org> # v6.0
Fixes: 6f643c57d57c56 ("xfs: implement ->notify_failure() for XFS")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_notify_failure.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 6be19fa1ebe2..64c8afb935c2 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -304,7 +304,7 @@ xfs_dax_notify_dev_failure(
 
 			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
 			if (error) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 
@@ -340,7 +340,7 @@ xfs_dax_notify_dev_failure(
 		if (rtg)
 			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 		if (error) {
-			xfs_group_put(xg);
+			xfs_group_rele(xg);
 			break;
 		}
 	}

From 94014a23e91a3944947048169ccf38b4561cfd0c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:37 -0800
Subject: [PATCH 0383/1303] xfs: fix potential pointer access race in
 xfs_healthmon_get

Pankaj Raghav asks about this code in xfs_healthmon_get:

  hm = mp->m_healthmon;
  if (hm && !refcount_inc_not_zero(&hm->ref))
    hm = NULL;
  rcu_read_unlock();
  return hm;

(slightly edited to compress a mailing list thread)

"Nit: Should we do a READ_ONCE(mp->m_healthmon) here to avoid any
compiler tricks that can result in an undefined behaviour? I am not sure
if I am being paranoid here.

"So this is my understanding: RCU guarantees that we get a valid object
(actual data of m_healthmon) but does not guarantee the compiler will
not reread the pointer between checking if hm is !NULL and accessing the
pointer as we are doing it lockless.

"So just a barrier() call in rcu_read_lock is enough to make sure this
doesn't happen and probably adding a READ_ONCE() is not needed?"

After some initial confusion I concluded that he's correct.  The
compiler could very well eliminate the hm variable in favor of walking
the pointers twice, turning the code into:

  if (mp->m_healthmon && !refcount_inc_not_zero(&mp->m_healthmon->ref))

If this happens, then xfs_healthmon_detach can sneak in between the
two sides of the && expression and set mp->m_healthmon to NULL, and
thereby cause a null pointer dereference crash.  Fix this by using the
rcu pointer assignment and dereference functions, which ensure that the
proper reordering barriers are in place.

Practically speaking, gcc seems to allocate an actual variable for hm
and only reads mp->m_healthmon once (as intended), but we ought to be
more explicit about requiring this.

Reported-by: Pankaj Raghav <pankaj.raghav@linux.dev>
Fixes: a48373e7d35a89f6f ("xfs: start creating infrastructure for health monitoring")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_healthmon.c | 11 +++++++----
 fs/xfs/xfs_mount.h     |  2 +-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c
index e37c18cec372..4a06d6632f65 100644
--- a/fs/xfs/xfs_healthmon.c
+++ b/fs/xfs/xfs_healthmon.c
@@ -69,7 +69,7 @@ xfs_healthmon_get(
 	struct xfs_healthmon		*hm;
 
 	rcu_read_lock();
-	hm = mp->m_healthmon;
+	hm = rcu_dereference(mp->m_healthmon);
 	if (hm && !refcount_inc_not_zero(&hm->ref))
 		hm = NULL;
 	rcu_read_unlock();
@@ -110,13 +110,13 @@ xfs_healthmon_attach(
 	struct xfs_healthmon	*hm)
 {
 	spin_lock(&xfs_healthmon_lock);
-	if (mp->m_healthmon != NULL) {
+	if (rcu_access_pointer(mp->m_healthmon) != NULL) {
 		spin_unlock(&xfs_healthmon_lock);
 		return -EEXIST;
 	}
 
 	refcount_inc(&hm->ref);
-	mp->m_healthmon = hm;
+	rcu_assign_pointer(mp->m_healthmon, hm);
 	hm->mount_cookie = (uintptr_t)mp->m_super;
 	spin_unlock(&xfs_healthmon_lock);
 
@@ -128,13 +128,16 @@ STATIC void
 xfs_healthmon_detach(
 	struct xfs_healthmon	*hm)
 {
+	struct xfs_mount	*mp;
+
 	spin_lock(&xfs_healthmon_lock);
 	if (hm->mount_cookie == DETACHED_MOUNT_COOKIE) {
 		spin_unlock(&xfs_healthmon_lock);
 		return;
 	}
 
-	XFS_M((struct super_block *)hm->mount_cookie)->m_healthmon = NULL;
+	mp = XFS_M((struct super_block *)hm->mount_cookie);
+	rcu_assign_pointer(mp->m_healthmon, NULL);
 	hm->mount_cookie = DETACHED_MOUNT_COOKIE;
 	spin_unlock(&xfs_healthmon_lock);
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 61c71128d171..ddd4028be8d6 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -345,7 +345,7 @@ typedef struct xfs_mount {
 	struct xfs_hooks	m_dir_update_hooks;
 
 	/* Private data referring to a health monitor object. */
-	struct xfs_healthmon	*m_healthmon;
+	struct xfs_healthmon __rcu	*m_healthmon;
 } xfs_mount_t;
 
 #define M_IGEO(mp)		(&(mp)->m_ino_geo)

From 75690e5fdd74fc4d2a4aec58be9a82aec7cee721 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:38 -0800
Subject: [PATCH 0384/1303] xfs: don't report metadata inodes to fserror

Internal metadata inodes are not exposed to userspace programs, so it
makes no sense to pass them to the fserror functions (aka fsnotify).
Instead, report metadata file problems as general filesystem corruption.

Fixes: 5eb4cb18e445d0 ("xfs: convey metadata health events to the health monitor")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_health.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 169123772cb3..6475159eb930 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -314,6 +314,18 @@ xfs_rgno_mark_sick(
 	xfs_rtgroup_put(rtg);
 }
 
+static inline void xfs_inode_report_fserror(struct xfs_inode *ip)
+{
+	/* Report metadata inodes as general filesystem corruption */
+	if (xfs_is_internal_inode(ip)) {
+		fserror_report_metadata(ip->i_mount->m_super, -EFSCORRUPTED,
+				GFP_NOFS);
+		return;
+	}
+
+	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+}
+
 /* Mark the unhealthy parts of an inode. */
 void
 xfs_inode_mark_sick(
@@ -339,7 +351,7 @@ xfs_inode_mark_sick(
 	inode_state_clear(VFS_I(ip), I_DONTCACHE);
 	spin_unlock(&VFS_I(ip)->i_lock);
 
-	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+	xfs_inode_report_fserror(ip);
 	if (mask)
 		xfs_healthmon_report_inode(ip, XFS_HEALTHMON_SICK, old_mask,
 				mask);
@@ -371,7 +383,7 @@ xfs_inode_mark_corrupt(
 	inode_state_clear(VFS_I(ip), I_DONTCACHE);
 	spin_unlock(&VFS_I(ip)->i_lock);
 
-	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+	xfs_inode_report_fserror(ip);
 	if (mask)
 		xfs_healthmon_report_inode(ip, XFS_HEALTHMON_CORRUPT, old_mask,
 				mask);

From 115ea07b94d2f13942fbd93c6acde376db36b16a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:38 -0800
Subject: [PATCH 0385/1303] xfs: don't report half-built inodes to fserror

Sam Sun apparently found a syzbot way to fuzz a filesystem such that
xfs_iget_cache_miss would free the inode before the fserror code could
catch up.  Frustratingly he doesn't use the syzbot dashboard so there's
no C reproducer and not even a full error report, so I'm guessing that:

Inodes that are being constructed or torn down inside XFS are not
visible to the VFS.  They should never be reported to fserror.
Also, any inode that has been freshly allocated in _cache_miss should be
marked INEW immediately because, well, it's an incompletely constructed
inode that isn't yet visible to the VFS.

Reported-by: Sam Sun <samsun1006219@gmail.com>
Fixes: 5eb4cb18e445d0 ("xfs: convey metadata health events to the health monitor")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_health.c | 8 ++++++--
 fs/xfs/xfs_icache.c | 9 ++++++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 6475159eb930..239b843e83d4 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -316,8 +316,12 @@ xfs_rgno_mark_sick(
 
 static inline void xfs_inode_report_fserror(struct xfs_inode *ip)
 {
-	/* Report metadata inodes as general filesystem corruption */
-	if (xfs_is_internal_inode(ip)) {
+	/*
+	 * Do not report inodes being constructed or freed, or metadata inodes,
+	 * to fsnotify.
+	 */
+	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIM) ||
+	    xfs_is_internal_inode(ip)) {
 		fserror_report_metadata(ip->i_mount->m_super, -EFSCORRUPTED,
 				GFP_NOFS);
 		return;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f2d4294efd37..a7a09e7eec81 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -639,6 +639,14 @@ xfs_iget_cache_miss(
 	if (!ip)
 		return -ENOMEM;
 
+	/*
+	 * Set XFS_INEW as early as possible so that the health code won't pass
+	 * the inode to the fserror code if the ondisk inode cannot be loaded.
+	 * We're going to free the xfs_inode immediately if that happens, which
+	 * would lead to UAF problems.
+	 */
+	xfs_iflags_set(ip, XFS_INEW);
+
 	error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags);
 	if (error)
 		goto out_destroy;
@@ -716,7 +724,6 @@ xfs_iget_cache_miss(
 	ip->i_udquot = NULL;
 	ip->i_gdquot = NULL;
 	ip->i_pdquot = NULL;
-	xfs_iflags_set(ip, XFS_INEW);
 
 	/* insert the new inode */
 	spin_lock(&pag->pag_ici_lock);

From 8baa9bccc0156d6952d337bf17f57ce15902dfe4 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:23:58 +0530
Subject: [PATCH 0386/1303] xfs: Fix xfs_last_rt_bmblock()

Bug description:

If the size of the last rtgroup i.e, the rtg passed to
xfs_last_rt_bmblock() is such that the last rtextent falls in 0th word
offset of a bmblock of the bitmap file tracking this (last) rtgroup,
then in that case xfs_last_rt_bmblock() incorrectly returns the next
bmblock number instead of the current/last used bmblock number.
When xfs_last_rt_bmblock() incorrectly returns the next bmblock,
the loop to grow/modify the bmblocks in xfs_growfs_rtg() doesn't
execute and xfs_growfs basically does a nop in certain cases.

xfs_growfs will do a nop when the new size of the fs will have the same
number of rtgroups i.e, we are only growing the last rtgroup.

Reproduce:
$ mkfs.xfs -m metadir=0 -r rtdev=/dev/loop1 /dev/loop0 \
	-r size=32769b -f
$ mount -o rtdev=/dev/loop1 /dev/loop0 /mnt/scratch
$ xfs_growfs -R $(( 32769 + 1 )) /mnt/scratch
$ xfs_info /mnt/scratch | grep rtextents
$ # We can see that rtextents hasn't changed

Fix:
Fix this by returning the current/last used bmblock when the last
rtgroup size is not a multiple xfs_rtbitmap_rtx_per_rbmblock()
and the next bmblock when the rtgroup size is a multiple of
xfs_rtbitmap_rtx_per_rbmblock() i.e, the existing blocks are
completely used up.
Also, I have renamed xfs_last_rt_bmblock() to
xfs_last_rt_bmblock_to_extend() to signify that this function
returns the bmblock number to extend and NOT always the last used
bmblock number.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index aab59f66384e..ae53ba2093b2 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1082,17 +1082,27 @@ xfs_last_rtgroup_extents(
 }
 
 /*
- * Calculate the last rbmblock currently used.
+ * This will return the bitmap block number (indexed at 0) that will be
+ * extended/modified. There are 2 cases here:
+ * 1. The size of the rtg is such that it is a multiple of
+ *    xfs_rtbitmap_rtx_per_rbmblock() i.e, an integral number of bitmap blocks
+ *    are completely filled up. In this case, we should return
+ *    1 + (the last used bitmap block number).
+ * 2. The size of the rtg is not an multiple of xfs_rtbitmap_rtx_per_rbmblock().
+ *    Here we will return the block number of last used block number. In this
+ *    case, we will modify the last used bitmap block to extend the size of the
+ *    rtgroup.
  *
  * This also deals with the case where there were no rtextents before.
  */
 static xfs_fileoff_t
-xfs_last_rt_bmblock(
+xfs_last_rt_bmblock_to_extend(
 	struct xfs_rtgroup	*rtg)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	xfs_rgnumber_t		rgno = rtg_rgno(rtg);
 	xfs_fileoff_t		bmbno = 0;
+	unsigned int		mod = 0;
 
 	ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1);
 
@@ -1100,9 +1110,16 @@ xfs_last_rt_bmblock(
 		xfs_rtxnum_t	nrext = xfs_last_rtgroup_extents(mp);
 
 		/* Also fill up the previous block if not entirely full. */
-		bmbno = xfs_rtbitmap_blockcount_len(mp, nrext);
-		if (xfs_rtx_to_rbmword(mp, nrext) != 0)
-			bmbno--;
+		/* We are doing a -1 to convert it to a 0 based index */
+		bmbno = xfs_rtbitmap_blockcount_len(mp, nrext) - 1;
+		div_u64_rem(nrext, xfs_rtbitmap_rtx_per_rbmblock(mp), &mod);
+		/*
+		 * mod = 0 means that all the current blocks are full. So
+		 * return the next block number to be used for the rtgroup
+		 * growth.
+		 */
+		if (mod == 0)
+			bmbno++;
 	}
 
 	return bmbno;
@@ -1207,7 +1224,8 @@ xfs_growfs_rtg(
 			goto out_rele;
 	}
 
-	for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) {
+	for (bmbno = xfs_last_rt_bmblock_to_extend(rtg); bmbno < bmblocks;
+			bmbno++) {
 		error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno);
 		if (error)
 			goto out_error;

From ac1d977096a17d56c55bd7f90be48e81ac4cec3f Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:23:59 +0530
Subject: [PATCH 0387/1303] xfs: Add a comment in xfs_log_sb()

Add a comment explaining why the sb_frextents are updated outside the
if (xfs_has_lazycount(mp) check even though it is a lazycounter.
RT groups are supported only in v5 filesystems which always have
lazycounter enabled - so putting it inside the if(xfs_has_lazycount(mp)
check is redundant.

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_sb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 38d16fe1f6d8..47322adb7690 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1347,6 +1347,9 @@ xfs_log_sb(
 	 * feature was introduced.  This counter can go negative due to the way
 	 * we handle nearly-lockless reservations, so we must use the _positive
 	 * variant here to avoid writing out nonsense frextents.
+	 *
+	 * RT groups are only supported on v5 file systems, which always
+	 * have lazy SB counters.
 	 */
 	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) {
 		mp->m_sb.sb_frextents =

From c2368fc89a684be2900daaa2bbf68cbc147e8d3d Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:24:00 +0530
Subject: [PATCH 0388/1303] xfs: Update lazy counters in
 xfs_growfs_rt_bmblock()

Update lazy counters in xfs_growfs_rt_bmblock() similar to the way it
is done xfs_growfs_data_private(). This is because the lazy counters are
not always updated and synching the counters will avoid inconsistencies
between frexents and rtextents(total realtime extent count). This will
be more useful once realtime shrink is implemented as this will prevent
some transient state to occur where frexents might be greater than
total rtextents.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index ae53ba2093b2..153f3c378f9f 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1050,6 +1050,15 @@ xfs_growfs_rt_bmblock(
 	 */
 	xfs_trans_resv_calc(mp, &mp->m_resv);
 
+	/*
+	 * Sync sb counters now to reflect the updated values. Lazy counters are
+	 * not always updated and in order to avoid inconsistencies between
+	 * frextents and rtextents, it is better to sync the counters.
+	 */
+
+	if (xfs_has_lazysbcount(mp))
+		xfs_log_sb(args.tp);
+
 	error = xfs_trans_commit(args.tp);
 	if (error)
 		goto out_free;

From 9a654a8fa3191e9ea32c4494b943c0872a3f5d27 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:24:01 +0530
Subject: [PATCH 0389/1303] xfs: Add comments for usages of some macros.

Add comments explaining when to use XFS_IS_CORRUPT() and ASSERT()

Suggested-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_platform.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h
index 1e59bf94d1f2..59a33c60e0ca 100644
--- a/fs/xfs/xfs_platform.h
+++ b/fs/xfs/xfs_platform.h
@@ -235,6 +235,10 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
 
 #ifdef XFS_WARN
 
+/*
+ * Please note that this ASSERT doesn't kill the kernel. It will if the kernel
+ * has panic_on_warn set.
+ */
 #define ASSERT(expr)	\
 	(likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__))
 
@@ -245,6 +249,11 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
 #endif /* XFS_WARN */
 #endif /* DEBUG */
 
+/*
+ * Use this to catch metadata corruptions that are not caught by block or
+ * structure verifiers. The reason is that the verifiers check corruptions only
+ * within the scope of the object being verified.
+ */
 #define XFS_IS_CORRUPT(mp, expr)	\
 	(unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \
 					       NULL, 0, __FILE__, __LINE__, \

From e97cbf863d8918452c9f81bebdade8d04e2e7b60 Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Wed, 11 Feb 2026 13:29:02 +1000
Subject: [PATCH 0390/1303] xfs: remove duplicate static size checks

In libxfs/xfs_ondisk.h, remove some duplicate entries of
XFS_CHECK_STRUCT_SIZE().

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 70605019383c..7bccfa7b695c 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -136,16 +136,7 @@ xfs_check_ondisk_structs(void)
 	/* ondisk dir/attr structures from xfs/122 */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry,		3);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,	4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused,	6);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry,	8);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail,	4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry,		3);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr,		10);
 
 	/* log structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);

From 650b774cf94495465d6a38c31bb1a6ce697b6b37 Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Wed, 11 Feb 2026 13:29:04 +1000
Subject: [PATCH 0391/1303] xfs: add static size checks for ioctl UABI

The ioctl structures in libxfs/xfs_fs.h are missing static size checks.
It is useful to have static size checks for these structures as adding
new fields to them could cause issues (e.g. extra padding that may be
inserted by the compiler). So add these checks to xfs/xfs_ondisk.h.

Due to different padding/alignment requirements across different
architectures, to avoid build failures, some structures are ommited from
the size checks. For example, structures with "compat_" definitions in
xfs/xfs_ioctl32.h are ommited.

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 39 +++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 7bccfa7b695c..23cde1248f01 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -208,11 +208,6 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic,	0);
 	XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0);
 
-	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat,		192);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
-
 	/*
 	 * Make sure the incore inode timestamp range corresponds to hand
 	 * converted values based on the ondisk format specification.
@@ -292,6 +287,40 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_SB_OFFSET(sb_pad,			281);
 	XFS_CHECK_SB_OFFSET(sb_rtstart,			288);
 	XFS_CHECK_SB_OFFSET(sb_rtreserved,		296);
+
+	/*
+	 * ioctl UABI
+	 *
+	 * Due to different padding/alignment requirements across
+	 * different architectures, some structures are ommited from
+	 * the size checks. In addition, structures with architecture
+	 * dependent size fields are also ommited (e.g. __kernel_long_t).
+	 */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat,		192);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
+	XFS_CHECK_STRUCT_SIZE(struct dioattr,			12);
+	XFS_CHECK_STRUCT_SIZE(struct getbmap,			32);
+	XFS_CHECK_STRUCT_SIZE(struct getbmapx,			48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_cursor,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_ent,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_ag_geometry,		128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtgroup_geometry,	128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_error_injection,	8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom,		256);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom_v4,		112);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_counts,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_resblks,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_growfs_log,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulk_ireq,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fs_eofblocks,		128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsid,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_metadata,	64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec_head,	40);
 }
 
 #endif /* __XFS_ONDISK_H */

From 6b050482ec40569429d963ac52afa878691b04c9 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 24 Feb 2026 16:17:52 -0800
Subject: [PATCH 0392/1303] cpufreq: intel_pstate: Fix crash during turbo
 disable

When the system is booted with kernel command line argument "nosmt" or
"maxcpus" to limit the number of CPUs, disabling turbo via:

 echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo

results in a crash:

 PF: supervisor read access in kernel mode
 PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] SMP PTI
 ...
 RIP: 0010:store_no_turbo+0x100/0x1f0
 ...

This occurs because for_each_possible_cpu() returns CPUs even if they
are not online. For those CPUs, all_cpu_data[] will be NULL. Since
commit 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency
updates handling code"), all_cpu_data[] is dereferenced even for CPUs
which are not online, causing the NULL pointer dereference.

To fix that, pass CPU number to intel_pstate_update_max_freq() and use
all_cpu_data[] for those CPUs for which there is a valid cpufreq policy.

Fixes: 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency updates handling code")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221068
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 6.16+ <stable@vger.kernel.org> # 6.16+
Link: https://patch.msgid.link/20260225001752.890164-1-srinivas.pandruvada@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index bdc37080d319..11c58af41900 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1476,13 +1476,13 @@ static void __intel_pstate_update_max_freq(struct cpufreq_policy *policy,
 	refresh_frequency_limits(policy);
 }
 
-static bool intel_pstate_update_max_freq(struct cpudata *cpudata)
+static bool intel_pstate_update_max_freq(int cpu)
 {
-	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return false;
 
-	__intel_pstate_update_max_freq(policy, cpudata);
+	__intel_pstate_update_max_freq(policy, all_cpu_data[cpu]);
 
 	return true;
 }
@@ -1501,7 +1501,7 @@ static void intel_pstate_update_limits_for_all(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		intel_pstate_update_max_freq(all_cpu_data[cpu]);
+		intel_pstate_update_max_freq(cpu);
 
 	mutex_lock(&hybrid_capacity_lock);
 
@@ -1910,7 +1910,7 @@ static void intel_pstate_notify_work(struct work_struct *work)
 	struct cpudata *cpudata =
 		container_of(to_delayed_work(work), struct cpudata, hwp_notify_work);
 
-	if (intel_pstate_update_max_freq(cpudata)) {
+	if (intel_pstate_update_max_freq(cpudata->cpu)) {
 		/*
 		 * The driver will not be unregistered while this function is
 		 * running, so update the capacity without acquiring the driver

From c9bc1753b3cc41d0e01fbca7f035258b5f4db0ae Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 24 Feb 2026 13:29:09 +0100
Subject: [PATCH 0393/1303] perf: Fix __perf_event_overflow() vs
 perf_remove_from_context() race

Make sure that __perf_event_overflow() runs with IRQs disabled for all
possible callchains. Specifically the software events can end up running
it with only preemption disabled.

This opens up a race vs perf_event_exit_event() and friends that will go
and free various things the overflow path expects to be present, like
the BPF program.

Fixes: 592903cdcbf6 ("perf_counter: add an event_list")
Reported-by: Simond Hu <cmdhh1767@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Simond Hu <cmdhh1767@gmail.com>
Link: https://patch.msgid.link/20260224122909.GV1395416@noisy.programming.kicks-ass.net
---
 kernel/events/core.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 22a0f405585b..1f5699b339ec 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10777,6 +10777,13 @@ int perf_event_overflow(struct perf_event *event,
 			struct perf_sample_data *data,
 			struct pt_regs *regs)
 {
+	/*
+	 * Entry point from hardware PMI, interrupts should be disabled here.
+	 * This serializes us against perf_event_remove_from_context() in
+	 * things like perf_event_release_kernel().
+	 */
+	lockdep_assert_irqs_disabled();
+
 	return __perf_event_overflow(event, 1, data, regs);
 }
 
@@ -10853,6 +10860,19 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	/*
+	 * This is:
+	 *   - software		preempt
+	 *   - tracepoint	preempt
+	 *   -   tp_target_task	irq (ctx->lock)
+	 *   - uprobes		preempt/irq
+	 *   - kprobes		preempt/irq
+	 *   - hw_breakpoint	irq
+	 *
+	 * Any of these are sufficient to hold off RCU and thus ensure @event
+	 * exists.
+	 */
+	lockdep_assert_preemption_disabled();
 	local64_add(nr, &event->count);
 
 	if (!regs)
@@ -10861,6 +10881,16 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 	if (!is_sampling_event(event))
 		return;
 
+	/*
+	 * Serialize against event_function_call() IPIs like normal overflow
+	 * event handling. Specifically, must not allow
+	 * perf_event_release_kernel() -> perf_remove_from_context() to make
+	 * progress and 'release' the event from under us.
+	 */
+	guard(irqsave)();
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
 		data->period = nr;
 		return perf_swevent_overflow(event, 1, data, regs);
@@ -11359,6 +11389,11 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	struct perf_sample_data data;
 	struct perf_event *event;
 
+	/*
+	 * Per being a tracepoint, this runs with preemption disabled.
+	 */
+	lockdep_assert_preemption_disabled();
+
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = entry_size,
@@ -11691,6 +11726,11 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	struct perf_sample_data sample;
 	struct pt_regs *regs = data;
 
+	/*
+	 * Exception context, will have interrupts disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
 	perf_sample_data_init(&sample, bp->attr.bp_addr, 0);
 
 	if (!bp->hw.state && !perf_exclude_event(bp, regs))
@@ -12155,7 +12195,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && is_idle_task(current)))
-			if (__perf_event_overflow(event, 1, &data, regs))
+			if (perf_event_overflow(event, &data, regs))
 				ret = HRTIMER_NORESTART;
 	}
 

From ab6088e7a95943af3452b20e3b96caaaef3eeebd Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 24 Feb 2026 16:16:30 -0700
Subject: [PATCH 0394/1303] lib/Kconfig.debug: Require a release version of
 LLVM 22 for context analysis

Using a prerelease version as a minimum supported version for
CONFIG_WARN_CONTEXT_ANALYSIS was reasonable to do while LLVM 22 was the
development version so that people could immediately build from main and
start testing and validating this in their own code. However, it can be
problematic when using prerelease versions of LLVM 22, such as Android
clang 22.0.1 (the current android mainline compiler) or when bisecting
LLVM between llvmorg-22-init and llvmorg-23-init, to build the kernel,
as all compiler fixes for the context analysis may not be present,
potentially resulting in warnings that can easily turn into errors.

Now that LLVM 22 is released as 22.1.0, upgrade the check to require at
least this version to ensure that a user's toolchain actually has all
the changes needed for a smooth experience with context analysis.

Fixes: 3269701cb256 ("compiler-context-analysis: Add infrastructure for Context Analysis with Clang")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Marco Elver <elver@google.com>
Link: https://patch.msgid.link/20260224-bump-clang-ver-context-analysis-v1-1-16cc7a90a040@kernel.org
---
 lib/Kconfig.debug | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e2dfbbd3d78..8e2b858078e6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -630,7 +630,7 @@ config DEBUG_FORCE_WEAK_PER_CPU
 
 config WARN_CONTEXT_ANALYSIS
 	bool "Compiler context-analysis warnings"
-	depends on CC_IS_CLANG && CLANG_VERSION >= 220000
+	depends on CC_IS_CLANG && CLANG_VERSION >= 220100
 	# Branch profiling re-defines "if", which messes with the compiler's
 	# ability to analyze __cond_acquires(..), resulting in false positives.
 	depends on !TRACE_BRANCH_PROFILING
@@ -641,7 +641,7 @@ config WARN_CONTEXT_ANALYSIS
 	  and releasing user-definable "context locks".
 
 	  Clang's name of the feature is "Thread Safety Analysis". Requires
-	  Clang 22 or later.
+	  Clang 22.1.0 or later.
 
 	  Produces warnings by default. Select CONFIG_WERROR if you wish to
 	  turn these warnings into errors.

From e9fb2028f1eb563e653cff3b0d1c87c5e0203d45 Mon Sep 17 00:00:00 2001
From: Panagiotis Foliadis <pfoliadis@posteo.net>
Date: Wed, 25 Feb 2026 14:53:43 +0000
Subject: [PATCH 0395/1303] ALSA: hda/intel: increase default bdl_pos_adj for
 Nvidia controllers

The default bdl_pos_adj of 32 for Nvidia HDA controllers is
insufficient on GA102 (and likely other recent Nvidia GPUs) after S3
suspend/resume. The controller's DMA timing degrades after resume,
causing premature IRQ detection in azx_position_ok() which results in
silent HDMI/DP audio output despite userspace reporting a valid
playback state and correct ELD data.

Increase bdl_pos_adj to 64 for AZX_DRIVER_NVIDIA, matching the value
already used by Intel Apollo Lake for the same class of timing issue.

Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221069
Suggested-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Panagiotis Foliadis <pfoliadis@posteo.net>
Link: https://patch.msgid.link/20260225-nvidia-audio-fix-v1-1-b1383c37ec49@posteo.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/controllers/intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c
index 6fddf400c4a3..3f434994c18d 100644
--- a/sound/hda/controllers/intel.c
+++ b/sound/hda/controllers/intel.c
@@ -1751,6 +1751,8 @@ static int default_bdl_pos_adj(struct azx *chip)
 		return 1;
 	case AZX_DRIVER_ZHAOXINHDMI:
 		return 128;
+	case AZX_DRIVER_NVIDIA:
+		return 64;
 	default:
 		return 32;
 	}

From 85f6c439a69afe4fa8a688512e586971e97e273a Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 25 Feb 2026 10:35:57 +0000
Subject: [PATCH 0396/1303] io_uring/timeout: READ_ONCE sqe->addr

We should use READ_ONCE when reading from a SQE, make sure timeout gets
a stable timespec address.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/timeout.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 84dda24f3eb2..cb61d4862fc6 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -462,7 +462,7 @@ int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 			tr->ltimeout = true;
 		if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS))
 			return -EINVAL;
-		if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
+		if (get_timespec64(&tr->ts, u64_to_user_ptr(READ_ONCE(sqe->addr2))))
 			return -EFAULT;
 		if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0)
 			return -EINVAL;
@@ -557,7 +557,7 @@ static int __io_timeout_prep(struct io_kiocb *req,
 	data->req = req;
 	data->flags = flags;
 
-	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
+	if (get_timespec64(&data->ts, u64_to_user_ptr(READ_ONCE(sqe->addr))))
 		return -EFAULT;
 
 	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)

From 0d785e2c324c90662baa4fe07a0d02233ff92824 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:04 +0100
Subject: [PATCH 0397/1303] s390/idle: Fix cpu idle exit cpu time accounting

With the conversion to generic entry [1] cpu idle exit cpu time accounting
was converted from assembly to C. This introduced an reversed order of cpu
time accounting.

On cpu idle exit the current accounting happens with the following call
chain:

-> do_io_irq()/do_ext_irq()
 -> irq_enter_rcu()
  -> account_hardirq_enter()
   -> vtime_account_irq()
    -> vtime_account_kernel()

vtime_account_kernel() accounts the passed cpu time since last_update_timer
as system time, and updates last_update_timer to the current cpu timer
value.

However the subsequent call of

 -> account_idle_time_irq()

will incorrectly subtract passed cpu time from timer_idle_enter to the
updated last_update_timer value from system_timer. Then last_update_timer
is updated to a sys_enter_timer, which means that last_update_timer goes
back in time.

Subsequently account_hardirq_exit() will account too much cpu time as
hardirq time. The sum of all accounted cpu times is still correct, however
some cpu time which was previously accounted as system time is now
accounted as hardirq time, plus there is the oddity that last_update_timer
goes back in time.

Restore previous behavior by extracting cpu time accounting code from
account_idle_time_irq() into a new update_timer_idle() function and call it
before irq_enter_rcu().

Fixes: 56e62a737028 ("s390: convert to generic entry") [1]
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h |  1 +
 arch/s390/kernel/idle.c      | 13 +++++++++----
 arch/s390/kernel/irq.c       | 10 ++++++++--
 3 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 09f763b9eb40..133059d9a949 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -23,5 +23,6 @@ extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
 void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
+void update_timer_idle(void);
 
 #endif /* _S390_IDLE_H */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 39cb8d0ae348..0f9e53f0a068 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -21,11 +21,10 @@
 
 static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
-void account_idle_time_irq(void)
+void update_timer_idle(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	struct lowcore *lc = get_lowcore();
-	unsigned long idle_time;
 	u64 cycles_new[8];
 	int i;
 
@@ -35,13 +34,19 @@ void account_idle_time_irq(void)
 			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
-	idle_time = lc->int_clock - idle->clock_idle_enter;
-
 	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
 	lc->last_update_clock = lc->int_clock;
 
 	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
 	lc->last_update_timer = lc->sys_enter_timer;
+}
+
+void account_idle_time_irq(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	unsigned long idle_time;
+
+	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
 	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f81723bc8856..d10a17e6531d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -146,6 +146,10 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle)
+		update_timer_idle();
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -154,7 +158,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			current->thread.last_break = regs->last_break;
 	}
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -182,6 +185,10 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle)
+		update_timer_idle();
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -194,7 +201,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	regs->int_parm = get_lowcore()->ext_params;
 	regs->int_parm_long = get_lowcore()->ext_params2;
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 

From dbc0fb35679ed5d0adecf7d02137ac2c77244b3b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:05 +0100
Subject: [PATCH 0398/1303] s390/vtime: Fix virtual timer forwarding

Since delayed accounting of system time [1] the virtual timer is
forwarded by do_account_vtime() but also vtime_account_kernel(),
vtime_account_softirq(), and vtime_account_hardirq(). This leads
to double accounting of system, guest, softirq, and hardirq time.

Remove accounting from the vtime_account*() family to restore old behavior.

There is only one user of the vtimer interface, which might explain
why nobody noticed this so far.

Fixes: b7394a5f4ce9 ("sched/cputime, s390: Implement delayed accounting of system time") [1]
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 234a0ba30510..122d30b10440 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -225,10 +225,6 @@ static u64 vtime_delta(void)
 	return timer - lc->last_update_timer;
 }
 
-/*
- * Update process times based on virtual cpu times stored by entry.S
- * to the lowcore fields user_timer, system_timer & steal_clock.
- */
 void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct lowcore *lc = get_lowcore();
@@ -238,27 +234,17 @@ void vtime_account_kernel(struct task_struct *tsk)
 		lc->guest_timer += delta;
 	else
 		lc->system_timer += delta;
-
-	virt_timer_forward(delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_softirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->softirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->softirq_timer += vtime_delta();
 }
 
 void vtime_account_hardirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->hardirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->hardirq_timer += vtime_delta();
 }
 
 /*

From aefa6ec890f0d39a89fc80e95908ec1996337eee Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:06 +0100
Subject: [PATCH 0399/1303] s390/idle: Add comment for non obvious code

Add a comment to update_timer_idle() which describes why wall time (not
steal time) is added to steal_timer. This is not obvious and was reported
by Frederic Weisbecker.

Reported-by: Frederic Weisbecker <frederic@kernel.org>
Closes: https://lore.kernel.org/all/aXEVM-04lj0lntMr@localhost.localdomain/
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/idle.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 0f9e53f0a068..4e09f126d4fc 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -34,6 +34,15 @@ void update_timer_idle(void)
 			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
 	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
 	lc->last_update_clock = lc->int_clock;
 

From 00d8b035eb71262abb547d47717b19f4a55ad4f2 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:07 +0100
Subject: [PATCH 0400/1303] s390/idle: Slightly optimize idle time accounting

Slightly optimize account_idle_time_irq() and update_timer_idle():

- Use fast single instruction __atomic64() primitives to update per
  cpu idle_time and idle_count, instead of READ_ONCE() / WRITE_ONCE()
  pairs

- stcctm() is an inline assembly with a full memory barrier. This
  leads to a not necessary extra dereference of smp_cpu_mtid in
  update_timer_idle(). Avoid this and read smp_cpu_mtid into a
  variable

- Use __this_cpu_add() instead of this_cpu_add() to avoid disabling /
  enabling of preemption several times in a loop in update_timer_idle().

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/idle.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 4e09f126d4fc..627d82dd900e 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -26,12 +26,13 @@ void update_timer_idle(void)
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	struct lowcore *lc = get_lowcore();
 	u64 cycles_new[8];
-	int i;
+	int i, mtid;
 
-	if (smp_cpu_mtid) {
-		stcctm(MT_DIAG, smp_cpu_mtid, cycles_new);
-		for (i = 0; i < smp_cpu_mtid; i++)
-			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
 	/*
@@ -58,8 +59,8 @@ void account_idle_time_irq(void)
 	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
-	WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1);
+	__atomic64_add(idle_time, &idle->idle_time);
+	__atomic64_add_const(1, &idle->idle_count);
 	account_idle_time(cputime_to_nsecs(idle_time));
 }
 

From 257c14e5a1d8de40fded80fd8b525af55a6ded26 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:08 +0100
Subject: [PATCH 0401/1303] s390/idle: Inline update_timer_idle()

Inline update_timer_idle() again to avoid an extra function call. This
way the generated code is close to old assembler version again.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h  |  3 ++-
 arch/s390/include/asm/vtime.h | 34 ++++++++++++++++++++++++++++++++++
 arch/s390/kernel/entry.h      |  2 --
 arch/s390/kernel/idle.c       | 34 ++--------------------------------
 4 files changed, 38 insertions(+), 35 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 133059d9a949..8c5aa7329461 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -19,10 +19,11 @@ struct s390_idle_data {
 	unsigned long mt_cycles_enter[8];
 };
 
+DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
+
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
 void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-void update_timer_idle(void);
 
 #endif /* _S390_IDLE_H */
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index 9d25fb35a042..b1db75d14e9d 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,6 +2,12 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
+#include <asm/lowcore.h>
+#include <asm/cpu_mf.h>
+#include <asm/idle.h>
+
+DECLARE_PER_CPU(u64, mt_cycles[8]);
+
 static inline void update_timer_sys(void)
 {
 	struct lowcore *lc = get_lowcore();
@@ -20,4 +26,32 @@ static inline void update_timer_mcck(void)
 	lc->last_update_timer = lc->mcck_enter_timer;
 }
 
+static inline void update_timer_idle(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	struct lowcore *lc = get_lowcore();
+	u64 cycles_new[8];
+	int i, mtid;
+
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	}
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
+	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
+	lc->last_update_clock = lc->int_clock;
+	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
+	lc->last_update_timer = lc->sys_enter_timer;
+}
+
 #endif /* _S390_VTIME_H */
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index dd55cc6bbc28..fb67b4abe68c 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags);
 
-DECLARE_PER_CPU(u64, mt_cycles[8]);
-
 unsigned long stack_alloc(void);
 void stack_free(unsigned long stack);
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 627d82dd900e..1f1b06b6b4ef 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -15,41 +15,11 @@
 #include <trace/events/power.h>
 #include <asm/cpu_mf.h>
 #include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
-#include "entry.h"
 
-static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
-
-void update_timer_idle(void)
-{
-	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	struct lowcore *lc = get_lowcore();
-	u64 cycles_new[8];
-	int i, mtid;
-
-	mtid = smp_cpu_mtid;
-	if (mtid) {
-		stcctm(MT_DIAG, mtid, cycles_new);
-		for (i = 0; i < mtid; i++)
-			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
-	}
-
-	/*
-	 * This is a bit subtle: Forward last_update_clock so it excludes idle
-	 * time. For correct steal time calculation in do_account_vtime() add
-	 * passed wall time before idle_enter to steal_timer:
-	 * During the passed wall time before idle_enter CPU time may have
-	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
-	 * The accounted CPU times will be subtracted again from steal_timer
-	 * when accumulated steal time is calculated in do_account_vtime().
-	 */
-	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
-	lc->last_update_clock = lc->int_clock;
-
-	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
-	lc->last_update_timer = lc->sys_enter_timer;
-}
+DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
 void account_idle_time_irq(void)
 {

From d8b5cf9c63143fae54a734c41e3bb55cf3f365c7 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:09 +0100
Subject: [PATCH 0402/1303] s390/irq/idle: Remove psw bits early

Remove wait, io, external interrupt bits early in do_io_irq()/do_ext_irq()
when previous context was idle. This saves one conditional branch and is
closer to the original old assembly code.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/irq.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index d10a17e6531d..7fdf960191d3 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -147,8 +147,10 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle)
+	if (from_idle) {
 		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
 
 	irq_enter_rcu();
 
@@ -174,9 +176,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -186,8 +185,10 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle)
+	if (from_idle) {
 		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
 
 	irq_enter_rcu();
 
@@ -209,9 +210,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)

From e282ccd308de7b2a65eb4596da8030c18b543071 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:10 +0100
Subject: [PATCH 0403/1303] s390/vtime: Use __this_cpu_read() / get rid of
 READ_ONCE()

do_account_vtime() runs always with interrupts disabled, therefore use
__this_cpu_read() instead of this_cpu_read() to get rid of a pointless
preempt_disable() / preempt_enable() pair.

Also there are no concurrent writers to the cpu time accounting fields
in lowcore. Therefore get rid of READ_ONCE() usages.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 122d30b10440..4111ff4d727c 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -137,23 +137,16 @@ static int do_account_vtime(struct task_struct *tsk)
 		lc->system_timer += timer;
 
 	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+	if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
 	/* Calculate cputime delta */
-	user = update_tsk_timer(&tsk->thread.user_timer,
-				READ_ONCE(lc->user_timer));
-	guest = update_tsk_timer(&tsk->thread.guest_timer,
-				 READ_ONCE(lc->guest_timer));
-	system = update_tsk_timer(&tsk->thread.system_timer,
-				  READ_ONCE(lc->system_timer));
-	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
-				   READ_ONCE(lc->hardirq_timer));
-	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
-				   READ_ONCE(lc->softirq_timer));
-	lc->steal_timer +=
-		clock - user - guest - system - hardirq - softirq;
+	user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer);
+	guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer);
+	system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer);
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer);
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer);
+	lc->steal_timer += clock - user - guest - system - hardirq - softirq;
 
 	/* Push account value */
 	if (user) {

From 80f63fd09efe9d9c016fd6378116eb7394edd2f2 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:11 +0100
Subject: [PATCH 0404/1303] s390/vtime: Use lockdep_assert_irqs_disabled()
 instead of BUG_ON()

Use lockdep_assert_irqs_disabled() instead of BUG_ON(). This avoids
crashing the kernel, and generates better code if CONFIG_PROVE_LOCKING
is disabled.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 4111ff4d727c..bf48744d0912 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires)
 
 static inline int virt_timer_forward(u64 elapsed)
 {
-	BUG_ON(!irqs_disabled());
-
+	lockdep_assert_irqs_disabled();
 	if (list_empty(&virt_timer_list))
 		return 0;
 	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);

From acbc0437ca3cf6c19005476a4f1f5a7c96ff4256 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:12 +0100
Subject: [PATCH 0405/1303] s390/idle: Remove psw_idle() prototype

psw_idle() does not exist anymore. Remove its prototype.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 8c5aa7329461..32536ee34aa0 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -24,6 +24,4 @@ DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
-void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-
 #endif /* _S390_IDLE_H */

From 1623a554c68f352c17d0a358bc62580dc187f06b Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 23 Feb 2026 23:33:52 +0100
Subject: [PATCH 0406/1303] s390/kexec: Disable stack protector in
 s390_reset_system()

s390_reset_system() calls set_prefix(0), which switches back to the
absolute lowcore. At that point the stack protector canary no longer
matches the canary from the lowcore the function was entered with, so
the stack check fails.

Mark s390_reset_system() __no_stack_protector. This is safe here since
its callers (__do_machine_kdump() and __do_machine_kexec()) are
effectively no-return and fall back to disabled_wait() on failure.

Fixes: f5730d44e05e ("s390: Add stackprotector support")
Reported-by: Nikita Dubrovskii <nikita@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/ipl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index dcdc7e274848..049c557c452f 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2377,7 +2377,7 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void s390_reset_system(void)
+void __no_stack_protector s390_reset_system(void)
 {
 	/* Disable prefixing */
 	set_prefix(0);

From d879ac6756b662a085a743e76023c768c3241579 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Tue, 24 Feb 2026 07:41:07 +0100
Subject: [PATCH 0407/1303] s390/pfault: Fix virtual vs physical address
 confusion

When Linux is running as guest, runs a user space process and the
user space process accesses a page that the host has paged out,
the guest gets a pfault interrupt and schedules a different process.
Without this mechanism the host would have to suspend the whole
virtual CPU until the page has been paged in.

To setup the pfault interrupt the real address of parameter list
should be passed to DIAGNOSE 0x258, but a virtual address is passed
instead.

That has a performance impact, since the pfault setup never succeeds,
the interrupt is never delivered to a guest and the whole virtual CPU
is suspended as result.

Cc: stable@vger.kernel.org
Fixes: c98d2ecae08f ("s390/mm: Uncouple physical vs virtual address spaces")
Reported-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/mm/pfault.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index 2f829448c719..6ecd6b0a22a8 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -62,7 +62,7 @@ int __pfault_init(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		: [rc] "+d" (rc)
-		: [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk)
 		: "cc");
 	return rc;
 }
@@ -84,7 +84,7 @@ void __pfault_fini(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		:
-		: [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk)
 		: "cc");
 }
 

From 3ea20672d23b21327266534e08ca10d8f281f4ab Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 24 Feb 2026 13:41:20 +0100
Subject: [PATCH 0408/1303] MAINTAINERS: Update contact with the kernel.org
 address

Use the kernel.org address as a unified single entry to send patches
to. At the same time, update mailmap to group all past contributions.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 .mailmap    |  4 ++++
 MAINTAINERS | 12 ++++++------
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..463de4784ecb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -210,6 +210,10 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
 Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linaro.org>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@free.fr>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linexp.org>
+Daniel Lezcano <daniel.lezcano@kernel.org> <dlezcano@fr.ibm.com>
 Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..6c8752099924 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6280,7 +6280,7 @@ S:	Maintained
 F:	include/linux/clk.h
 
 CLOCKSOURCE, CLOCKEVENT DRIVERS
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Thomas Gleixner <tglx@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
@@ -6669,7 +6669,7 @@ F:	rust/kernel/cpu.rs
 
 CPU IDLE TIME MANAGEMENT FRAMEWORK
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 R:	Christian Loehle <christian.loehle@arm.com>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -6699,7 +6699,7 @@ F:	arch/x86/kernel/msr.c
 
 CPUIDLE DRIVER - ARM BIG LITTLE
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 L:	linux-pm@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -6707,7 +6707,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 F:	drivers/cpuidle/cpuidle-big_little.c
 
 CPUIDLE DRIVER - ARM EXYNOS
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Kukjin Kim <kgene@kernel.org>
 R:	Krzysztof Kozlowski <krzk@kernel.org>
 L:	linux-pm@vger.kernel.org
@@ -26217,7 +26217,7 @@ F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
 M:	Rafael J. Wysocki <rafael@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 R:	Zhang Rui <rui.zhang@intel.com>
 R:	Lukasz Luba <lukasz.luba@arm.com>
 L:	linux-pm@vger.kernel.org
@@ -26247,7 +26247,7 @@ F:	drivers/thermal/amlogic_thermal.c
 
 THERMAL/CPU_COOLING
 M:	Amit Daniel Kachhap <amit.kachhap@gmail.com>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 R:	Lukasz Luba <lukasz.luba@arm.com>
 L:	linux-pm@vger.kernel.org

From 085f067389d12bd9800c0a9672a174c1de7a8069 Mon Sep 17 00:00:00 2001
From: Chen Ridong <chenridong@huawei.com>
Date: Wed, 25 Feb 2026 01:15:23 +0000
Subject: [PATCH 0409/1303] cgroup/cpuset: fix null-ptr-deref in
 rebuild_sched_domains_cpuslocked

A null-pointer-dereference bug was reported by syzbot:

Oops: general protection fault, probably for address 0xdffffc0000000000:
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:bitmap_subset include/linux/bitmap.h:433 [inline]
RIP: 0010:cpumask_subset include/linux/cpumask.h:836 [inline]
RIP: 0010:rebuild_sched_domains_locked kernel/cgroup/cpuset.c:967
RSP: 0018:ffffc90003ecfbc0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000020
RDX: ffff888028de0000 RSI: ffffffff8200f003 RDI: ffffffff8df14f28
RBP: 0000000000000000 R08: 0000000000000cc0 R09: 00000000ffffffff
R10: ffffffff8e7d95b3 R11: 0000000000000001 R12: 0000000000000000
R13: 00000000000f4240 R14: dffffc0000000000 R15: 0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2f463fff CR3: 000000003704c000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 rebuild_sched_domains_cpuslocked kernel/cgroup/cpuset.c:983 [inline]
 rebuild_sched_domains+0x21/0x40 kernel/cgroup/cpuset.c:990
 sched_rt_handler+0xb5/0xe0 kernel/sched/rt.c:2911
 proc_sys_call_handler+0x47f/0x5a0 fs/proc/proc_sysctl.c:600
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6ac/0x1070 fs/read_write.c:688
 ksys_write+0x12a/0x250 fs/read_write.c:740
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The issue occurs when generate_sched_domains() returns ndoms = 1 and
doms = NULL due to a kmalloc failure. This leads to a null-pointer
dereference when accessing doms in rebuild_sched_domains_locked().

Fix this by adding a NULL check for doms before accessing it.

Fixes: 6ee43047e8ad ("cpuset: Remove unnecessary checks in rebuild_sched_domains_locked")
Reported-by: syzbot+460792609a79c085f79f@syzkaller.appspotmail.com
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index aa45351c6f38..271bb99b1b9d 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1002,7 +1002,7 @@ void rebuild_sched_domains_locked(void)
 	* offline CPUs, a warning is emitted and we return directly to
 	* prevent the panic.
 	*/
-	for (i = 0; i < ndoms; ++i) {
+	for (i = 0; doms && i < ndoms; i++) {
 		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask)))
 			return;
 	}

From 2d6d260e9a3576256fe9ef6d1f7930c9ec348723 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 9 Feb 2026 15:20:48 +0100
Subject: [PATCH 0410/1303] usb: mdc800: handle signal and read racing

If a signal arrives after a read has partially completed,
we need to return the number of bytes read. -EINTR is correct
only if that number is zero.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260209142048.1503791-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/image/mdc800.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index 8d8e79afa600..e76a502fa9da 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -707,7 +707,7 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l
 		if (signal_pending (current)) 
 		{
 			mutex_unlock(&mdc800->io_lock);
-			return -EINTR;
+			return len == left ? -EINTR : len-left;
 		}
 
 		sts=left > (mdc800->out_count-mdc800->out_ptr)?mdc800->out_count-mdc800->out_ptr:left;

From 1be3b77de4eb89af8ae2fd6610546be778e25589 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Mon, 9 Feb 2026 15:19:37 +0000
Subject: [PATCH 0411/1303] usb: image: mdc800: kill download URB on timeout

mdc800_device_read() submits download_urb and waits for completion.
If the timeout fires and the device has not responded, the function
returns without killing the URB, leaving it active.

A subsequent read() resubmits the same URB while it is still
in-flight, triggering the WARN in usb_submit_urb():

  "URB submitted while active"

Check the return value of wait_event_timeout() and kill the URB if
it indicates timeout, ensuring the URB is complete before its status
is inspected or the URB is resubmitted.

Similar to
- commit 372c93131998 ("USB: yurex: fix control-URB timeout handling")
- commit b98d5000c505 ("media: rc: iguanair: handle timeouts")

Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260209151937.2247202-1-n7l8m4@u.northwestern.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/image/mdc800.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index e76a502fa9da..ca287b770e8c 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -730,9 +730,11 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l
 					mutex_unlock(&mdc800->io_lock);
 					return len-left;
 				}
-				wait_event_timeout(mdc800->download_wait,
+				retval = wait_event_timeout(mdc800->download_wait,
 				     mdc800->downloaded,
 				     msecs_to_jiffies(TO_DOWNLOAD_GET_READY));
+				if (!retval)
+					usb_kill_urb(mdc800->download_urb);
 				mdc800->downloaded = 0;
 				if (mdc800->download_urb->status != 0)
 				{

From 712896ac4bce38a965a1c175f6e7804ed0381334 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 5 Jan 2026 06:47:28 +0000
Subject: [PATCH 0412/1303] idpf: increment completion queue next_to_clean in
 sw marker wait routine

Currently, in idpf_wait_for_sw_marker_completion(), when an
IDPF_TXD_COMPLT_SW_MARKER packet is found, the routine breaks out of
the for loop and does not increment the next_to_clean counter. This
causes the subsequent NAPI polls to run into the same
IDPF_TXD_COMPLT_SW_MARKER packet again and print out the following:

    [   23.261341] idpf 0000:05:00.0 eth1: Unknown TX completion type: 5

Instead, we should increment next_to_clean regardless when an
IDPF_TXD_COMPLT_SW_MARKER packet is found.

Tested: with the patch applied, we do not see the errors above from NAPI
polls anymore.

Fixes: 9d39447051a0 ("idpf: remove SW marker handling from NAPI")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 376050308b06..761a77510467 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2348,7 +2348,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 
 	do {
 		struct idpf_splitq_4b_tx_compl_desc *tx_desc;
-		struct idpf_tx_queue *target;
+		struct idpf_tx_queue *target = NULL;
 		u32 ctype_gen, id;
 
 		tx_desc = flow ? &complq->comp[ntc].common :
@@ -2368,14 +2368,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 		target = complq->txq_grp->txqs[id];
 
 		idpf_queue_clear(SW_MARKER, target);
-		if (target == txq)
-			break;
 
 next:
 		if (unlikely(++ntc == complq->desc_count)) {
 			ntc = 0;
 			gen_flag = !gen_flag;
 		}
+		if (target == txq)
+			break;
 	} while (time_before(jiffies, timeout));
 
 	idpf_queue_assign(GEN_CHK, complq, gen_flag);

From d11e5da2d6d87d123e339dc9af7bc1682fc533ce Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 12 Jan 2026 23:09:43 +0000
Subject: [PATCH 0413/1303] idpf: skip deallocating bufq_sets from rx_qgrp if
 it is NULL

In idpf_rxq_group_alloc(), if rx_qgrp->splitq.bufq_sets failed to get
allocated:

	rx_qgrp->splitq.bufq_sets = kcalloc(vport->num_bufqs_per_qgrp,
					    sizeof(struct idpf_bufq_set),
					    GFP_KERNEL);
	if (!rx_qgrp->splitq.bufq_sets) {
		err = -ENOMEM;
		goto err_alloc;
	}

idpf_rxq_group_rel() would attempt to deallocate it in
idpf_rxq_sw_queue_rel(), causing a kernel panic:

```
[    7.967242] early-network-sshd-n-rexd[3148]: knetbase: Info: [    8.127804] BUG: kernel NULL pointer dereference, address: 00000000000000c0
...
[    8.129779] RIP: 0010:idpf_rxq_group_rel+0x101/0x170
...
[    8.133854] Call Trace:
[    8.133980]  <TASK>
[    8.134092]  idpf_vport_queues_alloc+0x286/0x500
[    8.134313]  idpf_vport_open+0x4d/0x3f0
[    8.134498]  idpf_open+0x71/0xb0
[    8.134668]  __dev_open+0x142/0x260
[    8.134840]  netif_open+0x2f/0xe0
[    8.135004]  dev_open+0x3d/0x70
[    8.135166]  bond_enslave+0x5ed/0xf50
[    8.135345]  ? nla_put_ifalias+0x3d/0x90
[    8.135533]  ? kvfree_call_rcu+0xb5/0x3b0
[    8.135725]  ? kvfree_call_rcu+0xb5/0x3b0
[    8.135916]  do_set_master+0x114/0x160
[    8.136098]  do_setlink+0x412/0xfb0
[    8.136269]  ? security_sock_rcv_skb+0x2a/0x50
[    8.136509]  ? sk_filter_trim_cap+0x7c/0x320
[    8.136714]  ? skb_queue_tail+0x20/0x50
[    8.136899]  ? __nla_validate_parse+0x92/0xe50
[    8.137112]  ? security_capable+0x35/0x60
[    8.137304]  rtnl_newlink+0x95c/0xa00
[    8.137483]  ? __rtnl_unlock+0x37/0x70
[    8.137664]  ? netdev_run_todo+0x63/0x530
[    8.137855]  ? allocate_slab+0x280/0x870
[    8.138044]  ? security_capable+0x35/0x60
[    8.138235]  rtnetlink_rcv_msg+0x2e6/0x340
[    8.138431]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[    8.138650]  netlink_rcv_skb+0x16a/0x1a0
[    8.138840]  netlink_unicast+0x20a/0x320
[    8.139028]  netlink_sendmsg+0x304/0x3b0
[    8.139217]  __sock_sendmsg+0x89/0xb0
[    8.139399]  ____sys_sendmsg+0x167/0x1c0
[    8.139588]  ? ____sys_recvmsg+0xed/0x150
[    8.139780]  ___sys_sendmsg+0xdd/0x120
[    8.139960]  ? ___sys_recvmsg+0x124/0x1e0
[    8.140152]  ? rcutree_enqueue+0x1f/0xb0
[    8.140341]  ? rcutree_enqueue+0x1f/0xb0
[    8.140528]  ? call_rcu+0xde/0x2a0
[    8.140695]  ? evict+0x286/0x2d0
[    8.140856]  ? rcutree_enqueue+0x1f/0xb0
[    8.141043]  ? kmem_cache_free+0x2c/0x350
[    8.141236]  __x64_sys_sendmsg+0x72/0xc0
[    8.141424]  do_syscall_64+0x6f/0x890
[    8.141603]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[    8.141841] RIP: 0033:0x7f2799d21bd0
...
[    8.149905] Kernel panic - not syncing: Fatal exception
[    8.175940] Kernel Offset: 0xf800000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[    8.176425] Rebooting in 10 seconds..
```

Tested: With this patch, the kernel panic no longer appears.

Fixes: 95af467d9a4e ("idpf: configure resources for RX queues")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 761a77510467..59aafadae3d0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1341,6 +1341,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc)
  */
 static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp)
 {
+	if (!rx_qgrp->splitq.bufq_sets)
+		return;
+
 	for (unsigned int i = 0; i < rx_qgrp->splitq.num_bufq_sets; i++) {
 		struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i];
 

From e403bf4013a665961bdfdf65193e3076c3d155a5 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 12 Jan 2026 23:09:44 +0000
Subject: [PATCH 0414/1303] idpf: skip deallocating txq group's txqs if it is
 NULL

In idpf_txq_group_alloc(), if any txq group's txqs failed to
allocate memory:

	for (j = 0; j < tx_qgrp->num_txq; j++) {
		tx_qgrp->txqs[j] = kzalloc(sizeof(*tx_qgrp->txqs[j]),
					   GFP_KERNEL);
		if (!tx_qgrp->txqs[j])
			goto err_alloc;
	}

It would cause a NULL ptr kernel panic in idpf_txq_group_rel():

	for (j = 0; j < txq_grp->num_txq; j++) {
		if (flow_sch_en) {
			kfree(txq_grp->txqs[j]->refillq);
			txq_grp->txqs[j]->refillq = NULL;
		}

		kfree(txq_grp->txqs[j]);
		txq_grp->txqs[j] = NULL;
	}

[    6.532461] BUG: kernel NULL pointer dereference, address: 0000000000000058
...
[    6.534433] RIP: 0010:idpf_txq_group_rel+0xc9/0x110
...
[    6.538513] Call Trace:
[    6.538639]  <TASK>
[    6.538760]  idpf_vport_queues_alloc+0x75/0x550
[    6.538978]  idpf_vport_open+0x4d/0x3f0
[    6.539164]  idpf_open+0x71/0xb0
[    6.539324]  __dev_open+0x142/0x260
[    6.539506]  netif_open+0x2f/0xe0
[    6.539670]  dev_open+0x3d/0x70
[    6.539827]  bond_enslave+0x5ed/0xf50
[    6.540005]  ? rcutree_enqueue+0x1f/0xb0
[    6.540193]  ? call_rcu+0xde/0x2a0
[    6.540375]  ? barn_get_empty_sheaf+0x5c/0x80
[    6.540594]  ? __kfree_rcu_sheaf+0xb6/0x1a0
[    6.540793]  ? nla_put_ifalias+0x3d/0x90
[    6.540981]  ? kvfree_call_rcu+0xb5/0x3b0
[    6.541173]  ? kvfree_call_rcu+0xb5/0x3b0
[    6.541365]  do_set_master+0x114/0x160
[    6.541547]  do_setlink+0x412/0xfb0
[    6.541717]  ? security_sock_rcv_skb+0x2a/0x50
[    6.541931]  ? sk_filter_trim_cap+0x7c/0x320
[    6.542136]  ? skb_queue_tail+0x20/0x50
[    6.542322]  ? __nla_validate_parse+0x92/0xe50
ro[o t   t o6 .d5e4f2a5u4l0t]-  ? security_capable+0x35/0x60
[    6.542792]  rtnl_newlink+0x95c/0xa00
[    6.542972]  ? __rtnl_unlock+0x37/0x70
[    6.543152]  ? netdev_run_todo+0x63/0x530
[    6.543343]  ? allocate_slab+0x280/0x870
[    6.543531]  ? security_capable+0x35/0x60
[    6.543722]  rtnetlink_rcv_msg+0x2e6/0x340
[    6.543918]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[    6.544138]  netlink_rcv_skb+0x16a/0x1a0
[    6.544328]  netlink_unicast+0x20a/0x320
[    6.544516]  netlink_sendmsg+0x304/0x3b0
[    6.544748]  __sock_sendmsg+0x89/0xb0
[    6.544928]  ____sys_sendmsg+0x167/0x1c0
[    6.545116]  ? ____sys_recvmsg+0xed/0x150
[    6.545308]  ___sys_sendmsg+0xdd/0x120
[    6.545489]  ? ___sys_recvmsg+0x124/0x1e0
[    6.545680]  ? rcutree_enqueue+0x1f/0xb0
[    6.545867]  ? rcutree_enqueue+0x1f/0xb0
[    6.546055]  ? call_rcu+0xde/0x2a0
[    6.546222]  ? evict+0x286/0x2d0
[    6.546389]  ? rcutree_enqueue+0x1f/0xb0
[    6.546577]  ? kmem_cache_free+0x2c/0x350
[    6.546784]  __x64_sys_sendmsg+0x72/0xc0
[    6.546972]  do_syscall_64+0x6f/0x890
[    6.547150]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[    6.547393] RIP: 0033:0x7fc1a3347bd0
...
[    6.551375] RIP: 0010:idpf_txq_group_rel+0xc9/0x110
...
[    6.578856] Rebooting in 10 seconds..

We should skip deallocating txqs[j] if it is NULL in the first place.

Tested: with this patch, the kernel panic no longer appears.

Fixes: 1c325aac10a8 ("idpf: configure resources for TX queues")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 59aafadae3d0..7613f020b622 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1316,6 +1316,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc)
 		struct idpf_txq_group *txq_grp = &rsrc->txq_grps[i];
 
 		for (unsigned int j = 0; j < txq_grp->num_txq; j++) {
+			if (!txq_grp->txqs[j])
+				continue;
+
 			if (idpf_queue_has(FLOW_SCH_EN, txq_grp->txqs[j])) {
 				kfree(txq_grp->txqs[j]->refillq);
 				txq_grp->txqs[j]->refillq = NULL;

From bc3b31977314433e4685ae92853d1b6e91ad7bc2 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Fri, 23 Jan 2026 06:58:06 +0000
Subject: [PATCH 0415/1303] idpf: nullify pointers after they are freed

rss_data->rss_key needs to be nullified after it is freed.
Checks like "if (!rss_data->rss_key)" in the code could fail
if it is not nullified.

Tested: built and booted the kernel.

Fixes: 83f38f210b85 ("idpf: Fix RSS LUT NULL pointer crash on early ethtool operations")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 94da5fbd56f1..7ce6a0e4acb6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1320,6 +1320,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 
 free_rss_key:
 	kfree(rss_data->rss_key);
+	rss_data->rss_key = NULL;
 free_qreg_chunks:
 	idpf_vport_deinit_queue_reg_chunks(adapter->vport_config[idx]);
 free_vector_idxs:

From 1500a8662d2d41d6bb03e034de45ddfe6d7d362d Mon Sep 17 00:00:00 2001
From: Brian Vazquez <brianvv@google.com>
Date: Mon, 26 Jan 2026 21:55:59 +0000
Subject: [PATCH 0416/1303] idpf: change IRQ naming to match netdev and ethtool
 queue numbering

The code uses the vidx for the IRQ name but that doesn't match ethtool
reporting nor netdev naming, this makes it hard to tune the device and
associate queues with IRQs. Sequentially requesting irqs starting from
'0' makes the output consistent.

This commit changes the interrupt numbering but preserves the name
format, maintaining ABI compatibility. Existing tools relying on the old
numbering are already non-functional, as they lack a useful correlation
to the interrupts.

Before:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list
/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167
/proc/irq/68/idpf-eth1-TxRx-1/../smp_affinity_list:0
/proc/irq/70/idpf-eth1-TxRx-3/../smp_affinity_list:1
/proc/irq/71/idpf-eth1-TxRx-4/../smp_affinity_list:2
/proc/irq/72/idpf-eth1-Tx-5/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:
     tx_q-0_pkts: 1002
     tx_q-1_pkts: 2679
     tx_q-2_pkts: 1113
     tx_q-3_pkts: 1192 <----- tx_q-3 vs idpf-eth1-Tx-5
     rx_q-0_pkts: 1143
     rx_q-1_pkts: 3172
     rx_q-2_pkts: 1074

After:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list

/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167
/proc/irq/68/idpf-eth1-TxRx-0/../smp_affinity_list:0
/proc/irq/70/idpf-eth1-TxRx-1/../smp_affinity_list:1
/proc/irq/71/idpf-eth1-TxRx-2/../smp_affinity_list:2
/proc/irq/72/idpf-eth1-Tx-3/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:
     tx_q-0_pkts: 118
     tx_q-1_pkts: 134
     tx_q-2_pkts: 228
     tx_q-3_pkts: 138 <--- tx_q-3 matches idpf-eth1-Tx-3
     rx_q-0_pkts: 111
     rx_q-1_pkts: 366
     rx_q-2_pkts: 120

Fixes: d4d558718266 ("idpf: initialize interrupts and enable vport")
Signed-off-by: Brian Vazquez <brianvv@google.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 7613f020b622..b7e922fffc96 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -4077,7 +4077,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport,
 			continue;
 
 		name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name,
-				 vec_name, vidx);
+				 vec_name, vector);
 
 		err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0,
 				  name, q_vector);

From 2c31557336a8e4d209ed8d4513cef2c0f15e7ef4 Mon Sep 17 00:00:00 2001
From: Sreedevi Joshi <sreedevi.joshi@intel.com>
Date: Tue, 13 Jan 2026 12:01:13 -0600
Subject: [PATCH 0417/1303] idpf: Fix flow rule delete failure due to invalid
 validation

When deleting a flow rule using "ethtool -N <dev> delete <location>",
idpf_sideband_action_ena() incorrectly validates fsp->ring_cookie even
though ethtool doesn't populate this field for delete operations. The
uninitialized ring_cookie may randomly match RX_CLS_FLOW_DISC or
RX_CLS_FLOW_WAKE, causing validation to fail and preventing legitimate
rule deletions. Remove the unnecessary sideband action enable check and
ring_cookie validation during delete operations since action validation
is not required when removing existing rules.

Fixes: ada3e24b84a0 ("idpf: add flow steering support")
Signed-off-by: Sreedevi Joshi <sreedevi.joshi@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_ethtool.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 1d78a621d65b..3275b0215655 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -307,9 +307,6 @@ static int idpf_del_flow_steer(struct net_device *netdev,
 	vport_config = vport->adapter->vport_config[np->vport_idx];
 	user_config = &vport_config->user_config;
 
-	if (!idpf_sideband_action_ena(vport, fsp))
-		return -EOPNOTSUPP;
-
 	rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL);
 	if (!rule)
 		return -ENOMEM;

From 6aa07e23dd3ccd35a0100c06fcb6b6c3b01e7965 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Thu, 29 Jan 2026 12:00:26 +0800
Subject: [PATCH 0418/1303] ice: recap the VSI and QoS info after rebuild

Fix IRDMA hardware initialization timeout (-110) after resume by
separating VSI-dependent configuration from RDMA resource allocation,
ensuring VSI is rebuilt before IRDMA accesses it.

After resume from suspend, IRDMA hardware initialization fails:
  ice: IRDMA hardware initialization FAILED init_state=4 status=-110

Separate RDMA initialization into two phases:
1. ice_init_rdma() - Allocate resources only (no VSI/QoS access, no plug)
2. ice_rdma_finalize_setup() - Assign VSI/QoS info and plug device

This allows:
- ice_init_rdma() to stay in ice_resume() (mirrors ice_deinit_rdma()
  in ice_suspend())
- VSI assignment deferred until after ice_vsi_rebuild() completes
- QoS info updated after ice_dcb_rebuild() completes
- Device plugged only when control queues, VSI, and DCB are all ready

Fixes: bc69ad74867db ("ice: avoid IRQ collision to fix init failure on ACPI S3 resume")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_idc.c  | 44 +++++++++++++++++------
 drivers/net/ethernet/intel/ice/ice_main.c |  7 +++-
 3 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index def7efa15447..2b2b22af42be 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -987,6 +987,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
+void ice_rdma_finalize_setup(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
 void ice_deinit_rdma(struct ice_pf *pf);
 bool ice_is_wol_supported(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 420d45c2558b..ded029aa71d7 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -360,6 +360,39 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 	auxiliary_device_uninit(adev);
 }
 
+/**
+ * ice_rdma_finalize_setup - Complete RDMA setup after VSI is ready
+ * @pf: ptr to ice_pf
+ *
+ * Sets VSI-dependent information and plugs aux device.
+ * Must be called after ice_init_rdma(), ice_vsi_rebuild(), and
+ * ice_dcb_rebuild() complete.
+ */
+void ice_rdma_finalize_setup(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct iidc_rdma_priv_dev_info *privd;
+	int ret;
+
+	if (!ice_is_rdma_ena(pf) || !pf->cdev_info)
+		return;
+
+	privd = pf->cdev_info->iidc_priv;
+	if (!privd || !pf->vsi || !pf->vsi[0] || !pf->vsi[0]->netdev)
+		return;
+
+	/* Assign VSI info now that VSI is valid */
+	privd->netdev = pf->vsi[0]->netdev;
+	privd->vport_id = pf->vsi[0]->vsi_num;
+
+	/* Update QoS info after DCB has been rebuilt */
+	ice_setup_dcb_qos_info(pf, &privd->qos_info);
+
+	ret = ice_plug_aux_dev(pf);
+	if (ret)
+		dev_warn(dev, "Failed to plug RDMA aux device: %d\n", ret);
+}
+
 /**
  * ice_init_rdma - initializes PF for RDMA use
  * @pf: ptr to ice_pf
@@ -398,22 +431,14 @@ int ice_init_rdma(struct ice_pf *pf)
 	}
 
 	cdev->iidc_priv = privd;
-	privd->netdev = pf->vsi[0]->netdev;
 
 	privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr;
 	cdev->pdev = pf->pdev;
-	privd->vport_id = pf->vsi[0]->vsi_num;
 
 	pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
-	ice_setup_dcb_qos_info(pf, &privd->qos_info);
-	ret = ice_plug_aux_dev(pf);
-	if (ret)
-		goto err_plug_aux_dev;
+
 	return 0;
 
-err_plug_aux_dev:
-	pf->cdev_info->adev = NULL;
-	xa_erase(&ice_aux_id, pf->aux_idx);
 err_alloc_xa:
 	kfree(privd);
 err_privd_alloc:
@@ -432,7 +457,6 @@ void ice_deinit_rdma(struct ice_pf *pf)
 	if (!ice_is_rdma_ena(pf))
 		return;
 
-	ice_unplug_aux_dev(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
 	kfree(pf->cdev_info->iidc_priv);
 	kfree(pf->cdev_info);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4da37caa3ec9..62914167d121 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5138,6 +5138,9 @@ int ice_load(struct ice_pf *pf)
 	if (err)
 		goto err_init_rdma;
 
+	/* Finalize RDMA: VSI already created, assign info and plug device */
+	ice_rdma_finalize_setup(pf);
+
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5169,6 +5172,7 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
@@ -5595,6 +5599,7 @@ static int ice_suspend(struct device *dev)
 	 */
 	disabled = ice_service_task_stop(pf);
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 
 	/* Already suspended?, then there is nothing to do */
@@ -7859,7 +7864,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ice_health_clear(pf);
 
-	ice_plug_aux_dev(pf);
+	ice_rdma_finalize_setup(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
 

From a9c354e656597aededa027d63d2ff0973f6b033f Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Mon, 2 Feb 2026 11:17:54 +0100
Subject: [PATCH 0419/1303] ice: fix crash in ethtool offline loopback test

Since the conversion of ice to page pool, the ethtool loopback test
crashes:

 BUG: kernel NULL pointer dereference, address: 000000000000000c
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 1100f1067 P4D 0
 Oops: Oops: 0002 [#1] SMP NOPTI
 CPU: 23 UID: 0 PID: 5904 Comm: ethtool Kdump: loaded Not tainted 6.19.0-0.rc7.260128g1f97d9dcf5364.49.eln154.x86_64 #1 PREEMPT(lazy)
 Hardware name: [...]
 RIP: 0010:ice_alloc_rx_bufs+0x1cd/0x310 [ice]
 Code: 83 6c 24 30 01 66 41 89 47 08 0f 84 c0 00 00 00 41 0f b7 dc 48 8b 44 24 18 48 c1 e3 04 41 bb 00 10 00 00 48 8d 2c 18 8b 04 24 <89> 45 0c 41 8b 4d 00 49 d3 e3 44 3b 5c 24 24 0f 83 ac fe ff ff 44
 RSP: 0018:ff7894738aa1f768 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000700 RDI: 0000000000000000
 RBP: 0000000000000000 R08: ff16dcae79880200 R09: 0000000000000019
 R10: 0000000000000001 R11: 0000000000001000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: ff16dcae6c670000
 FS:  00007fcf428850c0(0000) GS:ff16dcb149710000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000000000c CR3: 0000000121227005 CR4: 0000000000773ef0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ice_vsi_cfg_rxq+0xca/0x460 [ice]
  ice_vsi_cfg_rxqs+0x54/0x70 [ice]
  ice_loopback_test+0xa9/0x520 [ice]
  ice_self_test+0x1b9/0x280 [ice]
  ethtool_self_test+0xe5/0x200
  __dev_ethtool+0x1106/0x1a90
  dev_ethtool+0xbe/0x1a0
  dev_ioctl+0x258/0x4c0
  sock_do_ioctl+0xe3/0x130
  __x64_sys_ioctl+0xb9/0x100
  do_syscall_64+0x7c/0x700
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [...]

It crashes because we have not initialized libeth for the rx ring.

Fix it by treating ICE_VSI_LB VSIs slightly more like normal PF VSIs and
letting them have a q_vector. It's just a dummy, because the loopback
test does not use interrupts, but it contains a napi struct that can be
passed to libeth_rx_fq_create() called from ice_vsi_cfg_rxq() ->
ice_rxq_pp_create().

Fixes: 93f53db9f9dc ("ice: switch to Page Pool")
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c    |  5 ++++-
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  4 ++++
 drivers/net/ethernet/intel/ice/ice_lib.c     | 15 ++++++++++-----
 3 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index afbff8aa9ceb..49b4304c4975 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -124,6 +124,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 	if (vsi->type == ICE_VSI_VF) {
 		ice_calc_vf_reg_idx(vsi->vf, q_vector);
 		goto out;
+	} else if (vsi->type == ICE_VSI_LB) {
+		goto skip_alloc;
 	} else if (vsi->type == ICE_VSI_CTRL && vsi->vf) {
 		struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi);
 
@@ -662,7 +664,8 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 	u32 rx_buf_len;
 	int err;
 
-	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) {
+	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
+	    ring->vsi->type == ICE_VSI_LB) {
 		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index c6bc29cfb8e6..ff003529beba 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1289,6 +1289,10 @@ static u64 ice_loopback_test(struct net_device *netdev)
 	test_vsi->netdev = netdev;
 	tx_ring = test_vsi->tx_rings[0];
 	rx_ring = test_vsi->rx_rings[0];
+	/* Dummy q_vector and napi. Fill the minimum required for
+	 * ice_rxq_pp_create().
+	 */
+	rx_ring->q_vector->napi.dev = netdev;
 
 	if (ice_lbtest_prepare_rings(test_vsi)) {
 		ret = 2;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d921269e1fe7..3cd6296a1fbe 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -107,10 +107,6 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->rxq_map)
 		goto err_rxq_map;
 
-	/* There is no need to allocate q_vectors for a loopback VSI. */
-	if (vsi->type == ICE_VSI_LB)
-		return 0;
-
 	/* allocate memory for q_vector pointers */
 	vsi->q_vectors = devm_kcalloc(dev, vsi->num_q_vectors,
 				      sizeof(*vsi->q_vectors), GFP_KERNEL);
@@ -241,6 +237,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 	case ICE_VSI_LB:
 		vsi->alloc_txq = 1;
 		vsi->alloc_rxq = 1;
+		/* A dummy q_vector, no actual IRQ. */
+		vsi->num_q_vectors = 1;
 		break;
 	default:
 		dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type);
@@ -2428,14 +2426,21 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 		}
 		break;
 	case ICE_VSI_LB:
-		ret = ice_vsi_alloc_rings(vsi);
+		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
 			goto unroll_vsi_init;
 
+		ret = ice_vsi_alloc_rings(vsi);
+		if (ret)
+			goto unroll_alloc_q_vector;
+
 		ret = ice_vsi_alloc_ring_stats(vsi);
 		if (ret)
 			goto unroll_vector_base;
 
+		/* Simply map the dummy q_vector to the only rx_ring */
+		vsi->rx_rings[0]->q_vector = vsi->q_vectors[0];
+
 		break;
 	default:
 		/* clean up the resources and exit */

From 4b3d54a85bd37ebf2d9836f0d0de775c0ff21af9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Sat, 7 Feb 2026 11:50:23 +0100
Subject: [PATCH 0420/1303] i40e: Fix preempt count leak in napi poll
 tracepoint

Using get_cpu() in the tracepoint assignment causes an obvious preempt
count leak because nothing invokes put_cpu() to undo it:

  softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101?

This clearly has seen a lot of testing in the last 3+ years...

Use smp_processor_id() instead.

Fixes: 6d4d584a7ea8 ("i40e: Add i40e_napi_poll tracepoint")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: Tony Nguyen <anthony.l.nguyen@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Cc: netdev@vger.kernel.org
Reviewed-by: Joe Damato <joe@dama.to>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h
index 759f3d1c4c8f..dde0ccd789ed 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_trace.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h
@@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll,
 		__entry->rx_clean_complete = rx_clean_complete;
 		__entry->tx_clean_complete = tx_clean_complete;
 		__entry->irq_num = q->irq_num;
-		__entry->curr_cpu = get_cpu();
+		__entry->curr_cpu = smp_processor_id();
 		__assign_str(qname);
 		__assign_str(dev_name);
 		__assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask),

From feae40a6a178bb525a15f19288016e5778102a99 Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Wed, 10 Dec 2025 12:26:51 +0100
Subject: [PATCH 0421/1303] ixgbevf: fix link setup issue

It may happen that VF spawned for E610 adapter has problem with setting
link up. This happens when ixgbevf supporting mailbox API 1.6 cooperates
with PF driver which doesn't support this version of API, and hence
doesn't support new approach for getting PF link data.

In that case VF asks PF to provide link data but as PF doesn't support
it, returns -EOPNOTSUPP what leads to early bail from link configuration
sequence.

Avoid such situation by using legacy VFLINKS approach whenever negotiated
API version is less than 1.6.

To reproduce the issue just create VF and set its link up - adapter must
be any from the E610 family, ixgbevf must support API 1.6 or higher while
ixgbevf must not.

Fixes: 53f0eb62b4d2 ("ixgbevf: fix getting link speed data for E610 devices")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Cc: stable@vger.kernel.org
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbevf/vf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 74d320879513..b67b580f7f1c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -852,7 +852,8 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	if (!mac->get_link_status)
 		goto out;
 
-	if (hw->mac.type == ixgbe_mac_e610_vf) {
+	if (hw->mac.type == ixgbe_mac_e610_vf &&
+	    hw->api_version >= ixgbe_mbox_api_16) {
 		ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up);
 		if (ret_val)
 			goto out;

From 5b644464eeeac485685c6632bcc95347ae6c8677 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 6 Jan 2026 16:14:19 +0200
Subject: [PATCH 0422/1303] e1000e: introduce new board type for Panther Lake
 PCH

Add new board type for Panther Lake devices for separating device-specific
features and flows.
Additionally, remove the deprecated device IDs 0x57B5 and 0x57B6, which
are not used by any existing devices.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/e1000.h   |  4 +++-
 drivers/net/ethernet/intel/e1000e/hw.h      |  2 --
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 22 ++++++++++++++++++++-
 drivers/net/ethernet/intel/e1000e/netdev.c  | 15 +++++++-------
 4 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index aa08f397988e..63ebe00376f5 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -117,7 +117,8 @@ enum e1000_boards {
 	board_pch_cnp,
 	board_pch_tgp,
 	board_pch_adp,
-	board_pch_mtp
+	board_pch_mtp,
+	board_pch_ptp
 };
 
 struct e1000_ps_page {
@@ -527,6 +528,7 @@ extern const struct e1000_info e1000_pch_cnp_info;
 extern const struct e1000_info e1000_pch_tgp_info;
 extern const struct e1000_info e1000_pch_adp_info;
 extern const struct e1000_info e1000_pch_mtp_info;
+extern const struct e1000_info e1000_pch_ptp_info;
 extern const struct e1000_info e1000_es2_info;
 
 void e1000e_ptp_init(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index fc8ed38aa095..c7ac599e5a7a 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -118,8 +118,6 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_ARL_I219_V24		0x57A1
 #define E1000_DEV_ID_PCH_PTP_I219_LM25		0x57B3
 #define E1000_DEV_ID_PCH_PTP_I219_V25		0x57B4
-#define E1000_DEV_ID_PCH_PTP_I219_LM26		0x57B5
-#define E1000_DEV_ID_PCH_PTP_I219_V26		0x57B6
 #define E1000_DEV_ID_PCH_PTP_I219_LM27		0x57B7
 #define E1000_DEV_ID_PCH_PTP_I219_V27		0x57B8
 #define E1000_DEV_ID_PCH_NVL_I219_LM29		0x57B9
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 0ff8688ac3b8..23421a640097 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -528,7 +528,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 
 	phy->id = e1000_phy_unknown;
 
-	if (hw->mac.type == e1000_pch_mtp) {
+	if (hw->mac.type == e1000_pch_mtp || hw->mac.type == e1000_pch_ptp) {
 		phy->retry_count = 2;
 		e1000e_enable_phy_retry(hw);
 	}
@@ -6208,3 +6208,23 @@ const struct e1000_info e1000_pch_mtp_info = {
 	.phy_ops		= &ich8_phy_ops,
 	.nvm_ops		= &spt_nvm_ops,
 };
+
+const struct e1000_info e1000_pch_ptp_info = {
+	.mac			= e1000_pch_ptp,
+	.flags			= FLAG_IS_ICH
+				  | FLAG_HAS_WOL
+				  | FLAG_HAS_HW_TIMESTAMP
+				  | FLAG_HAS_CTRLEXT_ON_LOAD
+				  | FLAG_HAS_AMT
+				  | FLAG_HAS_FLASH
+				  | FLAG_HAS_JUMBO_FRAMES
+				  | FLAG_APME_IN_WUC,
+	.flags2			= FLAG2_HAS_PHY_STATS
+				  | FLAG2_HAS_EEE,
+	.pba			= 26,
+	.max_hw_frame_size	= 9022,
+	.get_variants		= e1000_get_variants_ich8lan,
+	.mac_ops		= &ich8_mac_ops,
+	.phy_ops		= &ich8_phy_ops,
+	.nvm_ops		= &spt_nvm_ops,
+};
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index ddbe2f7d8112..814698807f3d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -55,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = {
 	[board_pch_tgp]		= &e1000_pch_tgp_info,
 	[board_pch_adp]		= &e1000_pch_adp_info,
 	[board_pch_mtp]		= &e1000_pch_mtp_info,
+	[board_pch_ptp]		= &e1000_pch_ptp_info,
 };
 
 struct e1000_reg_info {
@@ -7925,14 +7926,12 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_ptp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };

From 0942fc6d324eb9c6b16187b2aa994c0823557f06 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 6 Jan 2026 16:14:20 +0200
Subject: [PATCH 0423/1303] e1000e: clear DPG_EN after reset to avoid
 autonomous power-gating

Panther Lake systems introduced an autonomous power gating feature for
the integrated Gigabit Ethernet in shutdown state (S5) state. As part of
it, the reset value of DPG_EN bit was changed to 1. Clear this bit after
performing hardware reset to avoid errors such as Tx/Rx hangs, or packet
loss/corruption.

Fixes: 0c9183ce61bc ("e1000e: Add support for the next LOM generation")
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/defines.h | 1 +
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index ba331899d186..d4a1041e456d 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -33,6 +33,7 @@
 
 /* Extended Device Control */
 #define E1000_CTRL_EXT_LPCD  0x00000004     /* LCD Power Cycle Done */
+#define E1000_CTRL_EXT_DPG_EN	0x00000008 /* Dynamic Power Gating Enable */
 #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */
 #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */
 #define E1000_CTRL_EXT_EE_RST    0x00002000 /* Reinitialize from EEPROM */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 23421a640097..dea208db1be5 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -4932,6 +4932,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
 	reg |= E1000_KABGTXD_BGSQLBIAS;
 	ew32(KABGTXD, reg);
 
+	/* The hardware reset value of the DPG_EN bit is 1.
+	 * Clear DPG_EN to prevent unexpected autonomous power gating.
+	 */
+	if (hw->mac.type >= e1000_pch_ptp) {
+		reg = er32(CTRL_EXT);
+		reg &= ~E1000_CTRL_EXT_DPG_EN;
+		ew32(CTRL_EXT, reg);
+	}
+
 	return 0;
 }
 

From f6bf47ab32e0863df50f5501d207dcdddb7fc507 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 23 Feb 2026 22:10:10 +0000
Subject: [PATCH 0424/1303] arm64: io: Rename ioremap_prot() to
 __ioremap_prot()

Rename our ioremap_prot() implementation to __ioremap_prot() and convert
all arch-internal callers over to the new function.

ioremap_prot() remains as a #define to __ioremap_prot() for
generic_access_phys() and will be subsequently extended to handle user
permissions in 'prot'.

Cc: Zeng Heng <zengheng4@huawei.com>
Cc: Jinjiang Tu <tujinjiang@huawei.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/io.h | 11 ++++++-----
 arch/arm64/kernel/acpi.c    |  2 +-
 arch/arm64/mm/ioremap.c     |  6 +++---
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 83e03abbb2ca..cd2fddfe814a 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -264,19 +264,20 @@ __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size,
 				   pgprot_t *prot);
 int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
+void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot);
 
-#define ioremap_prot ioremap_prot
+#define ioremap_prot __ioremap_prot
 
 #define _PAGE_IOREMAP PROT_DEVICE_nGnRE
 
 #define ioremap_wc(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
+	__ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
 
 
 #define ioremap_encrypted(addr, size)	\
-	ioremap_prot((addr), (size), PAGE_KERNEL)
+	__ioremap_prot((addr), (size), PAGE_KERNEL)
 
 /*
  * io{read,write}{16,32,64}be() macros
@@ -297,7 +298,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
 	if (pfn_is_map_memory(__phys_to_pfn(addr)))
 		return (void __iomem *)__phys_to_virt(addr);
 
-	return ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
+	return __ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
 }
 
 /*
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index af90128cfed5..a9d884fd1d00 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -377,7 +377,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
-	return ioremap_prot(phys, size, prot);
+	return __ioremap_prot(phys, size, prot);
 }
 
 /*
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index b12cbed9b5ad..6eef48ef6278 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -14,8 +14,8 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook)
 	return 0;
 }
 
-void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   pgprot_t pgprot)
+void __iomem *__ioremap_prot(phys_addr_t phys_addr, size_t size,
+			     pgprot_t pgprot)
 {
 	unsigned long last_addr = phys_addr + size - 1;
 
@@ -39,7 +39,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
 
 	return generic_ioremap_prot(phys_addr, size, pgprot);
 }
-EXPORT_SYMBOL(ioremap_prot);
+EXPORT_SYMBOL(__ioremap_prot);
 
 /*
  * Must be called after early_fixmap_init

From 8f098037139b294050053123ab2bc0f819d08932 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 23 Feb 2026 22:10:11 +0000
Subject: [PATCH 0425/1303] arm64: io: Extract user memory type in
 ioremap_prot()

The only caller of ioremap_prot() outside of the generic ioremap()
implementation is generic_access_phys(), which passes a 'pgprot_t' value
determined from the user mapping of the target 'pfn' being accessed by
the kernel. On arm64, the 'pgprot_t' contains all of the non-address
bits from the pte, including the permission controls, and so we end up
returning a new user mapping from ioremap_prot() which faults when
accessed from the kernel on systems with PAN:

  | Unable to handle kernel read from unreadable memory at virtual address ffff80008ea89000
  | ...
  | Call trace:
  |   __memcpy_fromio+0x80/0xf8
  |   generic_access_phys+0x20c/0x2b8
  |   __access_remote_vm+0x46c/0x5b8
  |   access_remote_vm+0x18/0x30
  |   environ_read+0x238/0x3e8
  |   vfs_read+0xe4/0x2b0
  |   ksys_read+0xcc/0x178
  |   __arm64_sys_read+0x4c/0x68

Extract only the memory type from the user 'pgprot_t' in ioremap_prot()
and assert that we're being passed a user mapping, to protect us against
any changes in future that may require additional handling. To avoid
falsely flagging users of ioremap(), provide our own ioremap() macro
which simply wraps __ioremap_prot().

Cc: Zeng Heng <zengheng4@huawei.com>
Cc: Jinjiang Tu <tujinjiang@huawei.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 893dea9ccd08 ("arm64: Add HAVE_IOREMAP_PROT support")
Reported-by: Jinjiang Tu <tujinjiang@huawei.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/io.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index cd2fddfe814a..8cbd1e96fd50 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -266,10 +266,23 @@ typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size,
 int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
 void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot);
 
-#define ioremap_prot __ioremap_prot
+static inline void __iomem *ioremap_prot(phys_addr_t phys, size_t size,
+					 pgprot_t user_prot)
+{
+	pgprot_t prot;
+	ptdesc_t user_prot_val = pgprot_val(user_prot);
 
-#define _PAGE_IOREMAP PROT_DEVICE_nGnRE
+	if (WARN_ON_ONCE(!(user_prot_val & PTE_USER)))
+		return NULL;
 
+	prot = __pgprot_modify(PAGE_KERNEL, PTE_ATTRINDX_MASK,
+			       user_prot_val & PTE_ATTRINDX_MASK);
+	return __ioremap_prot(phys, size, prot);
+}
+#define ioremap_prot ioremap_prot
+
+#define ioremap(addr, size)	\
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)	\
 	__ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\

From 8a85b3131225a8c8143ba2ae29c0eef8c1f9117f Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:30 +0000
Subject: [PATCH 0426/1303] arm64: gcs: Do not set PTE_SHARED on GCS mappings
 if FEAT_LPA2 is enabled

When FEAT_LPA2 is enabled, bits 8-9 of the PTE replace the
shareability attribute with bits 50-51 of the output address. The
_PAGE_GCS{,_RO} definitions include the PTE_SHARED bits as 0b11 (this
matches the other _PAGE_* definitions) but using this macro directly
leads to the following panic when enabling GCS on a system/model with
LPA2:

  Unable to handle kernel paging request at virtual address fffff1ffc32d8008
  Mem abort info:
    ESR = 0x0000000096000004
    EC = 0x25: DABT (current EL), IL = 32 bits
    SET = 0, FnV = 0
    EA = 0, S1PTW = 0
    FSC = 0x04: level 0 translation fault
  Data abort info:
    ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
    CM = 0, WnR = 0, TnD = 0, TagAccess = 0
    GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
  swapper pgtable: 4k pages, 52-bit VAs, pgdp=0000000060f4d000
  [fffff1ffc32d8008] pgd=100000006184b003, p4d=0000000000000000
  Internal error: Oops: 0000000096000004 [#1]  SMP
  CPU: 0 UID: 0 PID: 513 Comm: gcs_write_fault Tainted: G   M                7.0.0-rc1 #1 PREEMPT
  Tainted: [M]=MACHINE_CHECK
  Hardware name: QEMU QEMU Virtual Machine, BIOS 2025.02-8+deb13u1 11/08/2025
  pstate: 03402005 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
  pc : zap_huge_pmd+0x168/0x468
  lr : zap_huge_pmd+0x2c/0x468
  sp : ffff800080beb660
  x29: ffff800080beb660 x28: fff00000c2058180 x27: ffff800080beb898
  x26: fff00000c2058180 x25: ffff800080beb820 x24: 00c800010b600f41
  x23: ffffc1ffc30af1a8 x22: fff00000c2058180 x21: 0000ffff8dc00000
  x20: fff00000c2bc6370 x19: ffff800080beb898 x18: ffff800080bebb60
  x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000007
  x14: 000000000000000a x13: 0000aaaacbbbffff x12: 0000000000000000
  x11: 0000ffff8ddfffff x10: 00000000000001fe x9 : 0000ffff8ddfffff
  x8 : 0000ffff8de00000 x7 : 0000ffff8da00000 x6 : fff00000c2bc6370
  x5 : 0000ffff8da00000 x4 : 000000010b600000 x3 : ffffc1ffc0000000
  x2 : fff00000c2058180 x1 : fffff1ffc32d8000 x0 : 000000c00010b600
  Call trace:
   zap_huge_pmd+0x168/0x468 (P)
   unmap_page_range+0xd70/0x1560
   unmap_single_vma+0x48/0x80
   unmap_vmas+0x90/0x180
   unmap_region+0x88/0xe4
   vms_complete_munmap_vmas+0xf8/0x1e0
   do_vmi_align_munmap+0x158/0x180
   do_vmi_munmap+0xac/0x160
   __vm_munmap+0xb0/0x138
   vm_munmap+0x14/0x20
   gcs_free+0x70/0x80
   mm_release+0x1c/0xc8
   exit_mm_release+0x28/0x38
   do_exit+0x190/0x8ec
   do_group_exit+0x34/0x90
   get_signal+0x794/0x858
   arch_do_signal_or_restart+0x11c/0x3e0
   exit_to_user_mode_loop+0x10c/0x17c
   el0_da+0x8c/0x9c
   el0t_64_sync_handler+0xd0/0xf0
   el0t_64_sync+0x198/0x19c
  Code: aa1603e2 d34cfc00 cb813001 8b011861 (f9400420)

Similarly to how the kernel handles protection_map[], use a
gcs_page_prot variable to store the protection bits and clear PTE_SHARED
if LPA2 is enabled.

Also remove the unused PAGE_GCS{,_RO} macros.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 6497b66ba694 ("arm64/mm: Map pages for guarded control stack")
Reported-by: Emanuele Rocca <emanuele.rocca@arm.com>
Cc: stable@vger.kernel.org
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 3 ---
 arch/arm64/mm/mmap.c                  | 8 ++++++--
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index d27e8872fe3c..2b32639160de 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -164,9 +164,6 @@ static inline bool __pure lpa2_is_enabled(void)
 #define _PAGE_GCS	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER)
 #define _PAGE_GCS_RO	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER)
 
-#define PAGE_GCS	__pgprot(_PAGE_GCS)
-#define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
-
 #define PIE_E0	( \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 08ee177432c2..75f343009b4b 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -34,6 +34,8 @@ static pgprot_t protection_map[16] __ro_after_init = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
 };
 
+static ptdesc_t gcs_page_prot __ro_after_init = _PAGE_GCS_RO;
+
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.
@@ -73,9 +75,11 @@ static int __init adjust_protection_map(void)
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}
 
-	if (lpa2_is_enabled())
+	if (lpa2_is_enabled()) {
 		for (int i = 0; i < ARRAY_SIZE(protection_map); i++)
 			pgprot_val(protection_map[i]) &= ~PTE_SHARED;
+		gcs_page_prot &= ~PTE_SHARED;
+	}
 
 	return 0;
 }
@@ -87,7 +91,7 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = _PAGE_GCS_RO;
+		prot = gcs_page_prot;
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);

From 47a8aad135ac1aed04b7b0c0a8157fd208075827 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:31 +0000
Subject: [PATCH 0427/1303] arm64: gcs: Honour mprotect(PROT_NONE) on shadow
 stack mappings

vm_get_page_prot() short-circuits the protection_map[] lookup for a
VM_SHADOW_STACK mapping since it uses a different PIE index from the
typical read/write/exec permissions. However, the side effect is that it
also ignores mprotect(PROT_NONE) by creating an accessible PTE.

Special-case the !(vm_flags & VM_ACCESS_FLAGS) flags to use the
protection_map[VM_NONE] permissions instead. No GCS attributes are
required for an inaccessible PTE.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 6497b66ba694 ("arm64/mm: Map pages for guarded control stack")
Cc: stable@vger.kernel.org
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmap.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 75f343009b4b..92b2f5097a96 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -91,7 +91,11 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = gcs_page_prot;
+		/* Honour mprotect(PROT_NONE) on shadow stack mappings */
+		if (vm_flags & VM_ACCESS_FLAGS)
+			prot = gcs_page_prot;
+		else
+			prot = pgprot_val(protection_map[VM_NONE]);
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);

From 9d1a7c4a457eac8a7e07e1685f95e54fa551db5e Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:32 +0000
Subject: [PATCH 0428/1303] kselftest: arm64: Check access to GCS after
 mprotect(PROT_NONE)

A GCS mapping should not be accessible after mprotect(PROT_NONE). Add a
kselftest for this scenario.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 .../signal/testcases/gcs_prot_none_fault.c    | 76 +++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c

diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c
new file mode 100644
index 000000000000..2259f454a202
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2026 ARM Limited
+ */
+
+#include <errno.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static uint64_t *gcs_page;
+static bool post_mprotect;
+
+#ifndef __NR_map_shadow_stack
+#define __NR_map_shadow_stack 453
+#endif
+
+static bool alloc_gcs(struct tdescr *td)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+
+	gcs_page = (void *)syscall(__NR_map_shadow_stack, 0,
+				   page_size, 0);
+	if (gcs_page == MAP_FAILED) {
+		fprintf(stderr, "Failed to map %ld byte GCS: %d\n",
+			page_size, errno);
+		return false;
+	}
+
+	return true;
+}
+
+static int gcs_prot_none_fault_trigger(struct tdescr *td)
+{
+	/* Verify that the page is readable (ie, not completely unmapped) */
+	fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]);
+
+	if (mprotect(gcs_page, sysconf(_SC_PAGE_SIZE), PROT_NONE) != 0) {
+		fprintf(stderr, "mprotect(PROT_NONE) failed: %d\n", errno);
+		return 0;
+	}
+	post_mprotect = true;
+
+	/* This should trigger a fault if PROT_NONE is honoured for the GCS page */
+	fprintf(stderr, "Read value after mprotect(PROT_NONE) 0x%lx\n", gcs_page[0]);
+	return 0;
+}
+
+static int gcs_prot_none_fault_signal(struct tdescr *td, siginfo_t *si,
+				      ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	/* A fault before mprotect(PROT_NONE) is unexpected. */
+	if (!post_mprotect)
+		return 0;
+
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "GCS PROT_NONE fault",
+	.descr = "Read from GCS after mprotect(PROT_NONE) segfaults",
+	.feats_required = FEAT_GCS,
+	.timeout = 3,
+	.sig_ok = SIGSEGV,
+	.sanity_disabled = true,
+	.init = alloc_gcs,
+	.trigger = gcs_prot_none_fault_trigger,
+	.run = gcs_prot_none_fault_signal,
+};

From bfd9c931d19aa59fb8371d557774fa169b15db9a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 18 Feb 2026 16:43:47 +0000
Subject: [PATCH 0429/1303] arm64: tlb: Allow XZR argument to TLBI ops

The TLBI instruction accepts XZR as a register argument, and for TLBI
operations with a register argument, there is no functional difference
between using XZR or another GPR which contains zeroes. Operations
without a register argument are encoded as if XZR were used.

Allow the __TLBI_1() macro to use XZR when a register argument is all
zeroes.

Today this only results in a trivial code saving in
__do_compat_cache_op()'s workaround for Neoverse-N1 erratum #1542419. In
subsequent patches this pattern will be used more generally.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oupton@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a2d65d7d6aae..bf1cc9949dc8 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -38,12 +38,12 @@
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
-			       "tlbi " #op ", %0\n"			       \
+			       "tlbi " #op ", %x0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %0",     \
+			       "dsb ish\n		tlbi " #op ", %x0",    \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
-			    : : "r" (arg))
+			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 

From a8f78680ee6bf795086384e8aea159a52814f827 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 18 Feb 2026 16:43:48 +0000
Subject: [PATCH 0430/1303] arm64: tlb: Optimize ARM64_WORKAROUND_REPEAT_TLBI

The ARM64_WORKAROUND_REPEAT_TLBI workaround is used to mitigate several
errata where broadcast TLBI;DSB sequences don't provide all the
architecturally required synchronization. The workaround performs more
work than necessary, and can have significant overhead. This patch
optimizes the workaround, as explained below.

The workaround was originally added for Qualcomm Falkor erratum 1009 in
commit:

  d9ff80f83ecb ("arm64: Work around Falkor erratum 1009")

As noted in the message for that commit, the workaround is applied even
in cases where it is not strictly necessary.

The workaround was later reused without changes for:

* Arm Cortex-A76 erratum #1286807
  SDEN v33: https://developer.arm.com/documentation/SDEN-885749/33-0/

* Arm Cortex-A55 erratum #2441007
  SDEN v16: https://developer.arm.com/documentation/SDEN-859338/1600/

* Arm Cortex-A510 erratum #2441009
  SDEN v19: https://developer.arm.com/documentation/SDEN-1873351/1900/

The important details to note are as follows:

1. All relevant errata only affect the ordering and/or completion of
   memory accesses which have been translated by an invalidated TLB
   entry. The actual invalidation of TLB entries is unaffected.

2. The existing workaround is applied to both broadcast and local TLB
   invalidation, whereas for all relevant errata it is only necessary to
   apply a workaround for broadcast invalidation.

3. The existing workaround replaces every TLBI with a TLBI;DSB;TLBI
   sequence, whereas for all relevant errata it is only necessary to
   execute a single additional TLBI;DSB sequence after any number of
   TLBIs are completed by a DSB.

   For example, for a sequence of batched TLBIs:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH

   ... the existing workaround will expand this to:

       TLBI <op1>[, <arg1>]
       DSB ISH                  // additional
       TLBI <op1>[, <arg1>]     // additional
       TLBI <op2>[, <arg2>]
       DSB ISH                  // additional
       TLBI <op2>[, <arg2>]     // additional
       TLBI <op3>[, <arg3>]
       DSB ISH                  // additional
       TLBI <op3>[, <arg3>]     // additional
       DSB ISH

   ... whereas it is sufficient to have:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH
       TLBI <opX>[, <argX>]     // additional
       DSB ISH                  // additional

   Using a single additional TBLI and DSB at the end of the sequence can
   have significantly lower overhead as each DSB which completes a TLBI
   must synchronize with other PEs in the system, with potential
   performance effects both locally and system-wide.

4. The existing workaround repeats each specific TLBI operation, whereas
   for all relevant errata it is sufficient for the additional TLBI to
   use *any* operation which will be broadcast, regardless of which
   translation regime or stage of translation the operation applies to.

   For example, for a single TLBI:

       TLBI ALLE2IS
       DSB ISH

   ... the existing workaround will expand this to:

       TLBI ALLE2IS
       DSB ISH
       TLBI ALLE2IS             // additional
       DSB ISH                  // additional

   ... whereas it is sufficient to have:

       TLBI ALLE2IS
       DSB ISH
       TLBI VALE1IS, XZR        // additional
       DSB ISH                  // additional

   As the additional TLBI doesn't have to match a specific earlier TLBI,
   the additional TLBI can be implemented in separate code, with no
   memory of the earlier TLBIs. The additional TLBI can also use a
   cheaper TLBI operation.

5. The existing workaround is applied to both Stage-1 and Stage-2 TLB
   invalidation, whereas for all relevant errata it is only necessary to
   apply a workaround for Stage-1 invalidation.

   Architecturally, TLBI operations which invalidate only Stage-2
   information (e.g. IPAS2E1IS) are not required to invalidate TLB
   entries which combine information from Stage-1 and Stage-2
   translation table entries, and consequently may not complete memory
   accesses translated by those combined entries. In these cases,
   completion of memory accesses is only guaranteed after subsequent
   invalidation of Stage-1 information (e.g. VMALLE1IS).

Taking the above points into account, this patch reworks the workaround
logic to reduce overhead:

* New __tlbi_sync_s1ish() and __tlbi_sync_s1ish_hyp() functions are
  added and used in place of any dsb(ish) which is used to complete
  broadcast Stage-1 TLB maintenance. When the
  ARM64_WORKAROUND_REPEAT_TLBI workaround is enabled, these helpers will
  execute an additional TLBI;DSB sequence.

  For consistency, it might make sense to add __tlbi_sync_*() helpers
  for local and stage 2 maintenance. For now I've left those with
  open-coded dsb() to keep the diff small.

* The duplication of TLBIs in __TLBI_0() and __TLBI_1() is removed. This
  is no longer needed as the necessary synchronization will happen in
  __tlbi_sync_s1ish() or __tlbi_sync_s1ish_hyp().

* The additional TLBI operation is chosen to have minimal impact:

  - __tlbi_sync_s1ish() uses "TLBI VALE1IS, XZR". This is only used at
    EL1 or at EL2 with {E2H,TGE}=={1,1}, where it will target an unused
    entry for the reserved ASID in the kernel's own translation regime,
    and have no adverse affect.

  - __tlbi_sync_s1ish_hyp() uses "TLBI VALE2IS, XZR". This is only used
    in hyp code, where it will target an unused entry in the hyp code's
    TTBR0 mapping, and should have no adverse effect.

* As __TLBI_0() and __TLBI_1() no longer replace each TLBI with a
  TLBI;DSB;TLBI sequence, batching TLBIs is worthwhile, and there's no
  need for arch_tlbbatch_should_defer() to consider
  ARM64_WORKAROUND_REPEAT_TLBI.

When building defconfig with GCC 15.1.0, compared to v6.19-rc1, this
patch saves ~1KiB of text, makes the vmlinux ~42KiB smaller, and makes
the resulting Image 64KiB smaller:

| [mark@lakrids:~/src/linux]% size vmlinux-*
|    text    data     bss     dec     hex filename
| 21179831        19660919         708216 41548966        279fca6 vmlinux-after
| 21181075        19660903         708216 41550194        27a0172 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l vmlinux-*
| -rwxr-xr-x 1 mark mark 157771472 Feb  4 12:05 vmlinux-after
| -rwxr-xr-x 1 mark mark 157815432 Feb  4 12:05 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l Image-*
| -rw-r--r-- 1 mark mark 41007616 Feb  4 12:05 Image-after
| -rw-r--r-- 1 mark mark 41073152 Feb  4 12:05 Image-before

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oupton@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 59 ++++++++++++++++++-------------
 arch/arm64/kernel/sys_compat.c    |  2 +-
 arch/arm64/kvm/hyp/nvhe/mm.c      |  2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c     |  8 ++---
 arch/arm64/kvm/hyp/pgtable.c      |  2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c      | 10 +++---
 6 files changed, 47 insertions(+), 36 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bf1cc9949dc8..1416e652612b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -31,18 +31,10 @@
  */
 #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op "\n"				       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op,	       \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op ", %x0\n"			       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %x0",    \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
@@ -181,6 +173,34 @@ static inline unsigned long get_trans_granule(void)
 		(__pages >> (5 * (scale) + 1)) - 1;			\
 	})
 
+#define __repeat_tlbi_sync(op, arg...)						\
+do {										\
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+		break;								\
+	__tlbi(op, ##arg);							\
+	dsb(ish);								\
+} while (0)
+
+/*
+ * Complete broadcast TLB maintenance issued by the host which invalidates
+ * stage 1 information in the host's own translation regime.
+ */
+static inline void __tlbi_sync_s1ish(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+}
+
+/*
+ * Complete broadcast TLB maintenance issued by hyp code which invalidates
+ * stage 1 translation information in any translation regime.
+ */
+static inline void __tlbi_sync_s1ish_hyp(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale2is, 0);
+}
+
 /*
  *	TLB Invalidation
  *	================
@@ -279,7 +299,7 @@ static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -291,7 +311,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	asid = __TLBI_VADDR(0, ASID(mm));
 	__tlbi(aside1is, asid);
 	__tlbi_user(aside1is, asid);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
@@ -345,20 +365,11 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
 	flush_tlb_page_nosync(vma, uaddr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-	/*
-	 * TLB flush deferral is not required on systems which are affected by
-	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
-	 * will have two consecutive TLBI instructions with a dsb(ish) in between
-	 * defeating the purpose (i.e save overall 'dsb ish' cost).
-	 */
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
-		return false;
-
 	return true;
 }
 
@@ -374,7 +385,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
  */
 static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 /*
@@ -509,7 +520,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 {
 	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
 				 last_level, tlb_level);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline void local_flush_tlb_contpte(struct vm_area_struct *vma,
@@ -557,7 +568,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	dsb(ishst);
 	__flush_tlb_range_op(vaale1is, start, pages, stride, 0,
 			     TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -571,7 +582,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 4a609e9b65de..b9d4998c97ef 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -37,7 +37,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 			 * We pick the reserved-ASID to minimise the impact.
 			 */
 			__tlbi(aside1is, __TLBI_VADDR(0, 0));
-			dsb(ish);
+			__tlbi_sync_s1ish();
 		}
 
 		ret = caches_clean_inval_user_pou(start, start + chunk);
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index ae8391baebc3..218976287d3f 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -271,7 +271,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 */
 	dsb(ishst);
 	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 48da9ca9763f..3dc1ce0d27fe 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -226,7 +226,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -240,7 +240,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt, false);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -266,5 +266,5 @@ void __kvm_flush_vm_context(void)
 	/* Same remark as in enter_vmid_context() */
 	dsb(ish);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0e4ddd28ef5d..9b480f947da2 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -501,7 +501,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 		*unmapped += granule;
 	}
 
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 	mm_ops->put_page(ctx->ptep);
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index ec2569818629..35855dadfb1b 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -115,7 +115,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -176,7 +176,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -192,7 +192,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -217,7 +217,7 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
 
 /*
@@ -358,7 +358,7 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	default:
 		ret = -EINVAL;
 	}
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	if (mmu)

From 468711a40d5dfc01bf0a24c1981246a2c93ac405 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 10 Feb 2026 19:12:25 +0100
Subject: [PATCH 0431/1303] PCI: dwc: ep: Refresh MSI Message Address cache on
 change

Endpoint drivers use dw_pcie_ep_raise_msi_irq() to raise MSI interrupts to
the host.  After 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU
mapping"), dw_pcie_ep_raise_msi_irq() caches the Message Address from the
MSI Capability in ep->msi_msg_addr.  But that Message Address is controlled
by the host, and it may change.  For example, if:

  - firmware on the host configures the Message Address and triggers an
    MSI,

  - a driver on the Endpoint raises the MSI via dw_pcie_ep_raise_msi_irq(),
    which caches the Message Address,

  - a kernel on the host reconfigures the Message Address and the host
    kernel driver triggers another MSI,

dw_pcie_ep_raise_msi_irq() notices that the Message Address no longer
matches the cached ep->msi_msg_addr, warns about it, and returns error
instead of raising the MSI.  The host kernel may hang because it never
receives the MSI.

This was seen with the nvmet_pci_epf_driver: the host UEFI performs NVMe
commands, e.g. Identify Controller to get the name of the controller,
nvmet-pci-epf posts the completion queue entry and raises an IRQ using
dw_pcie_ep_raise_msi_irq().  When the host boots Linux, we see a
WARN_ON_ONCE() from dw_pcie_ep_raise_msi_irq(), and the host kernel hangs
because the nvme driver never gets an IRQ.

Remove the warning when dw_pcie_ep_raise_msi_irq() notices that Message
Address has changed, remap using the new address, and update the
ep->msi_msg_addr cache.

Fixes: 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Koichiro Den <den@valinux.co.jp>
Acked-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20260210181225.3926165-2-cassel@kernel.org
---
 .../pci/controller/dwc/pcie-designware-ep.c   | 22 +++++++++++--------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 295076cf70de..35d8fc5e1d20 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -905,6 +905,19 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	 * supported, so we avoid reprogramming the region on every MSI,
 	 * specifically unmapping immediately after writel().
 	 */
+	if (ep->msi_iatu_mapped && (ep->msi_msg_addr != msg_addr ||
+				    ep->msi_map_size != map_size)) {
+		/*
+		 * The host changed the MSI target address or the required
+		 * mapping size changed. Reprogramming the iATU when there are
+		 * operations in flight is unsafe on this controller. However,
+		 * there is no unified way to check if we have operations in
+		 * flight, thus we don't know if we should WARN() or not.
+		 */
+		dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
+		ep->msi_iatu_mapped = false;
+	}
+
 	if (!ep->msi_iatu_mapped) {
 		ret = dw_pcie_ep_map_addr(epc, func_no, 0,
 					  ep->msi_mem_phys, msg_addr,
@@ -915,15 +928,6 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 		ep->msi_iatu_mapped = true;
 		ep->msi_msg_addr = msg_addr;
 		ep->msi_map_size = map_size;
-	} else if (WARN_ON_ONCE(ep->msi_msg_addr != msg_addr ||
-				ep->msi_map_size != map_size)) {
-		/*
-		 * The host changed the MSI target address or the required
-		 * mapping size changed. Reprogramming the iATU at runtime is
-		 * unsafe on this controller, so bail out instead of trying to
-		 * update the existing region.
-		 */
-		return -EINVAL;
 	}
 
 	writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset);

From c22533c66ccae10511ad6a7afc34bb26c47577e3 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Wed, 11 Feb 2026 18:55:41 +0100
Subject: [PATCH 0432/1303] PCI: dwc: ep: Flush MSI-X write before unmapping
 its ATU entry

Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X
interrupt to the host using a writel(), which generates a PCI posted write
transaction.  There's no completion for posted writes, so the writel() may
return before the PCI write completes.  dw_pcie_ep_raise_msix_irq() also
unmaps the outbound ATU entry used for the PCI write, so the write races
with the unmap.

If the PCI write loses the race with the ATU unmap, the write may corrupt
host memory or cause IOMMU errors, e.g., these when running fio with a
larger queue depth against nvmet-pci-epf:

  arm-smmu-v3 fc900000.iommu:      0x0000010000000010
  arm-smmu-v3 fc900000.iommu:      0x0000020000000000
  arm-smmu-v3 fc900000.iommu:      0x000000090000f040
  arm-smmu-v3 fc900000.iommu:      0x0000000000000000
  arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0
  arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0

Flush the write by performing a readl() of the same address to ensure that
the write has reached the destination before the ATU entry is unmapped.

The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit
8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there
it was solved by dedicating an outbound iATU only for MSI. We can't do the
same for MSI-X because each vector can have a different msg_addr and the
msg_addr may be changed while the vector is masked.

Fixes: beb4641a787d ("PCI: dwc: Add MSI-X callbacks handler")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260211175540.105677-2-cassel@kernel.org
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 35d8fc5e1d20..c57ae4d6c5c0 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -1014,6 +1014,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	writel(msg_data, ep->msi_mem + offset);
 
+	/* flush posted write before unmap */
+	readl(ep->msi_mem + offset);
+
 	dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
 
 	return 0;

From 75c151ceaacf5ca8f2f34ebf863d88002fb12587 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 25 Feb 2026 12:47:52 -0800
Subject: [PATCH 0433/1303] accel/amdxdna: Use a different name for latest
 firmware

Using legacy driver with latest firmware causes a power off issue.

Fix this by assigning a different filename (npu_7.sbin) to the latest
firmware. The driver attempts to load the latest firmware first and falls
back to the previous firmware version if loading fails.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5009
Fixes: f1eac46fe5f7 ("accel/amdxdna: Update firmware version check for latest firmware")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260225204752.2711734-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_pci.c        | 20 +++++++++++++++++++-
 drivers/accel/amdxdna/amdxdna_pci_drv.c |  3 +++
 drivers/accel/amdxdna/npu1_regs.c       |  2 +-
 drivers/accel/amdxdna/npu4_regs.c       |  2 +-
 drivers/accel/amdxdna/npu5_regs.c       |  2 +-
 drivers/accel/amdxdna/npu6_regs.c       |  2 +-
 6 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 4b3e6bb97bd2..85079b6fc5d9 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -32,6 +32,11 @@ static int aie2_max_col = XRS_MAX_COL;
 module_param(aie2_max_col, uint, 0600);
 MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used");
 
+static char *npu_fw[] = {
+	"npu_7.sbin",
+	"npu.sbin"
+};
+
 /*
  * The management mailbox channel is allocated by firmware.
  * The related register and ring buffer information is on SRAM BAR.
@@ -489,6 +494,7 @@ static int aie2_init(struct amdxdna_dev *xdna)
 	struct psp_config psp_conf;
 	const struct firmware *fw;
 	unsigned long bars = 0;
+	char *fw_full_path;
 	int i, nvec, ret;
 
 	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
@@ -503,7 +509,19 @@ static int aie2_init(struct amdxdna_dev *xdna)
 	ndev->priv = xdna->dev_info->dev_priv;
 	ndev->xdna = xdna;
 
-	ret = request_firmware(&fw, ndev->priv->fw_path, &pdev->dev);
+	for (i = 0; i < ARRAY_SIZE(npu_fw); i++) {
+		fw_full_path = kasprintf(GFP_KERNEL, "%s%s", ndev->priv->fw_path, npu_fw[i]);
+		if (!fw_full_path)
+			return -ENOMEM;
+
+		ret = firmware_request_nowarn(&fw, fw_full_path, &pdev->dev);
+		kfree(fw_full_path);
+		if (!ret) {
+			XDNA_INFO(xdna, "Load firmware %s%s", ndev->priv->fw_path, npu_fw[i]);
+			break;
+		}
+	}
+
 	if (ret) {
 		XDNA_ERR(xdna, "failed to request_firmware %s, ret %d",
 			 ndev->priv->fw_path, ret);
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 4ada45d06fcf..a4384593bdcc 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -23,6 +23,9 @@ MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin");
 MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin");
 MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin");
 MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin");
+MODULE_FIRMWARE("amdnpu/1502_00/npu_7.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_10/npu_7.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_11/npu_7.sbin");
 
 /*
  * 0.0: Initial version
diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c
index 6f36a27b5a02..6e3d3ca69c04 100644
--- a/drivers/accel/amdxdna/npu1_regs.c
+++ b/drivers/accel/amdxdna/npu1_regs.c
@@ -72,7 +72,7 @@ static const struct aie2_fw_feature_tbl npu1_fw_feature_table[] = {
 };
 
 static const struct amdxdna_dev_priv npu1_dev_priv = {
-	.fw_path        = "amdnpu/1502_00/npu.sbin",
+	.fw_path        = "amdnpu/1502_00/",
 	.rt_config	= npu1_default_rt_cfg,
 	.dpm_clk_tbl	= npu1_dpm_clk_table,
 	.fw_feature_tbl = npu1_fw_feature_table,
diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c
index a8d6f76dde5f..ce25eef5fc34 100644
--- a/drivers/accel/amdxdna/npu4_regs.c
+++ b/drivers/accel/amdxdna/npu4_regs.c
@@ -98,7 +98,7 @@ const struct aie2_fw_feature_tbl npu4_fw_feature_table[] = {
 };
 
 static const struct amdxdna_dev_priv npu4_dev_priv = {
-	.fw_path        = "amdnpu/17f0_10/npu.sbin",
+	.fw_path        = "amdnpu/17f0_10/",
 	.rt_config	= npu4_default_rt_cfg,
 	.dpm_clk_tbl	= npu4_dpm_clk_table,
 	.fw_feature_tbl = npu4_fw_feature_table,
diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c
index c0a35cfd886c..c0ac5daf32ee 100644
--- a/drivers/accel/amdxdna/npu5_regs.c
+++ b/drivers/accel/amdxdna/npu5_regs.c
@@ -63,7 +63,7 @@
 #define NPU5_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
 
 static const struct amdxdna_dev_priv npu5_dev_priv = {
-	.fw_path        = "amdnpu/17f0_11/npu.sbin",
+	.fw_path        = "amdnpu/17f0_11/",
 	.rt_config	= npu4_default_rt_cfg,
 	.dpm_clk_tbl	= npu4_dpm_clk_table,
 	.fw_feature_tbl = npu4_fw_feature_table,
diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c
index 1fb07df99186..ce591ed0d483 100644
--- a/drivers/accel/amdxdna/npu6_regs.c
+++ b/drivers/accel/amdxdna/npu6_regs.c
@@ -63,7 +63,7 @@
 #define NPU6_SRAM_BAR_BASE	MMNPU_APERTURE1_BASE
 
 static const struct amdxdna_dev_priv npu6_dev_priv = {
-	.fw_path        = "amdnpu/17f0_10/npu.sbin",
+	.fw_path        = "amdnpu/17f0_10/",
 	.rt_config	= npu4_default_rt_cfg,
 	.dpm_clk_tbl	= npu4_dpm_clk_table,
 	.fw_feature_tbl = npu4_fw_feature_table,

From 49abfa812617a7f2d0132c70d23ac98b389c6ec1 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:30 +0000
Subject: [PATCH 0434/1303] drm/amdgpu/userq: Fix reference leak in
 amdgpu_userq_wait_ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop reference to syncobj and timeline fence when aborting the ioctl due
output array being too small.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: a292fdecd728 ("drm/amdgpu: Implement userqueue signal/wait IOCTL")
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 68951e9c3e6bb22396bc42ef2359751c8315dd27)
Cc: <stable@vger.kernel.org> # v6.16+
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 8013260e29dc..9b9947b94b89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -876,6 +876,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 				dma_fence_unwrap_for_each(f, &iter, fence) {
 					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
 						r = -EINVAL;
+						dma_fence_put(fence);
 						goto free_fences;
 					}
 
@@ -900,6 +901,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
 				r = -EINVAL;
+				dma_fence_put(fence);
 				goto free_fences;
 			}
 

From 7b7d7693a55d606d700beb9549c9f7f0e5d9c24f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:31 +0000
Subject: [PATCH 0435/1303] drm/amdgpu/userq: Do not allow userspace to
 trivially triger kernel warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userspace can either deliberately pass in the too small num_fences, or the
required number can legitimately grow between the two calls to the userq
wait ioctl. In both cases we do not want the emit the kernel warning
backtrace since nothing is wrong with the kernel and userspace will simply
get an errno reported back. So lets simply drop the WARN_ONs.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: a292fdecd728 ("drm/amdgpu: Implement userqueue signal/wait IOCTL")
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2c333ea579de6cc20ea7bc50e9595ef72863e65c)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 9b9947b94b89..d972dc46f5a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -833,7 +833,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_read[i]->resv,
 						DMA_RESV_USAGE_READ, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -850,7 +850,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_write[i]->resv,
 						DMA_RESV_USAGE_WRITE, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -874,7 +874,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 					goto free_fences;
 
 				dma_fence_unwrap_for_each(f, &iter, fence) {
-					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+					if (num_fences >= wait_info->num_fences) {
 						r = -EINVAL;
 						dma_fence_put(fence);
 						goto free_fences;
@@ -899,7 +899,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			if (r)
 				goto free_fences;
 
-			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+			if (num_fences >= wait_info->num_fences) {
 				r = -EINVAL;
 				dma_fence_put(fence);
 				goto free_fences;

From ea78f8c68f4f6211c557df49174c54d167821962 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Fri, 20 Feb 2026 13:47:58 +0530
Subject: [PATCH 0436/1303] drm/amdgpu: add upper bound check on user inputs in
 signal ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Huge input values in amdgpu_userq_signal_ioctl can lead to a OOM and
could be exploited.

So check these input value against AMDGPU_USERQ_MAX_HANDLES
which is big enough value for genuine use cases and could
potentially avoid OOM.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit be267e15f99bc97cbe202cd556717797cdcf79a5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index d972dc46f5a8..c5f5af20af75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -35,6 +35,8 @@
 static const struct dma_fence_ops amdgpu_userq_fence_ops;
 static struct kmem_cache *amdgpu_userq_fence_slab;
 
+#define AMDGPU_USERQ_MAX_HANDLES	(1U << 16)
+
 int amdgpu_userq_fence_slab_init(void)
 {
 	amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence",
@@ -478,6 +480,11 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (args->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_syncobj_handles = args->num_syncobj_handles;
 	syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles),
 				      size_mul(sizeof(u32), num_syncobj_handles));

From 64ac7c09fc44985ec9bb6a9db740899fa40ca613 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Tue, 24 Feb 2026 12:13:09 +0530
Subject: [PATCH 0437/1303] drm/amdgpu: add upper bound check on user inputs in
 wait ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Huge input values in amdgpu_userq_wait_ioctl can lead to a OOM and
could be exploited.

So check these input value against AMDGPU_USERQ_MAX_HANDLES
which is big enough value for genuine use cases and could
potentially avoid OOM.

v2: squash in Srini's fix

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fcec012c664247531aed3e662f4280ff804d1476)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index c5f5af20af75..7e9cf1868cc9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -671,6 +671,11 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (wait_info->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_read_bo_handles = wait_info->num_bo_read_handles;
 	bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles),
 				      size_mul(sizeof(u32), num_read_bo_handles));

From 28dfe4317541e57fe52f9a290394cd29c348228b Mon Sep 17 00:00:00 2001
From: Natalie Vock <natalie.vock@gmx.de>
Date: Mon, 23 Feb 2026 12:45:37 +0100
Subject: [PATCH 0438/1303] drm/amd/display: Use GFP_ATOMIC in
 dc_create_stream_for_sink

This can be called while preemption is disabled, for example by
dcn32_internal_validate_bw which is called with the FPU active.

Fixes "BUG: scheduling while atomic" messages I encounter on my Navi31
machine.

Signed-off-by: Natalie Vock <natalie.vock@gmx.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b42dae2ebc5c84a68de63ec4ffdfec49362d53f1)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 246893d80f1f..baf820e6eae8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -170,11 +170,11 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (sink == NULL)
 		goto fail;
 
-	stream = kzalloc_obj(struct dc_stream_state);
+	stream = kzalloc_obj(struct dc_stream_state, GFP_ATOMIC);
 	if (stream == NULL)
 		goto fail;
 
-	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_KERNEL);
+	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_ATOMIC);
 	if (stream->update_scratch == NULL)
 		goto fail;
 

From 5e0bcc7b88bcd081aaae6f481b10d9ab294fcb69 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:07 -0800
Subject: [PATCH 0439/1303] drm/amdgpu: Unlock a mutex before destroying it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Mutexes must be unlocked before these are destroyed. This has been detected
by the Clang thread-safety analyzer.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Yang Wang <kevinyang.wang@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Fixes: f5e4cc8461c4 ("drm/amdgpu: implement RAS ACA driver framework")
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 270258ba320beb99648dceffb67e86ac76786e55)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index afe5ca81beec..db7858fe0c3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -641,6 +641,7 @@ static void aca_error_fini(struct aca_error *aerr)
 		aca_bank_error_remove(aerr, bank_error);
 
 out_unlock:
+	mutex_unlock(&aerr->lock);
 	mutex_destroy(&aerr->lock);
 }
 

From 480ad5f6ead4a47b969aab6618573cd6822bb6a4 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 13:50:23 -0800
Subject: [PATCH 0440/1303] drm/amdgpu: Fix locking bugs in error paths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Do not unlock psp->ras_context.mutex if it has not been locked. This has
been detected by the Clang thread-safety analyzer.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: YiPeng Chai <YiPeng.Chai@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Fixes: b3fb79cda568 ("drm/amdgpu: add mutex to protect ras shared memory")
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6fa01b4335978051d2cd80841728fd63cc597970)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 6e8aad91bcd3..0d3c18f04ac3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -332,13 +332,13 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	if (!context || !context->initialized) {
 		dev_err(adev->dev, "TA is not initialized\n");
 		ret = -EINVAL;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	if (!psp->ta_funcs || !psp->ta_funcs->fn_ta_invoke) {
 		dev_err(adev->dev, "Unsupported function to invoke TA\n");
 		ret = -EOPNOTSUPP;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	context->session_id = ta_id;
@@ -346,7 +346,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
-		goto err_free_shared_buf;
+		goto unlock;
 
 	ret = psp_fn_ta_invoke(psp, cmd_id);
 	if (ret || context->resp_status) {
@@ -354,15 +354,17 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 			ret, context->resp_status);
 		if (!ret) {
 			ret = -EINVAL;
-			goto err_free_shared_buf;
+			goto unlock;
 		}
 	}
 
 	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
-err_free_shared_buf:
+unlock:
 	mutex_unlock(&psp->ras_context.mutex);
+
+free_shared_buf:
 	kfree(shared_buf);
 
 	return ret;

From a5fe1a54513196e4bc8f9170006057dc31e7155e Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Sat, 21 Feb 2026 10:03:32 +0530
Subject: [PATCH 0441/1303] drm/amdgpu/vcn5: Add SMU dpm interface type

This will set AMDGPU_VCN_SMU_DPM_INTERFACE_* smu_type
based on soc type and fixing ring timeout issue seen
for DPM enabled case.

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f0f23c315b38c55e8ce9484cf59b65811f350630)
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 0202df5db1e1..6109124f852e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -174,6 +174,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
 		fw_shared->sq.is_enabled = 1;
 
+		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG);
+		fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ?
+			AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU;
+
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 

From b57c4ec98c17789136a4db948aec6daadceb5024 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Tue, 24 Feb 2026 10:18:51 +0530
Subject: [PATCH 0442/1303] drm/amdgpu: Fix error handling in slot reset

If the device has not recovered after slot reset is called, it goes to
out label for error handling. There it could make decision based on
uninitialized hive pointer and could result in accessing an uninitialized
list.

Initialize the list and hive properly so that it handles the error
situation and also releases the reset domain lock which is acquired
during error_detected callback.

Fixes: 732c6cefc1ec ("drm/amdgpu: Replace tmp_adev with hive in amdgpu_pci_slot_reset")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bb71362182e59caa227e4192da5a612b09349696)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d9789e0b5201..3e19b51a2763 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -7059,6 +7059,15 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
+	INIT_LIST_HEAD(&device_list);
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		mutex_lock(&hive->hive_lock);
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
+			list_add_tail(&tmp_adev->reset_list, &device_list);
+	} else {
+		list_add_tail(&adev->reset_list, &device_list);
+	}
 
 	if (adev->pcie_reset_ctx.swus)
 		link_dev = adev->pcie_reset_ctx.swus;
@@ -7099,19 +7108,13 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);
-	INIT_LIST_HEAD(&device_list);
 
-	hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
-		mutex_lock(&hive->hive_lock);
 		reset_context.hive = hive;
-		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			tmp_adev->pcie_reset_ctx.in_link_reset = true;
-			list_add_tail(&tmp_adev->reset_list, &device_list);
-		}
 	} else {
 		set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
-		list_add_tail(&adev->reset_list, &device_list);
 	}
 
 	r = amdgpu_device_asic_reset(adev, &device_list, &reset_context);

From 6b0d812971370c64b837a2db4275410f478272fe Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 25 Feb 2026 10:51:16 -0600
Subject: [PATCH 0443/1303] drm/amd: Disable MES LR compute W/A

A workaround was introduced in commit 1fb710793ce2 ("drm/amdgpu: Enable
MES lr_compute_wa by default") to help with some hangs observed in gfx1151.

This WA didn't fully fix the issue.  It was actually fixed by adjusting
the VGPR size to the correct value that matched the hardware in commit
b42f3bf9536c ("drm/amdkfd: bump minimum vgpr size for gfx1151").

There are reports of instability on other products with newer GC microcode
versions, and I believe they're caused by this workaround. As we don't
need the workaround any more, remove it.

Fixes: b42f3bf9536c ("drm/amdkfd: bump minimum vgpr size for gfx1151")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9973e64bd6ee7642860a6f3b6958cbf14e89cabd)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 5 -----
 2 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 09ebb13ca5e8..a926a330700e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -720,11 +720,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(mes->adev->dev,
-			      "MES FW version must be >= 0x7f to enable LR compute workaround.\n");
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b1c864dc79a8..5bfa5d1d0b36 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -779,11 +779,6 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(adev->dev,
-			      "MES FW version must be >= 0x82 to enable LR compute workaround.\n");
 
 	/*
 	 * Keep oversubscribe timer for sdma . When we have unmapped doorbell

From 2a064262eb378263792cf1fb044de631ac41bcc5 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Wed, 25 Feb 2026 21:15:23 +0000
Subject: [PATCH 0444/1303] sched_ext: Fix out-of-bounds access in
 scx_idle_init_masks()

scx_idle_node_masks is allocated with num_possible_nodes() elements but
indexed by NUMA node IDs via for_each_node(). On systems with
non-contiguous NUMA node numbering (e.g. nodes 0 and 4), node IDs can
exceed the array size, causing out-of-bounds memory corruption.

Use nr_node_ids instead, which represents the maximum node ID range and
is the correct size for arrays indexed by node ID.

Fixes: 7c60329e3521 ("sched_ext: Add NUMA-awareness to the default idle selection policy")
Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_idle.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 3d9d404d5cd2..e2da6c3968a6 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -663,8 +663,8 @@ void scx_idle_init_masks(void)
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL));
 
-	/* Allocate per-node idle cpumasks */
-	scx_idle_node_masks = kcalloc(num_possible_nodes(),
+	/* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */
+	scx_idle_node_masks = kcalloc(nr_node_ids,
 				      sizeof(*scx_idle_node_masks), GFP_KERNEL);
 	BUG_ON(!scx_idle_node_masks);
 

From 12133a483dfa832241fbbf09321109a0ea8a520e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 12:28:30 +0100
Subject: [PATCH 0445/1303] nfc: pn533: properly drop the usb interface
 reference on disconnect

When the device is disconnected from the driver, there is a "dangling"
reference count on the usb interface that was grabbed in the probe
callback.  Fix this up by properly dropping the reference after we are
done with it.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: c46ee38620a2 ("NFC: pn533: add NXP pn533 nfc device driver")
Link: https://patch.msgid.link/2026022329-flashing-ought-7573@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/pn533/usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 018a80674f06..0f12f86ebb02 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -628,6 +628,7 @@ static void pn533_usb_disconnect(struct usb_interface *interface)
 	usb_free_urb(phy->out_urb);
 	usb_free_urb(phy->ack_urb);
 	kfree(phy->ack_buffer);
+	usb_put_dev(phy->udev);
 
 	nfc_info(&interface->dev, "NXP PN533 NFC device disconnected\n");
 }

From 11de1d3ae5565ed22ef1f89d73d8f2d00322c699 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:58:48 +0100
Subject: [PATCH 0446/1303] net: usb: pegasus: validate USB endpoints

The pegasus driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: Petko Manolov <petkan@nucleusys.com>
Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022347-legibly-attest-cc5c@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/pegasus.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index b84968c5f074..c497202b78e8 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -812,8 +812,19 @@ static void unlink_all_urbs(pegasus_t *pegasus)
 
 static int alloc_urbs(pegasus_t *pegasus)
 {
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 	int res = -ENOMEM;
 
+	if (!usb_check_bulk_endpoints(pegasus->intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(pegasus->intf, int_ep_addr))
+		return -ENODEV;
+
 	pegasus->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!pegasus->rx_urb) {
 		return res;
@@ -1168,6 +1179,7 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	pegasus = netdev_priv(net);
 	pegasus->dev_index = dev_index;
+	pegasus->intf = intf;
 
 	res = alloc_urbs(pegasus);
 	if (res < 0) {
@@ -1179,7 +1191,6 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	INIT_DELAYED_WORK(&pegasus->carrier_check, check_carrier);
 
-	pegasus->intf = intf;
 	pegasus->usb = dev;
 	pegasus->net = net;
 

From c58b6c29a4c9b8125e8ad3bca0637e00b71e2693 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:59:26 +0100
Subject: [PATCH 0447/1303] net: usb: kalmia: validate USB endpoints

The kalmia driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: d40261236e8e ("net/usb: Add Samsung Kalmia driver for Samsung GT-B3730")
Link: https://patch.msgid.link/2026022326-shack-headstone-ef6f@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kalmia.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c
index 613fc6910f14..ee9c48f7f68f 100644
--- a/drivers/net/usb/kalmia.c
+++ b/drivers/net/usb/kalmia.c
@@ -132,11 +132,18 @@ kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	int status;
 	u8 ethernet_addr[ETH_ALEN];
+	static const u8 ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
 
 	/* Don't bind to AT command interface */
 	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
 		return -EINVAL;
 
+	if (!usb_check_bulk_endpoints(intf, ep_addr))
+		return -ENODEV;
+
 	dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK);
 	dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK);
 	dev->status = NULL;

From 4b063c002ca759d1b299988ee23f564c9609c875 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 14:00:06 +0100
Subject: [PATCH 0448/1303] net: usb: kaweth: validate USB endpoints

The kaweth driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://patch.msgid.link/2026022305-substance-virtual-c728@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kaweth.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index e01d14f6c366..cb2472b59e10 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -883,6 +883,13 @@ static int kaweth_probe(
 	const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 	int result = 0;
 	int rv = -EIO;
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 
 	dev_dbg(dev,
 		"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -896,6 +903,12 @@ static int kaweth_probe(
 		(int)udev->descriptor.bLength,
 		(int)udev->descriptor.bDescriptorType);
 
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(dev, "couldn't find required endpoints\n");
+		return -ENODEV;
+	}
+
 	netdev = alloc_etherdev(sizeof(*kaweth));
 	if (!netdev)
 		return -ENOMEM;

From 5cc619583c7e735c4fb801bede671fb6f9c79425 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 18:32:18 +0100
Subject: [PATCH 0449/1303] vsock: Use container_of() to get net namespace in
 sysctl handlers

current->nsproxy is should not be accessed directly as syzbot has found
that it could be NULL at times, causing crashes.  Fix up the af_vsock
sysctl handlers to use container_of() to deal with the current net
namespace instead of attempting to rely on current.

This is the same type of change done in commit 7f5611cbc487 ("rds:
sysctl: rds_tcp_{rcv,snd}buf: avoid using current->nsproxy")

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Fixes: eafb64f40ca4 ("vsock: add netns to vsock core")
Link: https://patch.msgid.link/2026022318-rearview-gallery-ae13@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9880756d9eff..f4062c6a1944 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2825,7 +2825,7 @@ static int vsock_net_mode_string(const struct ctl_table *table, int write,
 	if (write)
 		return -EPERM;
 
-	net = current->nsproxy->net_ns;
+	net = container_of(table->data, struct net, vsock.mode);
 
 	return __vsock_net_mode_string(table, write, buffer, lenp, ppos,
 				       vsock_net_mode(net), NULL);
@@ -2838,7 +2838,7 @@ static int vsock_net_child_mode_string(const struct ctl_table *table, int write,
 	struct net *net;
 	int ret;
 
-	net = current->nsproxy->net_ns;
+	net = container_of(table->data, struct net, vsock.child_ns_mode);
 
 	ret = __vsock_net_mode_string(table, write, buffer, lenp, ppos,
 				      vsock_net_child_mode(net), &new_mode);

From 1e3bb184e94125bae7c1703472109a646d0f79d9 Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Tue, 24 Feb 2026 09:20:12 +0100
Subject: [PATCH 0450/1303] tcp: re-enable acceptance of FIN packets when RWIN
 is 0

Commit 2bd99aef1b19 ("tcp: accept bare FIN packets under memory
pressure") allowed accepting FIN packets in tcp_data_queue() even when
the receive window was closed, to prevent ACK/FIN loops with broken
clients.

Such a FIN packet is in sequence, but because the FIN consumes a
sequence number, it extends beyond the window. Before commit
9ca48d616ed7 ("tcp: do not accept packets beyond window"),
tcp_sequence() only required the seq to be within the window. After
that change, the entire packet (including the FIN) must fit within the
window. As a result, such FIN packets are now dropped and the handling
path is no longer reached.

Be more lenient by not counting the sequence number consumed by the
FIN when calling tcp_sequence(), restoring the previous behavior for
cases where only the FIN extends beyond the window.

Fixes: 9ca48d616ed7 ("tcp: do not accept packets beyond window")
Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260224-fix_zero_wnd_fin-v2-1-a16677ea7cea@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e7b41abb82aa..1c6b8ca67918 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4858,15 +4858,24 @@ static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk,
  */
 
 static enum skb_drop_reason tcp_sequence(const struct sock *sk,
-					 u32 seq, u32 end_seq)
+					 u32 seq, u32 end_seq,
+					 const struct tcphdr *th)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
+	u32 seq_limit;
 
 	if (before(end_seq, tp->rcv_wup))
 		return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
 
-	if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) {
-		if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+	seq_limit = tp->rcv_nxt + tcp_receive_window(tp);
+	if (unlikely(after(end_seq, seq_limit))) {
+		/* Some stacks are known to handle FIN incorrectly; allow the
+		 * FIN to extend beyond the window and check it in detail later.
+		 */
+		if (!after(end_seq - th->fin, seq_limit))
+			return SKB_NOT_DROPPED_YET;
+
+		if (after(seq, seq_limit))
 			return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
 
 		/* Only accept this packet if receive queue is empty. */
@@ -6379,7 +6388,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 step1:
 	/* Step 1: check sequence number */
-	reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq,
+			      TCP_SKB_CB(skb)->end_seq, th);
 	if (reason) {
 		/* RFC793, page 37: "In all states except SYN-SENT, all reset
 		 * (RST) segments are validated by checking their SEQ-fields."

From 74511332309844c3de64970841b3c250d85f34ce Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Tue, 24 Feb 2026 09:20:13 +0100
Subject: [PATCH 0451/1303] selftests/net: packetdrill: Verify acceptance of
 FIN packets when RWIN is 0

Add a packetdrill test that verifies we accept bare FIN packets when
the advertised receive window is zero.

Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260224-fix_zero_wnd_fin-v2-2-a16677ea7cea@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_zero_wnd_fin.pkt  | 27 +++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
new file mode 100644
index 000000000000..e245359a1a91
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Some TCP stacks send FINs even though the window is closed. We break
+// a possible FIN/ACK loop by accepting the FIN.
+
+--mss=1000
+
+`./defaults.sh`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 < P. 1:60001(60000) ack 1 win 257
+    * > .  1:1(0) ack 60001 win 0
+
+   +0 < F. 60001:60001(0) ack 1 win 257
+   +0 > . 1:1(0) ack 60002 win 0

From 676c7af91fcd740d34e7cb788cbc58e3bcafde39 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 19:04:04 +0800
Subject: [PATCH 0452/1303] dpll: zl3073x: Remove redundant cleanup in
 devm_dpll_init()

The devm_add_action_or_reset() function already executes the cleanup
action on failure before returning an error, so the explicit goto error
and subsequent zl3073x_dev_dpll_fini() call causes double cleanup.

Fixes: ebb1031c5137 ("dpll: zl3073x: Refactor DPLL initialization")
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-dpll-v2-1-d7786414a830@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/zl3073x/core.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c
index 8c5ee28e02f4..37f3c33570ee 100644
--- a/drivers/dpll/zl3073x/core.c
+++ b/drivers/dpll/zl3073x/core.c
@@ -981,11 +981,7 @@ zl3073x_devm_dpll_init(struct zl3073x_dev *zldev, u8 num_dplls)
 	}
 
 	/* Add devres action to release DPLL related resources */
-	rc = devm_add_action_or_reset(zldev->dev, zl3073x_dev_dpll_fini, zldev);
-	if (rc)
-		goto error;
-
-	return 0;
+	return devm_add_action_or_reset(zldev->dev, zl3073x_dev_dpll_fini, zldev);
 
 error:
 	zl3073x_dev_dpll_fini(zldev);

From 916864e5eda0c52572b11b4cacce41b89622cc35 Mon Sep 17 00:00:00 2001
From: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Date: Tue, 24 Feb 2026 17:58:47 +0530
Subject: [PATCH 0453/1303] MAINTAINERS: Update maintainer entry for QUALCOMM
 ETHQOS ETHERNET DRIVER

Replace Vinod Koul with Mohd Ayaan Anwar as the maintainer of the
QUALCOMM ETHQOS ETHERNET DRIVER. Vinod confirmed he is no longer
active in this area and agreed to be removed.

Acked-by: Vinod Koul <vkoul@kernel.org>
Suggested-by: Russell King (Oracle) <linux@armlinux.org.uk>
Signed-off-by: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20260224-qcom_ethqos_maintainer-v1-1-24e02701ea52@oss.qualcomm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index cf0313ca6039..a461baa96483 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21692,7 +21692,7 @@ S:	Maintained
 F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
-M:	Vinod Koul <vkoul@kernel.org>
+M:	Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained

From f975a0955276579e2176a134366ed586071c7c6a Mon Sep 17 00:00:00 2001
From: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Date: Tue, 24 Feb 2026 04:38:36 -0800
Subject: [PATCH 0454/1303] net: mana: Fix double destroy_workqueue on service
 rescan PCI path

While testing corner cases in the driver, a use-after-free crash
was found on the service rescan PCI path.

When mana_serv_reset() calls mana_gd_suspend(), mana_gd_cleanup()
destroys gc->service_wq. If the subsequent mana_gd_resume() fails
with -ETIMEDOUT or -EPROTO, the code falls through to
mana_serv_rescan() which triggers pci_stop_and_remove_bus_device().
This invokes the PCI .remove callback (mana_gd_remove), which calls
mana_gd_cleanup() a second time, attempting to destroy the already-
freed workqueue. Fix this by NULL-checking gc->service_wq in
mana_gd_cleanup() and setting it to NULL after destruction.

Call stack of issue for reference:
[Sat Feb 21 18:53:48 2026] Call Trace:
[Sat Feb 21 18:53:48 2026]  <TASK>
[Sat Feb 21 18:53:48 2026]  mana_gd_cleanup+0x33/0x70 [mana]
[Sat Feb 21 18:53:48 2026]  mana_gd_remove+0x3a/0xc0 [mana]
[Sat Feb 21 18:53:48 2026]  pci_device_remove+0x41/0xb0
[Sat Feb 21 18:53:48 2026]  device_remove+0x46/0x70
[Sat Feb 21 18:53:48 2026]  device_release_driver_internal+0x1e3/0x250
[Sat Feb 21 18:53:48 2026]  device_release_driver+0x12/0x20
[Sat Feb 21 18:53:48 2026]  pci_stop_bus_device+0x6a/0x90
[Sat Feb 21 18:53:48 2026]  pci_stop_and_remove_bus_device+0x13/0x30
[Sat Feb 21 18:53:48 2026]  mana_do_service+0x180/0x290 [mana]
[Sat Feb 21 18:53:48 2026]  mana_serv_func+0x24/0x50 [mana]
[Sat Feb 21 18:53:48 2026]  process_one_work+0x190/0x3d0
[Sat Feb 21 18:53:48 2026]  worker_thread+0x16e/0x2e0
[Sat Feb 21 18:53:48 2026]  kthread+0xf7/0x130
[Sat Feb 21 18:53:48 2026]  ? __pfx_worker_thread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ? __pfx_kthread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ret_from_fork+0x269/0x350
[Sat Feb 21 18:53:48 2026]  ? __pfx_kthread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ret_from_fork_asm+0x1a/0x30
[Sat Feb 21 18:53:48 2026]  </TASK>

Fixes: 505cc26bcae0 ("net: mana: Add support for auxiliary device servicing events")
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/aZ2bzL64NagfyHpg@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 5 ++++-
 drivers/net/ethernet/microsoft/mana/mana_en.c   | 4 +++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 0055c231acf6..3926d18f1840 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1946,7 +1946,10 @@ static void mana_gd_cleanup(struct pci_dev *pdev)
 
 	mana_gd_remove_irqs(pdev);
 
-	destroy_workqueue(gc->service_wq);
+	if (gc->service_wq) {
+		destroy_workqueue(gc->service_wq);
+		gc->service_wq = NULL;
+	}
 	dev_dbg(&pdev->dev, "mana gdma cleanup successful\n");
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9b5a72ada5c4..f69e42651359 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -3762,7 +3762,9 @@ void mana_rdma_remove(struct gdma_dev *gd)
 	}
 
 	WRITE_ONCE(gd->rdma_teardown, true);
-	flush_workqueue(gc->service_wq);
+
+	if (gc->service_wq)
+		flush_workqueue(gc->service_wq);
 
 	if (gd->adev)
 		remove_adev(gd);

From bb4c698633c0e19717586a6524a33196cff01a32 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Tue, 24 Feb 2026 14:57:08 +0200
Subject: [PATCH 0455/1303] team: avoid NETDEV_CHANGEMTU event when
 unregistering slave

syzbot is reporting

  unregister_netdevice: waiting for netdevsim0 to become free. Usage count = 3
  ref_tracker: netdev@ffff88807dcf8618 has 1/2 users at
       __netdev_tracker_alloc include/linux/netdevice.h:4400 [inline]
       netdev_hold include/linux/netdevice.h:4429 [inline]
       inetdev_init+0x201/0x4e0 net/ipv4/devinet.c:286
       inetdev_event+0x251/0x1610 net/ipv4/devinet.c:1600
       notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
       call_netdevice_notifiers_mtu net/core/dev.c:2318 [inline]
       netif_set_mtu_ext+0x5aa/0x800 net/core/dev.c:9886
       netif_set_mtu+0xd7/0x1b0 net/core/dev.c:9907
       dev_set_mtu+0x126/0x260 net/core/dev_api.c:248
       team_port_del+0xb07/0xcb0 drivers/net/team/team_core.c:1333
       team_del_slave drivers/net/team/team_core.c:1936 [inline]
       team_device_event+0x207/0x5b0 drivers/net/team/team_core.c:2929
       notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
       call_netdevice_notifiers_extack net/core/dev.c:2281 [inline]
       call_netdevice_notifiers net/core/dev.c:2295 [inline]
       __dev_change_net_namespace+0xcb7/0x2050 net/core/dev.c:12592
       do_setlink+0x2ce/0x4590 net/core/rtnetlink.c:3060
       rtnl_changelink net/core/rtnetlink.c:3776 [inline]
       __rtnl_newlink net/core/rtnetlink.c:3935 [inline]
       rtnl_newlink+0x15a9/0x1be0 net/core/rtnetlink.c:4072
       rtnetlink_rcv_msg+0x7d5/0xbe0 net/core/rtnetlink.c:6958
       netlink_rcv_skb+0x232/0x4b0 net/netlink/af_netlink.c:2550
       netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
       netlink_unicast+0x80f/0x9b0 net/netlink/af_netlink.c:1344
       netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1894

problem. Ido Schimmel found steps to reproduce

  ip link add name team1 type team
  ip link add name dummy1 mtu 1499 master team1 type dummy
  ip netns add ns1
  ip link set dev dummy1 netns ns1
  ip -n ns1 link del dev dummy1

and also found that the same issue was fixed in the bond driver in
commit f51048c3e07b ("bonding: avoid NETDEV_CHANGEMTU event when
unregistering slave").

Let's do similar thing for the team driver, with commit ad7c7b2172c3 ("net:
hold netdev instance lock during sysfs operations") and commit 303a8487a657
("net: s/__dev_set_mtu/__netif_set_mtu/") also applied.

Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Suggested-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260224125709.317574-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team_core.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index c08a5c1bd6e4..a0fe998cc055 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -1292,7 +1292,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 static void __team_port_change_port_removed(struct team_port *port);
 
-static int team_port_del(struct team *team, struct net_device *port_dev)
+static int team_port_del(struct team *team, struct net_device *port_dev, bool unregister)
 {
 	struct net_device *dev = team->dev;
 	struct team_port *port;
@@ -1330,7 +1330,13 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 	__team_port_change_port_removed(port);
 
 	team_port_set_orig_dev_addr(port);
-	dev_set_mtu(port_dev, port->orig.mtu);
+	if (unregister) {
+		netdev_lock_ops(port_dev);
+		__netif_set_mtu(port_dev, port->orig.mtu);
+		netdev_unlock_ops(port_dev);
+	} else {
+		dev_set_mtu(port_dev, port->orig.mtu);
+	}
 	kfree_rcu(port, rcu);
 	netdev_info(dev, "Port device %s removed\n", portname);
 	netdev_compute_master_upper_features(team->dev, true);
@@ -1634,7 +1640,7 @@ static void team_uninit(struct net_device *dev)
 	ASSERT_RTNL();
 
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
-		team_port_del(team, port->dev);
+		team_port_del(team, port->dev, false);
 
 	__team_change_mode(team, NULL); /* cleanup */
 	__team_options_unregister(team, team_options, ARRAY_SIZE(team_options));
@@ -1933,7 +1939,16 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 
 	ASSERT_RTNL();
 
-	return team_port_del(team, port_dev);
+	return team_port_del(team, port_dev, false);
+}
+
+static int team_del_slave_on_unregister(struct net_device *dev, struct net_device *port_dev)
+{
+	struct team *team = netdev_priv(dev);
+
+	ASSERT_RTNL();
+
+	return team_port_del(team, port_dev, true);
 }
 
 static netdev_features_t team_fix_features(struct net_device *dev,
@@ -2926,7 +2941,7 @@ static int team_device_event(struct notifier_block *unused,
 					       !!netif_oper_up(port->dev));
 		break;
 	case NETDEV_UNREGISTER:
-		team_del_slave(port->team->dev, dev);
+		team_del_slave_on_unregister(port->team->dev, dev);
 		break;
 	case NETDEV_FEAT_CHANGE:
 		if (!port->team->notifier_ctx) {
@@ -2999,3 +3014,4 @@ MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
 MODULE_DESCRIPTION("Ethernet team device driver");
 MODULE_ALIAS_RTNL_LINK(DRV_NAME);
+MODULE_IMPORT_NS("NETDEV_INTERNAL");

From 58f8ef625e23a607f4a89758d6b328a2701f7354 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 24 Feb 2026 14:57:09 +0200
Subject: [PATCH 0456/1303] selftests: team: Add a reference count leak test

Add a test for the issue that was fixed in "team: avoid NETDEV_CHANGEMTU
event when unregistering slave".

The test hangs due to a reference count leak without the fix:

 # make -C tools/testing/selftests TARGETS="drivers/net/team" TEST_PROGS=refleak.sh TEST_GEN_PROGS="" run_tests
 [...]
 TAP version 13
 1..1
 # timeout set to 45
 # selftests: drivers/net/team: refleak.sh
 [   50.681299][  T496] unregister_netdevice: waiting for dummy1 to become free. Usage count = 3
 [   71.185325][  T496] unregister_netdevice: waiting for dummy1 to become free. Usage count = 3

And passes with the fix:

 # make -C tools/testing/selftests TARGETS="drivers/net/team" TEST_PROGS=refleak.sh TEST_GEN_PROGS="" run_tests
 [...]
 TAP version 13
 1..1
 # timeout set to 45
 # selftests: drivers/net/team: refleak.sh
 ok 1 selftests: drivers/net/team: refleak.sh

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260224125709.317574-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/team/Makefile |  1 +
 .../selftests/drivers/net/team/refleak.sh       | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/team/refleak.sh

diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 1340b3df9c31..45a3e7ad3dcb 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -5,6 +5,7 @@ TEST_PROGS := \
 	dev_addr_lists.sh \
 	options.sh \
 	propagation.sh \
+	refleak.sh \
 # end of TEST_PROGS
 
 TEST_INCLUDES := \
diff --git a/tools/testing/selftests/drivers/net/team/refleak.sh b/tools/testing/selftests/drivers/net/team/refleak.sh
new file mode 100755
index 000000000000..ef08213ab964
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/refleak.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/lib.sh
+
+trap cleanup_all_ns EXIT
+
+# Test that there is no reference count leak and that dummy1 can be deleted.
+# https://lore.kernel.org/netdev/4d69abe1-ca8d-4f0b-bcf8-13899b211e57@I-love.SAKURA.ne.jp/
+setup_ns ns1 ns2
+ip -n "$ns1" link add name team1 type team
+ip -n "$ns1" link add name dummy1 mtu 1499 type dummy
+ip -n "$ns1" link set dev dummy1 master team1
+ip -n "$ns1" link set dev dummy1 netns "$ns2"
+ip -n "$ns2" link del dev dummy1

From 2700b7e603af39ca55fe9fc876ca123efd44680f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:48 +0200
Subject: [PATCH 0457/1303] net/mlx5: DR, Fix circular locking dependency in
 dump

Fix a circular locking dependency between dbg_mutex and the domain
rx/tx mutexes that could lead to a deadlock.

The dump path in dr_dump_domain_all() was acquiring locks in the order:
  dbg_mutex -> rx.mutex -> tx.mutex

While the table/matcher creation paths acquire locks in the order:
  rx.mutex -> tx.mutex -> dbg_mutex

This inverted lock ordering creates a circular dependency. Fix this by
changing dr_dump_domain_all() to acquire the domain lock before
dbg_mutex, matching the order used in mlx5dr_table_create() and
mlx5dr_matcher_create().

Lockdep splat:
 ======================================================
 WARNING: possible circular locking dependency detected
 6.19.0-rc6net_next_e817c4e #1 Not tainted
 ------------------------------------------------------
 sos/30721 is trying to acquire lock:
 ffff888102df5900 (&dmn->info.rx.mutex){+.+.}-{4:4}, at:
dr_dump_start+0x131/0x450 [mlx5_core]

 but task is already holding lock:
 ffff888102df5bc0 (&dmn->dump_info.dbg_mutex){+.+.}-{4:4}, at:
dr_dump_start+0x10b/0x450 [mlx5_core]

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #2 (&dmn->dump_info.dbg_mutex){+.+.}-{4:4}:
        __mutex_lock+0x91/0x1060
        mlx5dr_matcher_create+0x377/0x5e0 [mlx5_core]
        mlx5_cmd_dr_create_flow_group+0x62/0xd0 [mlx5_core]
        mlx5_create_flow_group+0x113/0x1c0 [mlx5_core]
        mlx5_chains_create_prio+0x453/0x2290 [mlx5_core]
        mlx5_chains_get_table+0x2e2/0x980 [mlx5_core]
        esw_chains_create+0x1e6/0x3b0 [mlx5_core]
        esw_create_offloads_fdb_tables.cold+0x62/0x63f [mlx5_core]
        esw_offloads_enable+0x76f/0xd20 [mlx5_core]
        mlx5_eswitch_enable_locked+0x35a/0x500 [mlx5_core]
        mlx5_devlink_eswitch_mode_set+0x561/0x950 [mlx5_core]
        devlink_nl_eswitch_set_doit+0x67/0xe0
        genl_family_rcv_msg_doit+0xe0/0x130
        genl_rcv_msg+0x188/0x290
        netlink_rcv_skb+0x4b/0xf0
        genl_rcv+0x24/0x40
        netlink_unicast+0x1ed/0x2c0
        netlink_sendmsg+0x210/0x450
        __sock_sendmsg+0x38/0x60
        __sys_sendto+0x119/0x180
        __x64_sys_sendto+0x20/0x30
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #1 (&dmn->info.tx.mutex){+.+.}-{4:4}:
        __mutex_lock+0x91/0x1060
        mlx5dr_table_create+0x11d/0x530 [mlx5_core]
        mlx5_cmd_dr_create_flow_table+0x62/0x140 [mlx5_core]
        __mlx5_create_flow_table+0x46f/0x960 [mlx5_core]
        mlx5_create_flow_table+0x16/0x20 [mlx5_core]
        esw_create_offloads_fdb_tables+0x136/0x240 [mlx5_core]
        esw_offloads_enable+0x76f/0xd20 [mlx5_core]
        mlx5_eswitch_enable_locked+0x35a/0x500 [mlx5_core]
        mlx5_devlink_eswitch_mode_set+0x561/0x950 [mlx5_core]
        devlink_nl_eswitch_set_doit+0x67/0xe0
        genl_family_rcv_msg_doit+0xe0/0x130
        genl_rcv_msg+0x188/0x290
        netlink_rcv_skb+0x4b/0xf0
        genl_rcv+0x24/0x40
        netlink_unicast+0x1ed/0x2c0
        netlink_sendmsg+0x210/0x450
        __sock_sendmsg+0x38/0x60
        __sys_sendto+0x119/0x180
        __x64_sys_sendto+0x20/0x30
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #0 (&dmn->info.rx.mutex){+.+.}-{4:4}:
        __lock_acquire+0x18b6/0x2eb0
        lock_acquire+0xd3/0x2c0
        __mutex_lock+0x91/0x1060
        dr_dump_start+0x131/0x450 [mlx5_core]
        seq_read_iter+0xe3/0x410
        seq_read+0xfb/0x130
        full_proxy_read+0x53/0x80
        vfs_read+0xba/0x330
        ksys_read+0x65/0xe0
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&dmn->dump_info.dbg_mutex);
                                lock(&dmn->info.tx.mutex);
                                lock(&dmn->dump_info.dbg_mutex);
   lock(&dmn->info.rx.mutex);

                   *** DEADLOCK ***

Fixes: 9222f0b27da2 ("net/mlx5: DR, Add support for dumping steering info")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
index 8803fa071c50..18362e9c3314 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
@@ -1051,8 +1051,8 @@ static int dr_dump_domain_all(struct seq_file *file, struct mlx5dr_domain *dmn)
 	struct mlx5dr_table *tbl;
 	int ret;
 
-	mutex_lock(&dmn->dump_info.dbg_mutex);
 	mlx5dr_domain_lock(dmn);
+	mutex_lock(&dmn->dump_info.dbg_mutex);
 
 	ret = dr_dump_domain(file, dmn);
 	if (ret < 0)
@@ -1065,8 +1065,8 @@ static int dr_dump_domain_all(struct seq_file *file, struct mlx5dr_domain *dmn)
 	}
 
 unlock_mutex:
-	mlx5dr_domain_unlock(dmn);
 	mutex_unlock(&dmn->dump_info.dbg_mutex);
+	mlx5dr_domain_unlock(dmn);
 	return ret;
 }
 

From bd7b9f83fb9f85228c3ac9748d9cba9fab7fb5a2 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:49 +0200
Subject: [PATCH 0458/1303] net/mlx5: LAG, disable MPESW in
 lag_disable_change()

mlx5_lag_disable_change() unconditionally called mlx5_disable_lag() when
LAG was active, which is incorrect for MLX5_LAG_MODE_MPESW.
Hnece, call mlx5_disable_mpesw() when running in MPESW mode.

Fixes: a32327a3a02c ("net/mlx5: Lag, Control MultiPort E-Switch single FDB mode")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c   | 8 ++++++--
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h | 5 +++++
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 9fe47c836ebd..859f042caf79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1869,8 +1869,12 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 	mutex_lock(&ldev->lock);
 
 	ldev->mode_changes_in_progress++;
-	if (__mlx5_lag_is_active(ldev))
-		mlx5_disable_lag(ldev);
+	if (__mlx5_lag_is_active(ldev)) {
+		if (ldev->mode == MLX5_LAG_MODE_MPESW)
+			mlx5_lag_disable_mpesw(ldev);
+		else
+			mlx5_disable_lag(ldev);
+	}
 
 	mutex_unlock(&ldev->lock);
 	mlx5_devcom_comp_unlock(dev->priv.hca_devcom_comp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 04762562d7d9..a63d48d18878 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -65,7 +65,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	return err;
 }
 
-static int enable_mpesw(struct mlx5_lag *ldev)
+static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0;
 	int err;
@@ -126,7 +126,7 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	return err;
 }
 
-static void disable_mpesw(struct mlx5_lag *ldev)
+void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev)
 {
 	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
 		mlx5_mpesw_metadata_cleanup(ldev);
@@ -152,9 +152,9 @@ static void mlx5_mpesw_work(struct work_struct *work)
 	}
 
 	if (mpesww->op == MLX5_MPESW_OP_ENABLE)
-		mpesww->result = enable_mpesw(ldev);
+		mpesww->result = mlx5_lag_enable_mpesw(ldev);
 	else if (mpesww->op == MLX5_MPESW_OP_DISABLE)
-		disable_mpesw(ldev);
+		mlx5_lag_disable_mpesw(ldev);
 unlock:
 	mutex_unlock(&ldev->lock);
 	mlx5_devcom_comp_unlock(devcom);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
index f5d9b5c97b0d..b767dbb4f457 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -31,6 +31,11 @@ int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev,
 bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev);
 void mlx5_lag_mpesw_disable(struct mlx5_core_dev *dev);
 int mlx5_lag_mpesw_enable(struct mlx5_core_dev *dev);
+#ifdef CONFIG_MLX5_ESWITCH
+void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev);
+#else
+static inline void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev) {}
+#endif /* CONFIG_MLX5_ESWITCH */
 
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_mpesw_speed_update_work(struct work_struct *work);

From d7073e8b978ae925f1f0f08754f33f84d8547ea7 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:50 +0200
Subject: [PATCH 0459/1303] net/mlx5: E-switch, Clear legacy flag when moving
 to switchdev

The cited commit introduced MLX5_PRIV_FLAGS_SWITCH_LEGACY to identify
when a transition to legacy mode is requested via devlink.  However, the
logic failed to clear this flag if the mode was subsequently changed
back to MLX5_ESWITCH_OFFLOADS (switchdev).  Consequently, if a user
toggled from legacy to switchdev, the flag remained set, leaving the
driver with wrong state indicating

Fix this by explicitly clearing the MLX5_PRIV_FLAGS_SWITCH_LEGACY bit
when the requested mode is MLX5_ESWITCH_OFFLOADS.

Fixes: 2a4f56fbcc47 ("net/mlx5e: Keep netdev when leave switchdev for devlink set legacy only")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1b439cef3719..9d51d030596c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4068,6 +4068,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 
 	if (mlx5_mode == MLX5_ESWITCH_LEGACY)
 		esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS)
+		esw->dev->priv.flags &= ~MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_eswitch_disable_locked(esw);
 	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {

From 60253042c0b87b61596368489c44d12ba720d11c Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:51 +0200
Subject: [PATCH 0460/1303] net/mlx5: Fix missing devlink lock in SRIOV enable
 error path

The cited commit miss to add locking in the error path of
mlx5_sriov_enable(). When pci_enable_sriov() fails,
mlx5_device_disable_sriov() is called to clean up. This cleanup function
now expects to be called with the devlink instance lock held.

Add the missing devl_lock(devlink) and devl_unlock(devlink)

Fixes: 84a433a40d0e ("net/mlx5: Lock mlx5 devlink reload callbacks")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index a2fc937d5461..172862a70c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -193,7 +193,9 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
 		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
+		devl_lock(devlink);
 		mlx5_device_disable_sriov(dev, num_vfs, true, true);
+		devl_unlock(devlink);
 	}
 	return err;
 }

From 859380694f434597407632c29f30fdb5e763e6cc Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:52 +0200
Subject: [PATCH 0461/1303] net/mlx5e: Fix "scheduling while atomic" in IPsec
 MAC address query

Fix a "scheduling while atomic" bug in mlx5e_ipsec_init_macs() by
replacing mlx5_query_mac_address() with ether_addr_copy() to get the
local MAC address directly from netdev->dev_addr.

The issue occurs because mlx5_query_mac_address() queries the hardware
which involves mlx5_cmd_exec() that can sleep, but it is called from
the mlx5e_ipsec_handle_event workqueue which runs in atomic context.

The MAC address is already available in netdev->dev_addr, so no need
to query hardware. This avoids the sleeping call and resolves the bug.

Call trace:
  BUG: scheduling while atomic: kworker/u112:2/69344/0x00000200
  __schedule+0x7ab/0xa20
  schedule+0x1c/0xb0
  schedule_timeout+0x6e/0xf0
  __wait_for_common+0x91/0x1b0
  cmd_exec+0xa85/0xff0 [mlx5_core]
  mlx5_cmd_exec+0x1f/0x50 [mlx5_core]
  mlx5_query_nic_vport_mac_address+0x7b/0xd0 [mlx5_core]
  mlx5_query_mac_address+0x19/0x30 [mlx5_core]
  mlx5e_ipsec_init_macs+0xc1/0x720 [mlx5_core]
  mlx5e_ipsec_build_accel_xfrm_attrs+0x422/0x670 [mlx5_core]
  mlx5e_ipsec_handle_event+0x2b9/0x460 [mlx5_core]
  process_one_work+0x178/0x2e0
  worker_thread+0x2ea/0x430

Fixes: cee137a63431 ("net/mlx5e: Handle ESN update events")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 9c7064187ed0..f03507a522b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -259,7 +259,6 @@ static void mlx5e_ipsec_init_limits(struct mlx5e_ipsec_sa_entry *sa_entry,
 static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
 	struct mlx5e_ipsec_addr *addrs = &attrs->addrs;
 	struct net_device *netdev = sa_entry->dev;
 	struct xfrm_state *x = sa_entry->x;
@@ -276,7 +275,7 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	mlx5_query_mac_address(mdev, addr);
+	ether_addr_copy(addr, netdev->dev_addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;

From aa4876fe2d9fcbcaa0592b25f34ec6f6ea7876c1 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 9 Feb 2026 21:41:49 +0800
Subject: [PATCH 0462/1303] ALSA: hda/realtek: add quirk for Acer Nitro
 ANV15-51

fix mute/micmute LEDs and headset microphone for Acer Nitro ANV15-51.

[ The headset microphone issue is solved by Kailang]

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220279
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260209134149.3076957-1-zhangheng@kylinos.cn
---
 sound/hda/codecs/realtek/alc269.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 43ecfc63ef87..86bb22d19629 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -4075,6 +4075,7 @@ enum {
 	ALC236_FIXUP_HP_MUTE_LED_MICMUTE_GPIO,
 	ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY,
 	ALC245_FIXUP_BASS_HP_DAC,
+	ALC245_FIXUP_ACER_MICMUTE_LED,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -6599,6 +6600,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		/* Borrow the DAC routing selected for those Thinkpads */
 		.v.func = alc285_fixup_thinkpad_x1_gen7,
 	},
+	[ALC245_FIXUP_ACER_MICMUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_coef_micmute_led,
+		.chained = true,
+		.chain_id = ALC2XX_FIXUP_HEADSET_MIC,
+	}
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -6651,6 +6658,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED),
+	SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),

From 54f9d645a5453d0bfece0c465d34aaf072ea99fa Mon Sep 17 00:00:00 2001
From: Jun Seo <jun.seo.93@proton.me>
Date: Thu, 26 Feb 2026 10:08:20 +0900
Subject: [PATCH 0463/1303] ALSA: usb-audio: Use correct version for UAC3
 header validation

The entry of the validators table for UAC3 AC header descriptor is
defined with the wrong protocol version UAC_VERSION_2, while it should
have been UAC_VERSION_3.  This results in the validator never matching
for actual UAC3 devices (protocol == UAC_VERSION_3), causing their
header descriptors to bypass validation entirely.  A malicious USB
device presenting a truncated UAC3 header could exploit this to cause
out-of-bounds reads when the driver later accesses unvalidated
descriptor fields.

The bug was introduced in the same commit as the recently fixed UAC3
feature unit sub-type typo, and appears to be from the same copy-paste
error when the UAC3 section was created from the UAC2 section.

Fixes: 57f8770620e9 ("ALSA: usb-audio: More validations of descriptor units")
Cc: <stable@vger.kernel.org>
Signed-off-by: Jun Seo <jun.seo.93@proton.me>
Link: https://patch.msgid.link/20260226010820.36529-1-jun.seo.93@proton.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/validate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index 4bb4893f6e74..f62b7cc041dc 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -281,7 +281,7 @@ static const struct usb_desc_validator audio_validators[] = {
 	/* UAC_VERSION_2, UAC2_SAMPLE_RATE_CONVERTER: not implemented yet */
 
 	/* UAC3 */
-	FIXED(UAC_VERSION_2, UAC_HEADER, struct uac3_ac_header_descriptor),
+	FIXED(UAC_VERSION_3, UAC_HEADER, struct uac3_ac_header_descriptor),
 	FIXED(UAC_VERSION_3, UAC_INPUT_TERMINAL,
 	      struct uac3_input_terminal_descriptor),
 	FIXED(UAC_VERSION_3, UAC_OUTPUT_TERMINAL,

From cd3c877d04683b44a4d50dcdfad54b356e65d158 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 24 Feb 2026 07:46:37 -0800
Subject: [PATCH 0464/1303] iomap: don't report direct-io retries to fserror

iomap's directio implementation has two magic errno codes that it uses
to signal callers -- ENOTBLK tells the filesystem that it should retry
a write with the pagecache; and EAGAIN tells the caller that pagecache
flushing or invalidation failed and that it should try again.

Neither of these indicate data loss, so let's not report them.

Fixes: a9d573ee88af98 ("iomap: report file I/O errors to the VFS")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/20260224154637.GD2390381@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/direct-io.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 95254aa1b654..e911daedff65 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -87,6 +87,19 @@ static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio)
 	return FSERR_DIRECTIO_READ;
 }
 
+static inline bool should_report_dio_fserror(const struct iomap_dio *dio)
+{
+	switch (dio->error) {
+	case 0:
+	case -EAGAIN:
+	case -ENOTBLK:
+		/* don't send fsnotify for success or magic retry codes */
+		return false;
+	default:
+		return true;
+	}
+}
+
 ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
@@ -96,7 +109,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	if (dops && dops->end_io)
 		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
-	if (dio->error)
+	if (should_report_dio_fserror(dio))
 		fserror_report_io(file_inode(iocb->ki_filp),
 				  iomap_dio_err_type(dio), offset, dio->size,
 				  dio->error, GFP_NOFS);

From 28aaa9c39945b7925a1cc1d513c8f21ed38f5e4f Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 10:43:55 +0100
Subject: [PATCH 0465/1303] kthread: consolidate kthread exit paths to prevent
 use-after-free

Guillaume reported crashes via corrupted RCU callback function pointers
during KUnit testing. The crash was traced back to the pidfs rhashtable
conversion which replaced the 24-byte rb_node with an 8-byte rhash_head
in struct pid, shrinking it from 160 to 144 bytes.

struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With
CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to
192 bytes and share the same slab cache. struct pid.rcu.func and
struct kthread.affinity_node both sit at offset 0x78.

When a kthread exits via make_task_dead() it bypasses kthread_exit() and
misses the affinity_node cleanup. free_kthread_struct() frees the memory
while the node is still linked into the global kthread_affinity_list. A
subsequent list_del() by another kthread writes through dangling list
pointers into the freed and reused memory, corrupting the pid's
rcu.func pointer.

Instead of patching free_kthread_struct() to handle the missed cleanup,
consolidate all kthread exit paths. Turn kthread_exit() into a macro
that calls do_exit() and add kthread_do_exit() which is called from
do_exit() for any task with PF_KTHREAD set. This guarantees that
kthread-specific cleanup always happens regardless of the exit path -
make_task_dead(), direct do_exit(), or kthread_exit().

Replace __to_kthread() with a new tsk_is_kthread() accessor in the
public header. Export do_exit() since module code using the
kthread_exit() macro now needs it directly.

Reported-by: Guillaume Tucker <gtucker@gtucker.io>
Tested-by: Guillaume Tucker <gtucker@gtucker.io>
Tested-by: Mark Brown <broonie@kernel.org>
Tested-by: David Gow <davidgow@google.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/all/20260224-mittlerweile-besessen-2738831ae7f6@brauner
Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes: 4d13f4304fa4 ("kthread: Implement preferred affinity")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/kthread.h | 21 ++++++++++++++++++++-
 kernel/exit.c           |  6 ++++++
 kernel/kthread.c        | 41 +++++------------------------------------
 3 files changed, 31 insertions(+), 37 deletions(-)

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c92c1149ee6e..a01a474719a7 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -7,6 +7,24 @@
 
 struct mm_struct;
 
+/* opaque kthread data */
+struct kthread;
+
+/*
+ * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
+ * always remain a kthread.  For kthreads p->worker_private always
+ * points to a struct kthread.  For tasks that are not kthreads
+ * p->worker_private is used to point to other things.
+ *
+ * Return NULL for any task that is not a kthread.
+ */
+static inline struct kthread *tsk_is_kthread(struct task_struct *p)
+{
+	if (p->flags & PF_KTHREAD)
+		return p->worker_private;
+	return NULL;
+}
+
 __printf(4, 5)
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 					   void *data,
@@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
-void kthread_exit(long result) __noreturn;
+#define kthread_exit(result) do_exit(result)
 void kthread_complete_and_exit(struct completion *, long) __noreturn;
 int kthreads_update_housekeeping(void);
+void kthread_do_exit(struct kthread *, long);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/kernel/exit.c b/kernel/exit.c
index 8a87021211ae..ede3117fa7d4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
+	struct kthread *kthread;
 	int group_dead;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(tsk->plug);
 
+	kthread = tsk_is_kthread(tsk);
+	if (unlikely(kthread))
+		kthread_do_exit(kthread, code);
+
 	kcov_task_exit(tsk);
 	kmsan_task_exit(tsk);
 
@@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code)
 	lockdep_free_task(tsk);
 	do_task_dead();
 }
+EXPORT_SYMBOL(do_exit);
 
 void __noreturn make_task_dead(int signr)
 {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 20451b624b67..791210daf8b4 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return k->worker_private;
 }
 
-/*
- * Variant of to_kthread() that doesn't assume @p is a kthread.
- *
- * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
- * always remain a kthread.  For kthreads p->worker_private always
- * points to a struct kthread.  For tasks that are not kthreads
- * p->worker_private is used to point to other things.
- *
- * Return NULL for any task that is not a kthread.
- */
-static inline struct kthread *__to_kthread(struct task_struct *p)
-{
-	void *kthread = p->worker_private;
-	if (kthread && !(p->flags & PF_KTHREAD))
-		kthread = NULL;
-	return kthread;
-}
-
 void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 {
 	struct kthread *kthread = to_kthread(tsk);
@@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park);
 
 bool kthread_should_stop_or_park(void)
 {
-	struct kthread *kthread = __to_kthread(current);
+	struct kthread *kthread = tsk_is_kthread(current);
 
 	if (!kthread)
 		return false;
@@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	if (kthread)
 		return kthread->threadfn;
 	return NULL;
@@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	void *data = NULL;
 
 	if (kthread)
@@ -309,19 +291,8 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-/**
- * kthread_exit - Cause the current kthread return @result to kthread_stop().
- * @result: The integer value to return to kthread_stop().
- *
- * While kthread_exit can be called directly, it exists so that
- * functions which do some additional work in non-modular code such as
- * module_put_and_kthread_exit can be implemented.
- *
- * Does not return.
- */
-void __noreturn kthread_exit(long result)
+void kthread_do_exit(struct kthread *kthread, long result)
 {
-	struct kthread *kthread = to_kthread(current);
 	kthread->result = result;
 	if (!list_empty(&kthread->affinity_node)) {
 		mutex_lock(&kthread_affinity_lock);
@@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result)
 			kthread->preferred_affinity = NULL;
 		}
 	}
-	do_exit(0);
 }
-EXPORT_SYMBOL(kthread_exit);
 
 /**
  * kthread_complete_and_exit - Exit the current kthread.
@@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 
 bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = __to_kthread(p);
+	struct kthread *kthread = tsk_is_kthread(p);
 	if (!kthread)
 		return false;
 

From 7c2889af823340d1d410939b9d547bf184d5fa54 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 25 Feb 2026 15:48:59 +0200
Subject: [PATCH 0466/1303] RDMA/uverbs: Import DMA-BUF module in
 uverbs_std_types_dmabuf file

Fix the following compilation error:

ERROR: modpost: module ib_uverbs uses symbol dma_buf_move_notify
	from namespace DMA_BUF, but does not import it.

Fixes: 0ac6f4056c4a ("RDMA/uverbs: Add DMABUF object type and operations")
Link: https://patch.msgid.link/20260225-fix-uverbs-compilation-v1-1-acf7b3d0f9fa@nvidia.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_dmabuf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/core/uverbs_std_types_dmabuf.c b/drivers/infiniband/core/uverbs_std_types_dmabuf.c
index dfdfcd1d1a44..4a7f8b6f9dc8 100644
--- a/drivers/infiniband/core/uverbs_std_types_dmabuf.c
+++ b/drivers/infiniband/core/uverbs_std_types_dmabuf.c
@@ -10,6 +10,8 @@
 #include "rdma_core.h"
 #include "uverbs.h"
 
+MODULE_IMPORT_NS("DMA_BUF");
+
 static int uverbs_dmabuf_attach(struct dma_buf *dmabuf,
 				struct dma_buf_attachment *attachment)
 {

From a382a34276cb94d1cdc620b622dd85c55589a166 Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:32 -0800
Subject: [PATCH 0467/1303] selftests/vsock: change tests to respect write-once
 child ns mode

The child_ns_mode sysctl parameter becomes write-once in a future patch
in this series, which breaks existing tests. This patch updates the
tests to respect this new policy. No additional tests are added.

Add "global-parent" and "local-parent" namespaces as intermediaries to
spawn namespaces in the given modes. This avoids the need to change
"child_ns_mode" in the init_ns. nsenter must be used because ip netns
unshares the mount namespace so nested "ip netns add" breaks exec calls
from the init ns. Adds nsenter to the deps check.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-1-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/vsock/vmtest.sh | 39 +++++++++++++------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index dc8dbe74a6d0..86e338886b33 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -210,16 +210,21 @@ check_result() {
 }
 
 add_namespaces() {
-	local orig_mode
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
+	ip netns add "global-parent" 2>/dev/null
+	echo "global" | ip netns exec "global-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
+	ip netns add "local-parent" 2>/dev/null
+	echo "local" | ip netns exec "local-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
 
-	for mode in "${NS_MODES[@]}"; do
-		echo "${mode}" > /proc/sys/net/vsock/child_ns_mode
-		ip netns add "${mode}0" 2>/dev/null
-		ip netns add "${mode}1" 2>/dev/null
-	done
-
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global0" 2>/dev/null
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global1" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local0" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local1" 2>/dev/null
 }
 
 init_namespaces() {
@@ -237,6 +242,8 @@ del_namespaces() {
 		log_host "removed ns ${mode}0"
 		log_host "removed ns ${mode}1"
 	done
+	ip netns del "global-parent" &>/dev/null
+	ip netns del "local-parent" &>/dev/null
 }
 
 vm_ssh() {
@@ -287,7 +294,7 @@ check_args() {
 }
 
 check_deps() {
-	for dep in vng ${QEMU} busybox pkill ssh ss socat; do
+	for dep in vng ${QEMU} busybox pkill ssh ss socat nsenter; do
 		if [[ ! -x $(command -v "${dep}") ]]; then
 			echo -e "skip:    dependency ${dep} not found!\n"
 			exit "${KSFT_SKIP}"
@@ -1231,12 +1238,8 @@ test_ns_local_same_cid_ok() {
 }
 
 test_ns_host_vsock_child_ns_mode_ok() {
-	local orig_mode
-	local rc
+	local rc="${KSFT_PASS}"
 
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
-
-	rc="${KSFT_PASS}"
 	for mode in "${NS_MODES[@]}"; do
 		local ns="${mode}0"
 
@@ -1246,15 +1249,13 @@ test_ns_host_vsock_child_ns_mode_ok() {
 			continue
 		fi
 
-		if ! echo "${mode}" > /proc/sys/net/vsock/child_ns_mode; then
-			log_host "child_ns_mode should be writable to ${mode}"
+		if ! echo "${mode}" | ip netns exec "${ns}" \
+			tee /proc/sys/net/vsock/child_ns_mode &>/dev/null; then
 			rc="${KSFT_FAIL}"
 			continue
 		fi
 	done
 
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
-
 	return "${rc}"
 }
 

From 102eab95f025b4d3f3a6c0a858400aca2af2fe52 Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:33 -0800
Subject: [PATCH 0468/1303] vsock: lock down child_ns_mode as write-once

Two administrator processes may race when setting child_ns_mode as one
process sets child_ns_mode to "local" and then creates a namespace, but
another process changes child_ns_mode to "global" between the write and
the namespace creation. The first process ends up with a namespace in
"global" mode instead of "local". While this can be detected after the
fact by reading ns_mode and retrying, it is fragile and error-prone.

Make child_ns_mode write-once so that a namespace manager can set it
once and be sure it won't change. Writing a different value after the
first write returns -EBUSY. This applies to all namespaces, including
init_net, where an init process can write "local" to lock all future
namespaces into local mode.

Fixes: eafb64f40ca4 ("vsock: add netns to vsock core")
Suggested-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Co-developed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-2-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/af_vsock.h    | 13 +++++++++++--
 include/net/netns/vsock.h |  3 +++
 net/vmw_vsock/af_vsock.c  | 15 ++++++++++-----
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d3ff48a2fbe0..533d8e75f7bb 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -276,10 +276,19 @@ static inline bool vsock_net_mode_global(struct vsock_sock *vsk)
 	return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL;
 }
 
-static inline void vsock_net_set_child_mode(struct net *net,
+static inline bool vsock_net_set_child_mode(struct net *net,
 					    enum vsock_net_mode mode)
 {
-	WRITE_ONCE(net->vsock.child_ns_mode, mode);
+	int new_locked = mode + 1;
+	int old_locked = 0; /* unlocked */
+
+	if (try_cmpxchg(&net->vsock.child_ns_mode_locked,
+			&old_locked, new_locked)) {
+		WRITE_ONCE(net->vsock.child_ns_mode, mode);
+		return true;
+	}
+
+	return old_locked == new_locked;
 }
 
 static inline enum vsock_net_mode vsock_net_child_mode(struct net *net)
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
index b34d69a22fa8..dc8cbe45f406 100644
--- a/include/net/netns/vsock.h
+++ b/include/net/netns/vsock.h
@@ -17,5 +17,8 @@ struct netns_vsock {
 
 	enum vsock_net_mode mode;
 	enum vsock_net_mode child_ns_mode;
+
+	/* 0 = unlocked, 1 = locked to global, 2 = locked to local */
+	int child_ns_mode_locked;
 };
 #endif /* __NET_NET_NAMESPACE_VSOCK_H */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index f4062c6a1944..2f7d94d682cb 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -90,16 +90,20 @@
  *
  *   - /proc/sys/net/vsock/ns_mode (read-only) reports the current namespace's
  *     mode, which is set at namespace creation and immutable thereafter.
- *   - /proc/sys/net/vsock/child_ns_mode (writable) controls what mode future
+ *   - /proc/sys/net/vsock/child_ns_mode (write-once) controls what mode future
  *     child namespaces will inherit when created. The initial value matches
  *     the namespace's own ns_mode.
  *
  *   Changing child_ns_mode only affects newly created namespaces, not the
  *   current namespace or existing children. A "local" namespace cannot set
- *   child_ns_mode to "global". At namespace creation, ns_mode is inherited
- *   from the parent's child_ns_mode.
+ *   child_ns_mode to "global". child_ns_mode is write-once, so that it may be
+ *   configured and locked down by a namespace manager. Writing a different
+ *   value after the first write returns -EBUSY. At namespace creation, ns_mode
+ *   is inherited from the parent's child_ns_mode.
  *
- *   The init_net mode is "global" and cannot be modified.
+ *   The init_net mode is "global" and cannot be modified. The init_net
+ *   child_ns_mode is also write-once, so an init process (e.g. systemd) can
+ *   set it to "local" to ensure all new namespaces inherit local mode.
  *
  *   The modes affect the allocation and accessibility of CIDs as follows:
  *
@@ -2853,7 +2857,8 @@ static int vsock_net_child_mode_string(const struct ctl_table *table, int write,
 		    new_mode == VSOCK_NET_MODE_GLOBAL)
 			return -EPERM;
 
-		vsock_net_set_child_mode(net, new_mode);
+		if (!vsock_net_set_child_mode(net, new_mode))
+			return -EBUSY;
 	}
 
 	return 0;

From b6302e057fdc8f199ddae736ecdf45029f892e5c Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:34 -0800
Subject: [PATCH 0469/1303] vsock: document write-once behavior of the
 child_ns_mode sysctl

Update the vsock child_ns_mode documentation to include the new
write-once semantics of setting child_ns_mode. The semantics are
implemented in a preceding patch in this series.

Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-3-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/admin-guide/sysctl/net.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index c10530624f1e..3b2ad61995d4 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -594,6 +594,9 @@ Values:
 	  their sockets will only be able to connect within their own
 	  namespace.
 
+The first write to ``child_ns_mode`` locks its value. Subsequent writes of the
+same value succeed, but writing a different value returns ``-EBUSY``.
+
 Changing ``child_ns_mode`` only affects namespaces created after the change;
 it does not modify the current namespace or any existing children.
 

From 7aa767d0d3d04e50ae94e770db7db8197f666970 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 23 Feb 2026 15:51:00 -0800
Subject: [PATCH 0470/1303] net: consume xmit errors of GSO frames

udpgro_frglist.sh and udpgro_bench.sh are the flakiest tests
currently in NIPA. They fail in the same exact way, TCP GRO
test stalls occasionally and the test gets killed after 10min.

These tests use veth to simulate GRO. They attach a trivial
("return XDP_PASS;") XDP program to the veth to force TSO off
and NAPI on.

Digging into the failure mode we can see that the connection
is completely stuck after a burst of drops. The sender's snd_nxt
is at sequence number N [1], but the receiver claims to have
received (rcv_nxt) up to N + 3 * MSS [2]. Last piece of the puzzle
is that senders rtx queue is not empty (let's say the block in
the rtx queue is at sequence number N - 4 * MSS [3]).

In this state, sender sends a retransmission from the rtx queue
with a single segment, and sequence numbers N-4*MSS:N-3*MSS [3].
Receiver sees it and responds with an ACK all the way up to
N + 3 * MSS [2]. But sender will reject this ack as TCP_ACK_UNSENT_DATA
because it has no recollection of ever sending data that far out [1].
And we are stuck.

The root cause is the mess of the xmit return codes. veth returns
an error when it can't xmit a frame. We end up with a loss event
like this:

  -------------------------------------------------
  |   GSO super frame 1   |   GSO super frame 2   |
  |-----------------------------------------------|
  | seg | seg | seg | seg | seg | seg | seg | seg |
  |  1  |  2  |  3  |  4  |  5  |  6  |  7  |  8  |
  -------------------------------------------------
     x    ok    ok    <ok>|  ok    ok    ok   <x>
                          \\
			   snd_nxt

"x" means packet lost by veth, and "ok" means it went thru.
Since veth has TSO disabled in this test it sees individual segments.
Segment 1 is on the retransmit queue and will be resent.

So why did the sender not advance snd_nxt even tho it clearly did
send up to seg 8? tcp_write_xmit() interprets the return code
from the core to mean that data has not been sent at all. Since
TCP deals with GSO super frames, not individual segment the crux
of the problem is that loss of a single segment can be interpreted
as loss of all. TCP only sees the last return code for the last
segment of the GSO frame (in <> brackets in the diagram above).

Of course for the problem to occur we need a setup or a device
without a Qdisc. Otherwise Qdisc layer disconnects the protocol
layer from the device errors completely.

We have multiple ways to fix this.

 1) make veth not return an error when it lost a packet.
    While this is what I think we did in the past, the issue keeps
    reappearing and it's annoying to debug. The game of whack
    a mole is not great.

 2) fix the damn return codes
    We only talk about NETDEV_TX_OK and NETDEV_TX_BUSY in the
    documentation, so maybe we should make the return code from
    ndo_start_xmit() a boolean. I like that the most, but perhaps
    some ancient, not-really-networking protocol would suffer.

 3) make TCP ignore the errors
    It is not entirely clear to me what benefit TCP gets from
    interpreting the result of ip_queue_xmit()? Specifically once
    the connection is established and we're pushing data - packet
    loss is just packet loss?

 4) this fix
    Ignore the rc in the Qdisc-less+GSO case, since it's unreliable.
    We already always return OK in the TCQ_F_CAN_BYPASS case.
    In the Qdisc-less case let's be a bit more conservative and only
    mask the GSO errors. This path is taken by non-IP-"networks"
    like CAN, MCTP etc, so we could regress some ancient thing.
    This is the simplest, but also maybe the hackiest fix?

Similar fix has been proposed by Eric in the past but never committed
because original reporter was working with an OOT driver and wasn't
providing feedback (see Link).

Link: https://lore.kernel.org/CANn89iJcLepEin7EtBETrZ36bjoD9LrR=k4cfwWh046GB+4f9A@mail.gmail.com
Fixes: 1f59533f9ca5 ("qdisc: validate frames going through the direct_xmit path")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260223235100.108939-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f3426385f1ba..3d2d3b18915c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4822,6 +4822,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 		 * to -1 or to their cpu id, but not to our id.
 		 */
 		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
+			bool is_list = false;
+
 			if (dev_xmit_recursion())
 				goto recursion_alert;
 
@@ -4832,17 +4834,28 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
+				is_list = !!skb->next;
+
 				dev_xmit_recursion_inc();
 				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
 				dev_xmit_recursion_dec();
-				if (dev_xmit_complete(rc)) {
-					HARD_TX_UNLOCK(dev, txq);
-					goto out;
-				}
+
+				/* GSO segments a single SKB into
+				 * a list of frames. TCP expects error
+				 * to mean none of the data was sent.
+				 */
+				if (is_list)
+					rc = NETDEV_TX_OK;
 			}
 			HARD_TX_UNLOCK(dev, txq);
+			if (!skb) /* xmit completed */
+				goto out;
+
 			net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
 					     dev->name);
+			/* NETDEV_TX_BUSY or queue was stopped */
+			if (!is_list)
+				rc = -ENETDOWN;
 		} else {
 			/* Recursion is detected! It is possible,
 			 * unfortunately
@@ -4850,10 +4863,10 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 recursion_alert:
 			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
 					     dev->name);
+			rc = -ENETDOWN;
 		}
 	}
 
-	rc = -ENETDOWN;
 	rcu_read_unlock_bh();
 
 	dev_core_stats_tx_dropped_inc(dev);

From 8a5752c6dcc085a3bfc78589925182e4e98468c5 Mon Sep 17 00:00:00 2001
From: Junrui Luo <moonafterrain@outlook.com>
Date: Tue, 24 Feb 2026 19:05:56 +0800
Subject: [PATCH 0471/1303] dpaa2-switch: validate num_ifs to prevent
 out-of-bounds write

The driver obtains sw_attr.num_ifs from firmware via dpsw_get_attributes()
but never validates it against DPSW_MAX_IF (64). This value controls
iteration in dpaa2_switch_fdb_get_flood_cfg(), which writes port indices
into the fixed-size cfg->if_id[DPSW_MAX_IF] array. When firmware reports
num_ifs >= 64, the loop can write past the array bounds.

Add a bound check for num_ifs in dpaa2_switch_init().

dpaa2_switch_fdb_get_flood_cfg() appends the control interface (port
num_ifs) after all matched ports. When num_ifs == DPSW_MAX_IF and all
ports match the flood filter, the loop fills all 64 slots and the control
interface write overflows by one entry.

The check uses >= because num_ifs == DPSW_MAX_IF is also functionally
broken.

build_if_id_bitmap() silently drops any ID >= 64:
      if (id[i] < DPSW_MAX_IF)
          bmap[id[i] / 64] |= ...

Fixes: 539dda3c5d19 ("staging: dpaa2-switch: properly setup switching domains")
Signed-off-by: Junrui Luo <moonafterrain@outlook.com>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/SYBPR01MB78812B47B7F0470B617C408AAF74A@SYBPR01MB7881.ausprd01.prod.outlook.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 66240c340492..78e21b46a5ba 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -3034,6 +3034,13 @@ static int dpaa2_switch_init(struct fsl_mc_device *sw_dev)
 		goto err_close;
 	}
 
+	if (ethsw->sw_attr.num_ifs >= DPSW_MAX_IF) {
+		dev_err(dev, "DPSW num_ifs %u exceeds max %u\n",
+			ethsw->sw_attr.num_ifs, DPSW_MAX_IF);
+		err = -EINVAL;
+		goto err_close;
+	}
+
 	err = dpsw_get_api_version(ethsw->mc_io, 0,
 				   &ethsw->major,
 				   &ethsw->minor);

From 003ce8c9b2ca28fbb4860651e76fb1c9a91f2ea1 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:17:28 +0000
Subject: [PATCH 0472/1303] ALSA: hda: cs35l56: Fix signedness error in
 cs35l56_hda_posture_put()

In cs35l56_hda_posture_put() assign ucontrol->value.integer.value[0] to
a long instead of an unsigned long. ucontrol->value.integer.value[0] is
a long.

This fixes the sparse warning:

sound/hda/codecs/side-codecs/cs35l56_hda.c:256:20: warning: unsigned value
that used to be signed checked against zero?
sound/hda/codecs/side-codecs/cs35l56_hda.c:252:29: signed value source

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea8 ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://patch.msgid.link/20260226111728.1700431-1-rf@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/cs35l56_hda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c
index cfc8de2ae499..eb66827eabf8 100644
--- a/sound/hda/codecs/side-codecs/cs35l56_hda.c
+++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c
@@ -249,7 +249,7 @@ static int cs35l56_hda_posture_put(struct snd_kcontrol *kcontrol,
 				   struct snd_ctl_elem_value *ucontrol)
 {
 	struct cs35l56_hda *cs35l56 = snd_kcontrol_chip(kcontrol);
-	unsigned long pos = ucontrol->value.integer.value[0];
+	long pos = ucontrol->value.integer.value[0];
 	bool changed;
 	int ret;
 

From baed0d9ba91d4f390da12d5039128ee897253d60 Mon Sep 17 00:00:00 2001
From: Vahagn Vardanian <vahagn@redrays.io>
Date: Wed, 25 Feb 2026 14:06:18 +0100
Subject: [PATCH 0473/1303] netfilter: nf_conntrack_h323: fix OOB read in
 decode_choice()

In decode_choice(), the boundary check before get_len() uses the
variable `len`, which is still 0 from its initialization at the top of
the function:

    unsigned int type, ext, len = 0;
    ...
    if (ext || (son->attr & OPEN)) {
        BYTE_ALIGN(bs);
        if (nf_h323_error_boundary(bs, len, 0))  /* len is 0 here */
            return H323_ERROR_BOUND;
        len = get_len(bs);                        /* OOB read */

When the bitstream is exactly consumed (bs->cur == bs->end), the check
nf_h323_error_boundary(bs, 0, 0) evaluates to (bs->cur + 0 > bs->end),
which is false.  The subsequent get_len() call then dereferences
*bs->cur++, reading 1 byte past the end of the buffer.  If that byte
has bit 7 set, get_len() reads a second byte as well.

This can be triggered remotely by sending a crafted Q.931 SETUP message
with a User-User Information Element containing exactly 2 bytes of
PER-encoded data ({0x08, 0x00}) to port 1720 through a firewall with
the nf_conntrack_h323 helper active.  The decoder fully consumes the
PER buffer before reaching this code path, resulting in a 1-2 byte
heap-buffer-overflow read confirmed by AddressSanitizer.

Fix this by checking for 2 bytes (the maximum that get_len() may read)
instead of the uninitialized `len`.  This matches the pattern used at
every other get_len() call site in the same file, where the caller
checks for 2 bytes of available data before calling get_len().

Fixes: ec8a8f3c31dd ("netfilter: nf_ct_h323: Extend nf_h323_error_boundary to work on bits as well")
Signed-off-by: Vahagn Vardanian <vahagn@redrays.io>
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260225130619.1248-2-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/netfilter/nf_conntrack_h323_asn1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index 540d97715bd2..62aa22a07876 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -796,7 +796,7 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f,
 
 	if (ext || (son->attr & OPEN)) {
 		BYTE_ALIGN(bs);
-		if (nf_h323_error_boundary(bs, len, 0))
+		if (nf_h323_error_boundary(bs, 2, 0))
 			return H323_ERROR_BOUND;
 		len = get_len(bs);
 		if (nf_h323_error_boundary(bs, len, 0))

From 36d9579fed6c9429aa172f77bd28c58696ce8e2b Mon Sep 17 00:00:00 2001
From: Francesco Lavra <flavra@baylibre.com>
Date: Tue, 10 Feb 2026 19:09:32 +0100
Subject: [PATCH 0474/1303] drm/solomon: Fix page start when updating rectangle
 in page addressing mode

In page addressing mode, the pixel values of a dirty rectangle must be sent
to the display controller one page at a time. The range of pages
corresponding to a given rectangle is being incorrectly calculated as if
the Y value of the top left coordinate of the rectangle was 0. This can
result in rectangle updates being displayed on wrong parts of the screen.

Fix the above issue by consolidating the start page calculation in a single
place at the beginning of the update_rect function, and using the
calculated value for all addressing modes.

Fixes: b0daaa5cfaa5 ("drm/ssd130x: Support page addressing mode")
Signed-off-by: Francesco Lavra <flavra@baylibre.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://patch.msgid.link/20260210180932.736502-1-flavra@baylibre.com
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
---
 drivers/gpu/drm/solomon/ssd130x.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index 6ecf9e2ff61b..c77455b1834d 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -737,6 +737,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 	unsigned int height = drm_rect_height(rect);
 	unsigned int line_length = DIV_ROUND_UP(width, 8);
 	unsigned int page_height = SSD130X_PAGE_HEIGHT;
+	u8 page_start = ssd130x->page_offset + y / page_height;
 	unsigned int pages = DIV_ROUND_UP(height, page_height);
 	struct drm_device *drm = &ssd130x->drm;
 	u32 array_idx = 0;
@@ -774,14 +775,11 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 	 */
 
 	if (!ssd130x->page_address_mode) {
-		u8 page_start;
-
 		/* Set address range for horizontal addressing mode */
 		ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset + x, width);
 		if (ret < 0)
 			return ret;
 
-		page_start = ssd130x->page_offset + y / page_height;
 		ret = ssd130x_set_page_range(ssd130x, page_start, pages);
 		if (ret < 0)
 			return ret;
@@ -813,7 +811,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 		 */
 		if (ssd130x->page_address_mode) {
 			ret = ssd130x_set_page_pos(ssd130x,
-						   ssd130x->page_offset + i,
+						   page_start + i,
 						   ssd130x->col_offset + x);
 			if (ret < 0)
 				return ret;

From 786ea2b694f48e1b34f1dcf104e09357fc99ef34 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 12:41:15 +0000
Subject: [PATCH 0475/1303] ALSA: hda: cs35l56: Remove unnecessary struct
 cs_dsp_client_ops

Since commit af37511305c0 ("firmware: cs_dsp: Don't require client to
provide a struct cs_dsp_client_ops") the client doesn't have to provide
a struct cs_dsp_client_ops. So remove the dummy cs_dsp_client_ops.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226124115.1811187-1-rf@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/cs35l56_hda.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c
index eb66827eabf8..1ace4beef508 100644
--- a/sound/hda/codecs/side-codecs/cs35l56_hda.c
+++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c
@@ -403,10 +403,6 @@ static void cs35l56_hda_remove_controls(struct cs35l56_hda *cs35l56)
 	snd_ctl_remove(cs35l56->codec->card, cs35l56->volume_ctl);
 }
 
-static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
-	/* cs_dsp requires the client to provide this even if it is empty */
-};
-
 static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 					     const struct firmware **firmware, char **filename,
 					     const char *base_name, const char *system_name,
@@ -1149,7 +1145,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id)
 	cs35l56->base.cal_index = cs35l56->index;
 
 	cs35l56_init_cs_dsp(&cs35l56->base, &cs35l56->cs_dsp);
-	cs35l56->cs_dsp.client_ops = &cs35l56_hda_client_ops;
 
 	if (cs35l56->base.reset_gpio) {
 		dev_dbg(cs35l56->base.dev, "Hard reset\n");

From a0b4c7a49137ed21279f354eb59f49ddae8dffc2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 26 Feb 2026 13:32:33 +0000
Subject: [PATCH 0476/1303] netfs: Fix unbuffered/DIO writes to dispatch
 subrequests in strict sequence

Fix netfslib such that when it's making an unbuffered or DIO write, to make
sure that it sends each subrequest strictly sequentially, waiting till the
previous one is 'committed' before sending the next so that we don't have
pieces landing out of order and potentially leaving a hole if an error
occurs (ENOSPC for example).

This is done by copying in just those bits of issuing, collecting and
retrying subrequests that are necessary to do one subrequest at a time.
Retrying, in particular, is simpler because if the current subrequest needs
retrying, the source iterator can just be copied again and the subrequest
prepped and issued again without needing to be concerned about whether it
needs merging with the previous or next in the sequence.

Note that the issuing loop waits for a subrequest to complete right after
issuing it, but this wait could be moved elsewhere allowing preparatory
steps to be performed whilst the subrequest is in progress.  In particular,
once content encryption is available in netfslib, that could be done whilst
waiting, as could cleanup of buffers that have been completed.

Fixes: 153a9961b551 ("netfs: Implement unbuffered/DIO write support")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/58526.1772112753@warthog.procyon.org.uk
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/direct_write.c      | 228 ++++++++++++++++++++++++++++++++---
 fs/netfs/internal.h          |   4 +-
 fs/netfs/write_collect.c     |  21 ----
 fs/netfs/write_issue.c       |  41 +------
 include/trace/events/netfs.h |   4 +-
 5 files changed, 221 insertions(+), 77 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index a9d1c3b2c084..dd1451bf7543 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -9,6 +9,202 @@
 #include <linux/uio.h>
 #include "internal.h"
 
+/*
+ * Perform the cleanup rituals after an unbuffered write is complete.
+ */
+static void netfs_unbuffered_write_done(struct netfs_io_request *wreq)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+
+	_enter("R=%x", wreq->debug_id);
+
+	/* Okay, declare that all I/O is complete. */
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	if (!wreq->error)
+		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
+
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		/* mmap may have got underfoot and we may now have folios
+		 * locally covering the region we just wrote.  Attempt to
+		 * discard the folios, but leave in place any modified locally.
+		 * ->write_iter() is prevented from interfering by the DIO
+		 * counter.
+		 */
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
+	_debug("finished");
+	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
+
+	if (wreq->iocb) {
+		size_t written = umin(wreq->transferred, wreq->len);
+
+		wreq->iocb->ki_pos += written;
+		if (wreq->iocb->ki_complete) {
+			trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete);
+			wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written);
+		}
+		wreq->iocb = VFS_PTR_POISON;
+	}
+
+	netfs_clear_subrequests(wreq);
+}
+
+/*
+ * Collect the subrequest results of unbuffered write subrequests.
+ */
+static void netfs_unbuffered_write_collect(struct netfs_io_request *wreq,
+					   struct netfs_io_stream *stream,
+					   struct netfs_io_subrequest *subreq)
+{
+	trace_netfs_collect_sreq(wreq, subreq);
+
+	spin_lock(&wreq->lock);
+	list_del_init(&subreq->rreq_link);
+	spin_unlock(&wreq->lock);
+
+	wreq->transferred += subreq->transferred;
+	iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+	stream->collected_to = subreq->start + subreq->transferred;
+	wreq->collected_to = stream->collected_to;
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_done);
+
+	trace_netfs_collect_stream(wreq, stream);
+	trace_netfs_collect_state(wreq, wreq->collected_to, 0);
+}
+
+/*
+ * Write data to the server without going through the pagecache and without
+ * writing it to the local cache.  We dispatch the subrequests serially and
+ * wait for each to complete before dispatching the next, lest we leave a gap
+ * in the data written due to a failure such as ENOSPC.  We could, however
+ * attempt to do preparation such as content encryption for the next subreq
+ * whilst the current is in progress.
+ */
+static int netfs_unbuffered_write(struct netfs_io_request *wreq)
+{
+	struct netfs_io_subrequest *subreq = NULL;
+	struct netfs_io_stream *stream = &wreq->io_streams[0];
+	int ret;
+
+	_enter("%llx", wreq->len);
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
+	stream->collected_to = wreq->start;
+
+	for (;;) {
+		bool retry = false;
+
+		if (!subreq) {
+			netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred);
+			subreq = stream->construct;
+			stream->construct = NULL;
+			stream->front = NULL;
+		}
+
+		/* Check if (re-)preparation failed. */
+		if (unlikely(test_bit(NETFS_SREQ_FAILED, &subreq->flags))) {
+			netfs_write_subrequest_terminated(subreq, subreq->error);
+			wreq->error = subreq->error;
+			break;
+		}
+
+		iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred);
+		if (!iov_iter_count(&subreq->io_iter))
+			break;
+
+		subreq->len = netfs_limit_iter(&subreq->io_iter, 0,
+					       stream->sreq_max_len,
+					       stream->sreq_max_segs);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+		stream->submit_extendable_to = subreq->len;
+
+		trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+		stream->issue_write(subreq);
+
+		/* Async, need to wait. */
+		netfs_wait_for_in_progress_stream(wreq, stream);
+
+		if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
+			retry = true;
+		} else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) {
+			ret = subreq->error;
+			wreq->error = ret;
+			netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed);
+			subreq = NULL;
+			break;
+		}
+		ret = 0;
+
+		if (!retry) {
+			netfs_unbuffered_write_collect(wreq, stream, subreq);
+			subreq = NULL;
+			if (wreq->transferred >= wreq->len)
+				break;
+			if (!wreq->iocb && signal_pending(current)) {
+				ret = wreq->transferred ? -EINTR : -ERESTARTSYS;
+				trace_netfs_rreq(wreq, netfs_rreq_trace_intr);
+				break;
+			}
+			continue;
+		}
+
+		/* We need to retry the last subrequest, so first reset the
+		 * iterator, taking into account what, if anything, we managed
+		 * to transfer.
+		 */
+		subreq->error = -EAGAIN;
+		trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
+		if (subreq->transferred > 0)
+			iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+		if (stream->source == NETFS_UPLOAD_TO_SERVER &&
+		    wreq->netfs_ops->retry_request)
+			wreq->netfs_ops->retry_request(wreq, stream);
+
+		__clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_FAILED, &subreq->flags);
+		subreq->io_iter		= wreq->buffer.iter;
+		subreq->start		= wreq->start + wreq->transferred;
+		subreq->len		= wreq->len   - wreq->transferred;
+		subreq->transferred	= 0;
+		subreq->retry_count	+= 1;
+		stream->sreq_max_len	= UINT_MAX;
+		stream->sreq_max_segs	= INT_MAX;
+
+		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
+		stream->prepare_write(subreq);
+
+		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+		netfs_stat(&netfs_n_wh_retry_write_subreq);
+	}
+
+	netfs_unbuffered_write_done(wreq);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+static void netfs_unbuffered_write_async(struct work_struct *work)
+{
+	struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work);
+
+	netfs_unbuffered_write(wreq);
+	netfs_put_request(wreq, netfs_rreq_trace_put_complete);
+}
+
 /*
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
@@ -70,35 +266,35 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 			 */
 			wreq->buffer.iter = *iter;
 		}
+
+		wreq->len = iov_iter_count(&wreq->buffer.iter);
 	}
 
 	__set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags);
-	if (async)
-		__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 
 	/* Copy the data into the bounce buffer and encrypt it. */
 	// TODO
 
 	/* Dispatch the write. */
 	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
-	if (async)
+
+	if (async) {
+		INIT_WORK(&wreq->work, netfs_unbuffered_write_async);
 		wreq->iocb = iocb;
-	wreq->len = iov_iter_count(&wreq->buffer.iter);
-	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
-	if (ret < 0) {
-		_debug("begin = %zd", ret);
-		goto out;
-	}
-
-	if (!async) {
-		ret = netfs_wait_for_write(wreq);
-		if (ret > 0)
-			iocb->ki_pos += ret;
-	} else {
+		queue_work(system_dfl_wq, &wreq->work);
 		ret = -EIOCBQUEUED;
+	} else {
+		ret = netfs_unbuffered_write(wreq);
+		if (ret < 0) {
+			_debug("begin = %zd", ret);
+		} else {
+			iocb->ki_pos += wreq->transferred;
+			ret = wreq->transferred ?: wreq->error;
+		}
+
+		netfs_put_request(wreq, netfs_rreq_trace_put_complete);
 	}
 
-out:
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	return ret;
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 4319611f5354..d436e20d3418 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -198,6 +198,9 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 						struct file *file,
 						loff_t start,
 						enum netfs_io_origin origin);
+void netfs_prepare_write(struct netfs_io_request *wreq,
+			 struct netfs_io_stream *stream,
+			 loff_t start);
 void netfs_reissue_write(struct netfs_io_stream *stream,
 			 struct netfs_io_subrequest *subreq,
 			 struct iov_iter *source);
@@ -212,7 +215,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 			       struct folio **writethrough_cache);
 ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
 			       struct folio *writethrough_cache);
-int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len);
 
 /*
  * write_retry.c
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 61eab34ea67e..83eb3dc1adf8 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -399,27 +399,6 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 		ictx->ops->invalidate_cache(wreq);
 	}
 
-	if ((wreq->origin == NETFS_UNBUFFERED_WRITE ||
-	     wreq->origin == NETFS_DIO_WRITE) &&
-	    !wreq->error)
-		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
-
-	if (wreq->origin == NETFS_DIO_WRITE &&
-	    wreq->mapping->nrpages) {
-		/* mmap may have got underfoot and we may now have folios
-		 * locally covering the region we just wrote.  Attempt to
-		 * discard the folios, but leave in place any modified locally.
-		 * ->write_iter() is prevented from interfering by the DIO
-		 * counter.
-		 */
-		pgoff_t first = wreq->start >> PAGE_SHIFT;
-		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
-		invalidate_inode_pages2_range(wreq->mapping, first, last);
-	}
-
-	if (wreq->origin == NETFS_DIO_WRITE)
-		inode_dio_end(wreq->inode);
-
 	_debug("finished");
 	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
 	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 34894da5a23e..437268f65640 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -154,9 +154,9 @@ EXPORT_SYMBOL(netfs_prepare_write_failed);
  * Prepare a write subrequest.  We need to allocate a new subrequest
  * if we don't have one.
  */
-static void netfs_prepare_write(struct netfs_io_request *wreq,
-				struct netfs_io_stream *stream,
-				loff_t start)
+void netfs_prepare_write(struct netfs_io_request *wreq,
+			 struct netfs_io_stream *stream,
+			 loff_t start)
 {
 	struct netfs_io_subrequest *subreq;
 	struct iov_iter *wreq_iter = &wreq->buffer.iter;
@@ -698,41 +698,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c
 	return ret;
 }
 
-/*
- * Write data to the server without going through the pagecache and without
- * writing it to the local cache.
- */
-int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len)
-{
-	struct netfs_io_stream *upload = &wreq->io_streams[0];
-	ssize_t part;
-	loff_t start = wreq->start;
-	int error = 0;
-
-	_enter("%zx", len);
-
-	if (wreq->origin == NETFS_DIO_WRITE)
-		inode_dio_begin(wreq->inode);
-
-	while (len) {
-		// TODO: Prepare content encryption
-
-		_debug("unbuffered %zx", len);
-		part = netfs_advance_write(wreq, upload, start, len, false);
-		start += part;
-		len -= part;
-		rolling_buffer_advance(&wreq->buffer, part);
-		if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags))
-			netfs_wait_for_paused_write(wreq);
-		if (test_bit(NETFS_RREQ_FAILED, &wreq->flags))
-			break;
-	}
-
-	netfs_end_issue_write(wreq);
-	_leave(" = %d", error);
-	return error;
-}
-
 /*
  * Write some of a pending folio data back to the server and/or the cache.
  */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 64a382fbc31a..2d366be46a1c 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -57,6 +57,7 @@
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_end_copy_to_cache,	"END-C2C")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_intr,		"INTR   ")	\
 	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
@@ -169,7 +170,8 @@
 	EM(netfs_sreq_trace_put_oom,		"PUT OOM    ")	\
 	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
-	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
+	EM(netfs_sreq_trace_put_terminated,	"PUT TERM   ")	\
+	E_(netfs_sreq_trace_see_failed,		"SEE FAILED ")
 
 #define netfs_folio_traces					\
 	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\

From 2970525f789c080e7e82ecb09cd85a8bb1d284e4 Mon Sep 17 00:00:00 2001
From: Jingkai Tan <contact@jingk.ai>
Date: Thu, 22 Jan 2026 21:14:10 +0000
Subject: [PATCH 0477/1303] btrfs: handle discard errors in in
 btrfs_finish_extent_commit()

Coverity (ID: 1226842) reported that the return value of
btrfs_discard_extent() is assigned to ret but is immediately
overwritten by unpin_extent_range() without being checked.

Use the same error handling that is done later in the same function.

Signed-off-by: Jingkai Tan <contact@jingk.ai>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 03cf9f242c70..b0d9baf5b412 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2933,9 +2933,15 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 	while (!TRANS_ABORTED(trans) && cached_state) {
 		struct extent_state *next_state;
 
-		if (btrfs_test_opt(fs_info, DISCARD_SYNC))
+		if (btrfs_test_opt(fs_info, DISCARD_SYNC)) {
 			ret = btrfs_discard_extent(fs_info, start,
 						   end + 1 - start, NULL, true);
+			if (ret) {
+				btrfs_warn(fs_info,
+				"discard failed for extent [%llu, %llu]: errno=%d %s",
+					   start, end, ret, btrfs_decode_error(ret));
+			}
+		}
 
 		next_state = btrfs_next_extent_state(unpin, cached_state);
 		btrfs_clear_extent_dirty(unpin, start, end, &cached_state);

From a4fe134fc1d8eb7dcd07e0961c5711b443decd89 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 9 Feb 2026 14:01:45 +1030
Subject: [PATCH 0478/1303] btrfs: fix a double release on reserved extents in
 cow_one_range()

[BUG]
Commit c28214bde6da ("btrfs: refactor the main loop of
cow_file_range()") refactored the handling of COWing one range.

However it changed the error handling of the reserved extent.

The old cleanup looks like this:

out_drop_extent_cache:
	btrfs_drop_extent_map_range(inode, start, start + cur_alloc_size - 1, false);
out_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, true);
	[...]
	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
		     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
	/*
	 * For the range (2). If we reserved an extent for our delalloc range
	 * (or a subrange) and failed to create the respective ordered extent,
	 * then it means that when we reserved the extent we decremented the
	 * extent's size from the data space_info's bytes_may_use counter and
	 * incremented the space_info's bytes_reserved counter by the same
	 * amount. We must make sure extent_clear_unlock_delalloc() does not try
	 * to decrement again the data space_info's bytes_may_use counter,
	 * therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV.
	 */
	if (cur_alloc_size) {
	        extent_clear_unlock_delalloc(inode, start,
	                                     start + cur_alloc_size - 1,
	                                     locked_folio, &cached, clear_bits,
	                                     page_ops);
	        btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
	}

Which only calls EXTENT_CLEAR_META_RESV.
As the reserved extent is properly handled by
btrfs_free_reserved_extent().

However the new cleanup is:

	extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached,
				     EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW |
				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
				     PAGE_END_WRITEBACK);
	btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL);
	btrfs_dec_block_group_reservations(fs_info, ins->objectid);
	btrfs_free_reserved_extent(fs_info, ins->objectid, ins->offset, true);

The flag EXTENT_DO_ACCOUNTING implies both EXTENT_CLEAR_META_RESV and
EXTENT_CLEAR_DATA_RESV, which will release the bytes_may_use, which
later btrfs_free_reserved_extent() will do again, causing incorrect
double release (and may underflow bytes_may_use).

[FIX]
Use EXTENT_CLEAR_META_RESV to replace EXTENT_DO_ACCOUNTING, and add back
the comments on why we only use EXTENT_CLEAR_META_RESV.

Fixes: c28214bde6da ("btrfs: refactor the main loop of cow_file_range()")
Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208184920.1102719-1-clm@meta.com/
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b6c763a17406..ade590707793 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1392,10 +1392,25 @@ static int cow_one_range(struct btrfs_inode *inode, struct folio *locked_folio,
 	return ret;
 
 free_reserved:
+	/*
+	 * If we have reserved an extent for the current range and failed to
+	 * create the respective extent map or ordered extent, it means that
+	 * when we reserved the extent we decremented the extent's size from
+	 * the data space_info's bytes_may_use counter and
+	 * incremented the space_info's bytes_reserved counter by the same
+	 * amount.
+	 *
+	 * We must make sure extent_clear_unlock_delalloc() does not try
+	 * to decrement again the data space_info's bytes_may_use counter, which
+	 * will be handled by btrfs_free_reserved_extent().
+	 *
+	 * Therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV, but only
+	 * EXTENT_CLEAR_META_RESV.
+	 */
 	extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached,
 				     EXTENT_LOCKED | EXTENT_DELALLOC |
 				     EXTENT_DELALLOC_NEW |
-				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
+				     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV,
 				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
 				     PAGE_END_WRITEBACK);
 	btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL);

From 0649355303995d6539df1fa8feaf50497f94db9b Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:27:14 +0000
Subject: [PATCH 0479/1303] btrfs: change warning messages to error level in
 open_ctree()

Failure to read the fs root results in a mount error, but we log a warning
message. Same goes for checking the UUID tree, an error results in a mount
failure but we log a warning message. Change the level of the logged
messages from warning to error.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 13e400046c87..de8ce9c588fe 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3642,7 +3642,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		ret = PTR_ERR(fs_info->fs_root);
-		btrfs_warn(fs_info, "failed to read fs tree: %d", ret);
+		btrfs_err(fs_info, "failed to read fs tree: %d", ret);
 		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}
@@ -3663,8 +3663,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_info(fs_info, "checking UUID tree");
 		ret = btrfs_check_uuid_tree(fs_info);
 		if (ret) {
-			btrfs_warn(fs_info,
-				"failed to check the UUID tree: %d", ret);
+			btrfs_err(fs_info, "failed to check the UUID tree: %d", ret);
 			close_ctree(fs_info);
 			return ret;
 		}

From 64def7d7d62b61044fe619e3cc9cbe60454decd9 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:37:41 +0000
Subject: [PATCH 0480/1303] btrfs: remove redundant warning message in
 btrfs_check_uuid_tree()

If we fail to start the UUID rescan kthread, btrfs_check_uuid_tree() logs
an error message and returns the error to the single caller, open_ctree().

This however is redundant since the caller already logs an error message,
which is also more informative since it logs the error code. Some remove
the warning message from btrfs_check_uuid_tree() as it doesn't add any
value.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index de8ce9c588fe..b855e2cec2ec 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2972,7 +2972,6 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
 	task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
 	if (IS_ERR(task)) {
 		/* fs_info->update_uuid_tree_gen remains 0 in all error case */
-		btrfs_warn(fs_info, "failed to start uuid_rescan task");
 		up(&fs_info->uuid_tree_rescan_sem);
 		return PTR_ERR(task);
 	}

From 4db8d56c6f4cbea7293d4236efac4a507dbfa6b1 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:47:57 +0000
Subject: [PATCH 0481/1303] btrfs: remove btrfs_handle_fs_error() after failure
 to recover log trees

There is no need to call btrfs_handle_fs_error() (which we are trying to
deprecate) if we fail to recover log trees:

1) Such a failure results in failing the mount immediately;

2) If the recovery started a transaction before failing, it has already
   aborted the transaction down in the call chain.

So remove the btrfs_handle_fs_error() call, replace it with an error
message and assert that the FS is in error state (so that no partial
updates are committed due to a transaction that was not aborted).

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b855e2cec2ec..e6574456a306 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2023,9 +2023,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	/* returns with log_tree_root freed on success */
 	ret = btrfs_recover_log_trees(log_tree_root);
 	btrfs_put_root(log_tree_root);
-	if (ret) {
-		btrfs_handle_fs_error(fs_info, ret,
-				      "Failed to recover log tree");
+	if (unlikely(ret)) {
+		ASSERT(BTRFS_FS_ERROR(fs_info) != 0);
+		btrfs_err(fs_info, "failed to recover log trees with error: %d", ret);
 		return ret;
 	}
 

From 912db40655684a0a427c8b118dd0c36eb5a61fe4 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 09:49:49 +0000
Subject: [PATCH 0482/1303] btrfs: convert log messages to error level in
 btrfs_replay_log()

We are logging messages as warnings but they should really have an error
level instead, as if the respective conditions are met the mount will
fail. So convert them to error level and also log the error code returned
by read_tree_block().

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e6574456a306..028ba86bcf73 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1994,7 +1994,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	int level = btrfs_super_log_root_level(disk_super);
 
 	if (unlikely(fs_devices->rw_devices == 0)) {
-		btrfs_warn(fs_info, "log replay required on RO media");
+		btrfs_err(fs_info, "log replay required on RO media");
 		return -EIO;
 	}
 
@@ -2008,9 +2008,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	check.owner_root = BTRFS_TREE_LOG_OBJECTID;
 	log_tree_root->node = read_tree_block(fs_info, bytenr, &check);
 	if (IS_ERR(log_tree_root->node)) {
-		btrfs_warn(fs_info, "failed to read log tree");
 		ret = PTR_ERR(log_tree_root->node);
 		log_tree_root->node = NULL;
+		btrfs_err(fs_info, "failed to read log tree with error: %d", ret);
 		btrfs_put_root(log_tree_root);
 		return ret;
 	}

From 8ac7fad32b93044f4350ab35f11fee1a61286723 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Feb 2026 14:23:29 +0000
Subject: [PATCH 0483/1303] btrfs: remove pointless WARN_ON() in
 cache_save_setup()

This WARN_ON(ret) is never executed since the previous if statement makes
us jump into the 'out_put' label when ret is not zero. The existing
transaction abort inside the if statement also gives us a stack trace,
so we don't need to move the WARN_ON(ret) into the if statement either.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5f76683b3f21..77285ade3a0e 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -3341,7 +3341,6 @@ static int cache_save_setup(struct btrfs_block_group *block_group,
 		btrfs_abort_transaction(trans, ret);
 		goto out_put;
 	}
-	WARN_ON(ret);
 
 	/* We've already setup this transaction, go ahead and exit */
 	if (block_group->cache_generation == trans->transid &&

From 2ab22446425c2c72b44926bc964c263e06e7e137 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 11 Feb 2026 11:01:25 -0800
Subject: [PATCH 0484/1303] btrfs: fix referenced/exclusive check in
 squota_check_parent_usage()

We compared rfer_cmpr against excl_cmpr_sum instead of rfer_cmpr_sum
which is confusing.

I expect that
rfer_cmpr == excl_cmpr in squota, but it is much better to be consistent
in case of any surprises or bugs.

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/cover.1764796022.git.boris@bur.io/T/#mccb231643ffd290b44a010d4419474d280be5537
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 38adadb936dc..19edd25ff5d1 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -370,7 +370,7 @@ static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrf
 		nr_members++;
 	}
 	mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum ||
-		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum);
+		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != rfer_cmpr_sum);
 
 	WARN(mismatch,
 	     "parent squota qgroup %hu/%llu has mismatched usage from its %d members. "

From 3f501412f2079ca14bf68a18d80a2b7a823f1f64 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Miquel=20Sabat=C3=A9=20Sol=C3=A0?= <mssola@mssola.com>
Date: Mon, 16 Feb 2026 22:12:15 +0100
Subject: [PATCH 0485/1303] btrfs: free pages on error in
 btrfs_uring_read_extent()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In this function the 'pages' object is never freed in the hopes that it is
picked up by btrfs_uring_read_finished() whenever that executes in the
future. But that's just the happy path. Along the way previous
allocations might have gone wrong, or we might not get -EIOCBQUEUED from
btrfs_encoded_read_regular_fill_pages(). In all these cases, we go to a
cleanup section that frees all memory allocated by this function without
assuming any deferred execution, and this also needs to happen for the
'pages' allocation.

Fixes: 34310c442e17 ("btrfs: add io_uring command for encoded reads (ENCODED_READ ioctl)")
Signed-off-by: Miquel Sabaté Solà <mssola@mssola.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f1b56be6f8f4..dadf9bf30f08 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4651,7 +4651,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
 	struct extent_io_tree *io_tree = &inode->io_tree;
-	struct page **pages;
+	struct page **pages = NULL;
 	struct btrfs_uring_priv *priv = NULL;
 	unsigned long nr_pages;
 	int ret;
@@ -4709,6 +4709,11 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
 	btrfs_unlock_extent(io_tree, start, lockend, &cached_state);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	kfree(priv);
+	for (int i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			__free_page(pages[i]);
+	}
+	kfree(pages);
 	return ret;
 }
 

From a7526533128fd3210e15cee1e14c7a0fe97087c1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Miquel=20Sabat=C3=A9=20Sol=C3=A0?= <mssola@mssola.com>
Date: Mon, 16 Feb 2026 01:22:52 +0100
Subject: [PATCH 0486/1303] btrfs: don't commit the super block when unmounting
 a shutdown filesystem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When unmounting a filesystem we will try, among many other things, to
commit the super block. On a filesystem that was shutdown, though, this
will always fail with -EROFS as writes are forbidden on this context;
and an error will be reported.

Don't commit the super block on this situation, which should be fine as
the filesystem is frozen before shutdown and, therefore, it should be at
a consistent state.

Signed-off-by: Miquel Sabaté Solà <mssola@mssola.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 028ba86bcf73..6a38489a4e18 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4397,9 +4397,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 		 */
 		btrfs_flush_workqueue(fs_info->delayed_workers);
 
-		ret = btrfs_commit_super(fs_info);
-		if (ret)
-			btrfs_err(fs_info, "commit super ret %d", ret);
+		/*
+		 * If the filesystem is shutdown, then an attempt to commit the
+		 * super block (or any write) will just fail. Since we freeze
+		 * the filesystem before shutting it down, the filesystem is in
+		 * a consistent state and we don't need to commit super blocks.
+		 */
+		if (!btrfs_is_shutdown(fs_info)) {
+			ret = btrfs_commit_super(fs_info);
+			if (ret)
+				btrfs_err(fs_info, "commit super block returned %d", ret);
+		}
 	}
 
 	kthread_stop(fs_info->transaction_kthread);

From 3cf0f35779d364cf2003c617bb7f3f3e41023372 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 18:25:42 +0000
Subject: [PATCH 0487/1303] btrfs: fix error message order of parameters in
 btrfs_delete_delayed_dir_index()

Fix the error message in btrfs_delete_delayed_dir_index() if
__btrfs_add_delayed_item() fails: the message says root, inode, index,
error, but we're actually passing index, root, inode, error.

Fixes: adc1ef55dc04 ("btrfs: add details to error messages at btrfs_delete_delayed_dir_index()")
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 1739a0b29c49..2746841c167d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1657,7 +1657,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	if (unlikely(ret)) {
 		btrfs_err(trans->fs_info,
 "failed to add delayed dir index item, root: %llu, inode: %llu, index: %llu, error: %d",
-			  index, btrfs_root_id(node->root), node->inode_id, ret);
+			  btrfs_root_id(node->root), node->inode_id, index, ret);
 		btrfs_delayed_item_release_metadata(dir->root, item);
 		btrfs_release_delayed_item(item);
 	}

From 511dc8912ae3e929c1a182f5e6b2326516fd42a0 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 10:21:44 +0000
Subject: [PATCH 0488/1303] btrfs: fix incorrect key offset in error message in
 check_dev_extent_item()

Fix the error message in check_dev_extent_item(), when an overlapping
stripe is encountered. For dev extents, objectid is the disk number and
offset the physical address, so prev_key->objectid should actually be
prev_key->offset.

(I can't take any credit for this one - this was discovered by Chris and
his friend Claude.)

Reported-by: Chris Mason <clm@fb.com>
Fixes: 008e2512dc56 ("btrfs: tree-checker: add dev extent item checks")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 452394b34d01..9774779f060b 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1921,7 +1921,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf,
 		if (unlikely(prev_key->offset + prev_len > key->offset)) {
 			generic_err(leaf, slot,
 		"dev extent overlap, prev offset %llu len %llu current offset %llu",
-				    prev_key->objectid, prev_len, key->offset);
+				    prev_key->offset, prev_len, key->offset);
 			return -EUCLEAN;
 		}
 	}

From a10172780526c2002e062102ad4f2aabac495889 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 14:39:46 +0000
Subject: [PATCH 0489/1303] btrfs: fix objectid value in error message in
 check_extent_data_ref()

Fix a copy-paste error in check_extent_data_ref(): we're printing root
as in the message above, we should be printing objectid.

Fixes: f333a3c7e832 ("btrfs: tree-checker: validate dref root and objectid")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 9774779f060b..ac4c4573ee39 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1740,7 +1740,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
 			     objectid > BTRFS_LAST_FREE_OBJECTID)) {
 			extent_err(leaf, slot,
 				   "invalid extent data backref objectid value %llu",
-				   root);
+				   objectid);
 			return -EUCLEAN;
 		}
 		if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {

From 44e2fda66427a0442d8d2c0e6443256fb458ab6b Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:46:13 +0000
Subject: [PATCH 0490/1303] btrfs: fix warning in scrub_verify_one_metadata()

Commit b471965fdb2d ("btrfs: fix replace/scrub failure with
metadata_uuid") fixed the comparison in scrub_verify_one_metadata() to
use metadata_uuid rather than fsid, but left the warning as it was. Fix
it so it matches what we're doing.

Fixes: b471965fdb2d ("btrfs: fix replace/scrub failure with metadata_uuid")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2a64e2d50ced..052d83feea9a 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -744,7 +744,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		btrfs_warn_rl(fs_info,
 	      "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU",
 			      logical, stripe->mirror_num,
-			      header->fsid, fs_info->fs_devices->fsid);
+			      header->fsid, fs_info->fs_devices->metadata_uuid);
 		return;
 	}
 	if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid,

From 1c7e9111f4e6d6d42bc47759c9af1ef91f03ac2c Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:32:39 +0000
Subject: [PATCH 0491/1303] btrfs: print correct subvol num if active swapfile
 prevents deletion

Fix the error message in btrfs_delete_subvolume() if we can't delete a
subvolume because it has an active swapfile: we were printing the number
of the parent rather than the target.

Fixes: 60021bd754c6 ("btrfs: prevent subvol with swapfile from being deleted")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ade590707793..d28d55beaacd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4779,7 +4779,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
-			   btrfs_root_id(root));
+			   btrfs_root_id(dest));
 		ret = -EPERM;
 		goto out_up_write;
 	}

From 587bb33b10bda645a1028c1737ad3992b3d7cf61 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:46:41 +0000
Subject: [PATCH 0492/1303] btrfs: fix compat mask in error messages in
 btrfs_check_features()

Commit d7f67ac9a928 ("btrfs: relax block-group-tree feature dependency
checks") introduced a regression when it comes to handling unsupported
incompat or compat_ro flags. Beforehand we only printed the flags that
we didn't recognize, afterwards we printed them all, which is less
useful. Fix the error handling so it behaves like it used to.

Fixes: d7f67ac9a928 ("btrfs: relax block-group-tree feature dependency checks")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6a38489a4e18..49987334dd15 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3187,7 +3187,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
 		btrfs_err(fs_info,
 		"cannot mount because of unknown incompat features (0x%llx)",
-		    incompat);
+		    incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP);
 		return -EINVAL;
 	}
 
@@ -3219,7 +3219,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (compat_ro_unsupp && is_rw_mount) {
 		btrfs_err(fs_info,
 	"cannot mount read-write because of unknown compat_ro features (0x%llx)",
-		       compat_ro);
+		       compat_ro_unsupp);
 		return -EINVAL;
 	}
 
@@ -3232,7 +3232,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
 		btrfs_err(fs_info,
 "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
-			  compat_ro);
+			  compat_ro_unsupp);
 		return -EINVAL;
 	}
 

From f15fb3d41543244d1179f423da4a4832a55bc050 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Fri, 20 Feb 2026 12:53:17 +0000
Subject: [PATCH 0493/1303] btrfs: fix chunk map leak in btrfs_map_block()
 after btrfs_chunk_map_num_copies()

Fix a chunk map leak in btrfs_map_block(): if we return early with -EINVAL,
we're not freeing the chunk map that we've just looked up.

Fixes: 0ae653fbec2b ("btrfs: reduce chunk_map lookups in btrfs_map_block()")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 50f7aae70418..b8cbd3ecb94d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6921,8 +6921,10 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	}
 
 	num_copies = btrfs_chunk_map_num_copies(map);
-	if (io_geom.mirror_num > num_copies)
-		return -EINVAL;
+	if (io_geom.mirror_num > num_copies) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	map_offset = logical - map->start;
 	io_geom.raid56_full_stripe_start = (u64)-1;

From 54b9395b186a60d1655186c561a505c590654395 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Fri, 20 Feb 2026 12:52:56 +0000
Subject: [PATCH 0494/1303] btrfs: fix chunk map leak in btrfs_map_block()
 after btrfs_translate_remap()

If the call to btrfs_translate_remap() in btrfs_map_block() returns an
error code, we were leaking the chunk map. Fix it by jumping to out
rather than returning directly.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125830.2352988-1-clm@meta.com/
Fixes: 18ba64992871 ("btrfs: redirect I/O for remapped block groups")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b8cbd3ecb94d..3c37c5d2267b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6907,7 +6907,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 
 		ret = btrfs_translate_remap(fs_info, &new_logical, length);
 		if (ret)
-			return ret;
+			goto out;
 
 		if (new_logical != logical) {
 			btrfs_free_chunk_map(map);

From 7885ca40c305c64ffa444e1fc55edd6acb7a6e5b Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 14:16:02 +0000
Subject: [PATCH 0495/1303] btrfs: fix transaction handle leaks in
 btrfs_last_identity_remap_gone()

btrfs_abort_transaction(), unlike btrfs_commit_transaction(), doesn't
also free the transaction handle. Fix the instances in
btrfs_last_identity_remap_gone() where we're also leaking the
transaction on abort.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125129.2245240-1-clm@meta.com/
Fixes: 979e1dc3d69e ("btrfs: handle deletions from remapped block group")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fcd0a2ba3554..2119dddd6f8e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4723,6 +4723,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = btrfs_remove_dev_extents(trans, chunk_map);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 
@@ -4732,6 +4733,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 		if (unlikely(ret)) {
 			mutex_unlock(&trans->fs_info->chunk_mutex);
 			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
 			return ret;
 		}
 	}
@@ -4750,6 +4752,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = remove_chunk_stripes(trans, chunk_map, path);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 

From f8db8009ea65297dba7786668d4561f6dbd99678 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 14:30:59 +0000
Subject: [PATCH 0496/1303] btrfs: check block group lookup in
 remove_range_from_remap_tree()

Add a check in remove_range_from_remap_tree() after we call
btrfs_lookup_block_group(), to check if it is NULL. This shouldn't
happen, but if it does we at least get an error rather than a segfault.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125129.2245240-1-clm@meta.com/
Fixes: 979e1dc3d69e ("btrfs: handle deletions from remapped block group")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2119dddd6f8e..cdb53c0b26ec 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -5985,6 +5985,9 @@ static int remove_range_from_remap_tree(struct btrfs_trans_handle *trans,
 		struct btrfs_block_group *dest_bg;
 
 		dest_bg = btrfs_lookup_block_group(fs_info, new_addr);
+		if (unlikely(!dest_bg))
+			return -EUCLEAN;
+
 		adjust_block_group_remap_bytes(trans, dest_bg, -overlap_length);
 		btrfs_put_block_group(dest_bg);
 		ret = btrfs_add_to_free_space_tree(trans,

From 22f8bcec5aeb05104b3eaa950cb5a345e95f0aa8 Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 3 Feb 2026 08:55:07 +0800
Subject: [PATCH 0497/1303] HID: intel-ish-hid: ipc: Add Nova Lake-H/S PCI
 device IDs

Add device IDs of Nova Lake-H and Nova Lake-S into ishtp support list.

Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ipc/hw-ish.h  |  2 ++
 drivers/hid/intel-ish-hid/ipc/pci-ish.c | 12 ++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index fa5d68c36313..27389971b96c 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -39,6 +39,8 @@
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_H		0xE345
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P		0xE445
 #define PCI_DEVICE_ID_INTEL_ISH_WCL		0x4D45
+#define PCI_DEVICE_ID_INTEL_ISH_NVL_H		0xD354
+#define PCI_DEVICE_ID_INTEL_ISH_NVL_S		0x6E78
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 1612e8cb23f0..ed3405c05e73 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -28,11 +28,15 @@ enum ishtp_driver_data_index {
 	ISHTP_DRIVER_DATA_LNL_M,
 	ISHTP_DRIVER_DATA_PTL,
 	ISHTP_DRIVER_DATA_WCL,
+	ISHTP_DRIVER_DATA_NVL_H,
+	ISHTP_DRIVER_DATA_NVL_S,
 };
 
 #define ISH_FW_GEN_LNL_M "lnlm"
 #define ISH_FW_GEN_PTL "ptl"
 #define ISH_FW_GEN_WCL "wcl"
+#define ISH_FW_GEN_NVL_H "nvlh"
+#define ISH_FW_GEN_NVL_S "nvls"
 
 #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin"
 #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin"
@@ -47,6 +51,12 @@ static struct ishtp_driver_data ishtp_driver_data[] = {
 	[ISHTP_DRIVER_DATA_WCL] = {
 		.fw_generation = ISH_FW_GEN_WCL,
 	},
+	[ISHTP_DRIVER_DATA_NVL_H] = {
+		.fw_generation = ISH_FW_GEN_NVL_H,
+	},
+	[ISHTP_DRIVER_DATA_NVL_S] = {
+		.fw_generation = ISH_FW_GEN_NVL_S,
+	},
 };
 
 static const struct pci_device_id ish_pci_tbl[] = {
@@ -76,6 +86,8 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)},
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)},
 	{PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)},
+	{PCI_DEVICE_DATA(INTEL, ISH_NVL_H, ISHTP_DRIVER_DATA_NVL_H)},
+	{PCI_DEVICE_DATA(INTEL, ISH_NVL_S, ISHTP_DRIVER_DATA_NVL_S)},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);

From 7c698de0dc5daa1e1a5fd1f0c6aa1b6bb2f5d867 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 24 Feb 2026 10:00:02 +0100
Subject: [PATCH 0498/1303] HID: apple: Add EPOMAKER TH87 to the non-apple
 keyboards list

EPOMAKER TH87 has the very same ID as Apple Aluminum keyboard
(05ac:024f) although it doesn't work as expected in compatible way.

Put three entries to the non-apple keyboards list to exclude this
device: one for BT ("TH87"), one for USB ("HFD Epomaker TH87") and one
for dongle ("2.4G Wireless Receiver").

Link: https://bugzilla.suse.com/show_bug.cgi?id=1258455
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-apple.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 894adc23367b..9dcb252c5d6c 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -365,6 +365,9 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = {
 	{ "A3R" },
 	{ "hfd.cn" },
 	{ "WKB603" },
+	{ "TH87" },			/* EPOMAKER TH87 BT mode */
+	{ "HFD Epomaker TH87" },	/* EPOMAKER TH87 USB mode */
+	{ "2.4G Wireless Receiver" },	/* EPOMAKER TH87 dongle */
 };
 
 static bool apple_is_non_apple_keyboard(struct hid_device *hdev)

From 8f153eb745463b0715f1aad41e765cd83e9da8c0 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 29 Jan 2026 10:24:05 +0800
Subject: [PATCH 0499/1303] wifi: ath12k: use correct pdev id when requesting
 firmware stats

To get firmware statistics, currently ar->pdev->pdev_id is passed as an
argument to ath12k_mac_get_fw_stats() in ath12k_mac_op_sta_statistics().
For single pdev device like WCN7850, its value is 0 which represents the
SoC pdev id. As a result, WCN7850 firmware sends the same reply to host
twice, which further results in memory leak:

  unreferenced object 0xffff88812e286000 (size 192):
  comm "softirq", pid 0, jiffies 4294981997
  hex dump (first 32 bytes):
    10 a5 40 11 81 88 ff ff 10 a5 40 11 81 88 ff ff  ..@.......@.....
    00 00 00 00 00 00 00 00 80 ff ff ff 33 05 00 00  ............3...
  backtrace (crc cecc8c82):
    __kmalloc_cache_noprof
    ath12k_wmi_tlv_fw_stats_parse
    ath12k_wmi_tlv_iter
    ath12k_wmi_op_rx
    ath12k_htc_rx_completion_handler
    ath12k_ce_per_engine_service
    ath12k_pci_ce_workqueue
    process_one_work
    bh_worker
    tasklet_action
    handle_softirqs

Detailed explanation is:

  1. ath12k_mac_get_fw_stats() called in ath12k_mac_op_sta_statistics() to
     get vdev statistics, making the caller thread wait.
  2. firmware sends the first reply, ath12k_wmi_tlv_fw_stats_data_parse()
     allocates buffers to cache necessary information. Following that, in
     ath12k_wmi_fw_stats_process() if events of all started vdev haved been
     received, is_end flag is set hence the waiting thread gets waken up by
     the ar->fw_stats_done/->fw_stats_complete signals.
  3. ath12k_mac_get_fw_stats() wakes up and returns successfully.
     ath12k_mac_op_sta_statistics() saves required parameters and calls
     ath12k_fw_stats_reset() to free buffers allocated earlier.
  4. firmware sends the second reply. As usual, buffers are allocated and
     attached to the ar->fw_stats.vdevs list. Note this time there is no
     thread waiting, therefore no chance to free those buffers.
  5. ath12k module gets unloaded. If there has been no more firmware
     statistics request made since step 4, or if the request fails (see
     the example in the following patch), there is no chance to call
     ath12k_fw_stats_reset(). Consequently those buffers leak.

Actually for single pdev device, using SoC pdev id in
ath12k_mac_op_sta_statistics() is wrong, because the purpose is to get
statistics of a specific station, which is mapped to a specific pdev. That
said, the id of actual individual pdev should be fetched and used instead.
The helper ath12k_mac_get_target_pdev_id() serves for this purpose, hence
use it to fix this issue. Note it also works for other devices as well due
to the single_pdev_only check inside.

The same applies to ath12k_mac_op_get_txpower() and
ath12k_mac_op_link_sta_statistics() as well.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00302-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.115823.3

Fixes: 79e7b04b5388 ("wifi: ath12k: report station mode signal strength")
Fixes: e92c658b056b ("wifi: ath12k: add get_txpower mac ops")
Fixes: ebebe66ec208 ("wifi: ath12k: fill link station statistics for MLO")
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260129-ath12k-fw-stats-fixes-v1-1-55d66064f4d5@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 68431a0e128e..5287fa2f66e5 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5430,7 +5430,7 @@ int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw,
 					 ar->last_tx_power_update))
 		goto send_tx_power;
 
-	params.pdev_id = ar->pdev->pdev_id;
+	params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 	params.vdev_id = arvif->vdev_id;
 	params.stats_id = WMI_REQUEST_PDEV_STAT;
 	ret = ath12k_mac_get_fw_stats(ar, &params);
@@ -13452,7 +13452,7 @@ void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	/* TODO: Use real NF instead of default one. */
 	signal = rate_info.rssi_comb;
 
-	params.pdev_id = ar->pdev->pdev_id;
+	params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 	params.vdev_id = 0;
 	params.stats_id = WMI_REQUEST_VDEV_STAT;
 
@@ -13580,7 +13580,7 @@ void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw,
 	spin_unlock_bh(&ar->ab->dp->dp_lock);
 
 	if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA) {
-		params.pdev_id = ar->pdev->pdev_id;
+		params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 		params.vdev_id = 0;
 		params.stats_id = WMI_REQUEST_VDEV_STAT;
 

From 7259b1a0e54c2d3051ac8f1eb01de121b11118ea Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 29 Jan 2026 10:24:06 +0800
Subject: [PATCH 0500/1303] wifi: ath12k: fix station lookup failure when
 disconnecting from AP

In ath12k_wmi_tlv_fw_stats_data_parse() and
ath12k_wmi_tlv_rssi_chain_parse(), the driver uses
ieee80211_find_sta_by_ifaddr() to look up the station associated with the
incoming firmware statistics. This works under normal conditions but fails
during AP disconnection, resulting in log messages like:

 wlan0: deauthenticating from xxxxxx by local choice (Reason: 3=DEAUTH_LEAVING)
 wlan0: moving STA xxxxxx to state 3
 wlan0: moving STA xxxxxx to state 2
 wlan0: moving STA xxxxxx to state 1
 ath12k_pci 0000:02:00.0: not found station bssid xxxxxx for vdev stat
 ath12k_pci 0000:02:00.0: not found station of bssid xxxxxx for rssi chain
 ath12k_pci 0000:02:00.0: failed to pull fw stats: -71
 ath12k_pci 0000:02:00.0: time out while waiting for get fw stats
 wlan0: Removed STA xxxxxx
 wlan0: Destroyed STA xxxxxx

The failure happens because the station has already been removed from
ieee80211_local::sta_hash by the time firmware statistics are requested
through drv_sta_statistics().

Switch the lookup to ath12k_link_sta_find_by_addr(), which searches the
driver's link station hash table that still has the station recorded
at that time.  This also implicitly fixes another issue: the current code
always uses deflink regardless of which link the statistics belong to,
which is incorrect in MLO scenarios. The new helper returns the correct
link station.

Additionally, raise the log level on lookup failures. With the updated
helper, such failures should no longer occur under normal conditions.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00302-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.115823.3

Fixes: 79e7b04b5388 ("wifi: ath12k: report station mode signal strength")
Fixes: 6af5bc381b36 ("wifi: ath12k: report station mode per-chain signal strength")
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260129-ath12k-fw-stats-fixes-v1-2-55d66064f4d5@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 36 ++++++++++-----------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 7617fc3a2479..404f031a3c87 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8241,8 +8241,6 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 	struct ath12k_fw_stats *stats = parse->stats;
 	struct ath12k *ar;
 	struct ath12k_link_vif *arvif;
-	struct ieee80211_sta *sta;
-	struct ath12k_sta *ahsta;
 	struct ath12k_link_sta *arsta;
 	int i, ret = 0;
 	const void *data = ptr;
@@ -8278,21 +8276,19 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 
 		arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id));
 		if (arvif) {
-			sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar),
-							   arvif->bssid,
-							   NULL);
-			if (sta) {
-				ahsta = ath12k_sta_to_ahsta(sta);
-				arsta = &ahsta->deflink;
+			spin_lock_bh(&ab->base_lock);
+			arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid);
+			if (arsta) {
 				arsta->rssi_beacon = le32_to_cpu(src->beacon_snr);
 				ath12k_dbg(ab, ATH12K_DBG_WMI,
 					   "wmi stats vdev id %d snr %d\n",
 					   src->vdev_id, src->beacon_snr);
 			} else {
-				ath12k_dbg(ab, ATH12K_DBG_WMI,
-					   "not found station bssid %pM for vdev stat\n",
-					   arvif->bssid);
+				ath12k_warn(ab,
+					    "not found link sta with bssid %pM for vdev stat\n",
+					    arvif->bssid);
 			}
+			spin_unlock_bh(&ab->base_lock);
 		}
 
 		data += sizeof(*src);
@@ -8363,8 +8359,6 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab,
 	struct ath12k_fw_stats *stats = parse->stats;
 	struct ath12k_link_vif *arvif;
 	struct ath12k_link_sta *arsta;
-	struct ieee80211_sta *sta;
-	struct ath12k_sta *ahsta;
 	struct ath12k *ar;
 	int vdev_id;
 	int j;
@@ -8400,19 +8394,15 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab,
 		   "stats bssid %pM vif %p\n",
 		   arvif->bssid, arvif->ahvif->vif);
 
-	sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar),
-					   arvif->bssid,
-					   NULL);
-	if (!sta) {
-		ath12k_dbg(ab, ATH12K_DBG_WMI,
-			   "not found station of bssid %pM for rssi chain\n",
-			   arvif->bssid);
+	guard(spinlock_bh)(&ab->base_lock);
+	arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid);
+	if (!arsta) {
+		ath12k_warn(ab,
+			    "not found link sta with bssid %pM for rssi chain\n",
+			    arvif->bssid);
 		return -EPROTO;
 	}
 
-	ahsta = ath12k_sta_to_ahsta(sta);
-	arsta = &ahsta->deflink;
-
 	BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) >
 		     ARRAY_SIZE(stats_rssi->rssi_avg_beacon));
 

From 3540cc453f5679d8c4d5ccc9834a1f5f8184af3a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:43:48 +0100
Subject: [PATCH 0501/1303] ALSA: usb-audio: Drop superfluous kernel-doc
 markers

We don't process USB-audio driver code for kernel-doc, and the "/**"
marker leads to warnings with W=1 builds.  Drop the superfluous
markers.

Link: https://patch.msgid.link/20260226154414.1081568-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_s1810c.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/sound/usb/mixer_s1810c.c b/sound/usb/mixer_s1810c.c
index 473cb29efa7f..7eac7d1bce64 100644
--- a/sound/usb/mixer_s1810c.c
+++ b/sound/usb/mixer_s1810c.c
@@ -71,7 +71,7 @@
  *   * e I guess the same as with mixer
  *
  */
-/** struct s1810c_ctl_packet - basic vendor request
+/* struct s1810c_ctl_packet - basic vendor request
  * @selector: device/mixer/output
  * @b: request-dependant field b
  * @tag: fixed value identifying type of request
@@ -94,14 +94,14 @@ struct s1810c_ctl_packet {
 	__le32 e;
 };
 
-/** selectors for CMD request
+/* selectors for CMD request
  */
 #define SC1810C_SEL_DEVICE 0
 #define SC1810C_SEL_MIXER 0x64
 #define SC1810C_SEL_OUTPUT 0x65
 
 
-/** control ids */
+/* control ids */
 #define SC1810C_CTL_LINE_SW	0
 #define SC1810C_CTL_MUTE_SW	1
 #define SC1824C_CTL_MONO_SW	2
@@ -127,7 +127,7 @@ struct s1810c_ctl_packet {
 #define SC1810C_GET_STATE_TAG	SC1810C_SET_STATE_TAG
 #define SC1810C_GET_STATE_LEN	SC1810C_SET_STATE_LEN
 
-/** Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB).
+/* Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB).
  * raw_level = 2^24 * 10^(db_level / 20), thus
  * -3dB = 0xb53bf0 (technically, half-power -3.01...dB would be 0xb504f3)
  * -96dB = 0x109
@@ -145,7 +145,7 @@ struct s1810c_ctl_packet {
 #define MIXER_LEVEL_N3DB 0xb53bf0
 #define MIXER_LEVEL_0DB 0x1000000
 
-/**
+/*
  * This packet includes mixer volumes and
  * various other fields, it's an extended
  * version of ctl_packet, with a and b
@@ -155,7 +155,7 @@ struct s1810c_state_packet {
 	__le32 fields[63];
 };
 
-/** indices into s1810c_state_packet.fields[]
+/* indices into s1810c_state_packet.fields[]
  */
 #define SC1810C_STATE_TAG_IDX	2
 #define SC1810C_STATE_LEN_IDX	3

From 1d6452a0ce78cd3f4e48943b5ba21d273a658298 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:43:49 +0100
Subject: [PATCH 0502/1303] ALSA: usb: qcom: Correct parameter comment for
 uaudio_transfer_buffer_setup()

At fixing the memory leak of xfer buffer, we forgot to update the
corresponding comment, too.  This resulted in a kernel-doc warning
with W=1.  Let's correct it.

Fixes: 5c7ef5001292 ("ALSA: qc_audio_offload: avoid leaking xfer_buf allocation")
Link: https://patch.msgid.link/20260226154414.1081568-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/qcom/qc_audio_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 01e6063c2207..510b68cced33 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -1007,7 +1007,7 @@ static int enable_audio_stream(struct snd_usb_substream *subs,
 /**
  * uaudio_transfer_buffer_setup() - fetch and populate xfer buffer params
  * @subs: usb substream
- * @xfer_buf: xfer buf to be allocated
+ * @xfer_buf_cpu: xfer buf to be allocated
  * @xfer_buf_len: size of allocation
  * @mem_info: QMI response info
  *

From dc9786a06d53291a5af824e854dd0769b1a97dbe Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:54:45 +0100
Subject: [PATCH 0503/1303] ALSA: us144mkii: Drop kernel-doc markers

We don't process this driver code for kernel-doc, and the "/**" marker
leads to warnings with W=1 builds.  Drop the superfluous markers, and
also fix the invalid mark up, too.

Link: https://patch.msgid.link/20260226155456.1092186-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/us144mkii.c          | 14 +++++-----
 sound/usb/usx2y/us144mkii_capture.c  | 12 ++++----
 sound/usb/usx2y/us144mkii_controls.c | 42 ++++++++++++++--------------
 sound/usb/usx2y/us144mkii_midi.c     | 22 +++++++--------
 sound/usb/usx2y/us144mkii_playback.c | 10 +++----
 5 files changed, 50 insertions(+), 50 deletions(-)

diff --git a/sound/usb/usx2y/us144mkii.c b/sound/usb/usx2y/us144mkii.c
index bc71968df8e2..0cf4fa74e210 100644
--- a/sound/usb/usx2y/us144mkii.c
+++ b/sound/usb/usx2y/us144mkii.c
@@ -10,8 +10,8 @@ MODULE_AUTHOR("Šerif Rami <ramiserifpersia@gmail.com>");
 MODULE_DESCRIPTION("ALSA Driver for TASCAM US-144MKII");
 MODULE_LICENSE("GPL");
 
-/**
- * @brief Module parameters for ALSA card instantiation.
+/*
+ * Module parameters for ALSA card instantiation.
  *
  * These parameters allow users to configure how the ALSA sound card
  * for the TASCAM US-144MKII is instantiated.
@@ -269,7 +269,7 @@ void tascam_stop_work_handler(struct work_struct *work)
 	atomic_set(&tascam->active_urbs, 0);
 }
 
-/**
+/*
  * tascam_card_private_free() - Frees private data associated with the sound
  * card.
  * @card: Pointer to the ALSA sound card instance.
@@ -291,7 +291,7 @@ static void tascam_card_private_free(struct snd_card *card)
 	}
 }
 
-/**
+/*
  * tascam_suspend() - Handles device suspension.
  * @intf: The USB interface being suspended.
  * @message: Power management message.
@@ -332,7 +332,7 @@ static int tascam_suspend(struct usb_interface *intf, pm_message_t message)
 	return 0;
 }
 
-/**
+/*
  * tascam_resume() - Handles device resumption from suspend.
  * @intf: The USB interface being resumed.
  *
@@ -390,7 +390,7 @@ static void tascam_error_timer(struct timer_list *t)
 		schedule_work(&tascam->midi_out_work);
 }
 
-/**
+/*
  * tascam_probe() - Probes for the TASCAM US-144MKII device.
  * @intf: The USB interface being probed.
  * @usb_id: The USB device ID.
@@ -565,7 +565,7 @@ static int tascam_probe(struct usb_interface *intf,
 	return err;
 }
 
-/**
+/*
  * tascam_disconnect() - Disconnects the TASCAM US-144MKII device.
  * @intf: The USB interface being disconnected.
  *
diff --git a/sound/usb/usx2y/us144mkii_capture.c b/sound/usb/usx2y/us144mkii_capture.c
index 00188ff6cd51..af120bf62173 100644
--- a/sound/usb/usx2y/us144mkii_capture.c
+++ b/sound/usb/usx2y/us144mkii_capture.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_capture_open() - Opens the PCM capture substream.
  * @substream: The ALSA PCM substream to open.
  *
@@ -23,7 +23,7 @@ static int tascam_capture_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_close() - Closes the PCM capture substream.
  * @substream: The ALSA PCM substream to close.
  *
@@ -41,7 +41,7 @@ static int tascam_capture_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_prepare() - Prepares the PCM capture substream for use.
  * @substream: The ALSA PCM substream to prepare.
  *
@@ -62,7 +62,7 @@ static int tascam_capture_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_pointer() - Returns the current capture pointer position.
  * @substream: The ALSA PCM substream.
  *
@@ -91,7 +91,7 @@ tascam_capture_pointer(struct snd_pcm_substream *substream)
 	return do_div(pos, runtime->buffer_size);
 }
 
-/**
+/*
  * tascam_capture_ops - ALSA PCM operations for capture.
  *
  * This structure defines the callback functions for capture stream operations,
@@ -109,7 +109,7 @@ const struct snd_pcm_ops tascam_capture_ops = {
 	.pointer = tascam_capture_pointer,
 };
 
-/**
+/*
  * decode_tascam_capture_block() - Decodes a raw 512-byte block from the device.
  * @src_block: Pointer to the 512-byte raw source block.
  * @dst_block: Pointer to the destination buffer for decoded audio frames.
diff --git a/sound/usb/usx2y/us144mkii_controls.c b/sound/usb/usx2y/us144mkii_controls.c
index 62055fb8e7ba..81ded11e3709 100644
--- a/sound/usb/usx2y/us144mkii_controls.c
+++ b/sound/usb/usx2y/us144mkii_controls.c
@@ -3,8 +3,8 @@
 
 #include "us144mkii.h"
 
-/**
- * @brief Text descriptions for playback output source options.
+/*
+ * Text descriptions for playback output source options.
  *
  * Used by ALSA kcontrol elements to provide user-friendly names for
  * the playback routing options (e.g., "Playback 1-2", "Playback 3-4").
@@ -12,15 +12,15 @@
 static const char *const playback_source_texts[] = { "Playback 1-2",
 						     "Playback 3-4" };
 
-/**
- * @brief Text descriptions for capture input source options.
+/*
+ * Text descriptions for capture input source options.
  *
  * Used by ALSA kcontrol elements to provide user-friendly names for
  * the capture routing options (e.g., "Analog In", "Digital In").
  */
 static const char *const capture_source_texts[] = { "Analog In", "Digital In" };
 
-/**
+/*
  * tascam_playback_source_info() - ALSA control info callback for playback
  * source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -38,7 +38,7 @@ static int tascam_playback_source_info(struct snd_kcontrol *kcontrol,
 	return snd_ctl_enum_info(uinfo, 1, 2, playback_source_texts);
 }
 
-/**
+/*
  * tascam_line_out_get() - ALSA control get callback for Line Outputs Source.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure to fill.
@@ -60,7 +60,7 @@ static int tascam_line_out_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_line_out_put() - ALSA control put callback for Line Outputs Source.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure containing the new value.
@@ -89,7 +89,7 @@ static int tascam_line_out_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_line_out_control - ALSA kcontrol definition for Line Outputs Source.
  *
  * This defines a new ALSA mixer control named "Line OUTPUTS Source" that allows
@@ -106,7 +106,7 @@ static const struct snd_kcontrol_new tascam_line_out_control = {
 	.put = tascam_line_out_put,
 };
 
-/**
+/*
  * tascam_digital_out_get() - ALSA control get callback for Digital Outputs
  * Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -129,7 +129,7 @@ static int tascam_digital_out_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_digital_out_put() - ALSA control put callback for Digital Outputs
  * Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -159,7 +159,7 @@ static int tascam_digital_out_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_digital_out_control - ALSA kcontrol definition for Digital Outputs
  * Source.
  *
@@ -177,7 +177,7 @@ static const struct snd_kcontrol_new tascam_digital_out_control = {
 	.put = tascam_digital_out_put,
 };
 
-/**
+/*
  * tascam_capture_source_info() - ALSA control info callback for capture source.
  * @kcontrol: The ALSA kcontrol instance.
  * @uinfo: The ALSA control element info structure to fill.
@@ -194,7 +194,7 @@ static int tascam_capture_source_info(struct snd_kcontrol *kcontrol,
 	return snd_ctl_enum_info(uinfo, 1, 2, capture_source_texts);
 }
 
-/**
+/*
  * tascam_capture_12_get() - ALSA control get callback for Capture channels 1
  * and 2 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -217,7 +217,7 @@ static int tascam_capture_12_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_12_put() - ALSA control put callback for Capture channels 1
  * and 2 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -247,7 +247,7 @@ static int tascam_capture_12_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_capture_12_control - ALSA kcontrol definition for Capture channels 1
  * and 2 Source.
  *
@@ -265,7 +265,7 @@ static const struct snd_kcontrol_new tascam_capture_12_control = {
 	.put = tascam_capture_12_put,
 };
 
-/**
+/*
  * tascam_capture_34_get() - ALSA control get callback for Capture channels 3
  * and 4 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -288,7 +288,7 @@ static int tascam_capture_34_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_34_put() - ALSA control put callback for Capture channels 3
  * and 4 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -318,7 +318,7 @@ static int tascam_capture_34_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_capture_34_control - ALSA kcontrol definition for Capture channels 3
  * and 4 Source.
  *
@@ -336,7 +336,7 @@ static const struct snd_kcontrol_new tascam_capture_34_control = {
 	.put = tascam_capture_34_put,
 };
 
-/**
+/*
  * tascam_samplerate_info() - ALSA control info callback for Sample Rate.
  * @kcontrol: The ALSA kcontrol instance.
  * @uinfo: The ALSA control element info structure to fill.
@@ -356,7 +356,7 @@ static int tascam_samplerate_info(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_samplerate_get() - ALSA control get callback for Sample Rate.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure to fill.
@@ -400,7 +400,7 @@ static int tascam_samplerate_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_samplerate_control - ALSA kcontrol definition for Sample Rate.
  *
  * This defines a new ALSA mixer control named "Sample Rate" that displays
diff --git a/sound/usb/usx2y/us144mkii_midi.c b/sound/usb/usx2y/us144mkii_midi.c
index ed2afec2a89a..4871797b1670 100644
--- a/sound/usb/usx2y/us144mkii_midi.c
+++ b/sound/usb/usx2y/us144mkii_midi.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_midi_in_work_handler() - Deferred work for processing MIDI input.
  * @work: The work_struct instance.
  *
@@ -75,7 +75,7 @@ void tascam_midi_in_urb_complete(struct urb *urb)
 	usb_put_urb(urb);
 }
 
-/**
+/*
  * tascam_midi_in_open() - Opens the MIDI input substream.
  * @substream: The ALSA rawmidi substream to open.
  *
@@ -92,7 +92,7 @@ static int tascam_midi_in_open(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_in_close() - Closes the MIDI input substream.
  * @substream: The ALSA rawmidi substream to close.
  *
@@ -103,7 +103,7 @@ static int tascam_midi_in_close(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_in_trigger() - Triggers MIDI input stream activity.
  * @substream: The ALSA rawmidi substream.
  * @up: Boolean indicating whether to start (1) or stop (0) the stream.
@@ -150,7 +150,7 @@ static void tascam_midi_in_trigger(struct snd_rawmidi_substream *substream,
 	}
 }
 
-/**
+/*
  * tascam_midi_in_ops - ALSA rawmidi operations for MIDI input.
  *
  * This structure defines the callback functions for MIDI input stream
@@ -205,7 +205,7 @@ void tascam_midi_out_urb_complete(struct urb *urb)
 	usb_put_urb(urb);
 }
 
-/**
+/*
  * tascam_midi_out_work_handler() - Deferred work for sending MIDI data
  * @work: The work_struct instance.
  *
@@ -282,7 +282,7 @@ static void tascam_midi_out_work_handler(struct work_struct *work)
 	}
 }
 
-/**
+/*
  * tascam_midi_out_open() - Opens the MIDI output substream.
  * @substream: The ALSA rawmidi substream to open.
  *
@@ -301,7 +301,7 @@ static int tascam_midi_out_open(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_out_close() - Closes the MIDI output substream.
  * @substream: The ALSA rawmidi substream to close.
  *
@@ -312,7 +312,7 @@ static int tascam_midi_out_close(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_out_drain() - Drains the MIDI output stream.
  * @substream: The ALSA rawmidi substream.
  *
@@ -340,7 +340,7 @@ static void tascam_midi_out_drain(struct snd_rawmidi_substream *substream)
 	usb_kill_anchored_urbs(&tascam->midi_out_anchor);
 }
 
-/**
+/*
  * tascam_midi_out_trigger() - Triggers MIDI output stream activity.
  * @substream: The ALSA rawmidi substream.
  * @up: Boolean indicating whether to start (1) or stop (0) the stream.
@@ -361,7 +361,7 @@ static void tascam_midi_out_trigger(struct snd_rawmidi_substream *substream,
 	}
 }
 
-/**
+/*
  * tascam_midi_out_ops - ALSA rawmidi operations for MIDI output.
  *
  * This structure defines the callback functions for MIDI output stream
diff --git a/sound/usb/usx2y/us144mkii_playback.c b/sound/usb/usx2y/us144mkii_playback.c
index 0cb9699ec211..7efaca0a6489 100644
--- a/sound/usb/usx2y/us144mkii_playback.c
+++ b/sound/usb/usx2y/us144mkii_playback.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_playback_open() - Opens the PCM playback substream.
  * @substream: The ALSA PCM substream to open.
  *
@@ -23,7 +23,7 @@ static int tascam_playback_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_close() - Closes the PCM playback substream.
  * @substream: The ALSA PCM substream to close.
  *
@@ -41,7 +41,7 @@ static int tascam_playback_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_prepare() - Prepares the PCM playback substream for use.
  * @substream: The ALSA PCM substream to prepare.
  *
@@ -108,7 +108,7 @@ static int tascam_playback_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_pointer() - Returns the current playback pointer position.
  * @substream: The ALSA PCM substream.
  *
@@ -137,7 +137,7 @@ tascam_playback_pointer(struct snd_pcm_substream *substream)
 	return do_div(pos, runtime->buffer_size);
 }
 
-/**
+/*
  * tascam_playback_ops - ALSA PCM operations for playback.
  *
  * This structure defines the callback functions for playback stream operations,

From ec3070f01fa30f2c5547d645dbb76174304bf0e4 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Thu, 8 Jan 2026 17:09:54 +0100
Subject: [PATCH 0504/1303] HID: multitouch: Keep latency normal on deactivate
 for reactivation gesture

Uniwill devices have a built in gesture in the touchpad to de- and
reactivate it by double taping the upper left corner. This gesture stops
working when latency is set to high, so this patch keeps the latency on
normal.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
[jkosina@suse.com: change bit from 24 to 25]
[jkosina@suse.com: update shortlog]
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-multitouch.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 8052b35bfd7d..b8a748bbf0fd 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -77,6 +77,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_ORIENTATION_INVERT	BIT(22)
 #define MT_QUIRK_APPLE_TOUCHBAR		BIT(23)
 #define MT_QUIRK_YOGABOOK9I		BIT(24)
+#define MT_QUIRK_KEEP_LATENCY_ON_CLOSE	BIT(25)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -214,6 +215,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_WIN_8_DISABLE_WAKEUP		0x0016
 #define MT_CLS_WIN_8_NO_STICKY_FINGERS		0x0017
 #define MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU	0x0018
+#define MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE	0x0019
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -335,6 +337,15 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_WIN8_PTP_BUTTONS,
 		.export_all_inputs = true },
+	{ .name = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_STICKY_FINGERS |
+			MT_QUIRK_WIN8_PTP_BUTTONS |
+			MT_QUIRK_KEEP_LATENCY_ON_CLOSE,
+		.export_all_inputs = true },
 
 	/*
 	 * vendor specific classes
@@ -855,7 +866,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			if ((cls->name == MT_CLS_WIN_8 ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU ||
-			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) &&
+			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP ||
+			     cls->name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE) &&
 				(field->application == HID_DG_TOUCHPAD ||
 				 field->application == HID_DG_TOUCHSCREEN))
 				app->quirks |= MT_QUIRK_CONFIDENCE;
@@ -1768,7 +1780,8 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	int ret;
 
 	if (td->is_haptic_touchpad && (td->mtclass.name == MT_CLS_WIN_8 ||
-	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT)) {
+	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
+	    td->mtclass.name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE)) {
 		if (hid_haptic_input_configured(hdev, td->haptic, hi) == 0)
 			td->is_haptic_touchpad = false;
 	} else {
@@ -2081,7 +2094,12 @@ static void mt_on_hid_hw_open(struct hid_device *hdev)
 
 static void mt_on_hid_hw_close(struct hid_device *hdev)
 {
-	mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
+	struct mt_device *td = hid_get_drvdata(hdev);
+
+	if (td->mtclass.quirks & MT_QUIRK_KEEP_LATENCY_ON_CLOSE)
+		mt_set_modes(hdev, HID_LATENCY_NORMAL, TOUCHPAD_REPORT_NONE);
+	else
+		mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
 }
 
 /*
@@ -2468,6 +2486,14 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_UNITEC,
 			USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) },
 
+	/* Uniwill touchpads */
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0255) },
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0274) },
+
 	/* VTL panels */
 	{ .driver_data = MT_CLS_VTL,
 		MT_USB_DEVICE(USB_VENDOR_ID_VTL,

From 021ca6b670bebebc409d43845efcfe8c11c1dd54 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 23 Feb 2026 22:33:22 +0900
Subject: [PATCH 0505/1303] mm/slab: pass __GFP_NOWARN to refill_sheaf() if
 fallback is available

When refill_sheaf() is called, failing to refill the sheaf doesn't
necessarily mean the allocation will fail because a fallback path
might be available and serve the allocation request.

Suppress spurious warnings by passing __GFP_NOWARN along with
__GFP_NOMEMALLOC whenever a fallback path is available.

When the caller is alloc_full_sheaf() or __pcs_replace_empty_main(),
the kernel always falls back to the slowpath (__slab_alloc_node()).
For __prefill_sheaf_pfmemalloc(), the fallback path is available
only when gfp_pfmemalloc_allowed() returns true.

Reported-and-tested-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Closes: https://lore.kernel.org/linux-mm/aZt2-oS9lkmwT7Ch@debian.local
Fixes: 1ce20c28eafd ("slab: handle pfmemalloc slabs properly with sheaves")
Link: https://lore.kernel.org/linux-mm/aZwSreGj9-HHdD-j@hyeyoo
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260223133322.16705-1-harry.yoo@oracle.com
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 862642c165ed..4ce24d9ee7e4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2822,7 +2822,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 	if (!sheaf)
 		return NULL;
 
-	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC)) {
+	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 		free_empty_sheaf(s, sheaf);
 		return NULL;
 	}
@@ -4575,7 +4575,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 
 	if (empty) {
-		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC)) {
+		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 			full = empty;
 		} else {
 			/*
@@ -4890,9 +4890,14 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_noprof);
 static int __prefill_sheaf_pfmemalloc(struct kmem_cache *s,
 				      struct slab_sheaf *sheaf, gfp_t gfp)
 {
-	int ret = 0;
+	gfp_t gfp_nomemalloc;
+	int ret;
 
-	ret = refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC);
+	gfp_nomemalloc = gfp | __GFP_NOMEMALLOC;
+	if (gfp_pfmemalloc_allowed(gfp))
+		gfp_nomemalloc |= __GFP_NOWARN;
+
+	ret = refill_sheaf(s, sheaf, gfp_nomemalloc);
 
 	if (likely(!ret || !gfp_pfmemalloc_allowed(gfp)))
 		return ret;

From f3ec502b6755a3bfb12c1c47025ef989ff9efc72 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 25 Feb 2026 08:34:07 -0800
Subject: [PATCH 0506/1303] mm/slab: mark alloc tags empty for sheaves
 allocated with __GFP_NO_OBJ_EXT

alloc_empty_sheaf() allocates sheaves from SLAB_KMALLOC caches using
__GFP_NO_OBJ_EXT to avoid recursion, however it does not mark their
allocation tags empty before freeing, which results in a warning when
CONFIG_MEM_ALLOC_PROFILING_DEBUG is set. Fix this by marking allocation
tags for such sheaves as empty.

The problem was technically introduced in commit 4c0a17e28340 but only
becomes possible to hit with commit 913ffd3a1bf5.

Fixes: 4c0a17e28340 ("slab: prevent recursive kmalloc() in alloc_empty_sheaf()")
Fixes: 913ffd3a1bf5 ("slab: handle kmalloc sheaves bootstrap")
Reported-by: David Wang <00107082@163.com>
Closes: https://lore.kernel.org/all/20260223155128.3849-1-00107082@163.com/
Analyzed-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Tested-by: David Wang <00107082@163.com>
Link: https://patch.msgid.link/20260225163407.2218712-1-surenb@google.com
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 include/linux/gfp_types.h |  2 ++
 mm/slab.h                 |  4 ++--
 mm/slub.c                 | 33 +++++++++++++++++++++++----------
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 814bb2892f99..6c75df30a281 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
diff --git a/mm/slab.h b/mm/slab.h
index 71c7261bf822..f6ef862b60ef 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -290,14 +290,14 @@ static inline void *nearest_obj(struct kmem_cache *cache,
 
 /* Determine object index from a given position */
 static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
-					  void *addr, void *obj)
+					  void *addr, const void *obj)
 {
 	return reciprocal_divide(kasan_reset_tag(obj) - addr,
 				 cache->reciprocal_size);
 }
 
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
+					const struct slab *slab, const void *obj)
 {
 	if (is_kfence_address(obj))
 		return 0;
diff --git a/mm/slub.c b/mm/slub.c
index 4ce24d9ee7e4..52f021711744 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2041,18 +2041,18 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
+static inline void mark_obj_codetag_empty(const void *obj)
 {
-	struct slab *obj_exts_slab;
+	struct slab *obj_slab;
 	unsigned long slab_exts;
 
-	obj_exts_slab = virt_to_slab(obj_exts);
-	slab_exts = slab_obj_exts(obj_exts_slab);
+	obj_slab = virt_to_slab(obj);
+	slab_exts = slab_obj_exts(obj_slab);
 	if (slab_exts) {
 		get_slab_obj_exts(slab_exts);
-		unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
-						 obj_exts_slab, obj_exts);
-		struct slabobj_ext *ext = slab_obj_ext(obj_exts_slab,
+		unsigned int offs = obj_to_index(obj_slab->slab_cache,
+						 obj_slab, obj);
+		struct slabobj_ext *ext = slab_obj_ext(obj_slab,
 						       slab_exts, offs);
 
 		if (unlikely(is_codetag_empty(&ext->ref))) {
@@ -2090,7 +2090,7 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 
 #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {}
+static inline void mark_obj_codetag_empty(const void *obj) {}
 static inline bool mark_failed_objexts_alloc(struct slab *slab) { return false; }
 static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 			struct slabobj_ext *vec, unsigned int objects) {}
@@ -2211,7 +2211,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 		 * assign slabobj_exts in parallel. In this case the existing
 		 * objcg vector should be reused.
 		 */
-		mark_objexts_empty(vec);
+		mark_obj_codetag_empty(vec);
 		if (unlikely(!allow_spin))
 			kfree_nolock(vec);
 		else
@@ -2254,7 +2254,7 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin)
 	 * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that
 	 * the extension for obj_exts is expected to be NULL.
 	 */
-	mark_objexts_empty(obj_exts);
+	mark_obj_codetag_empty(obj_exts);
 	if (allow_spin)
 		kfree(obj_exts);
 	else
@@ -2312,6 +2312,10 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 
 #else /* CONFIG_SLAB_OBJ_EXT */
 
+static inline void mark_obj_codetag_empty(const void *obj)
+{
+}
+
 static inline void init_slab_obj_exts(struct slab *slab)
 {
 }
@@ -2783,6 +2787,15 @@ static inline struct slab_sheaf *alloc_empty_sheaf(struct kmem_cache *s,
 
 static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf)
 {
+	/*
+	 * If the sheaf was created with __GFP_NO_OBJ_EXT flag then its
+	 * corresponding extension is NULL and alloc_tag_sub() will throw a
+	 * warning, therefore replace NULL with CODETAG_EMPTY to indicate
+	 * that the extension for this sheaf is expected to be NULL.
+	 */
+	if (s->flags & SLAB_KMALLOC)
+		mark_obj_codetag_empty(sheaf);
+
 	kfree(sheaf);
 
 	stat(s, SHEAF_FREE);

From 2b351ea42820a7ecc2e8305724536512984f4419 Mon Sep 17 00:00:00 2001
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Date: Thu, 26 Feb 2026 11:17:12 +0530
Subject: [PATCH 0507/1303] mm/slub: drop duplicate kernel-doc for ksize()

The implementation of ksize() was updated with kernel-doc by commit
fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c")
However, the public header still contains a kernel-doc comment
attached to the ksize() prototype.

Having documentation both in the header and next to the implementation
causes Sphinx to treat the function as being documented twice,
resulting in the warning:

  WARNING: Duplicate C declaration, also defined at core-api/mm-api:521
  Declaration is '.. c:function:: size_t ksize(const void *objp)'

Kernel-doc guidelines recommend keeping the documentation with the
function implementation. Therefore remove the redundant kernel-doc
block from include/linux/slab.h so that the implementation in slub.c
remains the canonical source for documentation.

No functional change.

Fixes: fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c")
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Link: https://patch.msgid.link/20260226054712.3610744-1-sanjayembedded@gmail.com
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 include/linux/slab.h | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/include/linux/slab.h b/include/linux/slab.h
index a5a5e4108ae5..15a60b501b95 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp);
 DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T))
 DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T))
 
-/**
- * ksize - Report actual allocation size of associated object
- *
- * @objp: Pointer returned from a prior kmalloc()-family allocation.
- *
- * This should not be used for writing beyond the originally requested
- * allocation size. Either use krealloc() or round up the allocation size
- * with kmalloc_size_roundup() prior to allocation. If this is used to
- * access beyond the originally requested allocation size, UBSAN_BOUNDS
- * and/or FORTIFY_SOURCE may trip, since they only know about the
- * originally allocated size via the __alloc_size attribute.
- */
 size_t ksize(const void *objp);
 
 #ifdef CONFIG_PRINTK

From 71c1978ab6d2c6d48c31311855f1a85377c152ae Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:47:52 +0100
Subject: [PATCH 0508/1303] ASoC: SDCA: Fix comments for sdca_irq_request()

The kernel-doc comments for sdca_irq_request() contained some typos
that lead to build warnings with W=1.  Let's correct them.

Fixes: b126394d9ec6 ("ASoC: SDCA: Generic interrupt support")
Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260226154753.1083320-1-tiwai@suse.de
---
 sound/soc/sdca/sdca_interrupts.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index d9e22cf40f77..95b1ab4ba1b0 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -265,9 +265,9 @@ static int sdca_irq_request_locked(struct device *dev,
 }
 
 /**
- * sdca_request_irq - request an individual SDCA interrupt
+ * sdca_irq_request - request an individual SDCA interrupt
  * @dev: Pointer to the struct device against which things should be allocated.
- * @interrupt_info: Pointer to the interrupt information structure.
+ * @info: Pointer to the interrupt information structure.
  * @sdca_irq: SDCA interrupt position.
  * @name: Name to be given to the IRQ.
  * @handler: A callback thread function to be called for the IRQ.

From 795469820c638b4449f3bb90ee5e98ebccfbc480 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 23 Feb 2026 14:01:56 -0800
Subject: [PATCH 0509/1303] kcsan: test: Adjust "expect" allocation type for
 kmalloc_obj

The call to kmalloc_obj(observed.lines) returns "char (*)[3][512]",
a pointer to the whole 2D array. But "expect" wants to be "char (*)[512]",
the decayed pointer type, as if it were observed.lines itself (though
without the "3" bounds). This produces the following build error:

../kernel/kcsan/kcsan_test.c: In function '__report_matches':
../kernel/kcsan/kcsan_test.c:171:16: error: assignment to 'char (*)[512]' from incompatible pointer type 'char (*)[3][512]'
[-Wincompatible-pointer-types]
  171 |         expect = kmalloc_obj(observed.lines);
      |                ^

Instead of changing the "expect" type to "char (*)[3][512]" and
requiring a dereference at each use (e.g. "(expect*)[0]"), just
explicitly cast the return to the desired type.

Note that I'm intentionally not switching back to byte-based "kmalloc"
here because I cannot find a way for the Coccinelle script (which will
be used going forward to catch future conversions) to exclude this case.

Tested with:

$ ./tools/testing/kunit/kunit.py run \
	--kconfig_add CONFIG_DEBUG_KERNEL=y \
	--kconfig_add CONFIG_KCSAN=y \
	--kconfig_add CONFIG_KCSAN_KUNIT_TEST=y \
	--arch=x86_64 --qemu_args '-smp 2' kcsan

Reported-by: Nathan Chancellor <nathan@kernel.org>
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Signed-off-by: Kees Cook <kees@kernel.org>
---
 kernel/kcsan/kcsan_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 79e655ea4ca1..ae758150ccb9 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -168,7 +168,7 @@ static bool __report_matches(const struct expect_report *r)
 	if (!report_available())
 		return false;
 
-	expect = kmalloc_obj(observed.lines);
+	expect = (typeof(expect))kmalloc_obj(observed.lines);
 	if (WARN_ON(!expect))
 		return false;
 

From e5cb94ba5f96d691d8885175d4696d6ae6bc5ec9 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 26 Feb 2026 08:22:32 +0000
Subject: [PATCH 0510/1303] arm64: Fix sampling the "stable" virtual counter in
 preemptible section
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ben reports that when running with CONFIG_DEBUG_PREEMPT, using
__arch_counter_get_cntvct_stable() results in well deserves warnings,
as we access a per-CPU variable without preemption disabled.

Fix the issue by disabling preemption on reading the counter. We can
probably do a lot better by not disabling preemption on systems that
do not require horrible workarounds to return a valid counter value,
but this plugs the issue for the time being.

Fixes: 29cc0f3aa7c6 ("arm64: Force the use of CNTVCT_EL0 in __delay()")
Reported-by: Ben Horgan <ben.horgan@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/aZw3EGs4rbQvbAzV@e134344.arm.com
Tested-by: Ben Horgan <ben.horgan@arm.com>
Tested-by: André Draszik <andre.draszik@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/lib/delay.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index d02341303899..e278e060e78a 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -32,7 +32,11 @@ static inline unsigned long xloops_to_cycles(unsigned long xloops)
  * Note that userspace cannot change the offset behind our back either,
  * as the vcpu mutex is held as long as KVM_RUN is in progress.
  */
-#define __delay_cycles()	__arch_counter_get_cntvct_stable()
+static cycles_t notrace __delay_cycles(void)
+{
+	guard(preempt_notrace)();
+	return __arch_counter_get_cntvct_stable();
+}
 
 void __delay(unsigned long cycles)
 {

From df6e4ab654dc482c1d45776257a62ac10e14086c Mon Sep 17 00:00:00 2001
From: Sumit Gupta <sumitg@nvidia.com>
Date: Thu, 26 Feb 2026 17:29:11 +0530
Subject: [PATCH 0511/1303] arm64: topology: Fix false warning in
 counters_read_on_cpu() for same-CPU reads

The counters_read_on_cpu() function warns when called with IRQs
disabled to prevent deadlock in smp_call_function_single(). However,
this warning is spurious when reading counters on the current CPU,
since no IPI is needed for same CPU reads.

Commit 12eb8f4fff24 ("cpufreq: CPPC: Update FIE arch_freq_scale in
ticks for non-PCC regs") changed the CPPC Frequency Invariance Engine
to read AMU counters directly from the scheduler tick for non-PCC
register spaces (like FFH), instead of deferring to a kthread. This
means counters_read_on_cpu() is now called with IRQs disabled from the
tick handler, triggering the warning.

Fix this by restructuring the logic: when IRQs are disabled (tick
context), call the function directly for same-CPU reads. Otherwise
use smp_call_function_single().

Fixes: 997c021abc6e ("cpufreq: CPPC: Update FIE arch_freq_scale in ticks for non-PCC regs")
Suggested-by: Will Deacon <will@kernel.org>
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/topology.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 3fe1faab0362..b32f13358fbb 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -400,16 +400,25 @@ static inline
 int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
 {
 	/*
-	 * Abort call on counterless CPU or when interrupts are
-	 * disabled - can lead to deadlock in smp sync call.
+	 * Abort call on counterless CPU.
 	 */
 	if (!cpu_has_amu_feat(cpu))
 		return -EOPNOTSUPP;
 
-	if (WARN_ON_ONCE(irqs_disabled()))
-		return -EPERM;
-
-	smp_call_function_single(cpu, func, val, 1);
+	if (irqs_disabled()) {
+		/*
+		 * When IRQs are disabled (tick path: sched_tick ->
+		 * topology_scale_freq_tick or cppc_scale_freq_tick), only local
+		 * CPU counter reads are allowed. Remote CPU counter read would
+		 * require smp_call_function_single() which is unsafe with IRQs
+		 * disabled.
+		 */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			return -EPERM;
+		func(val);
+	} else {
+		smp_call_function_single(cpu, func, val, 1);
+	}
 
 	return 0;
 }

From 8678591b47469fe16357234efef9b260317b8be4 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 25 Feb 2026 15:02:51 -0700
Subject: [PATCH 0512/1303] kbuild: Split .modinfo out from ELF_DETAILS

Commit 3e86e4d74c04 ("kbuild: keep .modinfo section in
vmlinux.unstripped") added .modinfo to ELF_DETAILS while removing it
from COMMON_DISCARDS, as it was needed in vmlinux.unstripped and
ELF_DETAILS was present in all architecture specific vmlinux linker
scripts. While this shuffle is fine for vmlinux, ELF_DETAILS and
COMMON_DISCARDS may be used by other linker scripts, such as the s390
and x86 compressed boot images, which may not expect to have a .modinfo
section. In certain circumstances, this could result in a bootloader
failing to load the compressed kernel [1].

Commit ddc6cbef3ef1 ("s390/boot/vmlinux.lds.S: Ensure bzImage ends with
SecureBoot trailer") recently addressed this for the s390 bzImage but
the same bug remains for arm, parisc, and x86. The presence of .modinfo
in the x86 bzImage was the root cause of the issue worked around with
commit d50f21091358 ("kbuild: align modinfo section for Secureboot
Authenticode EDK2 compat"). misc.c in arch/x86/boot/compressed includes
lib/decompress_unzstd.c, which in turn includes lib/xxhash.c and its
MODULE_LICENSE / MODULE_DESCRIPTION macros due to the STATIC definition.

Split .modinfo out from ELF_DETAILS into its own macro and handle it in
all vmlinux linker scripts. Discard .modinfo in the places where it was
previously being discarded from being in COMMON_DISCARDS, as it has
never been necessary in those uses.

Cc: stable@vger.kernel.org
Fixes: 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped")
Reported-by: Ed W <lists@wildgooses.com>
Closes: https://lore.kernel.org/587f25e0-a80e-46a5-9f01-87cb40cfa377@wildgooses.com/ [1]
Tested-by: Ed W <lists@wildgooses.com> # x86_64
Link: https://patch.msgid.link/20260225-separate-modinfo-from-elf-details-v1-1-387ced6baf4b@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 arch/alpha/kernel/vmlinux.lds.S           | 1 +
 arch/arc/kernel/vmlinux.lds.S             | 1 +
 arch/arm/boot/compressed/vmlinux.lds.S    | 1 +
 arch/arm/kernel/vmlinux-xip.lds.S         | 1 +
 arch/arm/kernel/vmlinux.lds.S             | 1 +
 arch/arm64/kernel/vmlinux.lds.S           | 1 +
 arch/csky/kernel/vmlinux.lds.S            | 1 +
 arch/hexagon/kernel/vmlinux.lds.S         | 1 +
 arch/loongarch/kernel/vmlinux.lds.S       | 1 +
 arch/m68k/kernel/vmlinux-nommu.lds        | 1 +
 arch/m68k/kernel/vmlinux-std.lds          | 1 +
 arch/m68k/kernel/vmlinux-sun3.lds         | 1 +
 arch/mips/kernel/vmlinux.lds.S            | 1 +
 arch/nios2/kernel/vmlinux.lds.S           | 1 +
 arch/openrisc/kernel/vmlinux.lds.S        | 1 +
 arch/parisc/boot/compressed/vmlinux.lds.S | 1 +
 arch/parisc/kernel/vmlinux.lds.S          | 1 +
 arch/powerpc/kernel/vmlinux.lds.S         | 1 +
 arch/riscv/kernel/vmlinux.lds.S           | 1 +
 arch/s390/kernel/vmlinux.lds.S            | 1 +
 arch/sh/kernel/vmlinux.lds.S              | 1 +
 arch/sparc/kernel/vmlinux.lds.S           | 1 +
 arch/um/kernel/dyn.lds.S                  | 1 +
 arch/um/kernel/uml.lds.S                  | 1 +
 arch/x86/boot/compressed/vmlinux.lds.S    | 2 +-
 arch/x86/kernel/vmlinux.lds.S             | 1 +
 include/asm-generic/vmlinux.lds.h         | 4 +++-
 27 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 2efa7dfc798a..2d136c63db16 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -71,6 +71,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 61a1b2b96e1d..6af63084ff28 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -123,6 +123,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	DISCARDS
 
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index d411abd4310e..2d916647df03 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -21,6 +21,7 @@ SECTIONS
     COMMON_DISCARDS
     *(.ARM.exidx*)
     *(.ARM.extab*)
+    *(.modinfo)
     *(.note.*)
     *(.rel.*)
     *(.printk_index)
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index f2e8d4fac068..5afb725998ec 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -154,6 +154,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index d592a203f9c6..c07843c3c53d 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -153,6 +153,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ad6133b89e7a..2964aad0362e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -349,6 +349,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	HEAD_SYMBOLS
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
index d718961786d2..81943981b3af 100644
--- a/arch/csky/kernel/vmlinux.lds.S
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -109,6 +109,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 1150b77fa281..aae22283b5e0 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -62,6 +62,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.hexagon.attributes 0 : { *(.hexagon.attributes) }
 
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index 08ea921cdec1..d0e1377a041d 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -147,6 +147,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 #ifdef CONFIG_EFI_STUB
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index 2624fc18c131..45d7f4b0177b 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -85,6 +85,7 @@ SECTIONS {
 	_end = .;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* Sections to be discarded */
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 1ccdd04ae462..7326586afe15 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -58,6 +58,7 @@ SECTIONS
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index f13ddcc2af5c..1b19fef201fb 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -51,6 +51,7 @@ __init_begin = .;
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 2b708fac8d2c..579b2cc1995a 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -217,6 +217,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* These must appear regardless of  .  */
diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S
index 37b958055064..206f92445bfa 100644
--- a/arch/nios2/kernel/vmlinux.lds.S
+++ b/arch/nios2/kernel/vmlinux.lds.S
@@ -57,6 +57,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 049bff45f612..9b29c3211774 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -101,6 +101,7 @@ SECTIONS
 	/* Throw in the debugging sections */
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
         /* Sections to be discarded -- must be last */
diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S
index ab7b43990857..87d24cc824b6 100644
--- a/arch/parisc/boot/compressed/vmlinux.lds.S
+++ b/arch/parisc/boot/compressed/vmlinux.lds.S
@@ -90,6 +90,7 @@ SECTIONS
 	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
+		*(.modinfo)
 #ifdef CONFIG_64BIT
 		/* temporary hack until binutils is fixed to not emit these
 		 * for static binaries
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index b445e47903cf..0ca93d6d7235 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -165,6 +165,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.note 0 : { *(.note) }
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 15850296c0a9..8fc11d6565bf 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -397,6 +397,7 @@ SECTIONS
 	_end = . ;
 
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 61bd5ba6680a..997f9eb3b22b 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -170,6 +170,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.riscv.attributes 0 : { *(.riscv.attributes) }
 
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 53bcbb91bb9b..2b62395e35bf 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -221,6 +221,7 @@ SECTIONS
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/*
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 008c30289eaa..169c63fb3c1d 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -89,6 +89,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f1b86eb30340..7ea510d9b42f 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -191,6 +191,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index a36b7918a011..ad3cefeff2ac 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -172,6 +172,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index a409d4b66114..30aa24348d60 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -113,6 +113,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 587ce3e7c504..e0b152715d9c 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -88,7 +88,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
 		*(.hash) *(.gnu.hash)
-		*(.note.*)
+		*(.note.*) *(.modinfo)
 	}
 
 	.got.plt (INFO) : {
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3a24a3fc55f5..4711a35e706c 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -427,6 +427,7 @@ SECTIONS
 	.llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
 #endif
 
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index eeb070f330bd..1e1580febe4b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -848,12 +848,14 @@
 
 /* Required sections not related to debugging. */
 #define ELF_DETAILS							\
-		.modinfo : { *(.modinfo) . = ALIGN(8); }		\
 		.comment 0 : { *(.comment) }				\
 		.symtab 0 : { *(.symtab) }				\
 		.strtab 0 : { *(.strtab) }				\
 		.shstrtab 0 : { *(.shstrtab) }
 
+#define MODINFO								\
+		.modinfo : { *(.modinfo) . = ALIGN(8); }
+
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
 	. = ALIGN(8);							\

From d2395bb194ef212b36521ec4fa85e38b45675acb Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 25 Feb 2026 15:07:17 -0700
Subject: [PATCH 0513/1303] genksyms: Fix parsing a declarator with a preceding
 attribute

After commit 07919126ecfc ("netfilter: annotate NAT helper hook pointers
with __rcu"), genksyms fails to parse the __rcu annotation when building
with CONFIG_DEBUG_INFO_BTF=y, CONFIG_PAHOLE_HAS_BTF_TAG=y, and a version
of clang that supports btf_type_tag.

  $ clang --version | head -1
  ClangBuiltLinux clang version 22.1.0 (https://github.com/llvm/llvm-project.git 4434dabb69916856b824f68a64b029c67175e532)

  $ cat kernel/configs/repro.config
  CONFIG_BPF_SYSCALL=y
  CONFIG_MODVERSIONS=y
  # CONFIG_DEBUG_INFO_NONE is not set
  CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
  CONFIG_DEBUG_INFO_BTF=y

  $ make -skj"$(nproc)" ARCH=x86_64 LLVM=1 mrproper defconfig repro.config all
  WARNING: modpost: EXPORT symbol "nf_nat_ftp_hook" [vmlinux] version generation failed, symbol will not be versioned.
  ...
  WARNING: modpost: EXPORT symbol "nf_nat_irc_hook" [vmlinux] version generation failed, symbol will not be versioned.
  ...

genksyms falls over parsing the __rcu attribute in the declarator:

  # Kernel reproducer
  $ make -skj"$(nproc)" ARCH=x86_64 KCFLAGS=-D__GENKSYMS__ LLVM=1 net/netfilter/nf_conntrack_ftp.i

  $ scripts/genksyms/genksyms -w <net/netfilter/nf_conntrack_ftp.i &| rg 'syntax error'
  include/linux/netfilter/nf_conntrack_ftp.h:29: syntax error
  net/netfilter/nf_conntrack_ftp.c:46: syntax error

  # Trivial reproducer
  $ cat test.c
  int (*func)(void *foo, int bar);
  int (__attribute__((btf_type_tag("rcu"))) *func_with_attr)(void *foo, int bar);

  $ scripts/genksyms/genksyms -w <test.c
  <stdin>:2: syntax error

Optionally allow an attribute to precede a declarator to resolve this
error and properly generate symbol versions.

Fixes: 07919126ecfc ("netfilter: annotate NAT helper hook pointers with __rcu")
Link: https://patch.msgid.link/20260225-genksyms-fix-attribute-declarator-v1-1-1b21478663fb@kernel.org
Tested-by: Nicolas Schier <nsc@kernel.org>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/genksyms/parse.y | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index efdcf07c4eb6..cabcd146f3aa 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -325,8 +325,8 @@ direct_declarator:
 		{ $$ = $4; }
 	| direct_declarator BRACKET_PHRASE
 		{ $$ = $2; }
-	| '(' declarator ')'
-		{ $$ = $3; }
+	| '(' attribute_opt declarator ')'
+		{ $$ = $4; }
 	;
 
 /* Nested declarators differ from regular declarators in that they do

From ef06fd16d48704eac868441d98d4ef083d8f3d07 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 26 Feb 2026 07:55:25 +0000
Subject: [PATCH 0514/1303] bpf, arm64: Force 8-byte alignment for JIT buffer
 to prevent atomic tearing

struct bpf_plt contains a u64 target field. Currently, the BPF JIT
allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT
buffer.

Because the base address of the JIT buffer can be 4-byte aligned (e.g.,
ending in 0x4 or 0xc), the relative padding logic in build_plt() fails
to ensure that target lands on an 8-byte boundary.

This leads to two issues:
1. UBSAN reports misaligned-access warnings when dereferencing the
   structure.
2. More critically, target is updated concurrently via WRITE_ONCE() in
   bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64,
   64-bit loads/stores are only guaranteed to be single-copy atomic if
   they are 64-bit aligned. A misaligned target risks a torn read,
   causing the JIT to jump to a corrupted address.

Fix this by increasing the allocation alignment requirement to 8 bytes
(sizeof(u64)) in bpf_jit_binary_pack_alloc(). This anchors the base of
the JIT buffer to an 8-byte boundary, allowing the relative padding math
in build_plt() to correctly align the target field.

Fixes: b2ad54e1533e ("bpf, arm64: Implement bpf_arch_text_poke() for arm64")
Signed-off-by: Fuad Tabba <tabba@google.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20260226075525.233321-1-tabba@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 356d33c7a4ae..adf84962d579 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2119,7 +2119,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
-					      sizeof(u32), &header, &image_ptr,
+					      sizeof(u64), &header, &image_ptr,
 					      jit_fill_hole);
 	if (!ro_header) {
 		prog = orig_prog;

From ad6fface76da42721c15e8fb281570aaa44a2c01 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 25 Feb 2026 12:12:49 +0100
Subject: [PATCH 0515/1303] bpf: Fix kprobe_multi cookies access in show_fdinfo
 callback

We don't check if cookies are available on the kprobe_multi link
before accessing them in show_fdinfo callback, we should.

Cc: stable@vger.kernel.org
Fixes: da7e9c0a7fbc ("bpf: Add show_fdinfo for kprobe_multi")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20260225111249.186230-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9bc0dfd235af..0b040a417442 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2454,8 +2454,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_kprobe_multi_link *kmulti_link;
+	bool has_cookies;
 
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	has_cookies = !!kmulti_link->cookies;
 
 	seq_printf(seq,
 		   "kprobe_cnt:\t%u\n"
@@ -2467,7 +2469,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 	for (int i = 0; i < kmulti_link->cnt; i++) {
 		seq_printf(seq,
 			   "%llu\t %pS\n",
-			   kmulti_link->cookies[i],
+			   has_cookies ? kmulti_link->cookies[i] : 0,
 			   (void *)kmulti_link->addrs[i]);
 	}
 }

From b7bf516c3ecd9a2aae2dc2635178ab87b734fef1 Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Wed, 25 Feb 2026 05:34:44 +0000
Subject: [PATCH 0516/1303] bpf: Fix stack-out-of-bounds write in devmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

get_upper_ifindexes() iterates over all upper devices and writes their
indices into an array without checking bounds.

Also the callers assume that the max number of upper devices is
MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack,
but that assumption is not correct and the number of upper devices could
be larger than MAX_NEST_DEV (e.g., many macvlans), causing a
stack-out-of-bounds write.

Add a max parameter to get_upper_ifindexes() to avoid the issue.
When there are too many upper devices, return -EOVERFLOW and abort the
redirect.

To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with
an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS.
Then send a packet to the device to trigger the XDP redirect path.

Reported-by: syzbot+10cc7f13760b31bd2e61@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698c4ce3.050a0220.340abe.000b.GAE@google.com/T/
Fixes: aeea1b86f936 ("bpf, devmap: Exclude XDP broadcast to master device")
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Link: https://lore.kernel.org/r/20260225053506.4738-1-kohei@enjuk.jp
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/devmap.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2625601de76e..2984e938f94d 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -588,18 +588,22 @@ static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifin
 }
 
 /* Get ifindex of each upper device. 'indexes' must be able to hold at
- * least MAX_NEST_DEV elements.
- * Returns the number of ifindexes added.
+ * least 'max' elements.
+ * Returns the number of ifindexes added, or -EOVERFLOW if there are too
+ * many upper devices.
  */
-static int get_upper_ifindexes(struct net_device *dev, int *indexes)
+static int get_upper_ifindexes(struct net_device *dev, int *indexes, int max)
 {
 	struct net_device *upper;
 	struct list_head *iter;
 	int n = 0;
 
 	netdev_for_each_upper_dev_rcu(dev, upper, iter) {
+		if (n >= max)
+			return -EOVERFLOW;
 		indexes[n++] = upper->ifindex;
 	}
+
 	return n;
 }
 
@@ -615,7 +619,11 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 	int err;
 
 	if (exclude_ingress) {
-		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
+		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices,
+						   ARRAY_SIZE(excluded_devices) - 1);
+		if (num_excluded < 0)
+			return num_excluded;
+
 		excluded_devices[num_excluded++] = dev_rx->ifindex;
 	}
 
@@ -733,7 +741,11 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 	int err;
 
 	if (exclude_ingress) {
-		num_excluded = get_upper_ifindexes(dev, excluded_devices);
+		num_excluded = get_upper_ifindexes(dev, excluded_devices,
+						   ARRAY_SIZE(excluded_devices) - 1);
+		if (num_excluded < 0)
+			return num_excluded;
+
 		excluded_devices[num_excluded++] = dev->ifindex;
 	}
 

From 60e3cbef3500ad6101bc91946e645f69b1bb9556 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Tue, 24 Feb 2026 16:33:51 -0800
Subject: [PATCH 0517/1303] selftests/bpf: Fix a memory leak in xdp_flowtable
 test

test_progs run with ASAN reported [1]:

  ==126==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 32 byte(s) in 1 object(s) allocated from:
      #0 0x7f1ff3cfa340 in calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:77
      #1 0x5610c15bb520 in bpf_program_attach_fd /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/lib/bpf/libbpf.c:13164
      #2 0x5610c15bb740 in bpf_program__attach_xdp /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/lib/bpf/libbpf.c:13204
      #3 0x5610c14f91d3 in test_xdp_flowtable /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c:138
      #4 0x5610c1533566 in run_one_test /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/test_progs.c:1406
      #5 0x5610c1537fb0 in main /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/test_progs.c:2097
      #6 0x7f1ff25df1c9  (/lib/x86_64-linux-gnu/libc.so.6+0x2a1c9) (BuildId: 8e9fd827446c24067541ac5390e6f527fb5947bb)
      #7 0x7f1ff25df28a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2a28a) (BuildId: 8e9fd827446c24067541ac5390e6f527fb5947bb)
      #8 0x5610c0bd3180 in _start (/tmp/work/vmtest/vmtest/selftests/bpf/test_progs+0x593180) (BuildId: cdf9f103f42307dc0a2cd6cfc8afcbc1366cf8bd)

Fix by properly destroying bpf_link on exit in xdp_flowtable test.

[1] https://github.com/kernel-patches/vmtest/actions/runs/22361085418/job/64716490680

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Link: https://lore.kernel.org/r/20260225003351.465104-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
index 3f9146d83d79..325e0b64dc35 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
@@ -67,7 +67,7 @@ void test_xdp_flowtable(void)
 	struct nstoken *tok = NULL;
 	int iifindex, stats_fd;
 	__u32 value, key = 0;
-	struct bpf_link *link;
+	struct bpf_link *link = NULL;
 
 	if (SYS_NOFAIL("nft -v")) {
 		fprintf(stdout, "Missing required nft tool\n");
@@ -160,6 +160,7 @@ void test_xdp_flowtable(void)
 
 	ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed");
 out:
+	bpf_link__destroy(link);
 	xdp_flowtable__destroy(skel);
 	if (tok)
 		close_netns(tok);

From 6881af27f9ea0f5ca8f606f573ef5cc25ca31fe4 Mon Sep 17 00:00:00 2001
From: "T.J. Mercier" <tjmercier@google.com>
Date: Tue, 24 Feb 2026 16:33:48 -0800
Subject: [PATCH 0518/1303] selftests/bpf: Fix OOB read in dmabuf_collector

Dmabuf name allocations can be less than DMA_BUF_NAME_LEN characters,
but bpf_probe_read_kernel always tries to read exactly that many bytes.
If a name is less than DMA_BUF_NAME_LEN characters,
bpf_probe_read_kernel will read past the end. bpf_probe_read_kernel_str
stops at the first NUL terminator so use it instead, like
iter_dmabuf_for_each already does.

Fixes: ae5d2c59ecd7 ("selftests/bpf: Add test for dmabuf_iter")
Reported-by: Jerome Lee <jaewookl@quicinc.com>
Signed-off-by: T.J. Mercier <tjmercier@google.com>
Link: https://lore.kernel.org/r/20260225003349.113746-1-tjmercier@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/dmabuf_iter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
index 13cdb11fdeb2..9cbb7442646e 100644
--- a/tools/testing/selftests/bpf/progs/dmabuf_iter.c
+++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
@@ -48,7 +48,7 @@ int dmabuf_collector(struct bpf_iter__dmabuf *ctx)
 
 	/* Buffers are not required to be named */
 	if (pname) {
-		if (bpf_probe_read_kernel(name, sizeof(name), pname))
+		if (bpf_probe_read_kernel_str(name, sizeof(name), pname) < 0)
 			return 1;
 
 		/* Name strings can be provided by userspace */

From 459cb3c054c2352bb321648744b620259a716b60 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Thu, 26 Feb 2026 08:41:48 +0100
Subject: [PATCH 0519/1303] kbuild: install-extmod-build: Package
 resolve_btfids if necessary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CONFIG_DEBUG_INFO_BTF_MODULES is enabled and vmlinux is available,
Makefile.modfinal and gen-btf.sh will try to use resolve_btfids on the
module .ko. install-extmod-build currently does not package
resolve_btfids, so that step fails.

Package resolve_btfids if it may be used.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20260226-kbuild-resolve_btfids-v1-1-2bf38b93dfe7@linutronix.de
[nathan: Small commit message tweaks]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/package/install-extmod-build | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 2576cf7902db..f12e1ffe409e 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -32,6 +32,10 @@ mkdir -p "${destdir}"
 		echo tools/objtool/objtool
 	fi
 
+	if is_enabled CONFIG_DEBUG_INFO_BTF_MODULES; then
+		echo tools/bpf/resolve_btfids/resolve_btfids
+	fi
+
 	echo Module.symvers
 	echo "arch/${SRCARCH}/include/generated"
 	echo include/config/auto.conf

From 749989b2d90ddc7dd253ad3b11a77cf882721acf Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Thu, 26 Feb 2026 12:45:17 +0000
Subject: [PATCH 0520/1303] sched_ext: Fix SCX_EFLAG_INITIALIZED being a no-op
 flag

SCX_EFLAG_INITIALIZED is the sole member of enum scx_exit_flags with no
explicit value, so the compiler assigns it 0. This makes the bitwise OR
in scx_ops_init() a no-op:

    sch->exit_info->flags |= SCX_EFLAG_INITIALIZED; /* |= 0 */

As a result, BPF schedulers cannot distinguish whether ops.init()
completed successfully by inspecting exit_info->flags.

Assign the value 1LLU << 0 so the flag is actually set.

Fixes: f3aec2adce8d ("sched_ext: Add SCX_EFLAG_INITIALIZED to indicate successful ops.init()")
Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 386c677e4c9a..11ebb744d893 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -74,7 +74,7 @@ enum scx_exit_flags {
 	 * info communication. The following flag indicates whether ops.init()
 	 * finished successfully.
 	 */
-	SCX_EFLAG_INITIALIZED,
+	SCX_EFLAG_INITIALIZED   = 1LLU << 0,
 };
 
 /*

From dd677d0598387ea623820ab2bd0e029c377445a3 Mon Sep 17 00:00:00 2001
From: Justin Tee <justintee8345@gmail.com>
Date: Thu, 4 Dec 2025 12:26:13 -0800
Subject: [PATCH 0521/1303] nvmet-fcloop: Check remoteport port_state before
 calling done callback

In nvme_fc_handle_ls_rqst_work, the lsrsp->done callback is only set when
remoteport->port_state is FC_OBJSTATE_ONLINE.  Otherwise, the
nvme_fc_xmt_ls_rsp's LLDD call to lport->ops->xmt_ls_rsp is expected to
fail and the nvme-fc transport layer itself will directly call
nvme_fc_xmt_ls_rsp_free instead of relying on LLDD's done callback to free
the lsrsp resources.

Update the fcloop_t2h_xmt_ls_rsp routine to check remoteport->port_state.
If online, then lsrsp->done callback will free the lsrsp.  Else, return
-ENODEV to signal the nvme-fc transport to handle freeing lsrsp.

Cc: Ewan D. Milne <emilne@redhat.com>
Tested-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Closes: https://lore.kernel.org/linux-nvme/21255200-a271-4fa0-b099-97755c8acd4c@work/
Fixes: 10c165af35d2 ("nvmet-fcloop: call done callback even when remote port is gone")
Signed-off-by: Justin Tee <justintee8345@gmail.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fcloop.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c30e9a3e014f..38bd2db3d6bb 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -491,6 +491,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 	struct fcloop_rport *rport = remoteport->private;
 	struct nvmet_fc_target_port *targetport = rport->targetport;
 	struct fcloop_tport *tport;
+	int ret = 0;
 
 	if (!targetport) {
 		/*
@@ -500,12 +501,18 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 		 * We end up here from delete association exchange:
 		 * nvmet_fc_xmt_disconnect_assoc sends an async request.
 		 *
-		 * Return success because this is what LLDDs do; silently
-		 * drop the response.
+		 * Return success when remoteport is still online because this
+		 * is what LLDDs do and silently drop the response.  Otherwise,
+		 * return with error to signal upper layer to perform the lsrsp
+		 * resource cleanup.
 		 */
-		lsrsp->done(lsrsp);
+		if (remoteport->port_state == FC_OBJSTATE_ONLINE)
+			lsrsp->done(lsrsp);
+		else
+			ret = -ENODEV;
+
 		kmem_cache_free(lsreq_cache, tls_req);
-		return 0;
+		return ret;
 	}
 
 	memcpy(lsreq->rspaddr, lsrsp->rspbuf,

From b6c3af46c26f2d07c10a1452adc34b821719327e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 23 Feb 2026 19:06:51 +0100
Subject: [PATCH 0522/1303] pinctrl: cy8c95x0: Don't miss reading the last bank
 registers

When code had been changed to use for_each_set_clump8(), it mistakenly
switched from chip->nport to chip->tpin since the cy8c9540 and cy8c9560
have a 4-pin gap. This, in particular, led to the missed read of
the last bank interrupt status register and hence missing interrupts
on those pins. Restore the upper limit in for_each_set_clump8() to take
into consideration that gap.

Fixes: 83e29a7a1fdf ("pinctrl: cy8c95x0; Switch to use for_each_set_clump8()")
Cc: stable@vger.kernel.org
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index a4b04bf6d081..5c055d344ac9 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -627,7 +627,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		write_val = bitmap_get_value8(tval, offset);
@@ -655,7 +655,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		ret = cy8c95x0_regmap_read_bits(chip, reg, i, bits, &read_val);

From e96493229a6399e902062213c6381162464cdd50 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Tue, 24 Feb 2026 16:09:22 +0100
Subject: [PATCH 0523/1303] spi: stm32: fix missing pointer assignment in case
 of dma chaining

Commit c4f2c05ab029 ("spi: stm32: fix pointer-to-pointer variables usage")
introduced a regression since dma descriptors generated as part of the
stm32_spi_prepare_rx_dma_mdma_chaining function are not well propagated
to the caller function, leading to mdma-dma chaining being no more
functional.

Fixes: c4f2c05ab029 ("spi: stm32: fix pointer-to-pointer variables usage")
Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Acked-by: Antonio Quartulli <antonio@mandelbit.com>
Link: https://patch.msgid.link/20260224-spi-stm32-chaining-fix-v1-1-5da7a4851b66@foss.st.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index b99de8c4cc99..33f211e159ef 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1625,6 +1625,9 @@ static int stm32_spi_prepare_rx_dma_mdma_chaining(struct stm32_spi *spi,
 		return -EINVAL;
 	}
 
+	*rx_mdma_desc = _mdma_desc;
+	*rx_dma_desc = _dma_desc;
+
 	return 0;
 }
 

From 4fc3a433c13944ee5766ec5b9bf6f1eb4d29b880 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Mon, 23 Feb 2026 13:34:35 -0300
Subject: [PATCH 0524/1303] smb: client: use atomic_t for mnt_cifs_flags

Use atomic_t for cifs_sb_info::mnt_cifs_flags as it's currently
accessed locklessly and may be changed concurrently in mount/remount
and reconnect paths.

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c   |   2 +-
 fs/smb/client/cifs_fs_sb.h   |   2 +-
 fs/smb/client/cifs_ioctl.h   |   8 --
 fs/smb/client/cifs_unicode.c |  14 ----
 fs/smb/client/cifs_unicode.h |  14 +++-
 fs/smb/client/cifsacl.c      |  17 ++--
 fs/smb/client/cifsfs.c       |  84 ++++++++++----------
 fs/smb/client/cifsglob.h     |  61 +++++++++++---
 fs/smb/client/connect.c      |  65 ++++++++-------
 fs/smb/client/dfs_cache.c    |   2 +-
 fs/smb/client/dir.c          |  53 +++++++------
 fs/smb/client/file.c         |  90 +++++++++++----------
 fs/smb/client/fs_context.c   | 149 +++++++++++++++++------------------
 fs/smb/client/fs_context.h   |   2 +-
 fs/smb/client/inode.c        | 146 ++++++++++++++++++----------------
 fs/smb/client/ioctl.c        |   2 +-
 fs/smb/client/link.c         |  14 ++--
 fs/smb/client/misc.c         |  16 ++--
 fs/smb/client/readdir.c      |  39 ++++-----
 fs/smb/client/reparse.c      |  29 +++----
 fs/smb/client/reparse.h      |   4 +-
 fs/smb/client/smb1ops.c      |  22 ++++--
 fs/smb/client/smb2file.c     |   2 +-
 fs/smb/client/smb2misc.c     |  18 +----
 fs/smb/client/smb2ops.c      |   8 +-
 fs/smb/client/smb2pdu.c      |  13 ++-
 fs/smb/client/xattr.c        |   6 +-
 27 files changed, 465 insertions(+), 417 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index c327c246a9b4..04bb95091f49 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -118,7 +118,7 @@ static const char *path_no_prefix(struct cifs_sb_info *cifs_sb,
 	if (!*path)
 		return path;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 	    cifs_sb->prepath) {
 		len = strlen(cifs_sb->prepath) + 1;
 		if (unlikely(len > strlen(path)))
diff --git a/fs/smb/client/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h
index 5e8d163cb5f8..84e7e366b0ff 100644
--- a/fs/smb/client/cifs_fs_sb.h
+++ b/fs/smb/client/cifs_fs_sb.h
@@ -55,7 +55,7 @@ struct cifs_sb_info {
 	struct nls_table *local_nls;
 	struct smb3_fs_context *ctx;
 	atomic_t active;
-	unsigned int mnt_cifs_flags;
+	atomic_t mnt_cifs_flags;
 	struct delayed_work prune_tlinks;
 	struct rcu_head rcu;
 
diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h
index b51ce64fcccf..147496ac9f9f 100644
--- a/fs/smb/client/cifs_ioctl.h
+++ b/fs/smb/client/cifs_ioctl.h
@@ -122,11 +122,3 @@ struct smb3_notify_info {
 #define CIFS_GOING_FLAGS_DEFAULT                0x0     /* going down */
 #define CIFS_GOING_FLAGS_LOGFLUSH               0x1     /* flush log but not data */
 #define CIFS_GOING_FLAGS_NOLOGFLUSH             0x2     /* don't flush log nor data */
-
-static inline bool cifs_forced_shutdown(struct cifs_sb_info *sbi)
-{
-	if (CIFS_MOUNT_SHUTDOWN & sbi->mnt_cifs_flags)
-		return true;
-	else
-		return false;
-}
diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c
index e7891b4406f2..e2edc207cef2 100644
--- a/fs/smb/client/cifs_unicode.c
+++ b/fs/smb/client/cifs_unicode.c
@@ -11,20 +11,6 @@
 #include "cifsglob.h"
 #include "cifs_debug.h"
 
-int cifs_remap(struct cifs_sb_info *cifs_sb)
-{
-	int map_type;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
-		map_type = SFM_MAP_UNI_RSVD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
-		map_type = SFU_MAP_UNI_RSVD;
-	else
-		map_type = NO_MAP_UNI_RSVD;
-
-	return map_type;
-}
-
 /* Convert character using the SFU - "Services for Unix" remapping range */
 static bool
 convert_sfu_char(const __u16 src_char, char *target)
diff --git a/fs/smb/client/cifs_unicode.h b/fs/smb/client/cifs_unicode.h
index 9249db3b78c3..3e9cd9acf0a9 100644
--- a/fs/smb/client/cifs_unicode.h
+++ b/fs/smb/client/cifs_unicode.h
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 #include <linux/nls.h>
 #include "../../nls/nls_ucs2_utils.h"
+#include "cifsglob.h"
 
 /*
  * Macs use an older "SFM" mapping of the symbols above. Fortunately it does
@@ -65,10 +66,21 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen,
 			      const struct nls_table *codepage);
 int cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		       const struct nls_table *cp, int map_chars);
-int cifs_remap(struct cifs_sb_info *cifs_sb);
 __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
 			      int *utf16_len, const struct nls_table *cp,
 			      int remap);
 wchar_t cifs_toupper(wchar_t in);
 
+static inline int cifs_remap(const struct cifs_sb_info *cifs_sb)
+{
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_MAP_SFM_CHR)
+		return SFM_MAP_UNI_RSVD;
+	if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+		return SFU_MAP_UNI_RSVD;
+
+	return NO_MAP_UNI_RSVD;
+}
+
 #endif /* _CIFS_UNICODE_H */
diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 6fa12c901c14..f4cb3018a358 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -356,7 +356,7 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct smb_sid *psid,
 				psid->num_subauth, SID_MAX_SUB_AUTHORITIES);
 	}
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) ||
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_UID_FROM_ACL) ||
 	    (cifs_sb_master_tcon(cifs_sb)->posix_extensions)) {
 		uint32_t unix_id;
 		bool is_group;
@@ -1612,7 +1612,8 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 	struct smb_acl *dacl_ptr = NULL;
 	struct smb_ntsd *pntsd = NULL; /* acl obtained from server */
 	struct smb_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags;
 	struct tcon_link *tlink;
 	struct smb_version_operations *ops;
 	bool mode_from_sid, id_from_sid;
@@ -1643,15 +1644,9 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 		return rc;
 	}
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)
-		mode_from_sid = true;
-	else
-		mode_from_sid = false;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
-		id_from_sid = true;
-	else
-		id_from_sid = false;
+	sbflags = cifs_sb_flags(cifs_sb);
+	mode_from_sid = sbflags & CIFS_MOUNT_MODE_FROM_SID;
+	id_from_sid = sbflags & CIFS_MOUNT_UID_FROM_ACL;
 
 	/* Potentially, five new ACEs can be added to the ACL for U,G,O mapping */
 	if (pnmode && *pnmode != NO_CHANGE_64) { /* chmod */
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 99b04234a08e..427558404aa5 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -226,16 +226,18 @@ cifs_sb_deactive(struct super_block *sb)
 static int
 cifs_read_super(struct super_block *sb)
 {
-	struct inode *inode;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
+	unsigned int sbflags;
 	struct timespec64 ts;
+	struct inode *inode;
 	int rc = 0;
 
 	cifs_sb = CIFS_SB(sb);
 	tcon = cifs_sb_master_tcon(cifs_sb);
+	sbflags = cifs_sb_flags(cifs_sb);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
+	if (sbflags & CIFS_MOUNT_POSIXACL)
 		sb->s_flags |= SB_POSIXACL;
 
 	if (tcon->snapshot_time)
@@ -311,7 +313,7 @@ cifs_read_super(struct super_block *sb)
 	}
 
 #ifdef CONFIG_CIFS_NFSD_EXPORT
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		cifs_dbg(FYI, "export ops supported\n");
 		sb->s_export_op = &cifs_export_ops;
 	}
@@ -389,8 +391,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
-	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(CIFS_SB(file));
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct inode *inode = file_inode(file);
 	int rc;
@@ -418,11 +419,9 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
 static int cifs_permission(struct mnt_idmap *idmap,
 			   struct inode *inode, int mask)
 {
-	struct cifs_sb_info *cifs_sb;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 
-	cifs_sb = CIFS_SB(inode->i_sb);
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
+	if (sbflags & CIFS_MOUNT_NO_PERM) {
 		if ((mask & MAY_EXEC) && !execute_ok(inode))
 			return -EACCES;
 		else
@@ -568,15 +567,17 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 static void
 cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
 	seq_puts(s, ",cache=");
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+	if (sbflags & CIFS_MOUNT_STRICT_IO)
 		seq_puts(s, "strict");
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
+	else if (sbflags & CIFS_MOUNT_DIRECT_IO)
 		seq_puts(s, "none");
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
+	else if (sbflags & CIFS_MOUNT_RW_CACHE)
 		seq_puts(s, "singleclient"); /* assume only one client access */
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE)
+	else if (sbflags & CIFS_MOUNT_RO_CACHE)
 		seq_puts(s, "ro"); /* read only caching assumed */
 	else
 		seq_puts(s, "loose");
@@ -637,6 +638,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct sockaddr *srcaddr;
+	unsigned int sbflags;
+
 	srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr;
 
 	seq_show_option(s, "vers", tcon->ses->server->vals->version_string);
@@ -670,16 +673,17 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 				   (int)(srcaddr->sa_family));
 	}
 
+	sbflags = cifs_sb_flags(cifs_sb);
 	seq_printf(s, ",uid=%u",
 		   from_kuid_munged(&init_user_ns, cifs_sb->ctx->linux_uid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
+	if (sbflags & CIFS_MOUNT_OVERR_UID)
 		seq_puts(s, ",forceuid");
 	else
 		seq_puts(s, ",noforceuid");
 
 	seq_printf(s, ",gid=%u",
 		   from_kgid_munged(&init_user_ns, cifs_sb->ctx->linux_gid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
+	if (sbflags & CIFS_MOUNT_OVERR_GID)
 		seq_puts(s, ",forcegid");
 	else
 		seq_puts(s, ",noforcegid");
@@ -722,53 +726,53 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
+	if (sbflags & CIFS_MOUNT_NO_DFS)
 		seq_puts(s, ",nodfs");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+	if (sbflags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
+	if (sbflags & CIFS_MOUNT_SET_UID)
 		seq_puts(s, ",setuids");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
+	if (sbflags & CIFS_MOUNT_UID_FROM_ACL)
 		seq_puts(s, ",idsfromsid");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+	if (sbflags & CIFS_MOUNT_SERVER_INUM)
 		seq_puts(s, ",serverino");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+	if (sbflags & CIFS_MOUNT_RWPIDFORWARD)
 		seq_puts(s, ",rwpidforward");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
+	if (sbflags & CIFS_MOUNT_NOPOSIXBRL)
 		seq_puts(s, ",forcemand");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+	if (sbflags & CIFS_MOUNT_NO_XATTR)
 		seq_puts(s, ",nouser_xattr");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+	if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR)
 		seq_puts(s, ",mapchars");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+	if (sbflags & CIFS_MOUNT_MAP_SFM_CHR)
 		seq_puts(s, ",mapposix");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
+	if (sbflags & CIFS_MOUNT_UNX_EMUL)
 		seq_puts(s, ",sfu");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	if (sbflags & CIFS_MOUNT_NO_BRL)
 		seq_puts(s, ",nobrl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE)
+	if (sbflags & CIFS_MOUNT_NO_HANDLE_CACHE)
 		seq_puts(s, ",nohandlecache");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)
+	if (sbflags & CIFS_MOUNT_MODE_FROM_SID)
 		seq_puts(s, ",modefromsid");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
+	if (sbflags & CIFS_MOUNT_CIFS_ACL)
 		seq_puts(s, ",cifsacl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+	if (sbflags & CIFS_MOUNT_DYNPERM)
 		seq_puts(s, ",dynperm");
 	if (root->d_sb->s_flags & SB_POSIXACL)
 		seq_puts(s, ",acl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
+	if (sbflags & CIFS_MOUNT_MF_SYMLINKS)
 		seq_puts(s, ",mfsymlinks");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
+	if (sbflags & CIFS_MOUNT_FSCACHE)
 		seq_puts(s, ",fsc");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
+	if (sbflags & CIFS_MOUNT_NOSSYNC)
 		seq_puts(s, ",nostrictsync");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (sbflags & CIFS_MOUNT_NO_PERM)
 		seq_puts(s, ",noperm");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID)
 		seq_printf(s, ",backupuid=%u",
 			   from_kuid_munged(&init_user_ns,
 					    cifs_sb->ctx->backupuid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID)
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID)
 		seq_printf(s, ",backupgid=%u",
 			   from_kgid_munged(&init_user_ns,
 					    cifs_sb->ctx->backupgid));
@@ -909,10 +913,10 @@ static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 static int cifs_drop_inode(struct inode *inode)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 
 	/* no serverino => unconditional eviction */
-	return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) ||
+	return !(sbflags & CIFS_MOUNT_SERVER_INUM) ||
 		inode_generic_drop(inode);
 }
 
@@ -950,7 +954,7 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb)
 	char *s, *p;
 	char sep;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH)
 		return dget(sb->s_root);
 
 	full_path = cifs_build_path_to_root(ctx, cifs_sb,
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 080ea601c209..6f9b6c72962b 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1580,24 +1580,59 @@ CIFS_I(struct inode *inode)
 	return container_of(inode, struct cifsInodeInfo, netfs.inode);
 }
 
-static inline struct cifs_sb_info *
-CIFS_SB(struct super_block *sb)
+static inline void *cinode_to_fsinfo(struct cifsInodeInfo *cinode)
+{
+	return cinode->netfs.inode.i_sb->s_fs_info;
+}
+
+static inline void *super_to_fsinfo(struct super_block *sb)
 {
 	return sb->s_fs_info;
 }
 
-static inline struct cifs_sb_info *
-CIFS_FILE_SB(struct file *file)
+static inline void *inode_to_fsinfo(struct inode *inode)
 {
-	return CIFS_SB(file_inode(file)->i_sb);
+	return inode->i_sb->s_fs_info;
+}
+
+static inline void *file_to_fsinfo(struct file *file)
+{
+	return file_inode(file)->i_sb->s_fs_info;
+}
+
+static inline void *dentry_to_fsinfo(struct dentry *dentry)
+{
+	return dentry->d_sb->s_fs_info;
+}
+
+static inline void *const_dentry_to_fsinfo(const struct dentry *dentry)
+{
+	return dentry->d_sb->s_fs_info;
+}
+
+#define CIFS_SB(_ptr) \
+	((struct cifs_sb_info *) \
+	 _Generic((_ptr), \
+		  struct cifsInodeInfo * : cinode_to_fsinfo, \
+		  const struct dentry * : const_dentry_to_fsinfo, \
+		  struct super_block * : super_to_fsinfo, \
+		  struct dentry * : dentry_to_fsinfo, \
+		  struct inode * : inode_to_fsinfo, \
+		  struct file * : file_to_fsinfo)(_ptr))
+
+/*
+ * Use atomic_t for @cifs_sb->mnt_cifs_flags as it is currently accessed
+ * locklessly and may be changed concurrently by mount/remount and reconnect
+ * paths.
+ */
+static inline unsigned int cifs_sb_flags(const struct cifs_sb_info *cifs_sb)
+{
+	return atomic_read(&cifs_sb->mnt_cifs_flags);
 }
 
 static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
-		return '/';
-	else
-		return '\\';
+	return (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) ? '/' : '\\';
 }
 
 static inline void
@@ -2314,9 +2349,8 @@ static inline bool __cifs_cache_state_check(struct cifsInodeInfo *cinode,
 					    unsigned int oplock_flags,
 					    unsigned int sb_flags)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode->netfs.inode.i_sb);
+	unsigned int sflags = cifs_sb_flags(CIFS_SB(cinode));
 	unsigned int oplock = READ_ONCE(cinode->oplock);
-	unsigned int sflags = cifs_sb->mnt_cifs_flags;
 
 	return (oplock & oplock_flags) || (sflags & sb_flags);
 }
@@ -2336,4 +2370,9 @@ static inline void cifs_reset_oplock(struct cifsInodeInfo *cinode)
 		WRITE_ONCE(cinode->oplock, 0);
 }
 
+static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi)
+{
+	return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN;
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 33dfe116ca52..87686c804057 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2915,8 +2915,8 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 {
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
-	unsigned int oldflags = old->mnt_cifs_flags & CIFS_MOUNT_MASK;
-	unsigned int newflags = new->mnt_cifs_flags & CIFS_MOUNT_MASK;
+	unsigned int oldflags = cifs_sb_flags(old) & CIFS_MOUNT_MASK;
+	unsigned int newflags = cifs_sb_flags(new) & CIFS_MOUNT_MASK;
 
 	if ((sb->s_flags & CIFS_MS_MASK) != (mnt_data->flags & CIFS_MS_MASK))
 		return 0;
@@ -2971,9 +2971,9 @@ static int match_prepath(struct super_block *sb,
 	struct smb3_fs_context *ctx = mnt_data->ctx;
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
-	bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	bool old_set = (cifs_sb_flags(old) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 		old->prepath;
-	bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	bool new_set = (cifs_sb_flags(new) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 		new->prepath;
 
 	if (tcon->origin_fullpath &&
@@ -3004,7 +3004,7 @@ cifs_match_super(struct super_block *sb, void *data)
 	cifs_sb = CIFS_SB(sb);
 
 	/* We do not want to use a superblock that has been shutdown */
-	if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) {
+	if (cifs_forced_shutdown(cifs_sb)) {
 		spin_unlock(&cifs_tcp_ses_lock);
 		return 0;
 	}
@@ -3469,6 +3469,8 @@ ip_connect(struct TCP_Server_Info *server)
 int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 {
 	struct smb3_fs_context *ctx = cifs_sb->ctx;
+	unsigned int sbflags;
+	int rc = 0;
 
 	INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
 	INIT_LIST_HEAD(&cifs_sb->tcon_sb_link);
@@ -3493,17 +3495,16 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 	}
 	ctx->local_nls = cifs_sb->local_nls;
 
-	smb3_update_mnt_flags(cifs_sb);
+	sbflags = smb3_update_mnt_flags(cifs_sb);
 
 	if (ctx->direct_io)
 		cifs_dbg(FYI, "mounting share using direct i/o\n");
 	if (ctx->cache_ro) {
 		cifs_dbg(VFS, "mounting share with read only caching. Ensure that the share will not be modified while in use.\n");
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RO_CACHE;
+		sbflags |= CIFS_MOUNT_RO_CACHE;
 	} else if (ctx->cache_rw) {
 		cifs_dbg(VFS, "mounting share in single client RW caching mode. Ensure that no other systems will be accessing the share.\n");
-		cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_RO_CACHE |
-					    CIFS_MOUNT_RW_CACHE);
+		sbflags |= CIFS_MOUNT_RO_CACHE | CIFS_MOUNT_RW_CACHE;
 	}
 
 	if ((ctx->cifs_acl) && (ctx->dynperm))
@@ -3512,16 +3513,19 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 	if (ctx->prepath) {
 		cifs_sb->prepath = kstrdup(ctx->prepath, GFP_KERNEL);
 		if (cifs_sb->prepath == NULL)
-			return -ENOMEM;
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+			rc = -ENOMEM;
+		else
+			sbflags |= CIFS_MOUNT_USE_PREFIX_PATH;
 	}
 
-	return 0;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+	return rc;
 }
 
 /* Release all succeed connections */
 void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
 {
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
 	int rc = 0;
 
 	if (mnt_ctx->tcon)
@@ -3533,7 +3537,7 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
 	mnt_ctx->ses = NULL;
 	mnt_ctx->tcon = NULL;
 	mnt_ctx->server = NULL;
-	mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
+	atomic_andnot(CIFS_MOUNT_POSIX_PATHS, &cifs_sb->mnt_cifs_flags);
 	free_xid(mnt_ctx->xid);
 }
 
@@ -3587,19 +3591,23 @@ int cifs_mount_get_session(struct cifs_mount_ctx *mnt_ctx)
 int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 {
 	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon = NULL;
 	struct cifs_sb_info *cifs_sb;
 	struct smb3_fs_context *ctx;
-	struct cifs_tcon *tcon = NULL;
+	unsigned int sbflags;
 	int rc = 0;
 
-	if (WARN_ON_ONCE(!mnt_ctx || !mnt_ctx->server || !mnt_ctx->ses || !mnt_ctx->fs_ctx ||
-			 !mnt_ctx->cifs_sb)) {
-		rc = -EINVAL;
-		goto out;
+	if (WARN_ON_ONCE(!mnt_ctx))
+		return -EINVAL;
+	if (WARN_ON_ONCE(!mnt_ctx->server || !mnt_ctx->ses ||
+			 !mnt_ctx->fs_ctx || !mnt_ctx->cifs_sb)) {
+		mnt_ctx->tcon = NULL;
+		return -EINVAL;
 	}
 	server = mnt_ctx->server;
 	ctx = mnt_ctx->fs_ctx;
 	cifs_sb = mnt_ctx->cifs_sb;
+	sbflags = cifs_sb_flags(cifs_sb);
 
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(mnt_ctx->ses, ctx);
@@ -3614,9 +3622,9 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * path (i.e., do not remap / and \ and do not map any special characters)
 	 */
 	if (tcon->posix_extensions) {
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-		cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
-					     CIFS_MOUNT_MAP_SPECIAL_CHR);
+		sbflags |= CIFS_MOUNT_POSIX_PATHS;
+		sbflags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
+			     CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
@@ -3643,12 +3651,11 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	/* do not care if a following call succeed - informational */
 	if (!tcon->pipe && server->ops->qfs_tcon) {
 		server->ops->qfs_tcon(mnt_ctx->xid, tcon, cifs_sb);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) {
+		if (sbflags & CIFS_MOUNT_RO_CACHE) {
 			if (tcon->fsDevInfo.DeviceCharacteristics &
 			    cpu_to_le32(FILE_READ_ONLY_DEVICE))
 				cifs_dbg(VFS, "mounted to read only share\n");
-			else if ((cifs_sb->mnt_cifs_flags &
-				  CIFS_MOUNT_RW_CACHE) == 0)
+			else if (!(sbflags & CIFS_MOUNT_RW_CACHE))
 				cifs_dbg(VFS, "read only mount of RW share\n");
 			/* no need to log a RW mount of a typical RW share */
 		}
@@ -3660,11 +3667,12 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * Inside cifs_fscache_get_super_cookie it checks
 	 * that we do not get super cookie twice.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
+	if (sbflags & CIFS_MOUNT_FSCACHE)
 		cifs_fscache_get_super_cookie(tcon);
 
 out:
 	mnt_ctx->tcon = tcon;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
 	return rc;
 }
 
@@ -3783,7 +3791,8 @@ int cifs_is_path_remote(struct cifs_mount_ctx *mnt_ctx)
 			cifs_sb, full_path, tcon->Flags & SMB_SHARE_IS_IN_DFS);
 		if (rc != 0) {
 			cifs_server_dbg(VFS, "cannot query dirs between root and final path, enabling CIFS_MOUNT_USE_PREFIX_PATH\n");
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+			atomic_or(CIFS_MOUNT_USE_PREFIX_PATH,
+				  &cifs_sb->mnt_cifs_flags);
 			rc = 0;
 		}
 	}
@@ -3863,7 +3872,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 	 * Force the use of prefix path to support failover on DFS paths that resolve to targets
 	 * that have different prefix paths.
 	 */
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 	kfree(cifs_sb->prepath);
 	cifs_sb->prepath = ctx->prepath;
 	ctx->prepath = NULL;
@@ -4357,7 +4366,7 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
 	kuid_t fsuid = current_fsuid();
 	int err;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		return cifs_get_tlink(cifs_sb_master_tlink(cifs_sb));
 
 	spin_lock(&cifs_sb->tlink_tree_lock);
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 983132735d72..83f8cf2f8d2b 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1333,7 +1333,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
 	 * Force the use of prefix path to support failover on DFS paths that resolve to targets
 	 * that have different prefix paths.
 	 */
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 
 	refresh_tcon_referral(tcon, true);
 	return 0;
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index cb10088197d2..953f1fee8cb8 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -82,10 +82,11 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 					       const char *tree, int tree_len,
 					       bool prefix)
 {
-	int dfsplen;
-	int pplen = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	char dirsep = CIFS_DIR_SEP(cifs_sb);
+	int pplen = 0;
+	int dfsplen;
 	char *s;
 
 	if (unlikely(!page))
@@ -96,7 +97,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 	else
 		dfsplen = 0;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if (sbflags & CIFS_MOUNT_USE_PREFIX_PATH)
 		pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0;
 
 	s = dentry_path_raw(direntry, page, PATH_MAX);
@@ -123,7 +124,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 	if (dfsplen) {
 		s -= dfsplen;
 		memcpy(s, tree, dfsplen);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
+		if (sbflags & CIFS_MOUNT_POSIX_PATHS) {
 			int i;
 			for (i = 0; i < dfsplen; i++) {
 				if (s[i] == '\\')
@@ -152,7 +153,7 @@ char *build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page
 static int
 check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry);
 	int i;
 
 	if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength &&
@@ -160,7 +161,7 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 		     le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
 		return -ENAMETOOLONG;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS)) {
 		for (i = 0; i < direntry->d_name.len; i++) {
 			if (direntry->d_name.name[i] == '\\') {
 				cifs_dbg(FYI, "Invalid file name\n");
@@ -181,11 +182,12 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	int rc = -ENOENT;
 	int create_options = CREATE_NOT_DIR;
 	int desired_access;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon = tlink_tcon(tlink);
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct inode *newinode = NULL;
+	unsigned int sbflags;
 	int disposition;
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
@@ -365,6 +367,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	 * If Open reported that we actually created a file then we now have to
 	 * set the mode if possible.
 	 */
+	sbflags = cifs_sb_flags(cifs_sb);
 	if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
 		struct cifs_unix_set_info_args args = {
 				.mode	= mode,
@@ -374,7 +377,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 				.device	= 0,
 		};
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
 				args.gid = inode->i_gid;
@@ -411,9 +414,9 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 			if (server->ops->set_lease_key)
 				server->ops->set_lease_key(newinode, fid);
 			if ((*oplock & CIFS_CREATE_ACTION) && S_ISREG(newinode->i_mode)) {
-				if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+				if (sbflags & CIFS_MOUNT_DYNPERM)
 					newinode->i_mode = mode;
-				if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+				if (sbflags & CIFS_MOUNT_SET_UID) {
 					newinode->i_uid = current_fsuid();
 					if (inode->i_mode & S_ISGID)
 						newinode->i_gid = inode->i_gid;
@@ -458,18 +461,20 @@ int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		 struct file *file, unsigned int oflags, umode_t mode)
 {
-	int rc;
-	unsigned int xid;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_open_info_data buf = {};
+	struct TCP_Server_Info *server;
+	struct cifsFileInfo *file_info;
+	struct cifs_pending_open open;
+	struct cifs_fid fid = {};
 	struct tcon_link *tlink;
 	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
-	struct cifs_fid fid = {};
-	struct cifs_pending_open open;
+	unsigned int sbflags;
+	unsigned int xid;
 	__u32 oplock;
-	struct cifsFileInfo *file_info;
-	struct cifs_open_info_data buf = {};
+	int rc;
 
-	if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb))))
+	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
 
 	/*
@@ -499,7 +504,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
 		 inode, direntry, direntry);
 
-	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
 		rc = PTR_ERR(tlink);
 		goto out_free_xid;
@@ -536,13 +541,13 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		goto out;
 	}
 
-	if (file->f_flags & O_DIRECT &&
-	    CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-		if (CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) {
+		if (sbflags & CIFS_MOUNT_NO_BRL)
 			file->f_op = &cifs_file_direct_nobrl_ops;
 		else
 			file->f_op = &cifs_file_direct_ops;
-		}
+	}
 
 	file_info = cifs_new_fileinfo(&fid, file, tlink, oplock, buf.symlink_target);
 	if (file_info == NULL) {
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 18f31d4eb98d..f3ddcdf406c8 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -270,7 +270,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq)
 static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
 	struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode);
 	struct cifsFileInfo *open_file = NULL;
 
 	rreq->rsize = cifs_sb->ctx->rsize;
@@ -281,7 +281,7 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
 		open_file = file->private_data;
 		rreq->netfs_priv = file->private_data;
 		req->cfile = cifsFileInfo_get(open_file);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RWPIDFORWARD)
 			req->pid = req->cfile->pid;
 	} else if (rreq->origin != NETFS_WRITEBACK) {
 		WARN_ON_ONCE(1);
@@ -906,7 +906,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
 		 * close  because it may cause a error when we open this file
 		 * again and get at least level II oplock.
 		 */
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_STRICT_IO)
 			set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
 		cifs_set_oplock_level(cifsi, 0);
 	}
@@ -955,11 +955,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
 int cifs_file_flush(const unsigned int xid, struct inode *inode,
 		    struct cifsFileInfo *cfile)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon;
 	int rc;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC)
 		return 0;
 
 	if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) {
@@ -1015,24 +1015,24 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 int cifs_open(struct inode *inode, struct file *file)
 
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_open_info_data data = {};
+	struct cifsFileInfo *cfile = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_pending_open open;
+	bool posix_open_ok = false;
+	struct cifs_fid fid = {};
+	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	const char *full_path;
+	unsigned int sbflags;
 	int rc = -EACCES;
 	unsigned int xid;
 	__u32 oplock;
-	struct cifs_sb_info *cifs_sb;
-	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon;
-	struct tcon_link *tlink;
-	struct cifsFileInfo *cfile = NULL;
 	void *page;
-	const char *full_path;
-	bool posix_open_ok = false;
-	struct cifs_fid fid = {};
-	struct cifs_pending_open open;
-	struct cifs_open_info_data data = {};
 
 	xid = get_xid();
 
-	cifs_sb = CIFS_SB(inode->i_sb);
 	if (unlikely(cifs_forced_shutdown(cifs_sb))) {
 		free_xid(xid);
 		return smb_EIO(smb_eio_trace_forced_shutdown);
@@ -1056,9 +1056,9 @@ int cifs_open(struct inode *inode, struct file *file)
 	cifs_dbg(FYI, "inode = 0x%p file flags are 0x%x for %s\n",
 		 inode, file->f_flags, full_path);
 
-	if (file->f_flags & O_DIRECT &&
-	    cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) {
+		if (sbflags & CIFS_MOUNT_NO_BRL)
 			file->f_op = &cifs_file_direct_nobrl_ops;
 		else
 			file->f_op = &cifs_file_direct_ops;
@@ -1209,7 +1209,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode);
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 
 	down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
@@ -1222,7 +1222,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		rc = cifs_push_posix_locks(cfile);
 	else
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
@@ -2011,7 +2011,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode);
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 
 	/* we are going to update can_cache_brlcks here - need a write access */
@@ -2024,7 +2024,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		rc = cifs_push_posix_locks(cfile);
 	else
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
@@ -2428,11 +2428,11 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	cifs_read_flock(fl, &type, &lock, &unlock, &wait_flag,
 			tcon->ses->server);
-	cifs_sb = CIFS_FILE_SB(file);
+	cifs_sb = CIFS_SB(file);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		posix_lck = true;
 
 	if (!lock && !unlock) {
@@ -2455,14 +2455,14 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 {
-	int rc, xid;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
+	struct cifsFileInfo *cfile;
 	int lock = 0, unlock = 0;
 	bool wait_flag = false;
 	bool posix_lck = false;
-	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	struct cifsFileInfo *cfile;
 	__u32 type;
+	int rc, xid;
 
 	rc = -EACCES;
 	xid = get_xid();
@@ -2477,12 +2477,11 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 
 	cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag,
 			tcon->ses->server);
-	cifs_sb = CIFS_FILE_SB(file);
 	set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		posix_lck = true;
 	/*
 	 * BB add code here to normalize offset and length to account for
@@ -2532,11 +2531,11 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
 struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 					bool fsuid_only)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode);
 	struct cifsFileInfo *open_file = NULL;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
 
 	/* only filter by fsuid on multiuser mounts */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
 	spin_lock(&cifs_inode->open_file_lock);
@@ -2589,10 +2588,10 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
 		return rc;
 	}
 
-	cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
+	cifs_sb = CIFS_SB(cifs_inode);
 
 	/* only filter by fsuid on multiuser mounts */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
 	spin_lock(&cifs_inode->open_file_lock);
@@ -2787,7 +2786,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct TCP_Server_Info *server;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file_inode(file);
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 
 	rc = file_write_and_wait_range(file, start, end);
 	if (rc) {
@@ -2801,7 +2800,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		 file, datasync);
 
 	tcon = tlink_tcon(smbfile->tlink);
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
 		if (server->ops->flush == NULL) {
 			rc = -ENOSYS;
@@ -2853,7 +2852,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file->f_mapping->host;
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	ssize_t rc;
 
 	rc = netfs_start_io_write(inode);
@@ -2870,7 +2869,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	if (rc <= 0)
 		goto out;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) &&
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) &&
 	    (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
 				     server->vals->exclusive_lock_type, 0,
 				     NULL, CIFS_WRITE_OP))) {
@@ -2893,7 +2892,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)
 						iocb->ki_filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -2906,7 +2905,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 	if (CIFS_CACHE_WRITE(cinode)) {
 		if (cap_unix(tcon->ses) &&
 		    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-		    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+		    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
 			written = netfs_file_write_iter(iocb, from);
 			goto out;
 		}
@@ -2994,7 +2993,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)
 						iocb->ki_filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -3011,7 +3010,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 	if (!CIFS_CACHE_READ(cinode))
 		return netfs_unbuffered_read_iter(iocb, to);
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) {
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0) {
 		if (iocb->ki_flags & IOCB_DIRECT)
 			return netfs_unbuffered_read_iter(iocb, to);
 		return netfs_buffered_read_iter(iocb, to);
@@ -3130,10 +3129,9 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file,
 	if (is_inode_writable(cifsInode) ||
 		((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) {
 		/* This inode is open for write at least once */
-		struct cifs_sb_info *cifs_sb;
+		struct cifs_sb_info *cifs_sb = CIFS_SB(cifsInode);
 
-		cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DIRECT_IO) {
 			/* since no page cache to corrupt on directio
 			we can change size safely */
 			return true;
@@ -3181,7 +3179,7 @@ void cifs_oplock_break(struct work_struct *work)
 	server = tcon->ses->server;
 
 	scoped_guard(spinlock, &cinode->open_file_lock) {
-		unsigned int sbflags = cifs_sb->mnt_cifs_flags;
+		unsigned int sbflags = cifs_sb_flags(cifs_sb);
 
 		server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
 					      cfile->oplock_epoch, &purge_cache);
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 09fe749e97ee..54090739535f 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -2062,161 +2062,160 @@ smb3_cleanup_fs_context(struct smb3_fs_context *ctx)
 	kfree(ctx);
 }
 
-void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb)
+unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	struct smb3_fs_context *ctx = cifs_sb->ctx;
 
 	if (ctx->nodfs)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_DFS;
+		sbflags |= CIFS_MOUNT_NO_DFS;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_DFS;
+		sbflags &= ~CIFS_MOUNT_NO_DFS;
 
 	if (ctx->noperm)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
+		sbflags |= CIFS_MOUNT_NO_PERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_PERM;
+		sbflags &= ~CIFS_MOUNT_NO_PERM;
 
 	if (ctx->setuids)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID;
+		sbflags |= CIFS_MOUNT_SET_UID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SET_UID;
+		sbflags &= ~CIFS_MOUNT_SET_UID;
 
 	if (ctx->setuidfromacl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UID_FROM_ACL;
+		sbflags |= CIFS_MOUNT_UID_FROM_ACL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UID_FROM_ACL;
+		sbflags &= ~CIFS_MOUNT_UID_FROM_ACL;
 
 	if (ctx->server_ino)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
+		sbflags |= CIFS_MOUNT_SERVER_INUM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
+		sbflags &= ~CIFS_MOUNT_SERVER_INUM;
 
 	if (ctx->remap)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SFM_CHR;
+		sbflags |= CIFS_MOUNT_MAP_SFM_CHR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SFM_CHR;
+		sbflags &= ~CIFS_MOUNT_MAP_SFM_CHR;
 
 	if (ctx->sfu_remap)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
+		sbflags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR;
+		sbflags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR;
 
 	if (ctx->no_xattr)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR;
+		sbflags |= CIFS_MOUNT_NO_XATTR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_XATTR;
+		sbflags &= ~CIFS_MOUNT_NO_XATTR;
 
 	if (ctx->sfu_emul)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
+		sbflags |= CIFS_MOUNT_UNX_EMUL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UNX_EMUL;
+		sbflags &= ~CIFS_MOUNT_UNX_EMUL;
 
 	if (ctx->nobrl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
+		sbflags |= CIFS_MOUNT_NO_BRL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_BRL;
+		sbflags &= ~CIFS_MOUNT_NO_BRL;
 
 	if (ctx->nohandlecache)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE;
+		sbflags |= CIFS_MOUNT_NO_HANDLE_CACHE;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_HANDLE_CACHE;
+		sbflags &= ~CIFS_MOUNT_NO_HANDLE_CACHE;
 
 	if (ctx->nostrictsync)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC;
+		sbflags |= CIFS_MOUNT_NOSSYNC;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOSSYNC;
+		sbflags &= ~CIFS_MOUNT_NOSSYNC;
 
 	if (ctx->mand_lock)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOPOSIXBRL;
+		sbflags |= CIFS_MOUNT_NOPOSIXBRL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOPOSIXBRL;
+		sbflags &= ~CIFS_MOUNT_NOPOSIXBRL;
 
 	if (ctx->rwpidforward)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD;
+		sbflags |= CIFS_MOUNT_RWPIDFORWARD;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_RWPIDFORWARD;
+		sbflags &= ~CIFS_MOUNT_RWPIDFORWARD;
 
 	if (ctx->mode_ace)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MODE_FROM_SID;
+		sbflags |= CIFS_MOUNT_MODE_FROM_SID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MODE_FROM_SID;
+		sbflags &= ~CIFS_MOUNT_MODE_FROM_SID;
 
 	if (ctx->cifs_acl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
+		sbflags |= CIFS_MOUNT_CIFS_ACL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_ACL;
+		sbflags &= ~CIFS_MOUNT_CIFS_ACL;
 
 	if (ctx->backupuid_specified)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID;
+		sbflags |= CIFS_MOUNT_CIFS_BACKUPUID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPUID;
+		sbflags &= ~CIFS_MOUNT_CIFS_BACKUPUID;
 
 	if (ctx->backupgid_specified)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID;
+		sbflags |= CIFS_MOUNT_CIFS_BACKUPGID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPGID;
+		sbflags &= ~CIFS_MOUNT_CIFS_BACKUPGID;
 
 	if (ctx->override_uid)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID;
+		sbflags |= CIFS_MOUNT_OVERR_UID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_UID;
+		sbflags &= ~CIFS_MOUNT_OVERR_UID;
 
 	if (ctx->override_gid)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID;
+		sbflags |= CIFS_MOUNT_OVERR_GID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_GID;
+		sbflags &= ~CIFS_MOUNT_OVERR_GID;
 
 	if (ctx->dynperm)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM;
+		sbflags |= CIFS_MOUNT_DYNPERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DYNPERM;
+		sbflags &= ~CIFS_MOUNT_DYNPERM;
 
 	if (ctx->fsc)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_FSCACHE;
+		sbflags |= CIFS_MOUNT_FSCACHE;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_FSCACHE;
+		sbflags &= ~CIFS_MOUNT_FSCACHE;
 
 	if (ctx->multiuser)
-		cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER |
-					    CIFS_MOUNT_NO_PERM);
+		sbflags |= CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER;
+		sbflags &= ~CIFS_MOUNT_MULTIUSER;
 
 
 	if (ctx->strict_io)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO;
+		sbflags |= CIFS_MOUNT_STRICT_IO;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_STRICT_IO;
+		sbflags &= ~CIFS_MOUNT_STRICT_IO;
 
 	if (ctx->direct_io)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
+		sbflags |= CIFS_MOUNT_DIRECT_IO;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DIRECT_IO;
+		sbflags &= ~CIFS_MOUNT_DIRECT_IO;
 
 	if (ctx->mfsymlinks)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS;
+		sbflags |= CIFS_MOUNT_MF_SYMLINKS;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MF_SYMLINKS;
-	if (ctx->mfsymlinks) {
-		if (ctx->sfu_emul) {
-			/*
-			 * Our SFU ("Services for Unix") emulation allows now
-			 * creating new and reading existing SFU symlinks.
-			 * Older Linux kernel versions were not able to neither
-			 * read existing nor create new SFU symlinks. But
-			 * creating and reading SFU style mknod and FIFOs was
-			 * supported for long time. When "mfsymlinks" and
-			 * "sfu" are both enabled at the same time, it allows
-			 * reading both types of symlinks, but will only create
-			 * them with mfsymlinks format. This allows better
-			 * Apple compatibility, compatibility with older Linux
-			 * kernel clients (probably better for Samba too)
-			 * while still recognizing old Windows style symlinks.
-			 */
-			cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n");
-		}
-	}
-	cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SHUTDOWN;
+		sbflags &= ~CIFS_MOUNT_MF_SYMLINKS;
 
-	return;
+	if (ctx->mfsymlinks && ctx->sfu_emul) {
+		/*
+		 * Our SFU ("Services for Unix") emulation allows now
+		 * creating new and reading existing SFU symlinks.
+		 * Older Linux kernel versions were not able to neither
+		 * read existing nor create new SFU symlinks. But
+		 * creating and reading SFU style mknod and FIFOs was
+		 * supported for long time. When "mfsymlinks" and
+		 * "sfu" are both enabled at the same time, it allows
+		 * reading both types of symlinks, but will only create
+		 * them with mfsymlinks format. This allows better
+		 * Apple compatibility, compatibility with older Linux
+		 * kernel clients (probably better for Samba too)
+		 * while still recognizing old Windows style symlinks.
+		 */
+		cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n");
+	}
+	sbflags &= ~CIFS_MOUNT_SHUTDOWN;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+	return sbflags;
 }
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 49b2a6f09ca2..0b64fcb5d302 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -374,7 +374,7 @@ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx,
 			struct smb3_fs_context *ctx);
 int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb,
 				    struct cifs_ses *ses);
-void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
+unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
 
 /*
  * max deferred close timeout (jiffies) - 2^30
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index d4d3cfeb6c90..3e844c55ab8a 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -40,32 +40,33 @@ static void cifs_set_netfs_context(struct inode *inode)
 
 static void cifs_set_ops(struct inode *inode)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &cifs_file_inode_ops;
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
+		if (sbflags & CIFS_MOUNT_DIRECT_IO) {
 			set_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags);
-			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+			if (sbflags & CIFS_MOUNT_NO_BRL)
 				inode->i_fop = &cifs_file_direct_nobrl_ops;
 			else
 				inode->i_fop = &cifs_file_direct_ops;
-		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+		} else if (sbflags & CIFS_MOUNT_STRICT_IO) {
+			if (sbflags & CIFS_MOUNT_NO_BRL)
 				inode->i_fop = &cifs_file_strict_nobrl_ops;
 			else
 				inode->i_fop = &cifs_file_strict_ops;
-		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+		} else if (sbflags & CIFS_MOUNT_NO_BRL)
 			inode->i_fop = &cifs_file_nobrl_ops;
 		else { /* not direct, send byte range locks */
 			inode->i_fop = &cifs_file_ops;
 		}
 
 		/* check if server can support readahead */
-		if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read <
-				PAGE_SIZE + MAX_CIFS_HDR_SIZE)
+		if (tcon->ses->server->max_read < PAGE_SIZE + MAX_CIFS_HDR_SIZE)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
 		else
 			inode->i_data.a_ops = &cifs_addr_ops;
@@ -194,8 +195,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
 	inode->i_gid = fattr->cf_gid;
 
 	/* if dynperm is set, don't clobber existing mode */
-	if (inode_state_read(inode) & I_NEW ||
-	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM))
+	if ((inode_state_read(inode) & I_NEW) ||
+	    !(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DYNPERM))
 		inode->i_mode = fattr->cf_mode;
 
 	cifs_i->cifsAttrs = fattr->cf_cifsattrs;
@@ -248,10 +249,8 @@ cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
-		return;
-
-	fattr->cf_uniqueid = iunique(sb, ROOT_I);
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM))
+		fattr->cf_uniqueid = iunique(sb, ROOT_I);
 }
 
 /* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */
@@ -259,6 +258,8 @@ void
 cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 			 struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags;
+
 	memset(fattr, 0, sizeof(*fattr));
 	fattr->cf_uniqueid = le64_to_cpu(info->UniqueId);
 	fattr->cf_bytes = le64_to_cpu(info->NumOfBytes);
@@ -317,8 +318,9 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 		break;
 	}
 
+	sbflags = cifs_sb_flags(cifs_sb);
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) {
+	if (!(sbflags & CIFS_MOUNT_OVERR_UID)) {
 		u64 id = le64_to_cpu(info->Uid);
 		if (id < ((uid_t)-1)) {
 			kuid_t uid = make_kuid(&init_user_ns, id);
@@ -328,7 +330,7 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 	}
 	
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) {
+	if (!(sbflags & CIFS_MOUNT_OVERR_GID)) {
 		u64 id = le64_to_cpu(info->Gid);
 		if (id < ((gid_t)-1)) {
 			kgid_t gid = make_kgid(&init_user_ns, id);
@@ -382,7 +384,7 @@ static int update_inode_info(struct super_block *sb,
 	 *
 	 * If file type or uniqueid is different, return error.
 	 */
-	if (unlikely((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+	if (unlikely((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) &&
 		     CIFS_I(*inode)->uniqueid != fattr->cf_uniqueid)) {
 		CIFS_I(*inode)->time = 0; /* force reval */
 		return -ESTALE;
@@ -468,7 +470,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path,
 		cifs_fill_uniqueid(sb, fattr);
 
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1081,7 +1083,7 @@ cifs_backup_query_path_info(int xid,
 	else if ((tcon->ses->capabilities &
 		  tcon->ses->server->vals->cap_nt_find) == 0)
 		info.info_level = SMB_FIND_FILE_INFO_STANDARD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+	else if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)
 		info.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	else /* no srvino useful for fallback to some netapp */
 		info.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
@@ -1109,7 +1111,7 @@ static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_blo
 	struct TCP_Server_Info *server = tcon->ses->server;
 	int rc;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)) {
 		if (*inode)
 			fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid;
 		else
@@ -1263,14 +1265,15 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 			  struct inode **inode,
 			  const char *full_path)
 {
-	struct cifs_open_info_data tmp_data = {};
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
-	struct tcon_link *tlink;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	struct cifs_open_info_data tmp_data = {};
 	void *smb1_backup_rsp_buf = NULL;
-	int rc = 0;
+	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
+	unsigned int sbflags;
 	int tmprc = 0;
+	int rc = 0;
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
@@ -1370,16 +1373,17 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 handle_mnt_opt:
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
+	sbflags = cifs_sb_flags(cifs_sb);
 	/* query for SFU type info if supported and needed */
 	if ((fattr->cf_cifsattrs & ATTR_SYSTEM) &&
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
+	    (sbflags & CIFS_MOUNT_UNX_EMUL)) {
 		tmprc = cifs_sfu_type(fattr, full_path, cifs_sb, xid);
 		if (tmprc)
 			cifs_dbg(FYI, "cifs_sfu_type failed: %d\n", tmprc);
 	}
 
 	/* fill in 0777 bits from ACL */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) {
+	if (sbflags & CIFS_MOUNT_MODE_FROM_SID) {
 		rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode,
 				       true, full_path, fid);
 		if (rc == -EREMOTE)
@@ -1389,7 +1393,7 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 				 __func__, rc);
 			goto out;
 		}
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
+	} else if (sbflags & CIFS_MOUNT_CIFS_ACL) {
 		rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode,
 				       false, full_path, fid);
 		if (rc == -EREMOTE)
@@ -1399,7 +1403,7 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 				 __func__, rc);
 			goto out;
 		}
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
+	} else if (sbflags & CIFS_MOUNT_UNX_EMUL)
 		/* fill in remaining high mode bits e.g. SUID, VTX */
 		cifs_sfu_mode(fattr, full_path, cifs_sb, xid);
 	else if (!(tcon->posix_extensions))
@@ -1409,7 +1413,7 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 
 
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (sbflags & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1509,7 +1513,7 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	 * 3. Tweak fattr based on mount options
 	 */
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1660,7 +1664,7 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	int len;
 	int rc;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH)
 	    && cifs_sb->prepath) {
 		len = strlen(cifs_sb->prepath);
 		path = kzalloc(len + 2 /* leading sep + null */, GFP_KERNEL);
@@ -2098,8 +2102,9 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 		 const char *full_path, struct cifs_sb_info *cifs_sb,
 		 struct cifs_tcon *tcon, const unsigned int xid)
 {
-	int rc = 0;
 	struct inode *inode = NULL;
+	unsigned int sbflags;
+	int rc = 0;
 
 	if (tcon->posix_extensions) {
 		rc = smb311_posix_get_inode_info(&inode, full_path,
@@ -2139,6 +2144,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 	if (parent->i_mode & S_ISGID)
 		mode |= S_ISGID;
 
+	sbflags = cifs_sb_flags(cifs_sb);
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (tcon->unix_ext) {
 		struct cifs_unix_set_info_args args = {
@@ -2148,7 +2154,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 			.mtime	= NO_CHANGE_64,
 			.device	= 0,
 		};
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (parent->i_mode & S_ISGID)
 				args.gid = parent->i_gid;
@@ -2166,14 +2172,14 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 	{
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 		struct TCP_Server_Info *server = tcon->ses->server;
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
+		if (!(sbflags & CIFS_MOUNT_CIFS_ACL) &&
 		    (mode & S_IWUGO) == 0 && server->ops->mkdir_setinfo)
 			server->ops->mkdir_setinfo(inode, full_path, cifs_sb,
 						   tcon, xid);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+		if (sbflags & CIFS_MOUNT_DYNPERM)
 			inode->i_mode = (mode | S_IFDIR);
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			inode->i_uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
 				inode->i_gid = parent->i_gid;
@@ -2686,7 +2692,7 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct cached_fid *cfid = NULL;
 
@@ -2727,7 +2733,7 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 	}
 
 	/* hardlinked files w/ noserverino get "special" treatment */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) &&
 	    S_ISREG(inode->i_mode) && inode->i_nlink != 1)
 		return true;
 
@@ -2752,10 +2758,10 @@ cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 int
 cifs_revalidate_mapping(struct inode *inode)
 {
-	int rc;
 	struct cifsInodeInfo *cifs_inode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	unsigned long *flags = &cifs_inode->flags;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	int rc;
 
 	/* swapfiles are not supposed to be shared */
 	if (IS_SWAPFILE(inode))
@@ -2768,7 +2774,7 @@ cifs_revalidate_mapping(struct inode *inode)
 
 	if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) {
 		/* for cache=singleclient, do not invalidate */
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RW_CACHE)
 			goto skip_invalidate;
 
 		cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size;
@@ -2892,10 +2898,11 @@ int cifs_revalidate_dentry(struct dentry *dentry)
 int cifs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int flags)
 {
-	struct dentry *dentry = path->dentry;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(path->dentry);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct dentry *dentry = path->dentry;
 	struct inode *inode = d_inode(dentry);
+	unsigned int sbflags;
 	int rc;
 
 	if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb))))
@@ -2952,12 +2959,13 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	 * enabled, and the admin hasn't overridden them, set the ownership
 	 * to the fsuid/fsgid of the current process.
 	 */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) &&
-	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((sbflags & CIFS_MOUNT_MULTIUSER) &&
+	    !(sbflags & CIFS_MOUNT_CIFS_ACL) &&
 	    !tcon->unix_ext) {
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID))
+		if (!(sbflags & CIFS_MOUNT_OVERR_UID))
 			stat->uid = current_fsuid();
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID))
+		if (!(sbflags & CIFS_MOUNT_OVERR_GID))
 			stat->gid = current_fsgid();
 	}
 	return 0;
@@ -3102,7 +3110,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	void *page = alloc_dentry_path();
 	struct inode *inode = d_inode(direntry);
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	struct cifs_unix_set_info_args *args = NULL;
@@ -3113,7 +3121,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 
 	xid = get_xid();
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
 
 	rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs);
@@ -3266,26 +3274,26 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 static int
 cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 {
-	unsigned int xid;
+	struct inode *inode = d_inode(direntry);
+	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+	struct cifsFileInfo *cfile = NULL;
+	void *page = alloc_dentry_path();
+	__u64 mode = NO_CHANGE_64;
 	kuid_t uid = INVALID_UID;
 	kgid_t gid = INVALID_GID;
-	struct inode *inode = d_inode(direntry);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-	struct cifsFileInfo *cfile = NULL;
 	const char *full_path;
-	void *page = alloc_dentry_path();
-	int rc = -EACCES;
 	__u32 dosattr = 0;
-	__u64 mode = NO_CHANGE_64;
-	bool posix = cifs_sb_master_tcon(cifs_sb)->posix_extensions;
+	int rc = -EACCES;
+	unsigned int xid;
 
 	xid = get_xid();
 
 	cifs_dbg(FYI, "setattr on file %pd attrs->ia_valid 0x%x\n",
 		 direntry, attrs->ia_valid);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (sbflags & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
 
 	rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs);
@@ -3346,8 +3354,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if (attrs->ia_valid & ATTR_GID)
 		gid = attrs->ia_gid;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)) {
+	if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) {
 		if (uid_valid(uid) || gid_valid(gid)) {
 			mode = NO_CHANGE_64;
 			rc = id_mode_to_cifs_acl(inode, full_path, &mode,
@@ -3358,9 +3365,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 				goto cifs_setattr_exit;
 			}
 		}
-	} else
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID))
+	} else if (!(sbflags & CIFS_MOUNT_SET_UID)) {
 		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
+	}
 
 	/* skip mode change if it's just for clearing setuid/setgid */
 	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
@@ -3369,9 +3376,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if (attrs->ia_valid & ATTR_MODE) {
 		mode = attrs->ia_mode;
 		rc = 0;
-		if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-		    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) ||
-		    posix) {
+		if ((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) ||
+		    cifs_sb_master_tcon(cifs_sb)->posix_extensions) {
 			rc = id_mode_to_cifs_acl(inode, full_path, &mode,
 						INVALID_UID, INVALID_GID);
 			if (rc) {
@@ -3393,7 +3399,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 			dosattr = cifsInode->cifsAttrs | ATTR_READONLY;
 
 			/* fix up mode if we're not using dynperm */
-			if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
+			if ((sbflags & CIFS_MOUNT_DYNPERM) == 0)
 				attrs->ia_mode = inode->i_mode & ~S_IWUGO;
 		} else if ((mode & S_IWUGO) &&
 			   (cifsInode->cifsAttrs & ATTR_READONLY)) {
@@ -3404,7 +3410,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 				dosattr |= ATTR_NORMAL;
 
 			/* reset local inode permissions to normal */
-			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+			if (!(sbflags & CIFS_MOUNT_DYNPERM)) {
 				attrs->ia_mode &= ~(S_IALLUGO);
 				if (S_ISDIR(inode->i_mode))
 					attrs->ia_mode |=
@@ -3413,7 +3419,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 					attrs->ia_mode |=
 						cifs_sb->ctx->file_mode;
 			}
-		} else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+		} else if (!(sbflags & CIFS_MOUNT_DYNPERM)) {
 			/* ignore mode change - ATTR_READONLY hasn't changed */
 			attrs->ia_valid &= ~ATTR_MODE;
 		}
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 8dc2651e237f..9afab3237e54 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -216,7 +216,7 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
 	 */
 	case CIFS_GOING_FLAGS_LOGFLUSH:
 	case CIFS_GOING_FLAGS_NOLOGFLUSH:
-		sbi->mnt_cifs_flags |= CIFS_MOUNT_SHUTDOWN;
+		atomic_or(CIFS_MOUNT_SHUTDOWN, &sbi->mnt_cifs_flags);
 		goto shutdown_good;
 	default:
 		rc = -EINVAL;
diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c
index a2f7bfa8ad1e..434e8fe74080 100644
--- a/fs/smb/client/link.c
+++ b/fs/smb/client/link.c
@@ -544,14 +544,15 @@ int
 cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	     struct dentry *direntry, const char *symname)
 {
-	int rc = -EOPNOTSUPP;
-	unsigned int xid;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct inode *newinode = NULL;
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	const char *full_path;
+	int rc = -EOPNOTSUPP;
+	unsigned int sbflags;
+	unsigned int xid;
 	void *page;
-	struct inode *newinode = NULL;
 
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
@@ -580,6 +581,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	cifs_dbg(FYI, "symname is %s\n", symname);
 
 	/* BB what if DFS and this volume is on different share? BB */
+	sbflags = cifs_sb_flags(cifs_sb);
 	rc = -EOPNOTSUPP;
 	switch (cifs_symlink_type(cifs_sb)) {
 	case CIFS_SYMLINK_TYPE_UNIX:
@@ -594,14 +596,14 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 		break;
 
 	case CIFS_SYMLINK_TYPE_MFSYMLINKS:
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+		if (sbflags & CIFS_MOUNT_MF_SYMLINKS) {
 			rc = create_mf_symlink(xid, pTcon, cifs_sb,
 					       full_path, symname);
 		}
 		break;
 
 	case CIFS_SYMLINK_TYPE_SFU:
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+		if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 			rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon,
 						  full_path, S_IFLNK,
 						  0, symname);
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 22cde46309fe..bc24c92b8b95 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -275,13 +275,15 @@ dump_smb(void *buf, int smb_buf_length)
 void
 cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		struct cifs_tcon *tcon = NULL;
 
 		if (cifs_sb->master_tlink)
 			tcon = cifs_sb_master_tcon(cifs_sb);
 
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
+		atomic_andnot(CIFS_MOUNT_SERVER_INUM, &cifs_sb->mnt_cifs_flags);
 		cifs_sb->mnt_cifs_serverino_autodisabled = true;
 		cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s\n",
 			 tcon ? tcon->tree_name : "new server");
@@ -382,11 +384,13 @@ void cifs_done_oplock_break(struct cifsInodeInfo *cinode)
 bool
 backup_cred(struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID) {
 		if (uid_eq(cifs_sb->ctx->backupuid, current_fsuid()))
 			return true;
 	}
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) {
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID) {
 		if (in_group_p(cifs_sb->ctx->backupgid))
 			return true;
 	}
@@ -955,7 +959,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix)
 			convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb));
 	}
 
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 	return 0;
 }
 
@@ -984,7 +988,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
 	 * look up or tcon is not DFS.
 	 */
 	if (strlen(full_path) < 2 || !cifs_sb ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) ||
+	    (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS) ||
 	    !is_tcon_dfs(tcon))
 		return 0;
 
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 8615a8747b7f..be22bbc4a65a 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -121,7 +121,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 			 * want to clobber the existing one with the one that
 			 * the readdir code created.
 			 */
-			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM))
+			if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM))
 				fattr->cf_uniqueid = CIFS_I(inode)->uniqueid;
 
 			/*
@@ -177,6 +177,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	struct cifs_open_info_data data = {
 		.reparse = { .tag = fattr->cf_cifstag, },
 	};
+	unsigned int sbflags;
 
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
@@ -215,12 +216,12 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	 * may look wrong since the inodes may not have timed out by the time
 	 * "ls" does a stat() call on them.
 	 */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID))
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID))
 		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL &&
-	    fattr->cf_cifsattrs & ATTR_SYSTEM) {
+	if ((sbflags & CIFS_MOUNT_UNX_EMUL) &&
+	    (fattr->cf_cifsattrs & ATTR_SYSTEM)) {
 		if (fattr->cf_eof == 0)  {
 			fattr->cf_mode &= ~S_IFMT;
 			fattr->cf_mode |= S_IFIFO;
@@ -345,13 +346,14 @@ static int
 _initiate_cifs_search(const unsigned int xid, struct file *file,
 		     const char *full_path)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
+	struct tcon_link *tlink = NULL;
+	struct TCP_Server_Info *server;
+	struct cifsFileInfo *cifsFile;
+	struct cifs_tcon *tcon;
+	unsigned int sbflags;
 	__u16 search_flags;
 	int rc = 0;
-	struct cifsFileInfo *cifsFile;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
-	struct tcon_link *tlink = NULL;
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
 
 	if (file->private_data == NULL) {
 		tlink = cifs_sb_tlink(cifs_sb);
@@ -385,6 +387,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file,
 	cifs_dbg(FYI, "Full path: %s start at: %lld\n", full_path, file->f_pos);
 
 ffirst_retry:
+	sbflags = cifs_sb_flags(cifs_sb);
 	/* test for Unix extensions */
 	/* but now check for them on the share/mount not on the SMB session */
 	/* if (cap_unix(tcon->ses) { */
@@ -395,7 +398,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file,
 	else if ((tcon->ses->capabilities &
 		  tcon->ses->server->vals->cap_nt_find) == 0) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_INFO_STANDARD;
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	} else if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	} else /* not srvinos - BB fixme add check for backlevel? */ {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
@@ -411,8 +414,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file,
 
 	if (rc == 0) {
 		cifsFile->invalidHandle = false;
-	} else if ((rc == -EOPNOTSUPP) &&
-		   (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	} else if (rc == -EOPNOTSUPP && (sbflags & CIFS_MOUNT_SERVER_INUM)) {
 		cifs_autodisable_serverino(cifs_sb);
 		goto ffirst_retry;
 	}
@@ -690,7 +692,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 	loff_t first_entry_in_buffer;
 	loff_t index_to_find = pos;
 	struct cifsFileInfo *cfile = file->private_data;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	/* check if index in the buffer */
 
@@ -955,6 +957,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_dirent de = { NULL, };
 	struct cifs_fattr fattr;
+	unsigned int sbflags;
 	struct qstr name;
 	int rc = 0;
 
@@ -1019,15 +1022,15 @@ static int cifs_filldir(char *find_entry, struct file *file,
 		break;
 	}
 
-	if (de.ino && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (de.ino && (sbflags & CIFS_MOUNT_SERVER_INUM)) {
 		fattr.cf_uniqueid = de.ino;
 	} else {
 		fattr.cf_uniqueid = iunique(sb, ROOT_I);
 		cifs_autodisable_serverino(cifs_sb);
 	}
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) &&
-	    couldbe_mf_symlink(&fattr))
+	if ((sbflags & CIFS_MOUNT_MF_SYMLINKS) && couldbe_mf_symlink(&fattr))
 		/*
 		 * trying to get the type and mode can be slow,
 		 * so just call those regular files for now, and mark
@@ -1058,7 +1061,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct cached_fid *cfid = NULL;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 
 	xid = get_xid();
 
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index ce9b923498b5..cd1e1eaee67a 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -55,17 +55,18 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 				 const char *full_path, const char *symname)
 {
 	struct reparse_symlink_data_buffer *buf = NULL;
-	struct cifs_open_info_data data = {};
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	const char *symroot = cifs_sb->ctx->symlinkroot;
-	struct inode *new;
-	struct kvec iov;
-	__le16 *path = NULL;
-	bool directory;
-	char *symlink_target = NULL;
-	char *sym = NULL;
+	struct cifs_open_info_data data = {};
 	char sep = CIFS_DIR_SEP(cifs_sb);
+	char *symlink_target = NULL;
 	u16 len, plen, poff, slen;
+	unsigned int sbflags;
+	__le16 *path = NULL;
+	struct inode *new;
+	char *sym = NULL;
+	struct kvec iov;
+	bool directory;
 	int rc = 0;
 
 	if (strlen(symname) > REPARSE_SYM_PATH_MAX)
@@ -83,8 +84,8 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		.symlink_target = symlink_target,
 	};
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
-	    symroot && symname[0] == '/') {
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symroot && symname[0] == '/') {
 		/*
 		 * This is a request to create an absolute symlink on the server
 		 * which does not support POSIX paths, and expects symlink in
@@ -164,7 +165,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 	 * mask these characters in NT object prefix by '_' and then change
 	 * them back.
 	 */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/')
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/')
 		sym[0] = sym[1] = sym[2] = sym[5] = '_';
 
 	path = cifs_convert_path_to_utf16(sym, cifs_sb);
@@ -173,7 +174,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		goto out;
 	}
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
 		sym[0] = '\\';
 		sym[1] = sym[2] = '?';
 		sym[5] = ':';
@@ -197,7 +198,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 	slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX);
 	poff = 0;
 	plen = slen;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
 		/*
 		 * For absolute NT symlinks skip leading "\\??\\" in PrintName as
 		 * PrintName is user visible location in DOS/Win32 format (not in NT format).
@@ -824,7 +825,7 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
 		goto out;
 	}
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) &&
 	    symroot && !relative) {
 		/*
 		 * This is an absolute symlink from the server which does not
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index 570b0d25aeba..0164dc47bdfd 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -33,7 +33,7 @@ static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb,
 {
 	u32 uid = le32_to_cpu(*(__le32 *)ptr);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_UID)
 		return cifs_sb->ctx->linux_uid;
 	return make_kuid(current_user_ns(), uid);
 }
@@ -43,7 +43,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb,
 {
 	u32 gid = le32_to_cpu(*(__le32 *)ptr);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_GID)
 		return cifs_sb->ctx->linux_gid;
 	return make_kgid(current_user_ns(), gid);
 }
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index aed49aaef8c4..9643eca0cb70 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -49,6 +49,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 
 	if (!CIFSSMBQFSUnixInfo(xid, tcon)) {
 		__u64 cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
+		unsigned int sbflags;
 
 		cifs_dbg(FYI, "unix caps which server supports %lld\n", cap);
 		/*
@@ -75,14 +76,16 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 		if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)
 			cifs_dbg(VFS, "per-share encryption not supported yet\n");
 
+		if (cifs_sb)
+			sbflags = cifs_sb_flags(cifs_sb);
+
 		cap &= CIFS_UNIX_CAP_MASK;
 		if (ctx && ctx->no_psx_acl)
 			cap &= ~CIFS_UNIX_POSIX_ACL_CAP;
 		else if (CIFS_UNIX_POSIX_ACL_CAP & cap) {
 			cifs_dbg(FYI, "negotiated posix acl support\n");
 			if (cifs_sb)
-				cifs_sb->mnt_cifs_flags |=
-					CIFS_MOUNT_POSIXACL;
+				sbflags |= CIFS_MOUNT_POSIXACL;
 		}
 
 		if (ctx && ctx->posix_paths == 0)
@@ -90,10 +93,12 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 		else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) {
 			cifs_dbg(FYI, "negotiate posix pathnames\n");
 			if (cifs_sb)
-				cifs_sb->mnt_cifs_flags |=
-					CIFS_MOUNT_POSIX_PATHS;
+				sbflags |= CIFS_MOUNT_POSIX_PATHS;
 		}
 
+		if (cifs_sb)
+			atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+
 		cifs_dbg(FYI, "Negotiate caps 0x%x\n", (int)cap);
 #ifdef CONFIG_CIFS_DEBUG2
 		if (cap & CIFS_UNIX_FCNTL_CAP)
@@ -1147,7 +1152,7 @@ static int cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 				__u64 volatile_fid, __u16 net_fid,
 				struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__u8 op;
 
 	op = !!((oplock & CIFS_CACHE_READ_FLG) || (sbflags & CIFS_MOUNT_RO_CACHE));
@@ -1282,7 +1287,8 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 	       struct dentry *dentry, struct cifs_tcon *tcon,
 	       const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	struct inode *newinode = NULL;
 	int rc;
 
@@ -1298,7 +1304,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 			.mtime	= NO_CHANGE_64,
 			.device	= dev,
 		};
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			args.gid = current_fsgid();
 		} else {
@@ -1317,7 +1323,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 		if (rc == 0)
 			d_instantiate(dentry, newinode);
 		return rc;
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+	} else if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 		/*
 		 * Check if mounted with mount parm 'sfu' mount parm.
 		 * SFU emulation should work with all servers
diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c
index 1ab41de2b634..ed651c946251 100644
--- a/fs/smb/client/smb2file.c
+++ b/fs/smb/client/smb2file.c
@@ -72,7 +72,7 @@ int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_i
 	 * POSIX server does not distinguish between symlinks to file and
 	 * symlink directory. So nothing is needed to fix on the client side.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS)
 		return 0;
 
 	if (!*target)
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index e19674d9b92b..973fce3c959c 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -455,17 +455,8 @@ smb2_calc_size(void *buf)
 __le16 *
 cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 {
-	int len;
 	const char *start_of_path;
-	__le16 *to;
-	int map_type;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
-		map_type = SFM_MAP_UNI_RSVD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
-		map_type = SFU_MAP_UNI_RSVD;
-	else
-		map_type = NO_MAP_UNI_RSVD;
+	int len;
 
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
@@ -479,14 +470,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	} else
 		start_of_path = from;
 
-	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
-				   cifs_sb->local_nls, map_type);
-	return to;
+	return cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
+				     cifs_sb->local_nls, cifs_remap(cifs_sb));
 }
 
 __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__le32 lease = 0;
 
 	if ((oplock & CIFS_CACHE_WRITE_FLG) || (sbflags & CIFS_MOUNT_RW_CACHE))
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index fea9a35caa57..7f2d3459cbf9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -986,7 +986,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon,
 				rc = -EREMOTE;
 		}
 		if (rc == -EREMOTE && IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) &&
-		    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS))
+		    (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS))
 			rc = -EOPNOTSUPP;
 		goto out;
 	}
@@ -2691,7 +2691,7 @@ static int smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 				__u64 volatile_fid, __u16 net_fid,
 				struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__u8 op;
 
 	if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
@@ -5332,7 +5332,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode,
 			  struct dentry *dentry, struct cifs_tcon *tcon,
 			  const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 	int rc = -EOPNOTSUPP;
 
 	/*
@@ -5341,7 +5341,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode,
 	 * supports block and char device, socket & fifo,
 	 * and was used by default in earlier versions of Windows
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+	if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 		rc = cifs_sfu_make_node(xid, inode, dentry, tcon,
 					full_path, mode, dev);
 	} else if (CIFS_REPARSE_SUPPORT(tcon)) {
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index ef655acf673d..a2a96d817717 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3182,22 +3182,19 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 	}
 
 	if ((oparms->disposition != FILE_OPEN) && (oparms->cifs_sb)) {
+		unsigned int sbflags = cifs_sb_flags(oparms->cifs_sb);
 		bool set_mode;
 		bool set_owner;
 
-		if ((oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) &&
-		    (oparms->mode != ACL_NO_MODE))
+		if ((sbflags & CIFS_MOUNT_MODE_FROM_SID) &&
+		    oparms->mode != ACL_NO_MODE) {
 			set_mode = true;
-		else {
+		} else {
 			set_mode = false;
 			oparms->mode = ACL_NO_MODE;
 		}
 
-		if (oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
-			set_owner = true;
-		else
-			set_owner = false;
-
+		set_owner = sbflags & CIFS_MOUNT_UID_FROM_ACL;
 		if (set_owner | set_mode) {
 			cifs_dbg(FYI, "add sd with mode 0x%x\n", oparms->mode);
 			rc = add_sd_context(iov, &n_iov, oparms->mode, set_owner);
diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c
index e1a7d9a10a53..23227f2f9428 100644
--- a/fs/smb/client/xattr.c
+++ b/fs/smb/client/xattr.c
@@ -149,7 +149,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 			break;
 		}
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 			goto out;
 
 		if (pTcon->ses->server->ops->set_EA) {
@@ -309,7 +309,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 			break;
 		}
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 			goto out;
 
 		if (pTcon->ses->server->ops->query_all_EAs)
@@ -398,7 +398,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 		return -EOPNOTSUPP;
 
 	tlink = cifs_sb_tlink(cifs_sb);

From d9d1e319b39ea685ede59319002d567c159d23c3 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 25 Feb 2026 21:34:55 -0300
Subject: [PATCH 0525/1303] smb: client: fix broken multichannel with
 krb5+signing

When mounting a share with 'multichannel,max_channels=n,sec=krb5i',
the client was duplicating signing key for all secondary channels,
thus making the server fail all commands sent from secondary channels
due to bad signatures.

Every channel has its own signing key, so when establishing a new
channel with krb5 auth, make sure to use the new session key as the
derived key to generate channel's signing key in SMB2_auth_kerberos().

Repro:

$ mount.cifs //srv/share /mnt -o multichannel,max_channels=4,sec=krb5i
$ sleep 5
$ umount /mnt
$ dmesg
  ...
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x4 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13

Reported-by: Xiaoli Feng <xifeng@redhat.com>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a2a96d817717..04e361ed2356 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1714,19 +1714,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 	is_binding = (ses->ses_status == SES_GOOD);
 	spin_unlock(&ses->ses_lock);
 
-	/* keep session key if binding */
-	if (!is_binding) {
-		kfree_sensitive(ses->auth_key.response);
-		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
-						 GFP_KERNEL);
-		if (!ses->auth_key.response) {
-			cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n",
-				 msg->sesskey_len);
-			rc = -ENOMEM;
-			goto out_put_spnego_key;
-		}
-		ses->auth_key.len = msg->sesskey_len;
+	kfree_sensitive(ses->auth_key.response);
+	ses->auth_key.response = kmemdup(msg->data,
+					 msg->sesskey_len,
+					 GFP_KERNEL);
+	if (!ses->auth_key.response) {
+		cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n",
+			 __func__, msg->sesskey_len);
+		rc = -ENOMEM;
+		goto out_put_spnego_key;
 	}
+	ses->auth_key.len = msg->sesskey_len;
 
 	sess_data->iov[1].iov_base = msg->data + msg->sesskey_len;
 	sess_data->iov[1].iov_len = msg->secblob_len;

From 2f37dc436d4e61ff7ae0b0353cf91b8c10396e4d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 26 Feb 2026 22:28:45 +0100
Subject: [PATCH 0526/1303] smb: client: Don't log plaintext credentials in
 cifs_set_cifscreds

When debug logging is enabled, cifs_set_cifscreds() logs the key
payload and exposes the plaintext username and password. Remove the
debug log to avoid exposing credentials.

Fixes: 8a8798a5ff90 ("cifs: fetch credentials out of keyring for non-krb5 auth multiuser mounts")
Cc: stable@vger.kernel.org
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 87686c804057..4c34d9603e05 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2236,7 +2236,6 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	/* find first : in payload */
 	payload = upayload->data;
 	delim = strnchr(payload, upayload->datalen, ':');
-	cifs_dbg(FYI, "payload=%s\n", payload);
 	if (!delim) {
 		cifs_dbg(FYI, "Unable to find ':' in payload (datalen=%d)\n",
 			 upayload->datalen);

From e35626f610f3d2b7953ccddf6a77453da22b3a9e Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 24 Feb 2026 21:28:32 +0100
Subject: [PATCH 0527/1303] net/sched: ets: fix divide by zero in the offload
 path

Offloading ETS requires computing each class' WRR weight: this is done by
averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned
int, the same integer size as the individual DRR quanta, can overflow and
even cause division by zero, like it happened in the following splat:

 Oops: divide error: 0000 [#1] SMP PTI
 CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G            E       6.19.0-virtme #45 PREEMPT(full)
 Tainted: [E]=UNSIGNED_MODULE
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Call Trace:
  <TASK>
  ets_qdisc_change+0x870/0xf40 [sch_ets]
  qdisc_create+0x12b/0x540
  tc_modify_qdisc+0x6d7/0xbd0
  rtnetlink_rcv_msg+0x168/0x6b0
  netlink_rcv_skb+0x5c/0x110
  netlink_unicast+0x1d6/0x2b0
  netlink_sendmsg+0x22e/0x470
  ____sys_sendmsg+0x38a/0x3c0
  ___sys_sendmsg+0x99/0xe0
  __sys_sendmsg+0x8a/0xf0
  do_syscall_64+0x111/0xf80
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
 RIP: 0033:0x7f440b81c77e
 Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa
 RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e
 RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003
 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8
 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980
  </TASK>
 Modules linked in: sch_ets(E) netdevsim(E)
 ---[ end trace 0000000000000000 ]---
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
 ---[ end Kernel panic - not syncing: Fatal exception ]---

Fix this using 64-bit integers for 'q_sum' and 'q_psum'.

Cc: stable@vger.kernel.org
Fixes: d35eb52bd2ac ("net: sch_ets: Make the ETS qdisc offloadable")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/28504887df314588c7255e9911769c36f751edee.1771964872.git.dcaratti@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_ets.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 306e046276d4..a4b07b661b77 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch)
 	struct ets_sched *q = qdisc_priv(sch);
 	struct tc_ets_qopt_offload qopt;
 	unsigned int w_psum_prev = 0;
-	unsigned int q_psum = 0;
-	unsigned int q_sum = 0;
 	unsigned int quantum;
 	unsigned int w_psum;
 	unsigned int weight;
 	unsigned int i;
+	u64 q_psum = 0;
+	u64 q_sum = 0;
 
 	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
 		return;
@@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch)
 
 	for (i = 0; i < q->nbands; i++) {
 		quantum = q->classes[i].quantum;
-		q_psum += quantum;
-		w_psum = quantum ? q_psum * 100 / q_sum : 0;
+		if (quantum) {
+			q_psum += quantum;
+			w_psum = div64_u64(q_psum * 100, q_sum);
+		} else {
+			w_psum = 0;
+		}
 		weight = w_psum - w_psum_prev;
 		w_psum_prev = w_psum;
 

From 2ef2b20cf4e04ac8a6ba68493f8780776ff84300 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 25 Feb 2026 13:15:47 +0000
Subject: [PATCH 0528/1303] net: annotate data-races around
 sk->sk_{data_ready,write_space}

skmsg (and probably other layers) are changing these pointers
while other cpus might read them concurrently.

Add corresponding READ_ONCE()/WRITE_ONCE() annotations
for UDP, TCP and AF_UNIX.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by: syzbot+87f770387a9e5dc6b79b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/699ee9fc.050a0220.1cd54b.0009.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260225131547.1085509-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skmsg.c         | 14 +++++++-------
 net/ipv4/tcp.c           |  4 ++--
 net/ipv4/tcp_bpf.c       |  2 +-
 net/ipv4/tcp_input.c     | 14 ++++++++------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/udp.c           |  2 +-
 net/ipv4/udp_bpf.c       |  2 +-
 net/unix/af_unix.c       |  8 ++++----
 8 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2e26174c9919..3261793abe83 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_strp_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
@@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
-	psock->saved_data_ready = NULL;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
+	WRITE_ONCE(psock->saved_data_ready, NULL);
 	strp_stop(&psock->strp);
 }
 
@@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_verdict_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
@@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
 	psock->saved_data_ready = NULL;
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f84d9a45cc9d..8cdc26e8ad68 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1446,7 +1446,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
 	if (binding)
@@ -4181,7 +4181,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	case TCP_NOTSENT_LOWAT:
 		WRITE_ONCE(tp->notsent_lowat, val);
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		break;
 	case TCP_INQ:
 		if (val > 1 || val < 0)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index c449a044895e..813d2e498c93 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 			WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
 			tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 		} else {
-			sk->sk_write_space = psock->saved_write_space;
+			WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 			/* Pairs with lockless read in sk_clone_lock() */
 			sock_replace_proto(sk, psock->sk_proto);
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 41c57efd125c..6404e53382ca 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5425,7 +5425,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM);
 		return;
 	}
@@ -5635,7 +5635,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 void tcp_data_ready(struct sock *sk)
 {
 	if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE))
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5691,7 +5691,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			inet_csk(sk)->icsk_ack.pending |=
 					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
 			inet_csk_schedule_ack(sk);
-			sk->sk_data_ready(sk);
+			READ_ONCE(sk->sk_data_ready)(sk);
 
 			if (skb_queue_len(&sk->sk_receive_queue) && skb->len) {
 				reason = SKB_DROP_REASON_PROTO_MEM;
@@ -6114,7 +6114,9 @@ static void tcp_new_space(struct sock *sk)
 		tp->snd_cwnd_stamp = tcp_jiffies32;
 	}
 
-	INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk);
+	INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space),
+			sk_stream_write_space,
+			sk);
 }
 
 /* Caller made space either from:
@@ -6325,7 +6327,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 				BUG();
 			WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp);
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk);
+				READ_ONCE(sk->sk_data_ready)(sk);
 		}
 	}
 }
@@ -7792,7 +7794,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			sock_put(fastopen_sk);
 			goto drop_and_free;
 		}
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
 	} else {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index d9c5a43bd281..dafb63b923d0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 		reason = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent);
+			READ_ONCE(parent->sk_data_ready)(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6c6b68a66dcd..014fdfdd331b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 		 * using prepare_to_wait_exclusive().
 		 */
 		while (nb) {
-			INDIRECT_CALL_1(sk->sk_data_ready,
+			INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready),
 					sock_def_readable, sk);
 			nb--;
 		}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 91233e37cd97..779a3a03762f 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
 
 	if (restore) {
-		sk->sk_write_space = psock->saved_write_space;
+		WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3756a93dc63a..7eaa5b187fef 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1785,7 +1785,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr_unsized *uad
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	return 0;
 
@@ -2278,7 +2278,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	scm_destroy(&scm);
 	return len;
@@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 
 	return 0;
 out_unlock:
@@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		spin_unlock(&other->sk_receive_queue.lock);
 
 		unix_state_unlock(other);
-		other->sk_data_ready(other);
+		READ_ONCE(other->sk_data_ready)(other);
 		sent += size;
 	}
 

From 93c9475c04acad2457a7e7ea4e3ec40a6e6d94a7 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 25 Feb 2026 16:39:55 +0200
Subject: [PATCH 0529/1303] bridge: Check relevant per-VLAN options in VLAN
 range grouping

The br_vlan_opts_eq_range() function determines if consecutive VLANs can
be grouped together in a range for compact netlink notifications. It
currently checks state, tunnel info, and multicast router configuration,
but misses two categories of per-VLAN options that affect the output:
1. User-visible priv_flags (neigh_suppress, mcast_enabled)
2. Port multicast context (mcast_max_groups, mcast_n_groups)

When VLANs have different settings for these options, they are incorrectly
grouped into ranges, causing netlink notifications to report only one
VLAN's settings for the entire range.

Fix by checking priv_flags equality, but only for flags that affect netlink
output (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED and BR_VLFLAG_MCAST_ENABLED),
and comparing multicast context (mcast_max_groups and mcast_n_groups).

Example showing the bugs before the fix:

$ bridge vlan set vid 10 dev dummy1 neigh_suppress on
$ bridge vlan set vid 11 dev dummy1 neigh_suppress off
$ bridge -d vlan show dev dummy1
  port             vlan-id
  dummy1           10-11
                      ... neigh_suppress on

$ bridge vlan set vid 10 dev dummy1 mcast_max_groups 100
$ bridge vlan set vid 11 dev dummy1 mcast_max_groups 200
$ bridge -d vlan show dev dummy1
  port             vlan-id
  dummy1           10-11
                      ... mcast_max_groups 100

After the fix, VLANs 10 and 11 are shown as separate entries with their
correct individual settings.

Fixes: a1aee20d5db2 ("net: bridge: Add netlink knobs for number / maximum MDB entries")
Fixes: 83f6d600796c ("bridge: vlan: Allow setting VLAN neighbor suppression state")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260225143956.3995415-2-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_private.h      | 10 ++++++++++
 net/bridge/br_vlan_options.c | 26 +++++++++++++++++++++++---
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b9b2981c4841..9b55d38ea9ed 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1344,6 +1344,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1,
 	       true;
 }
 
+static inline bool
+br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1,
+				    const struct net_bridge_mcast_port *pmctx2)
+{
+	return br_multicast_ngroups_get(pmctx1) ==
+	       br_multicast_ngroups_get(pmctx2) &&
+	       br_multicast_ngroups_get_max(pmctx1) ==
+	       br_multicast_ngroups_get_max(pmctx2);
+}
+
 static inline bool
 br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx)
 {
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
index 8fa89b04ee94..5514e1fc8d1f 100644
--- a/net/bridge/br_vlan_options.c
+++ b/net/bridge/br_vlan_options.c
@@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr,
 	u8 range_mc_rtr = br_vlan_multicast_router(range_end);
 	u8 curr_mc_rtr = br_vlan_multicast_router(v_curr);
 
-	return v_curr->state == range_end->state &&
-	       __vlan_tun_can_enter_range(v_curr, range_end) &&
-	       curr_mc_rtr == range_mc_rtr;
+	if (v_curr->state != range_end->state)
+		return false;
+
+	if (!__vlan_tun_can_enter_range(v_curr, range_end))
+		return false;
+
+	if (curr_mc_rtr != range_mc_rtr)
+		return false;
+
+	/* Check user-visible priv_flags that affect output */
+	if ((v_curr->priv_flags ^ range_end->priv_flags) &
+	    (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED))
+		return false;
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	if (!br_vlan_is_master(v_curr) &&
+	    !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) &&
+	    !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx,
+						 &range_end->port_mcast_ctx))
+		return false;
+#endif
+
+	return true;
 }
 
 bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v,

From 13540021be228dcda63d02b2245ce8dad01d8473 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 25 Feb 2026 16:39:56 +0200
Subject: [PATCH 0530/1303] selftests: net: Add bridge VLAN range grouping
 tests

Add a new test file bridge_vlan_dump.sh with four test cases that verify
VLANs with different per-VLAN options are not incorrectly grouped into
ranges in the dump output.

The tests verify the kernel's br_vlan_opts_eq_range() function correctly
prevents VLAN range grouping when neigh_suppress, mcast_max_groups,
mcast_n_groups, or mcast_enabled options differ.

Each test verifies that VLANs with different option values appear as
individual entries rather than ranges, and that VLANs with matching
values are properly grouped together.

Example output:

$ ./bridge_vlan_dump.sh
TEST: VLAN range grouping with neigh_suppress                       [ OK ]
TEST: VLAN range grouping with mcast_max_groups                     [ OK ]
TEST: VLAN range grouping with mcast_n_groups                       [ OK ]
TEST: VLAN range grouping with mcast_enabled                        [ OK ]

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20260225143956.3995415-3-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |   1 +
 .../testing/selftests/net/bridge_vlan_dump.sh | 204 ++++++++++++++++++
 2 files changed, 205 insertions(+)
 create mode 100755 tools/testing/selftests/net/bridge_vlan_dump.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index afdea6d95bde..605c54c0e8a3 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -15,6 +15,7 @@ TEST_PROGS := \
 	big_tcp.sh \
 	bind_bhash.sh \
 	bpf_offload.py \
+	bridge_vlan_dump.sh \
 	broadcast_ether_dst.sh \
 	broadcast_pmtu.sh \
 	busy_poll_test.sh \
diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh
new file mode 100755
index 000000000000..ad66731d2a6f
--- /dev/null
+++ b/tools/testing/selftests/net/bridge_vlan_dump.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in
+# the dump if they have the same per-VLAN options. These tests verify that
+# VLANs with different per-VLAN option values are not grouped together.
+
+# shellcheck disable=SC1091,SC2034,SC2154,SC2317
+source lib.sh
+
+ALL_TESTS="
+	vlan_range_neigh_suppress
+	vlan_range_mcast_max_groups
+	vlan_range_mcast_n_groups
+	vlan_range_mcast_enabled
+"
+
+setup_prepare()
+{
+	setup_ns NS
+	defer cleanup_all_ns
+
+	ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \
+		vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1
+	ip -n "$NS" link set dev br0 up
+
+	ip -n "$NS" link add name dummy0 type dummy
+	ip -n "$NS" link set dev dummy0 master br0
+	ip -n "$NS" link set dev dummy0 up
+}
+
+vlan_range_neigh_suppress()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different neigh_suppress values and verify no range grouping
+	bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on
+	check_err $? "Failed to set neigh_suppress for VLAN 10"
+
+	bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off
+	check_err $? "Failed to set neigh_suppress for VLAN 11"
+
+	# Verify VLANs are not shown as a range, but individual entries exist
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different neigh_suppress incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same neigh_suppress value and verify range grouping
+	bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on
+	check_err $? "Failed to set neigh_suppress for VLAN 11"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same neigh_suppress not grouped"
+
+	log_test "VLAN range grouping with neigh_suppress"
+}
+
+vlan_range_mcast_max_groups()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different mcast_max_groups values and verify no range grouping
+	bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100
+	check_err $? "Failed to set mcast_max_groups for VLAN 10"
+
+	bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200
+	check_err $? "Failed to set mcast_max_groups for VLAN 11"
+
+	# Verify VLANs are not shown as a range, but individual entries exist
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_max_groups incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same mcast_max_groups value and verify range grouping
+	bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100
+	check_err $? "Failed to set mcast_max_groups for VLAN 11"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_max_groups not grouped"
+
+	log_test "VLAN range grouping with mcast_max_groups"
+}
+
+vlan_range_mcast_n_groups()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Add different numbers of multicast groups to each VLAN
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10
+	check_err $? "Failed to add mdb entry to VLAN 10"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10
+
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10
+	check_err $? "Failed to add second mdb entry to VLAN 10"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10
+
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11
+	check_err $? "Failed to add mdb entry to VLAN 11"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11
+
+	# Verify VLANs are not shown as a range due to different mcast_n_groups
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_n_groups incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Add another group to VLAN 11 to match VLAN 10's count
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11
+	check_err $? "Failed to add second mdb entry to VLAN 11"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_n_groups not grouped"
+
+	log_test "VLAN range grouping with mcast_n_groups"
+}
+
+vlan_range_mcast_enabled()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev br0 self
+	defer bridge -n "$NS" vlan del vid 10 dev br0 self
+
+	bridge -n "$NS" vlan add vid 11 dev br0 self
+	defer bridge -n "$NS" vlan del vid 11 dev br0 self
+
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different mcast_snooping for bridge VLANs
+	# Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs
+	bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1
+	bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0
+
+	# Verify port VLANs are not grouped due to different mcast_enabled
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_enabled incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same mcast_snooping and verify range grouping
+	bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_enabled not grouped"
+
+	log_test "VLAN range grouping with mcast_enabled"
+}
+
+# Verify the newest tested option is supported
+if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then
+	echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support"
+	exit "$ksft_skip"
+fi
+
+trap defer_scopes_cleanup EXIT
+setup_prepare
+tests_run
+
+exit "$EXIT_STATUS"

From be11a537224d72b906db6b98510619770298c8a4 Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Tue, 24 Feb 2026 23:43:59 +0530
Subject: [PATCH 0531/1303] net: ethernet: ti: am65-cpsw-nuss/cpsw-ale: Fix
 multicast entry handling in ALE table

In the current implementation, flushing multicast entries in MAC mode
incorrectly deletes entries for all ports instead of only the target port,
disrupting multicast traffic on other ports. The cause is adding multicast
entries by setting only host port bit, and not setting the MAC port bits.

Fix this by setting the MAC port's bit in the port mask while adding the
multicast entry. Also fix the flush logic to preserve the host port bit
during removal of MAC port and free ALE entries when mask contains only
host port.

Fixes: 5c50a856d550 ("drivers: net: ethernet: cpsw: add multicast address to ALE table")
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224181359.2055322-1-c-vankar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 drivers/net/ethernet/ti/cpsw_ale.c       | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 5924db6be3fe..967918050433 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(common->ale,
 			      ndev->flags & IFF_ALLMULTI, port->port_id);
 
-	port_mask = ALE_PORT_HOST;
+	port_mask = BIT(port->port_id) | ALE_PORT_HOST;
 	/* Clear all mcast from ALE */
 	cpsw_ale_flush_multicast(common->ale, port_mask, -1);
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index bb969dd435b4..be7b69319221 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -450,14 +450,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 				      ale->port_mask_bits);
 	if ((mask & port_mask) == 0)
 		return; /* ports dont intersect, not interested */
-	mask &= ~port_mask;
+	mask &= (~port_mask | ALE_PORT_HOST);
 
-	/* free if only remaining port is host port */
-	if (mask)
+	if (mask == 0x0 || mask == ALE_PORT_HOST)
+		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+	else
 		cpsw_ale_set_port_mask(ale_entry, mask,
 				       ale->port_mask_bits);
-	else
-		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
 int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)

From 4fc87c240b8f30e22b7ebaae29d57105589e1c0b Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Tue, 10 Feb 2026 23:28:20 +0000
Subject: [PATCH 0532/1303] rust_binder: fix oneway spam detection

The spam detection logic in TreeRange was executed before the current
request was inserted into the tree. So the new request was not being
factored in the spam calculation. Fix this by moving the logic after
the new range has been inserted.

Also, the detection logic for ArrayRange was missing altogether which
meant large spamming transactions could get away without being detected.
Fix this by implementing an equivalent low_oneway_space() in ArrayRange.

Note that I looked into centralizing this logic in RangeAllocator but
iterating through 'state' and 'size' got a bit too complicated (for me)
and I abandoned this effort.

Cc: stable <stable@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://patch.msgid.link/20260210232949.3770644-1-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/range_alloc/array.rs | 35 +++++++++++++++++++--
 drivers/android/binder/range_alloc/mod.rs   |  4 +--
 drivers/android/binder/range_alloc/tree.rs  | 18 +++++------
 3 files changed, 44 insertions(+), 13 deletions(-)

diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs
index 07e1dec2ce63..ada1d1b4302e 100644
--- a/drivers/android/binder/range_alloc/array.rs
+++ b/drivers/android/binder/range_alloc/array.rs
@@ -118,7 +118,7 @@ pub(crate) fn reserve_new(
         size: usize,
         is_oneway: bool,
         pid: Pid,
-    ) -> Result<usize> {
+    ) -> Result<(usize, bool)> {
         // Compute new value of free_oneway_space, which is set only on success.
         let new_oneway_space = if is_oneway {
             match self.free_oneway_space.checked_sub(size) {
@@ -146,7 +146,38 @@ pub(crate) fn reserve_new(
             .ok()
             .unwrap();
 
-        Ok(insert_at_offset)
+        // Start detecting spammers once we have less than 20%
+        // of async space left (which is less than 10% of total
+        // buffer size).
+        //
+        // (This will short-circuit, so `low_oneway_space` is
+        // only called when necessary.)
+        let oneway_spam_detected =
+            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
+
+        Ok((insert_at_offset, oneway_spam_detected))
+    }
+
+    /// Find the amount and size of buffers allocated by the current caller.
+    ///
+    /// The idea is that once we cross the threshold, whoever is responsible
+    /// for the low async space is likely to try to send another async transaction,
+    /// and at some point we'll catch them in the act.  This is more efficient
+    /// than keeping a map per pid.
+    fn low_oneway_space(&self, calling_pid: Pid) -> bool {
+        let mut total_alloc_size = 0;
+        let mut num_buffers = 0;
+
+        // Warn if this pid has more than 50 transactions, or more than 50% of
+        // async space (which is 25% of total buffer size). Oneway spam is only
+        // detected when the threshold is exceeded.
+        for range in &self.ranges {
+            if range.state.is_oneway() && range.state.pid() == calling_pid {
+                total_alloc_size += range.size;
+                num_buffers += 1;
+            }
+        }
+        num_buffers > 50 || total_alloc_size > self.size / 4
     }
 
     pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> {
diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs
index 2301e2bc1a1f..1f4734468ff1 100644
--- a/drivers/android/binder/range_alloc/mod.rs
+++ b/drivers/android/binder/range_alloc/mod.rs
@@ -188,11 +188,11 @@ pub(crate) fn reserve_new(&mut self, mut args: ReserveNewArgs<T>) -> Result<Rese
                 self.reserve_new(args)
             }
             Impl::Array(array) => {
-                let offset =
+                let (offset, oneway_spam_detected) =
                     array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?;
                 Ok(ReserveNew::Success(ReserveNewSuccess {
                     offset,
-                    oneway_spam_detected: false,
+                    oneway_spam_detected,
                     _empty_array_alloc: args.empty_array_alloc,
                     _new_tree_alloc: args.new_tree_alloc,
                     _tree_alloc: args.tree_alloc,
diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs
index 838fdd2b47ea..48796fcdb362 100644
--- a/drivers/android/binder/range_alloc/tree.rs
+++ b/drivers/android/binder/range_alloc/tree.rs
@@ -164,15 +164,6 @@ pub(crate) fn reserve_new(
             self.free_oneway_space
         };
 
-        // Start detecting spammers once we have less than 20%
-        // of async space left (which is less than 10% of total
-        // buffer size).
-        //
-        // (This will short-circut, so `low_oneway_space` is
-        // only called when necessary.)
-        let oneway_spam_detected =
-            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
-
         let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) {
             None => {
                 pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size);
@@ -203,6 +194,15 @@ pub(crate) fn reserve_new(
             self.free_tree.insert(free_tree_node);
         }
 
+        // Start detecting spammers once we have less than 20%
+        // of async space left (which is less than 10% of total
+        // buffer size).
+        //
+        // (This will short-circuit, so `low_oneway_space` is
+        // only called when necessary.)
+        let oneway_spam_detected =
+            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
+
         Ok((found_off, oneway_spam_detected))
     }
 

From 8ef2c15aeae07647f530d30f6daaf79eb801bcd1 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 11:53:26 +0000
Subject: [PATCH 0533/1303] rust_binder: check ownership before using vma

When installing missing pages (or zapping them), Rust Binder will look
up the vma in the mm by address, and then call vm_insert_page (or
zap_page_range_single). However, if the vma is closed and replaced with
a different vma at the same address, this can lead to Rust Binder
installing pages into the wrong vma.

By installing the page into a writable vma, it becomes possible to write
to your own binder pages, which are normally read-only. Although you're
not supposed to be able to write to those pages, the intent behind the
design of Rust Binder is that even if you get that ability, it should not
lead to anything bad. Unfortunately, due to another bug, that is not the
case.

To fix this, store a pointer in vm_private_data and check that the vma
returned by vma_lookup() has the right vm_ops and vm_private_data before
trying to use the vma. This should ensure that Rust Binder will refuse
to interact with any other VMA. The plan is to introduce more vma
abstractions to avoid this unsafe access to vm_ops and vm_private_data,
but for now let's start with the simplest possible fix.

C Binder performs the same check in a slightly different way: it
provides a vm_ops->close that sets a boolean to true, then checks that
boolean after calling vma_lookup(), but this is more fragile
than the solution in this patch. (We probably still want to do both, but
the vm_ops->close callback will be added later as part of the follow-up
vma API changes.)

It's still possible to remap the vma so that pages appear in the right
vma, but at the wrong offset, but this is a separate issue and will be
fixed when Rust Binder gets a vm_ops->close callback.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-check-v2-1-60f9d695a990@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/page_range.rs | 83 +++++++++++++++++++++-------
 1 file changed, 63 insertions(+), 20 deletions(-)

diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
index fdd97112ef5c..67aae783e8b8 100644
--- a/drivers/android/binder/page_range.rs
+++ b/drivers/android/binder/page_range.rs
@@ -142,6 +142,30 @@ pub(crate) struct ShrinkablePageRange {
     _pin: PhantomPinned,
 }
 
+// We do not define any ops. For now, used only to check identity of vmas.
+static BINDER_VM_OPS: bindings::vm_operations_struct = pin_init::zeroed();
+
+// To ensure that we do not accidentally install pages into or zap pages from the wrong vma, we
+// check its vm_ops and private data before using it.
+fn check_vma(vma: &virt::VmaRef, owner: *const ShrinkablePageRange) -> Option<&virt::VmaMixedMap> {
+    // SAFETY: Just reading the vm_ops pointer of any active vma is safe.
+    let vm_ops = unsafe { (*vma.as_ptr()).vm_ops };
+    if !ptr::eq(vm_ops, &BINDER_VM_OPS) {
+        return None;
+    }
+
+    // SAFETY: Reading the vm_private_data pointer of a binder-owned vma is safe.
+    let vm_private_data = unsafe { (*vma.as_ptr()).vm_private_data };
+    // The ShrinkablePageRange is only dropped when the Process is dropped, which only happens once
+    // the file's ->release handler is invoked, which means the ShrinkablePageRange outlives any
+    // VMA associated with it, so there can't be any false positives due to pointer reuse here.
+    if !ptr::eq(vm_private_data, owner.cast()) {
+        return None;
+    }
+
+    vma.as_mixedmap_vma()
+}
+
 struct Inner {
     /// Array of pages.
     ///
@@ -308,6 +332,18 @@ pub(crate) fn register_with_vma(&self, vma: &virt::VmaNew) -> Result<usize> {
         inner.size = num_pages;
         inner.vma_addr = vma.start();
 
+        // This pointer is only used for comparison - it's not dereferenced.
+        //
+        // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on
+        // `vm_private_data`.
+        unsafe {
+            (*vma.as_ptr()).vm_private_data = ptr::from_ref(self).cast_mut().cast::<c_void>()
+        };
+
+        // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on
+        // `vm_ops`.
+        unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS };
+
         Ok(num_pages)
     }
 
@@ -399,22 +435,24 @@ unsafe fn use_page_slow(&self, i: usize) -> Result<()> {
         //
         // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a
         // workqueue.
-        MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
-            .mmap_read_lock()
-            .vma_lookup(vma_addr)
-            .ok_or(ESRCH)?
-            .as_mixedmap_vma()
-            .ok_or(ESRCH)?
-            .vm_insert_page(user_page_addr, &new_page)
-            .inspect_err(|err| {
-                pr_warn!(
-                    "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
-                    user_page_addr,
-                    vma_addr,
-                    i,
-                    err
-                )
-            })?;
+        check_vma(
+            MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
+                .mmap_read_lock()
+                .vma_lookup(vma_addr)
+                .ok_or(ESRCH)?,
+            self,
+        )
+        .ok_or(ESRCH)?
+        .vm_insert_page(user_page_addr, &new_page)
+        .inspect_err(|err| {
+            pr_warn!(
+                "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
+                user_page_addr,
+                vma_addr,
+                i,
+                err
+            )
+        })?;
 
         let inner = self.lock.lock();
 
@@ -667,12 +705,15 @@ fn drop(self: Pin<&mut Self>) {
     let mmap_read;
     let mm_mutex;
     let vma_addr;
+    let range_ptr;
 
     {
         // CAST: The `list_head` field is first in `PageInfo`.
         let info = item as *mut PageInfo;
         // SAFETY: The `range` field of `PageInfo` is immutable.
-        let range = unsafe { &*((*info).range) };
+        range_ptr = unsafe { (*info).range };
+        // SAFETY: The `range` outlives its `PageInfo` values.
+        let range = unsafe { &*range_ptr };
 
         mm = match range.mm.mmget_not_zero() {
             Some(mm) => MmWithUser::into_mmput_async(mm),
@@ -717,9 +758,11 @@ fn drop(self: Pin<&mut Self>) {
     // SAFETY: The lru lock is locked when this method is called.
     unsafe { bindings::spin_unlock(&raw mut (*lru).lock) };
 
-    if let Some(vma) = mmap_read.vma_lookup(vma_addr) {
-        let user_page_addr = vma_addr + (page_index << PAGE_SHIFT);
-        vma.zap_page_range_single(user_page_addr, PAGE_SIZE);
+    if let Some(unchecked_vma) = mmap_read.vma_lookup(vma_addr) {
+        if let Some(vma) = check_vma(unchecked_vma, range_ptr) {
+            let user_page_addr = vma_addr + (page_index << PAGE_SHIFT);
+            vma.zap_page_range_single(user_page_addr, PAGE_SIZE);
+        }
     }
 
     drop(mmap_read);

From 4cb9e13fec0de7c942f5f927469beb8e48ddd20f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 11:53:27 +0000
Subject: [PATCH 0534/1303] rust_binder: avoid reading the written value in
 offsets array

When sending a transaction, its offsets array is first copied into the
target proc's vma, and then the values are read back from there. This is
normally fine because the vma is a read-only mapping, so the target
process cannot change the value under us.

However, if the target process somehow gains the ability to write to its
own vma, it could change the offset before it's read back, causing the
kernel to misinterpret what the sender meant. If the sender happens to
send a payload with a specific shape, this could in the worst case lead
to the receiver being able to privilege escalate into the sender.

The intent is that gaining the ability to change the read-only vma of
your own process should not be exploitable, so remove this TOCTOU read
even though it's unexploitable without another Binder bug.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-check-v2-2-60f9d695a990@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/thread.rs | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs
index 0b62d24b2118..c004214b1662 100644
--- a/drivers/android/binder/thread.rs
+++ b/drivers/android/binder/thread.rs
@@ -1015,12 +1015,9 @@ pub(crate) fn copy_transaction_data(
 
         // Copy offsets if there are any.
         if offsets_size > 0 {
-            {
-                let mut reader =
-                    UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size)
-                        .reader();
-                alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?;
-            }
+            let mut offsets_reader =
+                UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size)
+                    .reader();
 
             let offsets_start = aligned_data_size;
             let offsets_end = aligned_data_size + offsets_size;
@@ -1041,11 +1038,9 @@ pub(crate) fn copy_transaction_data(
                 .step_by(size_of::<u64>())
                 .enumerate()
             {
-                let offset: usize = view
-                    .alloc
-                    .read::<u64>(index_offset)?
-                    .try_into()
-                    .map_err(|_| EINVAL)?;
+                let offset = offsets_reader.read::<u64>()?;
+                view.alloc.write(index_offset, &offset)?;
+                let offset: usize = offset.try_into().map_err(|_| EINVAL)?;
 
                 if offset < end_of_previous_object || !is_aligned(offset, size_of::<u32>()) {
                     pr_warn!("Got transaction with invalid offset.");

From 2e303f0febb65a434040774b793ba8356698802b Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Tue, 24 Feb 2026 18:16:39 +0000
Subject: [PATCH 0535/1303] rust_binder: call set_notification_done() without
 proc lock

Consider the following sequence of events on a death listener:
1. The remote process dies and sends a BR_DEAD_BINDER message.
2. The local process invokes the BC_CLEAR_DEATH_NOTIFICATION command.
3. The local process then invokes the BC_DEAD_BINDER_DONE.
Then, the kernel will reply to the BC_DEAD_BINDER_DONE command with a
BR_CLEAR_DEATH_NOTIFICATION_DONE reply using push_work_if_looper().

However, this can result in a deadlock if the current thread is not a
looper. This is because dead_binder_done() still holds the proc lock
during set_notification_done(), which called push_work_if_looper().
Normally, push_work_if_looper() takes the thread lock, which is fine to
take under the proc lock. But if the current thread is not a looper,
then it falls back to delivering the reply to the process work queue,
which involves taking the proc lock. Since the proc lock is already
held, this is a deadlock.

Fix this by releasing the proc lock during set_notification_done(). It
was not intentional that it was held during that function to begin with.

I don't think this ever happens in Android because BC_DEAD_BINDER_DONE
is only invoked in response to BR_DEAD_BINDER messages, and the kernel
always delivers BR_DEAD_BINDER to a looper. So there's no scenario where
Android userspace will call BC_DEAD_BINDER_DONE on a non-looper thread.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com
Tested-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://patch.msgid.link/20260224-binder-dead-binder-done-proc-lock-v1-1-bbe1b8a6e74a@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/process.rs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs
index 41de5593197c..f06498129aa9 100644
--- a/drivers/android/binder/process.rs
+++ b/drivers/android/binder/process.rs
@@ -1295,7 +1295,8 @@ pub(crate) fn clear_death(&self, reader: &mut UserSliceReader, thread: &Thread)
     }
 
     pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) {
-        if let Some(death) = self.inner.lock().pull_delivered_death(cookie) {
+        let death = self.inner.lock().pull_delivered_death(cookie);
+        if let Some(death) = death {
             death.set_notification_done(thread);
         }
     }

From a0b9b0f1433c845bda708753db32befef78e0f1f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 15:13:23 +0000
Subject: [PATCH 0536/1303] rust_binder: use lock_vma_under_rcu() in
 use_page_slow()

There's no reason to lock the whole mm when we are doing operations on
the vma if we can help it, so to reduce contention, use the
lock_vma_under_rcu() abstraction.

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-rcu-v1-1-8bd45b2b1183@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/page_range.rs | 37 ++++++++++++++--------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
index 67aae783e8b8..9dfc154e5dd4 100644
--- a/drivers/android/binder/page_range.rs
+++ b/drivers/android/binder/page_range.rs
@@ -435,24 +435,25 @@ unsafe fn use_page_slow(&self, i: usize) -> Result<()> {
         //
         // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a
         // workqueue.
-        check_vma(
-            MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
-                .mmap_read_lock()
-                .vma_lookup(vma_addr)
-                .ok_or(ESRCH)?,
-            self,
-        )
-        .ok_or(ESRCH)?
-        .vm_insert_page(user_page_addr, &new_page)
-        .inspect_err(|err| {
-            pr_warn!(
-                "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
-                user_page_addr,
-                vma_addr,
-                i,
-                err
-            )
-        })?;
+        let mm = MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?);
+        {
+            let vma_read;
+            let mmap_read;
+            let vma = if let Some(ret) = mm.lock_vma_under_rcu(vma_addr) {
+                vma_read = ret;
+                check_vma(&vma_read, self)
+            } else {
+                mmap_read = mm.mmap_read_lock();
+                mmap_read
+                    .vma_lookup(vma_addr)
+                    .and_then(|vma| check_vma(vma, self))
+            };
+
+            match vma {
+                Some(vma) => vma.vm_insert_page(user_page_addr, &new_page)?,
+                None => return Err(ESRCH),
+            }
+        }
 
         let inner = self.lock.lock();
 

From 24d87712727a5017ad142d63940589a36cd25647 Mon Sep 17 00:00:00 2001
From: Ariel Silver <arielsilver77@gmail.com>
Date: Sat, 21 Feb 2026 15:26:00 +0100
Subject: [PATCH 0537/1303] media: dvb-net: fix OOB access in ULE extension
 header tables

The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables
in handle_one_ule_extension() are declared with 255 elements (valid
indices 0-254), but the index htype is derived from network-controlled
data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When
htype equals 255, an out-of-bounds read occurs on the function pointer
table, and the OOB value may be called as a function pointer.

Add a bounds check on htype against the array size before either table
is accessed. Out-of-range values now cause the SNDU to be discarded.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Ariel Silver <arielsilver77@gmail.com>
Signed-off-by: Ariel Silver <arielsilver77@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/dvb-core/dvb_net.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index 8bb8dd34c223..a2159b2bc176 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -228,6 +228,9 @@ static int handle_one_ule_extension( struct dvb_net_priv *p )
 	unsigned char hlen = (p->ule_sndu_type & 0x0700) >> 8;
 	unsigned char htype = p->ule_sndu_type & 0x00FF;
 
+	if (htype >= ARRAY_SIZE(ule_mandatory_ext_handlers))
+		return -1;
+
 	/* Discriminate mandatory and optional extension headers. */
 	if (hlen == 0) {
 		/* Mandatory extension header */

From 3385ea97c14d271dcb0c6e6fcf16972f819eecd8 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:50 +0100
Subject: [PATCH 0538/1303] platform/x86: oxpec: Add support for OneXPlayer
 APEX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OneXPlayer Apex is a new Strix Halo handheld. It uses the same registers
as the OneXPlayer Fly devices. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-2-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 144a454103b9..59d6f9d9a905 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -11,7 +11,7 @@
  *
  * Copyright (C) 2022 Joaquín I. Aramendía <samsagax@gmail.com>
  * Copyright (C) 2024 Derek J. Clark <derekjohn.clark@gmail.com>
- * Copyright (C) 2025 Antheas Kapenekakis <lkml@antheas.dev>
+ * Copyright (C) 2025-2026 Antheas Kapenekakis <lkml@antheas.dev>
  */
 
 #include <linux/acpi.h>
@@ -142,6 +142,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_2,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER APEX"),
+		},
+		.driver_data = (void *)oxp_fly,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),

From 4049c46edb5d44c0de045f6f504371705dd603dd Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:51 +0100
Subject: [PATCH 0539/1303] platform/x86: oxpec: Add support for OneXPlayer X1z
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

X1z is a variant of OneXPlayer X1 A with 8840U. It seems that only one
user has this one. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-3-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 59d6f9d9a905..623d9a452c46 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -219,6 +219,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_mini_amd_pro,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1z"),
+		},
+		.driver_data = (void *)oxp_x1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),

From 2a3b4a8c10a64a62c4243007139d253dc1324dfd Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:52 +0100
Subject: [PATCH 0540/1303] platform/x86: oxpec: Add support for OneXPlayer X1
 Air
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

X1 Air is an X1 variant with a newer Intel chipset. It uses the same
registers as the X1. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-4-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 623d9a452c46..d6ef8dbf568e 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -240,6 +240,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_x1,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1Air"),
+		},
+		.driver_data = (void *)oxp_x1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),

From cd0883055b04586770dab43c64159348bf480a3e Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:53 +0100
Subject: [PATCH 0541/1303] platform/x86: oxpec: Add support for Aokzoe A2 Pro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Aokzoe A2 Pro is an older device that the oxpec driver is missing the
quirk for. It has the same behavior as the AOKZOE A1 devices. Add a
quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-5-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index d6ef8dbf568e..6d4a53a2ed60 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -114,6 +114,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)aok_zoe_a1,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "AOKZOE A2 Pro"),
+		},
+		.driver_data = (void *)aok_zoe_a1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"),

From 916727cfdb72cd01fef3fa6746e648f8cb70e713 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 25 Feb 2026 15:06:46 -0600
Subject: [PATCH 0542/1303] platform/x86: hp-bioscfg: Support allocations of
 larger data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some systems have much larger amounts of enumeration attributes
than have been previously encountered. This can lead to page allocation
failures when using kcalloc().  Switch over to using kvcalloc() to
allow larger allocations.

Fixes: 6b2770bfd6f92 ("platform/x86: hp-bioscfg: enum-attributes")
Cc: stable@vger.kernel.org
Reported-by: Paul Kerry <p.kerry@sheffield.ac.uk>
Tested-by: Paul Kerry <p.kerry@sheffield.ac.uk>
Closes: https://bugs.debian.org/1127612
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patch.msgid.link/20260225210646.59381-1-mario.limonciello@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
index 470b9f44ed7a..af4d1920d488 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
@@ -94,8 +94,11 @@ int hp_alloc_enumeration_data(void)
 	bioscfg_drv.enumeration_instances_count =
 		hp_get_instance_count(HP_WMI_BIOS_ENUMERATION_GUID);
 
-	bioscfg_drv.enumeration_data = kzalloc_objs(*bioscfg_drv.enumeration_data,
-						    bioscfg_drv.enumeration_instances_count);
+	if (!bioscfg_drv.enumeration_instances_count)
+		return -EINVAL;
+	bioscfg_drv.enumeration_data = kvcalloc(bioscfg_drv.enumeration_instances_count,
+						sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL);
+
 	if (!bioscfg_drv.enumeration_data) {
 		bioscfg_drv.enumeration_instances_count = 0;
 		return -ENOMEM;
@@ -444,6 +447,6 @@ void hp_exit_enumeration_attributes(void)
 	}
 	bioscfg_drv.enumeration_instances_count = 0;
 
-	kfree(bioscfg_drv.enumeration_data);
+	kvfree(bioscfg_drv.enumeration_data);
 	bioscfg_drv.enumeration_data = NULL;
 }

From 622cc8d078e5d7586f0e40dd7aea515a946da48c Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Thu, 26 Feb 2026 15:19:43 +0100
Subject: [PATCH 0543/1303] platform/x86: asus-armoury: add support for GX650RX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model GX650RX.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260226141944.352923-2-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 32 +++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 001c011fdd56..f9d9136aec7b 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1457,6 +1457,38 @@ static const struct dmi_system_id power_limits[] = {
 			},
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GX650RX"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_def = 70,
+				.ppt_pl1_spl_max = 90,
+				.ppt_pl2_sppt_min = 28,
+				.ppt_pl2_sppt_def = 70,
+				.ppt_pl2_sppt_max = 100,
+				.ppt_pl3_fppt_min = 28,
+				.ppt_pl3_fppt_def = 110,
+				.ppt_pl3_fppt_max = 125,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 25,
+				.nv_temp_target_min = 76,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_max = 50,
+				.ppt_pl2_sppt_min = 28,
+				.ppt_pl2_sppt_max = 50,
+				.ppt_pl3_fppt_min = 28,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 76,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G513I"),

From c55b84fa567ed33bc651675bcaf8d53bd12d910a Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Thu, 26 Feb 2026 15:19:44 +0100
Subject: [PATCH 0544/1303] platform/x86: asus-armoury: add support for FA401UM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model FA401UM.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260226141944.352923-3-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index f9d9136aec7b..208f6fe16168 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -346,6 +346,35 @@ struct power_data {
  * _def is not required and will be assumed to be default == max if missing.
  */
 static const struct dmi_system_id power_limits[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "FA401UM"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 35,
+				.ppt_pl2_sppt_max = 80,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 80,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 15,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 25,
+				.ppt_pl1_spl_max = 35,
+				.ppt_pl2_sppt_min = 31,
+				.ppt_pl2_sppt_max = 44,
+				.ppt_pl3_fppt_min = 45,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "FA401UV"),

From 3350c2b3f2b8a3b985a020a4ef4f2f050a4b6a1d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 25 Feb 2026 21:12:29 -0800
Subject: [PATCH 0545/1303] platform_data/mlxreg: mlxreg.h: fix all kernel-doc
 warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the correct kernel-doc format & notation to eliminate
kernel-doc warnings:

Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE1' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE2' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE3' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:37 bad line:
 PHYs ready / unready state;
Warning: include/linux/platform_data/mlxreg.h:153 struct member 'np'
 not described in 'mlxreg_core_data'
Warning: include/linux/platform_data/mlxreg.h:153 struct member 'hpdev'
 not described in 'mlxreg_core_data'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260226051232.549537-1-rdunlap@infradead.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 include/linux/platform_data/mlxreg.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index f6cca7a035c7..50b6be57da66 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -13,10 +13,10 @@
 /**
  * enum mlxreg_wdt_type - type of HW watchdog
  *
- * TYPE1 HW watchdog implementation exist in old systems.
- * All new systems have TYPE2 HW watchdog.
- * TYPE3 HW watchdog can exist on all systems with new CPLD.
- * TYPE3 is selected by WD capability bit.
+ * @MLX_WDT_TYPE1: HW watchdog implementation in old systems.
+ * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog.
+ * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD.
+ *   TYPE3 is selected by WD capability bit.
  */
 enum mlxreg_wdt_type {
 	MLX_WDT_TYPE1,
@@ -35,7 +35,7 @@ enum mlxreg_wdt_type {
  * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming
  *			      after hardware-firmware synchronization handshake;
  * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card
-			     PHYs ready / unready state;
+ *			     PHYs ready / unready state;
  * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware
  *			      availability / unavailability for the ports on line card;
  * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive
@@ -123,8 +123,8 @@ struct mlxreg_hotplug_device {
  * @reg_pwr: attribute power register;
  * @reg_ena: attribute enable register;
  * @mode: access mode;
- * @np - pointer to node platform associated with attribute;
- * @hpdev - hotplug device data;
+ * @np: pointer to node platform associated with attribute;
+ * @hpdev: hotplug device data;
  * @notifier: pointer to event notifier block;
  * @health_cntr: dynamic device health indication counter;
  * @attached: true if device has been attached after good health indication;

From 377f8e788945d45b012ed9cfc35ca56c02e86cd8 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Mon, 16 Feb 2026 18:55:38 +0100
Subject: [PATCH 0546/1303] HID: asus: add xg mobile 2023 external hardware
 support

XG mobile stations have the 0x5a endpoint and has to be initialized:
add them to hid-asus.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-asus.c | 3 +++
 drivers/hid/hid-ids.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 7a08e964b9cc..687b785e2d0c 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1497,6 +1497,9 @@ static const struct hid_device_id asus_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+	    USB_DEVICE_ID_ASUSTEK_XGM_2023),
+	},
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
 	  QUIRK_ROG_CLAYMORE_II_KEYBOARD },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 3e299a30dcde..4ab7640b119a 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -229,6 +229,7 @@
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X		0x1b4c
 #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD	0x196b
 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD	0x1869
+#define USB_DEVICE_ID_ASUSTEK_XGM_2023	0x1a9a
 
 #define USB_VENDOR_ID_ATEN		0x0557
 #define USB_DEVICE_ID_ATEN_UC100KM	0x2004

From 6e3f4514e3b432871ac81717d24f56b441857f77 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Fri, 27 Feb 2026 12:49:01 +0000
Subject: [PATCH 0547/1303] drm/ttm: Fix ttm_pool_beneficial_order() return
 type
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a nasty copy and paste bug, where the incorrect boolean return type of
the ttm_pool_beneficial_order() helper had a consequence of avoiding
direct reclaim too eagerly for drivers which use this feature (currently
amdgpu).

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: 7e9c548d3709 ("drm/ttm: Allow drivers to specify maximum beneficial TTM pool size")
Cc: Christian König <christian.koenig@amd.com>
Cc: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.19+
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20260227124901.3177-1-tvrtko.ursulin@igalia.com
---
 drivers/gpu/drm/ttm/ttm_pool_internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/ttm/ttm_pool_internal.h b/drivers/gpu/drm/ttm/ttm_pool_internal.h
index 82c4b7e56a99..24c179fd69d1 100644
--- a/drivers/gpu/drm/ttm/ttm_pool_internal.h
+++ b/drivers/gpu/drm/ttm/ttm_pool_internal.h
@@ -17,7 +17,7 @@ static inline bool ttm_pool_uses_dma32(struct ttm_pool *pool)
 	return pool->alloc_flags & TTM_ALLOCATION_POOL_USE_DMA32;
 }
 
-static inline bool ttm_pool_beneficial_order(struct ttm_pool *pool)
+static inline unsigned int ttm_pool_beneficial_order(struct ttm_pool *pool)
 {
 	return pool->alloc_flags & 0xff;
 }

From e9217ca77dc35b4978db0fe901685ddb3f1e223a Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 23 Feb 2026 16:58:09 +0900
Subject: [PATCH 0548/1303] mm/slab: initialize slab->stride early to avoid
 memory ordering issues

When alloc_slab_obj_exts() is called later (instead of during slab
allocation and initialization), slab->stride and slab->obj_exts are
updated after the slab is already accessible by multiple CPUs.

The current implementation does not enforce memory ordering between
slab->stride and slab->obj_exts. For correctness, slab->stride must be
visible before slab->obj_exts. Otherwise, concurrent readers may observe
slab->obj_exts as non-zero while stride is still stale.

With stale slab->stride, slab_obj_ext() could return the wrong obj_ext.
This could cause two problems:

  - obj_cgroup_put() is called on the wrong objcg, leading to
    a use-after-free due to incorrect reference counting [1] by
    decrementing the reference count more than it was incremented.

  - refill_obj_stock() is called on the wrong objcg, leading to
    a page_counter overflow [2] by uncharging more memory than charged.

Fix this by unconditionally initializing slab->stride in
alloc_slab_obj_exts_early(), before the need_slab_obj_exts() check.
In the case of SLAB_OBJ_EXT_IN_OBJ, it is overridden in the function.

This ensures updates to slab->stride become visible before the slab
can be accessed by other CPUs via the per-node partial slab list
(protected by spinlock with acquire/release semantics).

Thanks to Shakeel Butt for pointing out this issue [3].

[vbabka@kernel.org: the bug reports [1] and [2] are not yet fully fixed,
 with investigation ongoing, but it is nevertheless a step in the right
 direction to only set stride once after allocating the slab and not
 change it later ]

Fixes: 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Link: https://lore.kernel.org/lkml/ca241daa-e7e7-4604-a48d-de91ec9184a5@linux.ibm.com [1]
Link: https://lore.kernel.org/all/ddff7c7d-c0c3-4780-808f-9a83268bbf0c@linux.ibm.com [2]
Link: https://lore.kernel.org/linux-mm/aZu9G9mVIVzSm6Ft@hyeyoo [3]
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 52f021711744..0c906fefc31b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2196,7 +2196,6 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 retry:
 	old_exts = READ_ONCE(slab->obj_exts);
 	handle_failed_objexts_alloc(old_exts, vec, objects);
-	slab_set_stride(slab, sizeof(struct slabobj_ext));
 
 	if (new_slab) {
 		/*
@@ -2272,6 +2271,9 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 	void *addr;
 	unsigned long obj_exts;
 
+	/* Initialize stride early to avoid memory ordering issues */
+	slab_set_stride(slab, sizeof(struct slabobj_ext));
+
 	if (!need_slab_obj_exts(s))
 		return;
 
@@ -2288,7 +2290,6 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 		obj_exts |= MEMCG_DATA_OBJEXTS;
 #endif
 		slab->obj_exts = obj_exts;
-		slab_set_stride(slab, sizeof(struct slabobj_ext));
 	} else if (s->flags & SLAB_OBJ_EXT_IN_OBJ) {
 		unsigned int offset = obj_exts_offset_in_object(s);
 

From 663eb8763c251dbcd0536b14ec134e63e4173348 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 4 Feb 2026 17:41:58 +0100
Subject: [PATCH 0549/1303] i3c: simplify combined i3c/i2c dependencies

All combined i2c/i3c drivers appear to suffer from the same link
time problem when CONFIG_I3C is set to 'm':

arm-linux-gnueabi-ld: drivers/iio/magnetometer/mmc5633.o: in function `mmc5633_i3c_driver_init':
mmc5633.c:(.init.text+0x30): undefined reference to `i3c_driver_register_with_owner'

This was previously fixed every time by marking individual
drivers as 'depends on I2C; depends on I3C || !I3C', but this gets
tedious and is somewhat confusing.

Add a Kconfig symbol 'I3C_OR_I2C' to help replace those dependencies,
and use this in all the existing drivers that had already fixed it
as well as the new mmc5633 driver.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260204164216.544409-1-arnd@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/hwmon/Kconfig            |  6 ++----
 drivers/i3c/Kconfig              | 12 ++++++++++++
 drivers/iio/magnetometer/Kconfig |  3 +--
 drivers/misc/amd-sbi/Kconfig     |  3 +--
 4 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 41c381764c2b..ecfba861f66d 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1493,8 +1493,7 @@ config SENSORS_LM73
 
 config SENSORS_LM75
 	tristate "National Semiconductor LM75 and compatibles"
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
 	help
@@ -2392,8 +2391,7 @@ config SENSORS_TMP103
 
 config SENSORS_TMP108
 	tristate "Texas Instruments TMP108"
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
 	help
diff --git a/drivers/i3c/Kconfig b/drivers/i3c/Kconfig
index 30a441506f61..626c54b386d5 100644
--- a/drivers/i3c/Kconfig
+++ b/drivers/i3c/Kconfig
@@ -22,3 +22,15 @@ menuconfig I3C
 if I3C
 source "drivers/i3c/master/Kconfig"
 endif # I3C
+
+config I3C_OR_I2C
+	tristate
+	default m if I3C=m
+	default I2C
+	help
+	  Device drivers using module_i3c_i2c_driver() can use either
+	  i2c or i3c hosts, but cannot be built-in for the kernel when
+	  CONFIG_I3C=m.
+
+	  Add 'depends on I2C_OR_I3C' in Kconfig for those drivers to
+	  get the correct dependencies.
diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig
index 9345fb6d5317..fb313e591e85 100644
--- a/drivers/iio/magnetometer/Kconfig
+++ b/drivers/iio/magnetometer/Kconfig
@@ -143,8 +143,7 @@ config MMC5633
 	tristate "MEMSIC MMC5633 3-axis magnetic sensor"
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	help
 	  Say yes here to build support for the MEMSIC MMC5633 3-axis
 	  magnetic sensor.
diff --git a/drivers/misc/amd-sbi/Kconfig b/drivers/misc/amd-sbi/Kconfig
index be022c71a90c..30e7fad7356c 100644
--- a/drivers/misc/amd-sbi/Kconfig
+++ b/drivers/misc/amd-sbi/Kconfig
@@ -1,10 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config AMD_SBRMI_I2C
 	tristate "AMD side band RMI support"
-	depends on I2C
+	depends on I3C_OR_I2C
 	depends on ARM || ARM64 || COMPILE_TEST
 	select REGMAP_I2C
-	depends on I3C || !I3C
 	select REGMAP_I3C if I3C
 	help
 	  Side band RMI over I2C/I3C support for AMD out of band management.

From 0f5197ea9a73a4c406c75e6d8af3a13f7f96ae89 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 25 Feb 2026 11:38:05 -0800
Subject: [PATCH 0550/1303] nvme-multipath: fix leak on try_module_get failure

We need to fall back to the synchronous removal if we can't get a
reference on the module needed for the deferred removal.

Fixes: 62188639ec16 ("nvme-multipath: introduce delayed removal of the multipath head node")
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/multipath.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index bfcc5904e6a2..fc6800a9f7f9 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1310,13 +1310,11 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	if (!list_empty(&head->list))
 		goto out;
 
-	if (head->delayed_removal_secs) {
-		/*
-		 * Ensure that no one could remove this module while the head
-		 * remove work is pending.
-		 */
-		if (!try_module_get(THIS_MODULE))
-			goto out;
+	/*
+	 * Ensure that no one could remove this module while the head
+	 * remove work is pending.
+	 */
+	if (head->delayed_removal_secs && try_module_get(THIS_MODULE)) {
 		mod_delayed_work(nvme_wq, &head->remove_work,
 				head->delayed_removal_secs * HZ);
 	} else {

From f505a45776d149632e3bd0b87f0da1609607161a Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 26 Feb 2026 23:15:22 +0100
Subject: [PATCH 0551/1303] smb: client: Use snprintf in cifs_set_cifscreds

Replace unbounded sprintf() calls with the safer snprintf(). Avoid using
magic numbers and use strlen() to calculate the key descriptor buffer
size. Save the size in a local variable and reuse it for the bounded
snprintf() calls. Remove CIFSCREDS_DESC_SIZE.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 4c34d9603e05..3bad2c5c523d 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2167,9 +2167,6 @@ void __cifs_put_smb_ses(struct cifs_ses *ses)
 
 #ifdef CONFIG_KEYS
 
-/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */
-#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1)
-
 /* Populate username and pw fields from keyring if possible */
 static int
 cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
@@ -2177,6 +2174,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	int rc = 0;
 	int is_domain = 0;
 	const char *delim, *payload;
+	size_t desc_sz;
 	char *desc;
 	ssize_t len;
 	struct key *key;
@@ -2185,7 +2183,9 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	struct sockaddr_in6 *sa6;
 	const struct user_key_payload *upayload;
 
-	desc = kmalloc(CIFSCREDS_DESC_SIZE, GFP_KERNEL);
+	/* "cifs:a:" and "cifs:d:" are the same length; +1 for NUL terminator */
+	desc_sz = strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1;
+	desc = kmalloc(desc_sz, GFP_KERNEL);
 	if (!desc)
 		return -ENOMEM;
 
@@ -2193,11 +2193,11 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	switch (server->dstaddr.ss_family) {
 	case AF_INET:
 		sa = (struct sockaddr_in *)&server->dstaddr;
-		sprintf(desc, "cifs:a:%pI4", &sa->sin_addr.s_addr);
+		snprintf(desc, desc_sz, "cifs:a:%pI4", &sa->sin_addr.s_addr);
 		break;
 	case AF_INET6:
 		sa6 = (struct sockaddr_in6 *)&server->dstaddr;
-		sprintf(desc, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr);
+		snprintf(desc, desc_sz, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr);
 		break;
 	default:
 		cifs_dbg(FYI, "Bad ss_family (%hu)\n",
@@ -2216,7 +2216,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 		}
 
 		/* didn't work, try to find a domain key */
-		sprintf(desc, "cifs:d:%s", ses->domainName);
+		snprintf(desc, desc_sz, "cifs:d:%s", ses->domainName);
 		cifs_dbg(FYI, "%s: desc=%s\n", __func__, desc);
 		key = request_key(&key_type_logon, desc, "");
 		if (IS_ERR(key)) {

From 39195990e4c093c9eecf88f29811c6de29265214 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 27 Feb 2026 06:10:08 -0600
Subject: [PATCH 0552/1303] PCI: Correct PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fb82437fdd8c ("PCI: Change capability register offsets to hex") incorrectly
converted the PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value from decimal 52 to hex
0x32:

  -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52      /* v2 endpoints with link end here */
  +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32    /* end of v2 EPs w/ link */

This broke PCI capabilities in a VMM because subsequent ones weren't
DWORD-aligned.

Change PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 to the correct value of 0x34.

fb82437fdd8c was from Baruch Siach <baruch@tkos.co.il>, but this was not
Baruch's fault; it's a mistake I made when applying the patch.

Fixes: fb82437fdd8c ("PCI: Change capability register offsets to hex")
Reported-by: David Woodhouse <dwmw2@infradead.org>
Closes: https://lore.kernel.org/all/3ae392a0158e9d9ab09a1d42150429dd8ca42791.camel@infradead.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 include/uapi/linux/pci_regs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index ec1c54b5a310..14f634ab9350 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -712,7 +712,7 @@
 #define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
 #define PCI_EXP_LNKSTA2		0x32	/* Link Status 2 */
 #define  PCI_EXP_LNKSTA2_FLIT		0x0400 /* Flit Mode Status */
-#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x32	/* end of v2 EPs w/ link */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x34	/* end of v2 EPs w/ link */
 #define PCI_EXP_SLTCAP2		0x34	/* Slot Capabilities 2 */
 #define  PCI_EXP_SLTCAP2_IBPD	0x00000001 /* In-band PD Disable Supported */
 #define PCI_EXP_SLTCTL2		0x38	/* Slot Control 2 */

From 550bae2c0931dbb664a61b08c21cf156f0a5362a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Thu, 12 Feb 2026 11:49:44 -0300
Subject: [PATCH 0553/1303] pmdomain: bcm: bcm2835-power: Fix broken reset
 status read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

bcm2835_reset_status() has a misplaced parenthesis on every PM_READ()
call. Since PM_READ(reg) expands to readl(power->base + (reg)), the
expression:

    PM_READ(PM_GRAFX & PM_V3DRSTN)

computes the bitwise AND of the register offset PM_GRAFX with the
bitmask PM_V3DRSTN before using the result as a register offset, reading
from the wrong MMIO address instead of the intended PM_GRAFX register.
The same issue affects the PM_IMAGE cases.

Fix by moving the closing parenthesis so PM_READ() receives only the
register offset, and the bitmask is applied to the value returned by
the read.

Fixes: 670c672608a1 ("soc: bcm: bcm2835-pm: Add support for power domains under a new binding.")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/bcm/bcm2835-power.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c
index 1d29addfe036..0450202bbee2 100644
--- a/drivers/pmdomain/bcm/bcm2835-power.c
+++ b/drivers/pmdomain/bcm/bcm2835-power.c
@@ -580,11 +580,11 @@ static int bcm2835_reset_status(struct reset_controller_dev *rcdev,
 
 	switch (id) {
 	case BCM2835_RESET_V3D:
-		return !PM_READ(PM_GRAFX & PM_V3DRSTN);
+		return !(PM_READ(PM_GRAFX) & PM_V3DRSTN);
 	case BCM2835_RESET_H264:
-		return !PM_READ(PM_IMAGE & PM_H264RSTN);
+		return !(PM_READ(PM_IMAGE) & PM_H264RSTN);
 	case BCM2835_RESET_ISP:
-		return !PM_READ(PM_IMAGE & PM_ISPRSTN);
+		return !(PM_READ(PM_IMAGE) & PM_ISPRSTN);
 	default:
 		return -EINVAL;
 	}

From e31b556c0ba21f20c298aa61181b96541140b7b9 Mon Sep 17 00:00:00 2001
From: Romain Sioen <romain.sioen@microchip.com>
Date: Fri, 6 Feb 2026 17:32:58 +0100
Subject: [PATCH 0554/1303] HID: mcp2221: cancel last I2C command on read error

When an I2C SMBus read operation fails, the MCP2221 internal state machine
may not reset correctly, causing subsequent transactions to fail.

By adding a short delay and explicitly cancelling the last command,
we ensure the device is ready for the next operation.

Fix an issue where i2cdetect was not able to detect all devices correctly
on the bus.

Signed-off-by: Romain Sioen <romain.sioen@microchip.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-mcp2221.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 33603b019f97..ef3b5c77c38e 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -353,6 +353,8 @@ static int mcp_i2c_smbus_read(struct mcp2221 *mcp,
 				usleep_range(90, 100);
 				retries++;
 			} else {
+				usleep_range(980, 1000);
+				mcp_cancel_last_cmd(mcp);
 				return ret;
 			}
 		} else {

From 032e084f0d43fda78c33abfc704ac13a0891a6e7 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Fri, 27 Feb 2026 18:43:09 +0000
Subject: [PATCH 0555/1303] tools/sched_ext: fix strtoul() misuse in
 scx_hotplug_seq()

scx_hotplug_seq() uses strtoul() but validates the result with a
negative check (val < 0), which can never be true for an unsigned
return value.

Use the endptr mechanism to verify the entire string was consumed,
and check errno == ERANGE for overflow detection.

Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/include/scx/compat.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index 8b4897fc8b99..edccc99c7294 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -125,6 +125,7 @@ static inline long scx_hotplug_seq(void)
 {
 	int fd;
 	char buf[32];
+	char *endptr;
 	ssize_t len;
 	long val;
 
@@ -137,8 +138,10 @@ static inline long scx_hotplug_seq(void)
 	buf[len] = 0;
 	close(fd);
 
-	val = strtoul(buf, NULL, 10);
-	SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val);
+	errno = 0;
+	val = strtoul(buf, &endptr, 10);
+	SCX_BUG_ON(errno == ERANGE || endptr == buf ||
+		   (*endptr != '\n' && *endptr != '\0'), "invalid num hotplug events: %ld", val);
 
 	return val;
 }

From 3d17d76d1ffb139a7492317b196ee03c8eabc9dc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 27 Feb 2026 09:07:45 -0800
Subject: [PATCH 0556/1303] io_uring/zcrx: don't set rx_page_size when not
 requested

The rx_buf_len parameter was recently added to the Rx zero-copy
implementation. The expectation is that when not set system will
maintain previous behavior and use the default buffer size (PAGE_SIZE).

This works correctly at the iouring level, but we don't preserve
the same "zero means default" semantics when registering the memory
provider on the netdev. mp_param.rx_page_size is unconditionally
set to PAGE_SIZE. This causes __net_mp_open_rxq() to check for
QCFG_RX_PAGE_SIZE support in the driver, and return -EOPNOTSUPP
for drivers that don't advertise it -- even though the user never
asked for large buffers.

Only set mp_param.rx_page_size when rx_buf_len was explicitly provided,
so that the default page size path works on all zcrx-capable drivers.
mlx5 and fbnic only support 4kB pages in the current release.

Fixes: 795663b4d160 ("io_uring/zcrx: implement large rx buffer support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 97984a73a95d..19b287d21f4b 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -837,7 +837,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	if (ret)
 		goto netdev_put_unlock;
 
-	mp_param.rx_page_size = 1U << ifq->niov_shift;
+	if (reg.rx_buf_len)
+		mp_param.rx_page_size = 1U << ifq->niov_shift;
 	mp_param.mp_ops = &io_uring_pp_zc_ops;
 	mp_param.mp_priv = ifq;
 	ret = __net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param, NULL);

From 7b6275c80a0c81c5f8943272292dfe67730ce849 Mon Sep 17 00:00:00 2001
From: Eric Badger <ebadger@purestorage.com>
Date: Mon, 23 Feb 2026 10:28:55 -0800
Subject: [PATCH 0557/1303] xprtrdma: Decrement re_receiving on the early exit
 paths

In the event that rpcrdma_post_recvs() fails to create a work request
(due to memory allocation failure, say) or otherwise exits early, we
should decrement ep->re_receiving before returning. Otherwise we will
hang in rpcrdma_xprt_drain() as re_receiving will never reach zero and
the completion will never be triggered.

On a system with high memory pressure, this can appear as the following
hung task:

    INFO: task kworker/u385:17:8393 blocked for more than 122 seconds.
          Tainted: G S          E       6.19.0 #3
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
    task:kworker/u385:17 state:D stack:0     pid:8393  tgid:8393  ppid:2      task_flags:0x4248060 flags:0x00080000
    Workqueue: xprtiod xprt_autoclose [sunrpc]
    Call Trace:
     <TASK>
     __schedule+0x48b/0x18b0
     ? ib_post_send_mad+0x247/0xae0 [ib_core]
     schedule+0x27/0xf0
     schedule_timeout+0x104/0x110
     __wait_for_common+0x98/0x180
     ? __pfx_schedule_timeout+0x10/0x10
     wait_for_completion+0x24/0x40
     rpcrdma_xprt_disconnect+0x444/0x460 [rpcrdma]
     xprt_rdma_close+0x12/0x40 [rpcrdma]
     xprt_autoclose+0x5f/0x120 [sunrpc]
     process_one_work+0x191/0x3e0
     worker_thread+0x2e3/0x420
     ? __pfx_worker_thread+0x10/0x10
     kthread+0x10d/0x230
     ? __pfx_kthread+0x10/0x10
     ret_from_fork+0x273/0x2b0
     ? __pfx_kthread+0x10/0x10
     ret_from_fork_asm+0x1a/0x30

Fixes: 15788d1d1077 ("xprtrdma: Do not refresh Receive Queue while it is draining")
Signed-off-by: Eric Badger <ebadger@purestorage.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/xprtrdma/verbs.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 15bbf953dfad..b51a162885bb 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 	needed += RPCRDMA_MAX_RECV_BATCH;
 
 	if (atomic_inc_return(&ep->re_receiving) > 1)
-		goto out;
+		goto out_dec;
 
 	/* fast path: all needed reps can be found on the free list */
 	wr = NULL;
@@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 		++count;
 	}
 	if (!wr)
-		goto out;
+		goto out_dec;
 
 	rc = ib_post_recv(ep->re_id->qp, wr,
 			  (const struct ib_recv_wr **)&bad_wr);
@@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 			--count;
 		}
 	}
+
+out_dec:
 	if (atomic_dec_return(&ep->re_receiving) > 0)
 		complete(&ep->re_done);
-
 out:
 	trace_xprtrdma_post_recvs(r_xprt, count);
 	ep->re_receive_count += count;

From 4529e0015432977af3ecc3b9f940fc2a1ef1b265 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <anna.schumaker@oracle.com>
Date: Wed, 18 Feb 2026 11:41:15 -0500
Subject: [PATCH 0558/1303] NFS: Fix NFS KConfig typos

Two issues were noticed after the NFS v4.0 KConfig changes were merged
upstream. First, the text of CONFIG_NFS_V4 should not encourage people
to select it if they are unsure. Second, the new CONFIG_NFS_V4_0 option
should default to "on" instead of "off" to avoid breaking people's
setups if they are using NFS v4.0.

Reported-by: Niklas Cassel <cassel@kernel.org>
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Fixes: 4e0269352534 ("NFS: Add a way to disable NFS v4.0 via KConfig")
Fixes: 7537db24806f ("NFS: Merge CONFIG_NFS_V4_1 with CONFIG_NFS_V4")
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 12cb0ca738af..6bb30543eff0 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -87,7 +87,7 @@ config NFS_V4
 	  space programs which can be found in the Linux nfs-utils package,
 	  available from http://linux-nfs.org/.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config NFS_SWAP
 	bool "Provide swap over NFS support"
@@ -100,6 +100,7 @@ config NFS_SWAP
 config NFS_V4_0
 	bool "NFS client support for NFSv4.0"
 	depends on NFS_V4
+	default y
 	help
 	  This option enables support for minor version 0 of the NFSv4 protocol
 	  (RFC 3530) in the kernel's NFS client.

From e6b899f08066e744f89df16ceb782e06868bd148 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:09 +0100
Subject: [PATCH 0559/1303] nsfs: tighten permission checks for ns iteration
 ioctls

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-1-d2c2853313bd@kernel.org
Fixes: a1d220d9dafa ("nsfs: iterate through mount namespaces")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.12+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c                 | 13 +++++++++++++
 include/linux/ns_common.h |  2 ++
 kernel/nscommon.c         |  6 ++++++
 3 files changed, 21 insertions(+)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index db91de208645..be36c10c38cf 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -199,6 +199,17 @@ static bool nsfs_ioctl_valid(unsigned int cmd)
 	return false;
 }
 
+static bool may_use_nsfs_ioctl(unsigned int cmd)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(NS_MNT_GET_NEXT):
+		fallthrough;
+	case _IOC_NR(NS_MNT_GET_PREV):
+		return may_see_all_namespaces();
+	}
+	return true;
+}
+
 static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			unsigned long arg)
 {
@@ -214,6 +225,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 
 	if (!nsfs_ioctl_valid(ioctl))
 		return -ENOIOCTLCMD;
+	if (!may_use_nsfs_ioctl(ioctl))
+		return -EPERM;
 
 	ns = get_proc_ns(file_inode(filp));
 	switch (ioctl) {
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 825f5865bfc5..c8e227a3f9e2 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns)
 
 #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
 
+bool may_see_all_namespaces(void);
+
 static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns)
 {
 	return atomic_read(&ns->__ns_ref_active);
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index bdc3c86231d3..3166c1fd844a 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns)
 			return;
 	}
 }
+
+bool may_see_all_namespaces(void)
+{
+	return (task_active_pid_ns(current) == &init_pid_ns) &&
+	       ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN);
+}

From d2324a9317f00013facb0ba00b00440e19d2af5e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:10 +0100
Subject: [PATCH 0560/1303] nsfs: tighten permission checks for handle opening

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-2-d2c2853313bd@kernel.org
Fixes: 5222470b2fbb ("nsfs: support file handles")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.18+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index be36c10c38cf..c215878d55e8 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -627,7 +627,7 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
-	if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) {
+	if (owning_ns && !may_see_all_namespaces()) {
 		ns->ops->put(ns);
 		return ERR_PTR(-EPERM);
 	}

From 8d76afe84fa2babf604b3c173730d4d2b067e361 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:11 +0100
Subject: [PATCH 0561/1303] nstree: tighten permission checks for listing

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-3-d2c2853313bd@kernel.org
Fixes: 76b6f5dfb3fd ("nstree: add listns()")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.19+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/nstree.c | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/kernel/nstree.c b/kernel/nstree.c
index f36c59e6951d..6d12e5900ac0 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls,
 static inline bool __must_check may_list_ns(const struct klistns *kls,
 					    struct ns_common *ns)
 {
-	if (kls->user_ns) {
-		if (kls->userns_capable)
-			return true;
-	} else {
-		struct ns_common *owner;
-		struct user_namespace *user_ns;
-
-		owner = ns_owner(ns);
-		if (owner)
-			user_ns = to_user_ns(owner);
-		else
-			user_ns = &init_user_ns;
-		if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN))
-			return true;
-	}
-
+	if (kls->user_ns && kls->userns_capable)
+		return true;
 	if (is_current_namespace(ns))
 		return true;
-
-	if (ns->ns_type != CLONE_NEWUSER)
-		return false;
-
-	if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN))
-		return true;
-
-	return false;
+	return may_see_all_namespaces();
 }
 
 static inline void ns_put(struct ns_common *ns)
@@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls)
 
 	ret = 0;
 	head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head;
-	kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN);
+	kls->userns_capable = may_see_all_namespaces();
 
 	rcu_read_lock();
 

From 4c7b2ec23cc5d880e3ffe35e8c2aad686b67723a Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:12 +0100
Subject: [PATCH 0562/1303] selftests: fix mntns iteration selftests

Now that we changed permission checking make sure that we reflect that
in the selftests.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-4-d2c2853313bd@kernel.org
Fixes: 9d87b1067382 ("selftests: add tests for mntns iteration")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.14+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 .../filesystems/nsfs/iterate_mntns.c          | 25 +++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
index 61e55dfbf121..e19ff8168baf 100644
--- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
+++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
@@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) {
 	__u64 mnt_ns_id[MNT_NS_COUNT];
 };
 
+static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info)
+{
+	for (int i = 0; i < MNT_NS_COUNT; i++) {
+		if (mnt_ns_id[i] == info->mnt_ns_id)
+			return true;
+	}
+	return false;
+}
+
 FIXTURE_SETUP(iterate_mount_namespaces)
 {
 	for (int i = 0; i < MNT_NS_COUNT; i++)
 		self->fd_mnt_ns[i] = -EBADF;
 
-	/*
-	 * Creating a new user namespace let's us guarantee that we only see
-	 * mount namespaces that we did actually create.
-	 */
-	ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
-
 	for (int i = 0; i < MNT_NS_COUNT; i++) {
 		struct mnt_ns_info info = {};
 
@@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward)
 	fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC);
 	ASSERT_GE(fd_mnt_ns_cur, 0);
 
-	for (;; count++) {
+	for (;;) {
 		struct mnt_ns_info info = {};
 		int fd_mnt_ns_next;
 
 		fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info);
 		if (fd_mnt_ns_next < 0 && errno == ENOENT)
 			break;
+		if (mntns_in_list(self->mnt_ns_id, &info))
+			count++;
 		ASSERT_GE(fd_mnt_ns_next, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_next;
@@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards)
 	fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC);
 	ASSERT_GE(fd_mnt_ns_cur, 0);
 
-	for (;; count++) {
+	for (;;) {
 		struct mnt_ns_info info = {};
 		int fd_mnt_ns_prev;
 
 		fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info);
 		if (fd_mnt_ns_prev < 0 && errno == ENOENT)
 			break;
+		if (mntns_in_list(self->mnt_ns_id, &info))
+			count++;
 		ASSERT_GE(fd_mnt_ns_prev, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_prev;
@@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward)
 		ASSERT_GE(fd_mnt_ns_next, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_next;
-		ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
 	}
 }
 
@@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward)
 		ASSERT_GE(fd_mnt_ns_prev, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_prev;
-		ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
 	}
 }
 

From 1df97a7453eec80c1912c2d0360290a3970a7671 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:01 -0800
Subject: [PATCH 0563/1303] bpf: Register dtor for freeing special fields

There is a race window where BPF hash map elements can leak special
fields if the program with access to the map value recreates these
special fields between the check_and_free_fields done on the map value
and its eventual return to the memory allocator.

Several ways were explored prior to this patch, most notably [0] tried
to use a poison value to reject attempts to recreate special fields for
map values that have been logically deleted but still accessible to BPF
programs (either while sitting in the free list or when reused). While
this approach works well for task work, timers, wq, etc., it is harder
to apply the idea to kptrs, which have a similar race and failure mode.

Instead, we change bpf_mem_alloc to allow registering destructor for
allocated elements, such that when they are returned to the allocator,
any special fields created while they were accessible to programs in the
mean time will be freed. If these values get reused, we do not free the
fields again before handing the element back. The special fields thus
may remain initialized while the map value sits in a free list.

When bpf_mem_alloc is retired in the future, a similar concept can be
introduced to kmalloc_nolock-backed kmem_cache, paired with the existing
idea of a constructor.

Note that the destructor registration happens in map_check_btf, after
the BTF record is populated and (at that point) avaiable for inspection
and duplication. Duplication is necessary since the freeing of embedded
bpf_mem_alloc can be decoupled from actual map lifetime due to logic
introduced to reduce the cost of rcu_barrier()s in mem alloc free path in
9f2c6e96c65e ("bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc.").

As such, once all callbacks are done, we must also free the duplicated
record. To remove dependency on the bpf_map itself, also stash the key
size of the map to obtain value from htab_elem long after the map is
gone.

  [0]: https://lore.kernel.org/bpf/20260216131341.1285427-1-mykyta.yatsenko5@gmail.com

Fixes: 14a324f6a67e ("bpf: Wire up freeing of referenced kptr")
Fixes: 1bfbc267ec91 ("bpf: Enable bpf_timer and bpf_wq in any context")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: syzbot@syzkaller.appspotmail.com
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_mem_alloc.h |  6 +++
 kernel/bpf/hashtab.c          | 87 +++++++++++++++++++++++++++++++++++
 kernel/bpf/memalloc.c         | 58 ++++++++++++++++++-----
 3 files changed, 140 insertions(+), 11 deletions(-)

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index e45162ef59bb..4ce0d27f8ea2 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -14,6 +14,8 @@ struct bpf_mem_alloc {
 	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
+	void (*dtor_ctx_free)(void *ctx);
+	void *dtor_ctx;
 };
 
 /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects.
@@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 /* The percpu allocation with a specific unit size. */
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma,
+			    void (*dtor)(void *obj, void *ctx),
+			    void (*dtor_ctx_free)(void *ctx),
+			    void *ctx);
 
 /* Check the allocation size for kmalloc equivalent allocator */
 int bpf_mem_alloc_check_size(bool percpu, size_t size);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3b9d297a53be..582f0192b7e1 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -125,6 +125,11 @@ struct htab_elem {
 	char key[] __aligned(8);
 };
 
+struct htab_btf_record {
+	struct btf_record *record;
+	u32 key_size;
+};
+
 static inline bool htab_is_prealloc(const struct bpf_htab *htab)
 {
 	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
@@ -457,6 +462,84 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	return 0;
 }
 
+static void htab_mem_dtor(void *obj, void *ctx)
+{
+	struct htab_btf_record *hrec = ctx;
+	struct htab_elem *elem = obj;
+	void *map_value;
+
+	if (IS_ERR_OR_NULL(hrec->record))
+		return;
+
+	map_value = htab_elem_value(elem, hrec->key_size);
+	bpf_obj_free_fields(hrec->record, map_value);
+}
+
+static void htab_pcpu_mem_dtor(void *obj, void *ctx)
+{
+	void __percpu *pptr = *(void __percpu **)obj;
+	struct htab_btf_record *hrec = ctx;
+	int cpu;
+
+	if (IS_ERR_OR_NULL(hrec->record))
+		return;
+
+	for_each_possible_cpu(cpu)
+		bpf_obj_free_fields(hrec->record, per_cpu_ptr(pptr, cpu));
+}
+
+static void htab_dtor_ctx_free(void *ctx)
+{
+	struct htab_btf_record *hrec = ctx;
+
+	btf_record_free(hrec->record);
+	kfree(ctx);
+}
+
+static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *))
+{
+	u32 key_size = htab->map.key_size;
+	const struct bpf_mem_alloc *ma;
+	struct htab_btf_record *hrec;
+	int err;
+
+	/* No need for dtors. */
+	if (IS_ERR_OR_NULL(htab->map.record))
+		return 0;
+
+	hrec = kzalloc(sizeof(*hrec), GFP_KERNEL);
+	if (!hrec)
+		return -ENOMEM;
+	hrec->key_size = key_size;
+	hrec->record = btf_record_dup(htab->map.record);
+	if (IS_ERR(hrec->record)) {
+		err = PTR_ERR(hrec->record);
+		kfree(hrec);
+		return err;
+	}
+	ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma;
+	/* Kinda sad, but cast away const-ness since we change ma->dtor. */
+	bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec);
+	return 0;
+}
+
+static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			      const struct btf_type *key_type, const struct btf_type *value_type)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+	if (htab_is_prealloc(htab))
+		return 0;
+	/*
+	 * We must set the dtor using this callback, as map's BTF record is not
+	 * populated in htab_map_alloc(), so it will always appear as NULL.
+	 */
+	if (htab_is_percpu(htab))
+		return htab_set_dtor(htab, htab_pcpu_mem_dtor);
+	else
+		return htab_set_dtor(htab, htab_mem_dtor);
+}
+
 static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -2281,6 +2364,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2303,6 +2387,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2482,6 +2567,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2502,6 +2588,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index bd45dda9dc35..682a9f34214b 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -102,6 +102,8 @@ struct bpf_mem_cache {
 	int percpu_size;
 	bool draining;
 	struct bpf_mem_cache *tgt;
+	void (*dtor)(void *obj, void *ctx);
+	void *dtor_ctx;
 
 	/* list of objects to be freed after RCU GP */
 	struct llist_head free_by_rcu;
@@ -260,12 +262,14 @@ static void free_one(void *obj, bool percpu)
 	kfree(obj);
 }
 
-static int free_all(struct llist_node *llnode, bool percpu)
+static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool percpu)
 {
 	struct llist_node *pos, *t;
 	int cnt = 0;
 
 	llist_for_each_safe(pos, t, llnode) {
+		if (c->dtor)
+			c->dtor((void *)pos + LLIST_NODE_SZ, c->dtor_ctx);
 		free_one(pos, percpu);
 		cnt++;
 	}
@@ -276,7 +280,7 @@ static void __free_rcu(struct rcu_head *head)
 {
 	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
 
-	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+	free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
 	atomic_set(&c->call_rcu_ttrace_in_progress, 0);
 }
 
@@ -308,7 +312,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
 		if (unlikely(READ_ONCE(c->draining))) {
 			llnode = llist_del_all(&c->free_by_rcu_ttrace);
-			free_all(llnode, !!c->percpu_size);
+			free_all(c, llnode, !!c->percpu_size);
 		}
 		return;
 	}
@@ -417,7 +421,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
 	dec_active(c, &flags);
 
 	if (unlikely(READ_ONCE(c->draining))) {
-		free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
+		free_all(c, llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
 		atomic_set(&c->call_rcu_in_progress, 0);
 	} else {
 		call_rcu_hurry(&c->rcu, __free_by_rcu);
@@ -635,13 +639,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
-	free_all(__llist_del_all(&c->free_llist), percpu);
-	free_all(__llist_del_all(&c->free_llist_extra), percpu);
-	free_all(__llist_del_all(&c->free_by_rcu), percpu);
-	free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp), percpu);
+	free_all(c, llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), percpu);
+	free_all(c, __llist_del_all(&c->free_llist), percpu);
+	free_all(c, __llist_del_all(&c->free_llist_extra), percpu);
+	free_all(c, __llist_del_all(&c->free_by_rcu), percpu);
+	free_all(c, __llist_del_all(&c->free_llist_extra_rcu), percpu);
+	free_all(c, llist_del_all(&c->waiting_for_gp), percpu);
 }
 
 static void check_mem_cache(struct bpf_mem_cache *c)
@@ -680,6 +684,9 @@ static void check_leaked_objs(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 {
+	/* We can free dtor ctx only once all callbacks are done using it. */
+	if (ma->dtor_ctx_free)
+		ma->dtor_ctx_free(ma->dtor_ctx);
 	check_leaked_objs(ma);
 	free_percpu(ma->cache);
 	free_percpu(ma->caches);
@@ -1014,3 +1021,32 @@ int bpf_mem_alloc_check_size(bool percpu, size_t size)
 
 	return 0;
 }
+
+void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, void (*dtor)(void *obj, void *ctx),
+			    void (*dtor_ctx_free)(void *ctx), void *ctx)
+{
+	struct bpf_mem_caches *cc;
+	struct bpf_mem_cache *c;
+	int cpu, i;
+
+	ma->dtor_ctx_free = dtor_ctx_free;
+	ma->dtor_ctx = ctx;
+
+	if (ma->cache) {
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(ma->cache, cpu);
+			c->dtor = dtor;
+			c->dtor_ctx = ctx;
+		}
+	}
+	if (ma->caches) {
+		for_each_possible_cpu(cpu) {
+			cc = per_cpu_ptr(ma->caches, cpu);
+			for (i = 0; i < NUM_CACHES; i++) {
+				c = &cc->cache[i];
+				c->dtor = dtor;
+				c->dtor_ctx = ctx;
+			}
+		}
+	}
+}

From ae51772b1e94ba1d76db19085957dbccac189c1c Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:02 -0800
Subject: [PATCH 0564/1303] bpf: Lose const-ness of map in map_check_btf()

BPF hash map may now use the map_check_btf() callback to decide whether
to set a dtor on its bpf_mem_alloc or not. Unlike C++ where members can
opt out of const-ness using mutable, we must lose the const qualifier on
the callback such that we can avoid the ugly cast. Make the change and
adjust all existing users, and lose the comment in hashtab.c.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h               | 4 ++--
 include/linux/bpf_local_storage.h | 2 +-
 kernel/bpf/arena.c                | 2 +-
 kernel/bpf/arraymap.c             | 2 +-
 kernel/bpf/bloom_filter.c         | 2 +-
 kernel/bpf/bpf_insn_array.c       | 2 +-
 kernel/bpf/bpf_local_storage.c    | 2 +-
 kernel/bpf/hashtab.c              | 9 ++++-----
 kernel/bpf/local_storage.c        | 2 +-
 kernel/bpf/lpm_trie.c             | 2 +-
 kernel/bpf/syscall.c              | 2 +-
 11 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b78b53198a2e..05b34a6355b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -124,7 +124,7 @@ struct bpf_map_ops {
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
-	int (*map_check_btf)(const struct bpf_map *map,
+	int (*map_check_btf)(struct bpf_map *map,
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
@@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 		map->ops->map_seq_show_elem;
 }
 
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
 		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 85efa9772530..8157e8da61d4 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage);
 void bpf_local_storage_map_free(struct bpf_map *map,
 				struct bpf_local_storage_cache *cache);
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+int bpf_local_storage_map_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type);
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 144f30e740e8..f355cf1c1a16 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -303,7 +303,7 @@ static long arena_map_update_elem(struct bpf_map *map, void *key,
 	return -EOPNOTSUPP;
 }
 
-static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int arena_map_check_btf(struct bpf_map *map, const struct btf *btf,
 			       const struct btf_type *key_type, const struct btf_type *value_type)
 {
 	return 0;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 26763df6134a..33de68c95ad8 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -548,7 +548,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int array_map_check_btf(const struct bpf_map *map,
+static int array_map_check_btf(struct bpf_map *map,
 			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index 35e1ddca74d2..b73336c976b7 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -180,7 +180,7 @@ static long bloom_map_update_elem(struct bpf_map *map, void *key,
 	return -EINVAL;
 }
 
-static int bloom_map_check_btf(const struct bpf_map *map,
+static int bloom_map_check_btf(struct bpf_map *map,
 			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
diff --git a/kernel/bpf/bpf_insn_array.c b/kernel/bpf/bpf_insn_array.c
index c0286f25ca3c..a2f84afe6f7c 100644
--- a/kernel/bpf/bpf_insn_array.c
+++ b/kernel/bpf/bpf_insn_array.c
@@ -98,7 +98,7 @@ static long insn_array_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
-static int insn_array_check_btf(const struct bpf_map *map,
+static int insn_array_check_btf(struct bpf_map *map,
 			      const struct btf *btf,
 			      const struct btf_type *key_type,
 			      const struct btf_type *value_type)
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b28f07d3a0db..2bf5ca5ae0df 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -797,7 +797,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
 	return 0;
 }
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+int bpf_local_storage_map_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 582f0192b7e1..bc6bc8bb871d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -496,10 +496,10 @@ static void htab_dtor_ctx_free(void *ctx)
 	kfree(ctx);
 }
 
-static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *))
+static int htab_set_dtor(struct bpf_htab *htab, void (*dtor)(void *, void *))
 {
 	u32 key_size = htab->map.key_size;
-	const struct bpf_mem_alloc *ma;
+	struct bpf_mem_alloc *ma;
 	struct htab_btf_record *hrec;
 	int err;
 
@@ -518,12 +518,11 @@ static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void
 		return err;
 	}
 	ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma;
-	/* Kinda sad, but cast away const-ness since we change ma->dtor. */
-	bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec);
+	bpf_mem_alloc_set_dtor(ma, dtor, htab_dtor_ctx_free, hrec);
 	return 0;
 }
 
-static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf,
 			      const struct btf_type *key_type, const struct btf_type *value_type)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 1ccbf28b2ad9..8fca0c64f7b1 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -364,7 +364,7 @@ static long cgroup_storage_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
-static int cgroup_storage_check_btf(const struct bpf_map *map,
+static int cgroup_storage_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1adeb4d3b8cf..0f57608b385d 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -751,7 +751,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
 	return err;
 }
 
-static int trie_check_btf(const struct bpf_map *map,
+static int trie_check_btf(struct bpf_map *map,
 			  const struct btf *btf,
 			  const struct btf_type *key_type,
 			  const struct btf_type *value_type)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0378e83b4099..274039e36465 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1234,7 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(bpf_obj_name_cpy);
 
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
 		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type)

From f41deee082dc7b1c198de21710cb5cb9c604cae0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:03 -0800
Subject: [PATCH 0565/1303] bpf: Delay freeing fields in local storage

Currently, when use_kmalloc_nolock is false, the freeing of fields for a
local storage selem is done eagerly before waiting for the RCU or RCU
tasks trace grace period to elapse. This opens up a window where the
program which has access to the selem can recreate the fields after the
freeing of fields is done eagerly, causing memory leaks when the element
is finally freed and returned to the kernel.

Make a few changes to address this. First, delay the freeing of fields
until after the grace periods have expired using a __bpf_selem_free_rcu
wrapper which is eventually invoked after transitioning through the
necessary number of grace period waits. Replace usage of the kfree_rcu
with call_rcu to be able to take a custom callback. Finally, care needs
to be taken to extend the rcu barriers for all cases, and not just when
use_kmalloc_nolock is true, as RCU and RCU tasks trace callbacks can be
in flight for either case and access the smap field, which is used to
obtain the BTF record to walk over special fields in the map value.

While we're at it, drop migrate_disable() from bpf_selem_free_rcu, since
migration should be disabled for RCU callbacks already.

Fixes: 9bac675e6368 ("bpf: Postpone bpf_obj_free_fields to the rcu callback")
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-4-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/bpf_local_storage.c | 42 ++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 2bf5ca5ae0df..d7db1ada2dad 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -164,16 +164,28 @@ static void bpf_local_storage_free(struct bpf_local_storage *local_storage,
 			     bpf_local_storage_free_trace_rcu);
 }
 
+/* rcu callback for use_kmalloc_nolock == false */
+static void __bpf_selem_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
+
+	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+	/* bpf_selem_unlink_nofail may have already cleared smap and freed fields. */
+	smap = rcu_dereference_check(SDATA(selem)->smap, 1);
+
+	if (smap)
+		bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
+	kfree(selem);
+}
+
 /* rcu tasks trace callback for use_kmalloc_nolock == false */
 static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
-	struct bpf_local_storage_elem *selem;
-
-	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
 	if (rcu_trace_implies_rcu_gp())
-		kfree(selem);
+		__bpf_selem_free_rcu(rcu);
 	else
-		kfree_rcu(selem, rcu);
+		call_rcu(rcu, __bpf_selem_free_rcu);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -181,7 +193,7 @@ static void __bpf_selem_free(struct bpf_local_storage_elem *selem,
 			     bool vanilla_rcu)
 {
 	if (vanilla_rcu)
-		kfree_rcu(selem, rcu);
+		call_rcu(&selem->rcu, __bpf_selem_free_rcu);
 	else
 		call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu);
 }
@@ -195,11 +207,8 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu)
 	/* The bpf_local_storage_map_free will wait for rcu_barrier */
 	smap = rcu_dereference_check(SDATA(selem)->smap, 1);
 
-	if (smap) {
-		migrate_disable();
+	if (smap)
 		bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
-		migrate_enable();
-	}
 	kfree_nolock(selem);
 }
 
@@ -214,18 +223,12 @@ static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 void bpf_selem_free(struct bpf_local_storage_elem *selem,
 		    bool reuse_now)
 {
-	struct bpf_local_storage_map *smap;
-
-	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
-
 	if (!selem->use_kmalloc_nolock) {
 		/*
 		 * No uptr will be unpin even when reuse_now == false since uptr
 		 * is only supported in task local storage, where
 		 * smap->use_kmalloc_nolock == true.
 		 */
-		if (smap)
-			bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
 		__bpf_selem_free(selem, reuse_now);
 		return;
 	}
@@ -958,10 +961,9 @@ void bpf_local_storage_map_free(struct bpf_map *map,
 	 */
 	synchronize_rcu();
 
-	if (smap->use_kmalloc_nolock) {
-		rcu_barrier_tasks_trace();
-		rcu_barrier();
-	}
+	/* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */
+	rcu_barrier_tasks_trace();
+	rcu_barrier();
 	kvfree(smap->buckets);
 	bpf_map_area_free(smap);
 }

From baa35b3cb6b642b903162aacff13181e170c4ecc Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:04 -0800
Subject: [PATCH 0566/1303] bpf: Retire rcu_trace_implies_rcu_gp() from local
 storage

This assumption will always hold going forward, hence just remove the
various checks and assume it is true with a comment for the uninformed
reader.

Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/bpf_local_storage.c | 37 +++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index d7db1ada2dad..9c96a4477f81 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -107,14 +107,12 @@ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
 {
 	struct bpf_local_storage *local_storage;
 
-	/* If RCU Tasks Trace grace period implies RCU grace period, do
-	 * kfree(), else do kfree_rcu().
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
 	 */
 	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
-	if (rcu_trace_implies_rcu_gp())
-		kfree(local_storage);
-	else
-		kfree_rcu(local_storage, rcu);
+	kfree(local_storage);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -138,10 +136,11 @@ static void bpf_local_storage_free_rcu(struct rcu_head *rcu)
 
 static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		bpf_local_storage_free_rcu(rcu);
-	else
-		call_rcu(rcu, bpf_local_storage_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	bpf_local_storage_free_rcu(rcu);
 }
 
 static void bpf_local_storage_free(struct bpf_local_storage *local_storage,
@@ -182,10 +181,11 @@ static void __bpf_selem_free_rcu(struct rcu_head *rcu)
 /* rcu tasks trace callback for use_kmalloc_nolock == false */
 static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		__bpf_selem_free_rcu(rcu);
-	else
-		call_rcu(rcu, __bpf_selem_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	__bpf_selem_free_rcu(rcu);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -214,10 +214,11 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu)
 
 static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		bpf_selem_free_rcu(rcu);
-	else
-		call_rcu(rcu, bpf_selem_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	bpf_selem_free_rcu(rcu);
 }
 
 void bpf_selem_free(struct bpf_local_storage_elem *selem,

From 2939d7b3b0e5f35359ce8f69dbbad0bfc4e920b6 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:05 -0800
Subject: [PATCH 0567/1303] selftests/bpf: Add tests for special fields races

Add a couple of tests to ensure that the refcount drops to zero when we
exercise the race where creation of a special field succeeds the logical
bpf_obj_free_fields done when deleting an element. Prior to previous
changes, the fields would be freed eagerly and repopulate and end up
leaking, causing the reference to not drop down correctly. Running this
test on a kernel without fixes will cause a hang in delete_module, since
the module reference stays active due to the leaked kptr not dropping
it. After the fixes tests succeed as expected.

Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-6-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/map_kptr_race.c  | 218 ++++++++++++++++++
 .../selftests/bpf/progs/map_kptr_race.c       | 197 ++++++++++++++++
 2 files changed, 415 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
 create mode 100644 tools/testing/selftests/bpf/progs/map_kptr_race.c

diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
new file mode 100644
index 000000000000..506ed55e8528
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "map_kptr_race.skel.h"
+
+static int get_map_id(int map_fd)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+
+	if (!ASSERT_OK(bpf_map_get_info_by_fd(map_fd, &info, &len), "get_map_info"))
+		return -1;
+	return info.id;
+}
+
+static int read_refs(struct map_kptr_race *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	int ret;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &opts);
+	if (!ASSERT_OK(ret, "count_ref run"))
+		return -1;
+	if (!ASSERT_OK(opts.retval, "count_ref retval"))
+		return -1;
+	return skel->bss->num_of_refs;
+}
+
+static void test_htab_leak(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct map_kptr_race *skel, *watcher;
+	int ret, map_id;
+
+	skel = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_htab_leak), &opts);
+	if (!ASSERT_OK(ret, "test_htab_leak run"))
+		goto out_skel;
+	if (!ASSERT_OK(opts.retval, "test_htab_leak retval"))
+		goto out_skel;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_hash_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "htab refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	map_kptr_race__destroy(skel);
+}
+
+static void test_percpu_htab_leak(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct map_kptr_race *skel, *watcher;
+	int ret, map_id;
+
+	skel = map_kptr_race__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+	if (skel->rodata->nr_cpus > 16)
+		skel->rodata->nr_cpus = 16;
+
+	ret = map_kptr_race__load(skel);
+	if (!ASSERT_OK(ret, "load"))
+		goto out_skel;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_percpu_htab_leak), &opts);
+	if (!ASSERT_OK(ret, "test_percpu_htab_leak run"))
+		goto out_skel;
+	if (!ASSERT_OK(opts.retval, "test_percpu_htab_leak retval"))
+		goto out_skel;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_percpu_hash_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "percpu_htab refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	map_kptr_race__destroy(skel);
+}
+
+static void test_sk_ls_leak(void)
+{
+	struct map_kptr_race *skel, *watcher;
+	int listen_fd = -1, client_fd = -1, map_id;
+
+	skel = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (!ASSERT_OK(map_kptr_race__attach(skel), "attach"))
+		goto out_skel;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(listen_fd, 0, "start_server"))
+		goto out_skel;
+
+	client_fd = connect_to_fd(listen_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto out_skel;
+
+	if (!ASSERT_EQ(skel->bss->sk_ls_leak_done, 1, "sk_ls_leak_done"))
+		goto out_skel;
+
+	close(client_fd);
+	client_fd = -1;
+	close(listen_fd);
+	listen_fd = -1;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_sk_ls_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.sk_map_free = bpf_program__attach(watcher->progs.sk_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.sk_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "sk_ls refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	if (client_fd >= 0)
+		close(client_fd);
+	if (listen_fd >= 0)
+		close(listen_fd);
+	map_kptr_race__destroy(skel);
+}
+
+void serial_test_map_kptr_race(void)
+{
+	if (test__start_subtest("htab_leak"))
+		test_htab_leak();
+	if (test__start_subtest("percpu_htab_leak"))
+		test_percpu_htab_leak();
+	if (test__start_subtest("sk_ls_leak"))
+		test_sk_ls_leak();
+}
diff --git a/tools/testing/selftests/bpf/progs/map_kptr_race.c b/tools/testing/selftests/bpf/progs/map_kptr_race.c
new file mode 100644
index 000000000000..f6f136cd8f60
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_kptr_race.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+struct map_value {
+	struct prog_test_ref_kfunc __kptr *ref_ptr;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} race_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} race_percpu_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} race_sk_ls_map SEC(".maps");
+
+int num_of_refs;
+int sk_ls_leak_done;
+int target_map_id;
+int map_freed;
+const volatile int nr_cpus;
+
+SEC("tc")
+int test_htab_leak(struct __sk_buff *skb)
+{
+	struct prog_test_ref_kfunc *p, *old;
+	struct map_value val = {};
+	struct map_value *v;
+	int key = 0;
+
+	if (bpf_map_update_elem(&race_hash_map, &key, &val, BPF_ANY))
+		return 1;
+
+	v = bpf_map_lookup_elem(&race_hash_map, &key);
+	if (!v)
+		return 2;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 3;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	bpf_map_delete_elem(&race_hash_map, &key);
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 4;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	return 0;
+}
+
+static int fill_percpu_kptr(struct map_value *v)
+{
+	struct prog_test_ref_kfunc *p, *old;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 1;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+	return 0;
+}
+
+SEC("tc")
+int test_percpu_htab_leak(struct __sk_buff *skb)
+{
+	struct map_value *v, *arr[16] = {};
+	struct map_value val = {};
+	int key = 0;
+	int err = 0;
+
+	if (bpf_map_update_elem(&race_percpu_hash_map, &key, &val, BPF_ANY))
+		return 1;
+
+	for (int i = 0; i < nr_cpus; i++) {
+		v = bpf_map_lookup_percpu_elem(&race_percpu_hash_map, &key, i);
+		if (!v)
+			return 2;
+		arr[i] = v;
+	}
+
+	bpf_map_delete_elem(&race_percpu_hash_map, &key);
+
+	for (int i = 0; i < nr_cpus; i++) {
+		v = arr[i];
+		err = fill_percpu_kptr(v);
+		if (err)
+			return 3;
+	}
+
+	return 0;
+}
+
+SEC("tp_btf/inet_sock_set_state")
+int BPF_PROG(test_sk_ls_leak, struct sock *sk, int oldstate, int newstate)
+{
+	struct prog_test_ref_kfunc *p, *old;
+	struct map_value *v;
+
+	if (newstate != BPF_TCP_SYN_SENT)
+		return 0;
+
+	if (sk_ls_leak_done)
+		return 0;
+
+	v = bpf_sk_storage_get(&race_sk_ls_map, sk, NULL,
+				BPF_SK_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 0;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	bpf_sk_storage_delete(&race_sk_ls_map, sk);
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 0;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	sk_ls_leak_done = 1;
+	return 0;
+}
+
+long target_map_ptr;
+
+SEC("fentry/bpf_map_put")
+int BPF_PROG(map_put, struct bpf_map *map)
+{
+	if (target_map_id && map->id == (u32)target_map_id)
+		target_map_ptr = (long)map;
+	return 0;
+}
+
+SEC("fexit/htab_map_free")
+int BPF_PROG(htab_map_free, struct bpf_map *map)
+{
+	if (target_map_ptr && (long)map == target_map_ptr)
+		map_freed = 1;
+	return 0;
+}
+
+SEC("fexit/bpf_sk_storage_map_free")
+int BPF_PROG(sk_map_free, struct bpf_map *map)
+{
+	if (target_map_ptr && (long)map == target_map_ptr)
+		map_freed = 1;
+	return 0;
+}
+
+SEC("syscall")
+int count_ref(void *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long arg = 0;
+
+	p = bpf_kfunc_call_test_acquire(&arg);
+	if (!p)
+		return 1;
+
+	num_of_refs = p->cnt.refs.counter;
+
+	bpf_kfunc_call_test_release(p);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

From 869c63d5975d55e97f6b168e885452b3da20ea47 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:14:55 +0800
Subject: [PATCH 0568/1303] bpf: Fix race in cpumap on PREEMPT_RT

On PREEMPT_RT kernels, the per-CPU xdp_bulk_queue (bq) can be accessed
concurrently by multiple preemptible tasks on the same CPU.

The original code assumes bq_enqueue() and __cpu_map_flush() run
atomically with respect to each other on the same CPU, relying on
local_bh_disable() to prevent preemption. However, on PREEMPT_RT,
local_bh_disable() only calls migrate_disable() (when
PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable
preemption, which allows CFS scheduling to preempt a task during
bq_flush_to_queue(), enabling another task on the same CPU to enter
bq_enqueue() and operate on the same per-CPU bq concurrently.

This leads to several races:

1. Double __list_del_clearprev(): after bq->count is reset in
   bq_flush_to_queue(), a preempting task can call bq_enqueue() ->
   bq_flush_to_queue() on the same bq when bq->count reaches
   CPU_MAP_BULK_SIZE. Both tasks then call __list_del_clearprev()
   on the same bq->flush_node, the second call dereferences the
   prev pointer that was already set to NULL by the first.

2. bq->count and bq->q[] races: concurrent bq_enqueue() can corrupt
   the packet queue while bq_flush_to_queue() is processing it.

The race between task A (__cpu_map_flush -> bq_flush_to_queue) and
task B (bq_enqueue -> bq_flush_to_queue) on the same CPU:

  Task A (xdp_do_flush)          Task B (cpu_map_enqueue)
  ----------------------         ------------------------
  bq_flush_to_queue(bq)
    spin_lock(&q->producer_lock)
    /* flush bq->q[] to ptr_ring */
    bq->count = 0
    spin_unlock(&q->producer_lock)
                                   bq_enqueue(rcpu, xdpf)
    <-- CFS preempts Task A -->      bq->q[bq->count++] = xdpf
                                     /* ... more enqueues until full ... */
                                     bq_flush_to_queue(bq)
                                       spin_lock(&q->producer_lock)
                                       /* flush to ptr_ring */
                                       spin_unlock(&q->producer_lock)
                                       __list_del_clearprev(flush_node)
                                         /* sets flush_node.prev = NULL */
    <-- Task A resumes -->
    __list_del_clearprev(flush_node)
      flush_node.prev->next = ...
      /* prev is NULL -> kernel oops */

Fix this by adding a local_lock_t to xdp_bulk_queue and acquiring it
in bq_enqueue() and __cpu_map_flush(). These paths already run under
local_bh_disable(), so use local_lock_nested_bh() which on non-RT is
a pure annotation with no overhead, and on PREEMPT_RT provides a
per-CPU sleeping lock that serializes access to the bq.

To reproduce, insert an mdelay(100) between bq->count = 0 and
__list_del_clearprev() in bq_flush_to_queue(), then run reproducer
provided by syzkaller.

Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Reported-by: syzbot+2b3391f44313b3983e91@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69369331.a70a0220.38f243.009d.GAE@google.com/T/
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://lore.kernel.org/r/20260225121459.183121-2-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cpumap.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 04171fbc39cb..32b43cb9061b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -29,6 +29,7 @@
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/local_lock.h>
 #include <linux/completion.h>
 #include <trace/events/xdp.h>
 #include <linux/btf_ids.h>
@@ -52,6 +53,7 @@ struct xdp_bulk_queue {
 	struct list_head flush_node;
 	struct bpf_cpu_map_entry *obj;
 	unsigned int count;
+	local_lock_t bq_lock;
 };
 
 /* Struct for every remote "destination" CPU in map */
@@ -451,6 +453,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	for_each_possible_cpu(i) {
 		bq = per_cpu_ptr(rcpu->bulkq, i);
 		bq->obj = rcpu;
+		local_lock_init(&bq->bq_lock);
 	}
 
 	/* Alloc queue */
@@ -722,6 +725,8 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 	struct ptr_ring *q;
 	int i;
 
+	lockdep_assert_held(&bq->bq_lock);
+
 	if (unlikely(!bq->count))
 		return;
 
@@ -749,11 +754,15 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 }
 
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+ * Thus, safe percpu variable access. PREEMPT_RT relies on
+ * local_lock_nested_bh() to serialise access to the per-CPU bq.
  */
 static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 {
-	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+	struct xdp_bulk_queue *bq;
+
+	local_lock_nested_bh(&rcpu->bulkq->bq_lock);
+	bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
 		bq_flush_to_queue(bq);
@@ -774,6 +783,8 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 
 		list_add(&bq->flush_node, flush_list);
 	}
+
+	local_unlock_nested_bh(&rcpu->bulkq->bq_lock);
 }
 
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
@@ -810,7 +821,9 @@ void __cpu_map_flush(struct list_head *flush_list)
 	struct xdp_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
+		local_lock_nested_bh(&bq->obj->bulkq->bq_lock);
 		bq_flush_to_queue(bq);
+		local_unlock_nested_bh(&bq->obj->bulkq->bq_lock);
 
 		/* If already running, costs spin_lock_irqsave + smb_mb */
 		wake_up_process(bq->obj->kthread);

From 1872e75375c40add4a35990de3be77b5741c252c Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:14:56 +0800
Subject: [PATCH 0569/1303] bpf: Fix race in devmap on PREEMPT_RT

On PREEMPT_RT kernels, the per-CPU xdp_dev_bulk_queue (bq) can be
accessed concurrently by multiple preemptible tasks on the same CPU.

The original code assumes bq_enqueue() and __dev_flush() run atomically
with respect to each other on the same CPU, relying on
local_bh_disable() to prevent preemption. However, on PREEMPT_RT,
local_bh_disable() only calls migrate_disable() (when
PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable
preemption, which allows CFS scheduling to preempt a task during
bq_xmit_all(), enabling another task on the same CPU to enter
bq_enqueue() and operate on the same per-CPU bq concurrently.

This leads to several races:

1. Double-free / use-after-free on bq->q[]: bq_xmit_all() snapshots
   cnt = bq->count, then iterates bq->q[0..cnt-1] to transmit frames.
   If preempted after the snapshot, a second task can call bq_enqueue()
   -> bq_xmit_all() on the same bq, transmitting (and freeing) the
   same frames. When the first task resumes, it operates on stale
   pointers in bq->q[], causing use-after-free.

2. bq->count and bq->q[] corruption: concurrent bq_enqueue() modifying
   bq->count and bq->q[] while bq_xmit_all() is reading them.

3. dev_rx/xdp_prog teardown race: __dev_flush() clears bq->dev_rx and
   bq->xdp_prog after bq_xmit_all(). If preempted between
   bq_xmit_all() return and bq->dev_rx = NULL, a preempting
   bq_enqueue() sees dev_rx still set (non-NULL), skips adding bq to
   the flush_list, and enqueues a frame. When __dev_flush() resumes,
   it clears dev_rx and removes bq from the flush_list, orphaning the
   newly enqueued frame.

4. __list_del_clearprev() on flush_node: similar to the cpumap race,
   both tasks can call __list_del_clearprev() on the same flush_node,
   the second dereferences the prev pointer already set to NULL.

The race between task A (__dev_flush -> bq_xmit_all) and task B
(bq_enqueue -> bq_xmit_all) on the same CPU:

  Task A (xdp_do_flush)          Task B (ndo_xdp_xmit redirect)
  ----------------------         --------------------------------
  __dev_flush(flush_list)
    bq_xmit_all(bq)
      cnt = bq->count  /* e.g. 16 */
      /* start iterating bq->q[] */
    <-- CFS preempts Task A -->
                                   bq_enqueue(dev, xdpf)
                                     bq->count == DEV_MAP_BULK_SIZE
                                     bq_xmit_all(bq, 0)
                                       cnt = bq->count  /* same 16! */
                                       ndo_xdp_xmit(bq->q[])
                                       /* frames freed by driver */
                                       bq->count = 0
    <-- Task A resumes -->
      ndo_xdp_xmit(bq->q[])
      /* use-after-free: frames already freed! */

Fix this by adding a local_lock_t to xdp_dev_bulk_queue and acquiring
it in bq_enqueue() and __dev_flush(). These paths already run under
local_bh_disable(), so use local_lock_nested_bh() which on non-RT is
a pure annotation with no overhead, and on PREEMPT_RT provides a
per-CPU sleeping lock that serializes access to the bq.

Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://lore.kernel.org/r/20260225121459.183121-3-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/devmap.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2984e938f94d..3d619d01088e 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -45,6 +45,7 @@
  * types of devmap; only the lookup and insertion is different.
  */
 #include <linux/bpf.h>
+#include <linux/local_lock.h>
 #include <net/xdp.h>
 #include <linux/filter.h>
 #include <trace/events/xdp.h>
@@ -60,6 +61,7 @@ struct xdp_dev_bulk_queue {
 	struct net_device *dev_rx;
 	struct bpf_prog *xdp_prog;
 	unsigned int count;
+	local_lock_t bq_lock;
 };
 
 struct bpf_dtab_netdev {
@@ -381,6 +383,8 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 	int to_send = cnt;
 	int i;
 
+	lockdep_assert_held(&bq->bq_lock);
+
 	if (unlikely(!cnt))
 		return;
 
@@ -425,10 +429,12 @@ void __dev_flush(struct list_head *flush_list)
 	struct xdp_dev_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
+		local_lock_nested_bh(&bq->dev->xdp_bulkq->bq_lock);
 		bq_xmit_all(bq, XDP_XMIT_FLUSH);
 		bq->dev_rx = NULL;
 		bq->xdp_prog = NULL;
 		__list_del_clearprev(&bq->flush_node);
+		local_unlock_nested_bh(&bq->dev->xdp_bulkq->bq_lock);
 	}
 }
 
@@ -451,12 +457,16 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 
 /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
  * variable access, and map elements stick around. See comment above
- * xdp_do_flush() in filter.c.
+ * xdp_do_flush() in filter.c. PREEMPT_RT relies on local_lock_nested_bh()
+ * to serialise access to the per-CPU bq.
  */
 static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)
 {
-	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
+	struct xdp_dev_bulk_queue *bq;
+
+	local_lock_nested_bh(&dev->xdp_bulkq->bq_lock);
+	bq = this_cpu_ptr(dev->xdp_bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
 		bq_xmit_all(bq, 0);
@@ -477,6 +487,8 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 	}
 
 	bq->q[bq->count++] = xdpf;
+
+	local_unlock_nested_bh(&dev->xdp_bulkq->bq_lock);
 }
 
 static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
@@ -1127,8 +1139,13 @@ static int dev_map_notification(struct notifier_block *notifier,
 		if (!netdev->xdp_bulkq)
 			return NOTIFY_BAD;
 
-		for_each_possible_cpu(cpu)
-			per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
+		for_each_possible_cpu(cpu) {
+			struct xdp_dev_bulk_queue *bq;
+
+			bq = per_cpu_ptr(netdev->xdp_bulkq, cpu);
+			bq->dev = netdev;
+			local_lock_init(&bq->bq_lock);
+		}
 		break;
 	case NETDEV_UNREGISTER:
 		/* This rcu_read_lock/unlock pair is needed because

From 62413a9c3cb183afb9bb6e94dd68caf4e4145f4c Mon Sep 17 00:00:00 2001
From: Paul Moses <p@1g4.org>
Date: Mon, 23 Feb 2026 15:05:44 +0000
Subject: [PATCH 0570/1303] net/sched: act_gate: snapshot parameters with RCU
 on replace

The gate action can be replaced while the hrtimer callback or dump path is
walking the schedule list.

Convert the parameters to an RCU-protected snapshot and swap updates under
tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits
the entry list, preserve the existing schedule so the effective state is
unchanged.

Fixes: a51c328df310 ("net: qos: introduce a gate control flow action")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moses <p@1g4.org>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260223150512.2251594-2-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tc_act/tc_gate.h |  33 ++++-
 net/sched/act_gate.c         | 267 ++++++++++++++++++++++++-----------
 2 files changed, 213 insertions(+), 87 deletions(-)

diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h
index b147a3bb1a46..e0fded18e18c 100644
--- a/include/net/tc_act/tc_gate.h
+++ b/include/net/tc_act/tc_gate.h
@@ -32,6 +32,7 @@ struct tcf_gate_params {
 	s32			tcfg_clockid;
 	size_t			num_entries;
 	struct list_head	entries;
+	struct rcu_head		rcu;
 };
 
 #define GATE_ACT_GATE_OPEN	BIT(0)
@@ -39,7 +40,7 @@ struct tcf_gate_params {
 
 struct tcf_gate {
 	struct tc_action	common;
-	struct tcf_gate_params	param;
+	struct tcf_gate_params __rcu *param;
 	u8			current_gate_status;
 	ktime_t			current_close_time;
 	u32			current_entry_octets;
@@ -51,47 +52,65 @@ struct tcf_gate {
 
 #define to_gate(a) ((struct tcf_gate *)a)
 
+static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a)
+{
+	struct tcf_gate *gact = to_gate(a);
+
+	return rcu_dereference_protected(gact->param,
+					 lockdep_is_held(&gact->tcf_lock));
+}
+
 static inline s32 tcf_gate_prio(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	s32 tcfg_prio;
 
-	tcfg_prio = to_gate(a)->param.tcfg_priority;
+	p = tcf_gate_params_locked(a);
+	tcfg_prio = p->tcfg_priority;
 
 	return tcfg_prio;
 }
 
 static inline u64 tcf_gate_basetime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_basetime;
 
-	tcfg_basetime = to_gate(a)->param.tcfg_basetime;
+	p = tcf_gate_params_locked(a);
+	tcfg_basetime = p->tcfg_basetime;
 
 	return tcfg_basetime;
 }
 
 static inline u64 tcf_gate_cycletime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletime;
 
-	tcfg_cycletime = to_gate(a)->param.tcfg_cycletime;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletime = p->tcfg_cycletime;
 
 	return tcfg_cycletime;
 }
 
 static inline u64 tcf_gate_cycletimeext(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletimeext;
 
-	tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletimeext = p->tcfg_cycletime_ext;
 
 	return tcfg_cycletimeext;
 }
 
 static inline u32 tcf_gate_num_entries(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u32 num_entries;
 
-	num_entries = to_gate(a)->param.num_entries;
+	p = tcf_gate_params_locked(a);
+	num_entries = p->num_entries;
 
 	return num_entries;
 }
@@ -105,7 +124,7 @@ static inline struct action_gate_entry
 	u32 num_entries;
 	int i = 0;
 
-	p = &to_gate(a)->param;
+	p = tcf_gate_params_locked(a);
 	num_entries = p->num_entries;
 
 	list_for_each_entry(entry, &p->entries, list)
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 686eaed81b81..fdbfcaa3e2ab 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact)
 	return KTIME_MAX;
 }
 
-static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
+static void tcf_gate_params_free_rcu(struct rcu_head *head);
+
+static void gate_get_start_time(struct tcf_gate *gact,
+				const struct tcf_gate_params *param,
+				ktime_t *start)
 {
-	struct tcf_gate_params *param = &gact->param;
 	ktime_t now, base, cycle;
 	u64 n;
 
@@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer)
 {
 	struct tcf_gate *gact = container_of(timer, struct tcf_gate,
 					     hitimer);
-	struct tcf_gate_params *p = &gact->param;
 	struct tcfg_gate_entry *next;
+	struct tcf_gate_params *p;
 	ktime_t close_time, now;
 
 	spin_lock(&gact->tcf_lock);
 
+	p = rcu_dereference_protected(gact->param,
+				      lockdep_is_held(&gact->tcf_lock));
 	next = gact->next_entry;
 
 	/* cycle start, clear pending bit, clear total octets */
@@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries)
 	}
 }
 
+static int tcf_gate_copy_entries(struct tcf_gate_params *dst,
+				 const struct tcf_gate_params *src,
+				 struct netlink_ext_ack *extack)
+{
+	struct tcfg_gate_entry *entry;
+	int i = 0;
+
+	list_for_each_entry(entry, &src->entries, list) {
+		struct tcfg_gate_entry *new;
+
+		new = kzalloc(sizeof(*new), GFP_ATOMIC);
+		if (!new) {
+			NL_SET_ERR_MSG(extack, "Not enough memory for entry");
+			return -ENOMEM;
+		}
+
+		new->index      = entry->index;
+		new->gate_state = entry->gate_state;
+		new->interval   = entry->interval;
+		new->ipv        = entry->ipv;
+		new->maxoctets  = entry->maxoctets;
+		list_add_tail(&new->list, &dst->entries);
+		i++;
+	}
+
+	dst->num_entries = i;
+	return 0;
+}
+
 static int parse_gate_list(struct nlattr *list_attr,
 			   struct tcf_gate_params *sched,
 			   struct netlink_ext_ack *extack)
@@ -270,24 +304,44 @@ static int parse_gate_list(struct nlattr *list_attr,
 	return err;
 }
 
-static void gate_setup_timer(struct tcf_gate *gact, u64 basetime,
-			     enum tk_offsets tko, s32 clockid,
-			     bool do_init)
+static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime,
+				    enum tk_offsets tko,
+				    enum tk_offsets old_tko,
+				    s32 clockid, s32 old_clockid)
 {
-	if (!do_init) {
-		if (basetime == gact->param.tcfg_basetime &&
-		    tko == gact->tk_offset &&
-		    clockid == gact->param.tcfg_clockid)
-			return;
+	return basetime != old_basetime ||
+	       clockid != old_clockid ||
+	       tko != old_tko;
+}
 
-		spin_unlock_bh(&gact->tcf_lock);
-		hrtimer_cancel(&gact->hitimer);
-		spin_lock_bh(&gact->tcf_lock);
+static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko,
+			      struct netlink_ext_ack *extack)
+{
+	switch (clockid) {
+	case CLOCK_REALTIME:
+		*tko = TK_OFFS_REAL;
+		return 0;
+	case CLOCK_MONOTONIC:
+		*tko = TK_OFFS_MAX;
+		return 0;
+	case CLOCK_BOOTTIME:
+		*tko = TK_OFFS_BOOT;
+		return 0;
+	case CLOCK_TAI:
+		*tko = TK_OFFS_TAI;
+		return 0;
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
+		return -EINVAL;
 	}
-	gact->param.tcfg_basetime = basetime;
-	gact->param.tcfg_clockid = clockid;
-	gact->tk_offset = tko;
-	hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT);
+}
+
+static void gate_setup_timer(struct tcf_gate *gact, s32 clockid,
+			     enum tk_offsets tko)
+{
+	WRITE_ONCE(gact->tk_offset, tko);
+	hrtimer_setup(&gact->hitimer, gate_timer_func, clockid,
+		      HRTIMER_MODE_ABS_SOFT);
 }
 
 static int tcf_gate_init(struct net *net, struct nlattr *nla,
@@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id);
-	enum tk_offsets tk_offset = TK_OFFS_TAI;
+	u64 cycletime = 0, basetime = 0, cycletime_ext = 0;
+	struct tcf_gate_params *p = NULL, *old_p = NULL;
+	enum tk_offsets old_tk_offset = TK_OFFS_TAI;
+	const struct tcf_gate_params *cur_p = NULL;
 	bool bind = flags & TCA_ACT_FLAGS_BIND;
 	struct nlattr *tb[TCA_GATE_MAX + 1];
+	enum tk_offsets tko = TK_OFFS_TAI;
 	struct tcf_chain *goto_ch = NULL;
-	u64 cycletime = 0, basetime = 0;
-	struct tcf_gate_params *p;
+	s32 timer_clockid = CLOCK_TAI;
+	bool use_old_entries = false;
+	s32 old_clockid = CLOCK_TAI;
+	bool need_cancel = false;
 	s32 clockid = CLOCK_TAI;
 	struct tcf_gate *gact;
 	struct tc_gate *parm;
+	u64 old_basetime = 0;
 	int ret = 0, err;
 	u32 gflags = 0;
 	s32 prio = -1;
@@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_GATE_PARMS])
 		return -EINVAL;
 
-	if (tb[TCA_GATE_CLOCKID]) {
+	if (tb[TCA_GATE_CLOCKID])
 		clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]);
-		switch (clockid) {
-		case CLOCK_REALTIME:
-			tk_offset = TK_OFFS_REAL;
-			break;
-		case CLOCK_MONOTONIC:
-			tk_offset = TK_OFFS_MAX;
-			break;
-		case CLOCK_BOOTTIME:
-			tk_offset = TK_OFFS_BOOT;
-			break;
-		case CLOCK_TAI:
-			tk_offset = TK_OFFS_TAI;
-			break;
-		default:
-			NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
-			return -EINVAL;
-		}
-	}
 
 	parm = nla_data(tb[TCA_GATE_PARMS]);
 	index = parm->index;
@@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		return -EEXIST;
 	}
 
+	gact = to_gate(*a);
+
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p) {
+		err = -ENOMEM;
+		goto chain_put;
+	}
+	INIT_LIST_HEAD(&p->entries);
+
+	use_old_entries = !tb[TCA_GATE_ENTRY_LIST];
+	if (!use_old_entries) {
+		err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
+		if (err < 0)
+			goto err_free;
+		use_old_entries = !err;
+	}
+
+	if (ret == ACT_P_CREATED && use_old_entries) {
+		NL_SET_ERR_MSG(extack, "The entry list is empty");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	if (ret != ACT_P_CREATED) {
+		rcu_read_lock();
+		cur_p = rcu_dereference(gact->param);
+
+		old_basetime  = cur_p->tcfg_basetime;
+		old_clockid   = cur_p->tcfg_clockid;
+		old_tk_offset = READ_ONCE(gact->tk_offset);
+
+		basetime      = old_basetime;
+		cycletime_ext = cur_p->tcfg_cycletime_ext;
+		prio          = cur_p->tcfg_priority;
+		gflags        = cur_p->tcfg_flags;
+
+		if (!tb[TCA_GATE_CLOCKID])
+			clockid = old_clockid;
+
+		err = 0;
+		if (use_old_entries) {
+			err = tcf_gate_copy_entries(p, cur_p, extack);
+			if (!err && !tb[TCA_GATE_CYCLE_TIME])
+				cycletime = cur_p->tcfg_cycletime;
+		}
+		rcu_read_unlock();
+		if (err)
+			goto err_free;
+	}
+
 	if (tb[TCA_GATE_PRIORITY])
 		prio = nla_get_s32(tb[TCA_GATE_PRIORITY]);
 
@@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GATE_FLAGS])
 		gflags = nla_get_u32(tb[TCA_GATE_FLAGS]);
 
-	gact = to_gate(*a);
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&gact->param.entries);
-
-	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
-	if (err < 0)
-		goto release_idr;
-
-	spin_lock_bh(&gact->tcf_lock);
-	p = &gact->param;
-
 	if (tb[TCA_GATE_CYCLE_TIME])
 		cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
 
-	if (tb[TCA_GATE_ENTRY_LIST]) {
-		err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
-		if (err < 0)
-			goto chain_put;
-	}
+	if (tb[TCA_GATE_CYCLE_TIME_EXT])
+		cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
+
+	err = gate_clock_resolve(clockid, &tko, extack);
+	if (err)
+		goto err_free;
+	timer_clockid = clockid;
+
+	need_cancel = ret != ACT_P_CREATED &&
+		      gate_timer_needs_cancel(basetime, old_basetime,
+					      tko, old_tk_offset,
+					      timer_clockid, old_clockid);
+
+	if (need_cancel)
+		hrtimer_cancel(&gact->hitimer);
+
+	spin_lock_bh(&gact->tcf_lock);
 
 	if (!cycletime) {
 		struct tcfg_gate_entry *entry;
@@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		list_for_each_entry(entry, &p->entries, list)
 			cycle = ktime_add_ns(cycle, entry->interval);
 		cycletime = cycle;
-		if (!cycletime) {
-			err = -EINVAL;
-			goto chain_put;
-		}
 	}
 	p->tcfg_cycletime = cycletime;
+	p->tcfg_cycletime_ext = cycletime_ext;
 
-	if (tb[TCA_GATE_CYCLE_TIME_EXT])
-		p->tcfg_cycletime_ext =
-			nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
-
-	gate_setup_timer(gact, basetime, tk_offset, clockid,
-			 ret == ACT_P_CREATED);
+	if (need_cancel || ret == ACT_P_CREATED)
+		gate_setup_timer(gact, timer_clockid, tko);
 	p->tcfg_priority = prio;
 	p->tcfg_flags = gflags;
-	gate_get_start_time(gact, &start);
+	p->tcfg_basetime = basetime;
+	p->tcfg_clockid = timer_clockid;
+	gate_get_start_time(gact, p, &start);
+
+	old_p = rcu_replace_pointer(gact->param, p,
+				    lockdep_is_held(&gact->tcf_lock));
 
 	gact->current_close_time = start;
 	gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING;
@@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 
+	if (old_p)
+		call_rcu(&old_p->rcu, tcf_gate_params_free_rcu);
+
 	return ret;
 
+err_free:
+	release_entry_list(&p->entries);
+	kfree(p);
 chain_put:
-	spin_unlock_bh(&gact->tcf_lock);
-
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 release_idr:
@@ -446,21 +546,29 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	 * without taking tcf_lock.
 	 */
 	if (ret == ACT_P_CREATED)
-		gate_setup_timer(gact, gact->param.tcfg_basetime,
-				 gact->tk_offset, gact->param.tcfg_clockid,
-				 true);
+		gate_setup_timer(gact, timer_clockid, tko);
+
 	tcf_idr_release(*a, bind);
 	return err;
 }
 
+static void tcf_gate_params_free_rcu(struct rcu_head *head)
+{
+	struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu);
+
+	release_entry_list(&p->entries);
+	kfree(p);
+}
+
 static void tcf_gate_cleanup(struct tc_action *a)
 {
 	struct tcf_gate *gact = to_gate(a);
 	struct tcf_gate_params *p;
 
-	p = &gact->param;
 	hrtimer_cancel(&gact->hitimer);
-	release_entry_list(&p->entries);
+	p = rcu_dereference_protected(gact->param, 1);
+	if (p)
+		call_rcu(&p->rcu, tcf_gate_params_free_rcu);
 }
 
 static int dumping_entry(struct sk_buff *skb,
@@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a,
 	struct nlattr *entry_list;
 	struct tcf_t t;
 
-	spin_lock_bh(&gact->tcf_lock);
-	opt.action = gact->tcf_action;
-
-	p = &gact->param;
+	rcu_read_lock();
+	opt.action = READ_ONCE(gact->tcf_action);
+	p = rcu_dereference(gact->param);
 
 	if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
@@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &gact->tcf_tm);
 	if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD))
 		goto nla_put_failure;
-	spin_unlock_bh(&gact->tcf_lock);
+	rcu_read_unlock();
 
 	return skb->len;
 
 nla_put_failure:
-	spin_unlock_bh(&gact->tcf_lock);
+	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }

From 76e954155b45294c502e3d3a9e15757c858ca55e Mon Sep 17 00:00:00 2001
From: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Date: Fri, 27 Feb 2026 22:32:21 +0100
Subject: [PATCH 0571/1303] bpf: Introduce tnum_step to step through tnum's
 members

This commit introduces tnum_step(), a function that, when given t, and a
number z returns the smallest member of t larger than z. The number z
must be greater or equal to the smallest member of t and less than the
largest member of t.

The first step is to compute j, a number that keeps all of t's known
bits, and matches all unknown bits to z's bits. Since j is a member of
the t, it is already a candidate for result. However, we want our result
to be (minimally) greater than z.

There are only two possible cases:

(1) Case j <= z. In this case, we want to increase the value of j and
make it > z.
(2) Case j > z. In this case, we want to decrease the value of j while
keeping it > z.

(Case 1) j <= z

t = xx11x0x0
z = 10111101 (189)
j = 10111000 (184)
         ^
         k

(Case 1.1) Let's first consider the case where j < z. We will address j
== z later.

Since z > j, there had to be a bit position that was 1 in z and a 0 in
j, beyond which all positions of higher significance are equal in j and
z. Further, this position could not have been unknown in a, because the
unknown positions of a match z. This position had to be a 1 in z and
known 0 in t.

Let k be position of the most significant 1-to-0 flip. In our example, k
= 3 (starting the count at 1 at the least significant bit).  Setting (to
1) the unknown bits of t in positions of significance smaller than
k will not produce a result > z. Hence, we must set/unset the unknown
bits at positions of significance higher than k. Specifically, we look
for the next larger combination of 1s and 0s to place in those
positions, relative to the combination that exists in z. We can achieve
this by concatenating bits at unknown positions of t into an integer,
adding 1, and writing the bits of that result back into the
corresponding bit positions previously extracted from z.

>From our example, considering only positions of significance greater
than k:

t =  xx..x
z =  10..1
    +    1
     -----
     11..0

This is the exact combination 1s and 0s we need at the unknown bits of t
in positions of significance greater than k. Further, our result must
only increase the value minimally above z. Hence, unknown bits in
positions of significance smaller than k should remain 0. We finally
have,

result = 11110000 (240)

(Case 1.2) Now consider the case when j = z, for example

t = 1x1x0xxx
z = 10110100 (180)
j = 10110100 (180)

Matching the unknown bits of the t to the bits of z yielded exactly z.
To produce a number greater than z, we must set/unset the unknown bits
in t, and *all* the unknown bits of t candidates for being set/unset. We
can do this similar to Case 1.1, by adding 1 to the bits extracted from
the masked bit positions of z. Essentially, this case is equivalent to
Case 1.1, with k = 0.

t =  1x1x0xxx
z =  .0.1.100
    +       1
    ---------
     .0.1.101

This is the exact combination of bits needed in the unknown positions of
t. After recalling the known positions of t, we get

result = 10110101 (181)

(Case 2) j > z

t = x00010x1
z = 10000010 (130)
j = 10001011 (139)
	^
	k

Since j > z, there had to be a bit position which was 0 in z, and a 1 in
j, beyond which all positions of higher significance are equal in j and
z. This position had to be a 0 in z and known 1 in t. Let k be the
position of the most significant 0-to-1 flip. In our example, k = 4.

Because of the 0-to-1 flip at position k, a member of t can become
greater than z if the bits in positions greater than k are themselves >=
to z. To make that member *minimally* greater than z, the bits in
positions greater than k must be exactly = z. Hence, we simply match all
of t's unknown bits in positions more significant than k to z's bits. In
positions less significant than k, we set all t's unknown bits to 0
to retain minimality.

In our example, in positions of greater significance than k (=4),
t=x000. These positions are matched with z (1000) to produce 1000. In
positions of lower significance than k, t=10x1. All unknown bits are set
to 0 to produce 1001. The final result is:

result = 10001001 (137)

This concludes the computation for a result > z that is a member of t.

The procedure for tnum_step() in this commit implements the idea
described above. As a proof of correctness, we verified the algorithm
against a logical specification of tnum_step. The specification asserts
the following about the inputs t, z and output res that:

1. res is a member of t, and
2. res is strictly greater than z, and
3. there does not exist another value res2 such that
	3a. res2 is also a member of t, and
	3b. res2 is greater than z
	3c. res2 is smaller than res

We checked the implementation against this logical specification using
an SMT solver. The verification formula in SMTLIB format is available
at [1]. The verification returned an "unsat": indicating that no input
assignment exists for which the implementation and the specification
produce different outputs.

In addition, we also automatically generated the logical encoding of the
C implementation using Agni [2] and verified it against the same
specification. This verification also returned an "unsat", confirming
that the implementation is equivalent to the specification. The formula
for this check is also available at [3].

Link: https://pastebin.com/raw/2eRWbiit [1]
Link: https://github.com/bpfverif/agni [2]
Link: https://pastebin.com/raw/EztVbBJ2 [3]
Co-developed-by: Srinivas Narayana <srinivas.narayana@rutgers.edu>
Signed-off-by: Srinivas Narayana <srinivas.narayana@rutgers.edu>
Co-developed-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu>
Signed-off-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu>
Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Link: https://lore.kernel.org/r/93fdf71910411c0f19e282ba6d03b4c65f9c5d73.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/tnum.h |  3 +++
 kernel/bpf/tnum.c    | 56 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index fa4654ffb621..ca2cfec8de08 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a)
 	return !(tnum_subreg(a)).mask;
 }
 
+/* Returns the smallest member of t larger than z */
+u64 tnum_step(struct tnum t, u64 z);
+
 #endif /* _LINUX_TNUM_H */
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 26fbfbb01700..4abc359b3db0 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -269,3 +269,59 @@ struct tnum tnum_bswap64(struct tnum a)
 {
 	return TNUM(swab64(a.value), swab64(a.mask));
 }
+
+/* Given tnum t, and a number z such that tmin <= z < tmax, where tmin
+ * is the smallest member of the t (= t.value) and tmax is the largest
+ * member of t (= t.value | t.mask), returns the smallest member of t
+ * larger than z.
+ *
+ * For example,
+ * t      = x11100x0
+ * z      = 11110001 (241)
+ * result = 11110010 (242)
+ *
+ * Note: if this function is called with z >= tmax, it just returns
+ * early with tmax; if this function is called with z < tmin, the
+ * algorithm already returns tmin.
+ */
+u64 tnum_step(struct tnum t, u64 z)
+{
+	u64 tmax, j, p, q, r, s, v, u, w, res;
+	u8 k;
+
+	tmax = t.value | t.mask;
+
+	/* if z >= largest member of t, return largest member of t */
+	if (z >= tmax)
+		return tmax;
+
+	/* if z < smallest member of t, return smallest member of t */
+	if (z < t.value)
+		return t.value;
+
+	/* keep t's known bits, and match all unknown bits to z */
+	j = t.value | (z & t.mask);
+
+	if (j > z) {
+		p = ~z & t.value & ~t.mask;
+		k = fls64(p); /* k is the most-significant 0-to-1 flip */
+		q = U64_MAX << k;
+		r = q & z; /* positions > k matched to z */
+		s = ~q & t.value; /* positions <= k matched to t.value */
+		v = r | s;
+		res = v;
+	} else {
+		p = z & ~t.value & ~t.mask;
+		k = fls64(p); /* k is the most-significant 1-to-0 flip */
+		q = U64_MAX << k;
+		r = q & t.mask & z; /* unknown positions > k, matched to z */
+		s = q & ~t.mask; /* known positions > k, set to 1 */
+		v = r | s;
+		/* add 1 to unknown positions > k to make value greater than z */
+		u = v + (1ULL << k);
+		/* extract bits in unknown positions > k from u, rest from t.value */
+		w = (u & t.mask) | t.value;
+		res = w;
+	}
+	return res;
+}

From efc11a667878a1d655ff034a93a539debbfedb12 Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:35:02 +0100
Subject: [PATCH 0572/1303] bpf: Improve bounds when tnum has a single possible
 value

We're hitting an invariant violation in Cilium that sometimes leads to
BPF programs being rejected and Cilium failing to start [1]. The
following extract from verifier logs shows what's happening:

  from 201 to 236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0
  236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0
  ; if (magic == MARK_MAGIC_HOST || magic == MARK_MAGIC_OVERLAY || magic == MARK_MAGIC_ENCRYPT) @ bpf_host.c:1337
  236: (16) if w9 == 0xe00 goto pc+45   ; R9=scalar(smin=umin=smin32=umin32=3585,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100))
  237: (16) if w9 == 0xf00 goto pc+1
  verifier bug: REG INVARIANTS VIOLATION (false_reg1): range bounds violation u64=[0xe01, 0xe00] s64=[0xe01, 0xe00] u32=[0xe01, 0xe00] s32=[0xe01, 0xe00] var_off=(0xe00, 0x0)

We reach instruction 236 with two possible values for R9, 0xe00 and
0xf00. This is perfectly reflected in the tnum, but of course the ranges
are less accurate and cover [0xe00; 0xf00]. Taking the fallthrough path
at instruction 236 allows the verifier to reduce the range to
[0xe01; 0xf00]. The tnum is however not updated.

With these ranges, at instruction 237, the verifier is not able to
deduce that R9 is always equal to 0xf00. Hence the fallthrough pass is
explored first, the verifier refines the bounds using the assumption
that R9 != 0xf00, and ends up with an invariant violation.

This pattern of impossible branch + bounds refinement is common to all
invariant violations seen so far. The long-term solution is likely to
rely on the refinement + invariant violation check to detect dead
branches, as started by Eduard. To fix the current issue, we need
something with less refactoring that we can backport.

This patch uses the tnum_step helper introduced in the previous patch to
detect the above situation. In particular, three cases are now detected
in the bounds refinement:

1. The u64 range and the tnum only overlap in umin.
   u64:  ---[xxxxxx]-----
   tnum: --xx----------x-

2. The u64 range and the tnum only overlap in the maximum value
   represented by the tnum, called tmax.
   u64:  ---[xxxxxx]-----
   tnum: xx-----x--------

3. The u64 range and the tnum only overlap in between umin (excluded)
   and umax.
   u64:  ---[xxxxxx]-----
   tnum: xx----x-------x-

To detect these three cases, we call tnum_step(tnum, umin), which
returns the smallest member of the tnum greater than umin, called
tnum_next here. We're in case (1) if umin is part of the tnum and
tnum_next is greater than umax. We're in case (2) if umin is not part of
the tnum and tnum_next is equal to tmax. Finally, we're in case (3) if
umin is not part of the tnum, tnum_next is inferior or equal to umax,
and calling tnum_step a second time gives us a value past umax.

This change implements these three cases. With it, the above bytecode
looks as follows:

  0: (85) call bpf_get_prandom_u32#7    ; R0=scalar()
  1: (47) r0 |= 3584                    ; R0=scalar(smin=0x8000000000000e00,umin=umin32=3584,smin32=0x80000e00,var_off=(0xe00; 0xfffffffffffff1ff))
  2: (57) r0 &= 3840                    ; R0=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100))
  3: (15) if r0 == 0xe00 goto pc+2      ; R0=3840
  4: (15) if r0 == 0xf00 goto pc+1
  4: R0=3840
  6: (95) exit

In addition to the new selftests, this change was also verified with
Agni [3]. For the record, the raw SMT is available at [4]. The property
it verifies is that: If a concrete value x is contained in all input
abstract values, after __update_reg_bounds, it will continue to be
contained in all output abstract values.

Link: https://github.com/cilium/cilium/issues/44216 [1]
Link: https://pchaigno.github.io/test-verifier-complexity.html [2]
Link: https://github.com/bpfverif/agni [3]
Link: https://pastebin.com/raw/naCfaqNx [4]
Fixes: 0df1a55afa83 ("bpf: Warn on internal verifier errors")
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Tested-by: Marco Schirrmeister <mschirrmeister@gmail.com>
Co-developed-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/ef254c4f68be19bd393d450188946821c588565d.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb12ba020649..401d6c4960ec 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2379,6 +2379,9 @@ static void __update_reg32_bounds(struct bpf_reg_state *reg)
 
 static void __update_reg64_bounds(struct bpf_reg_state *reg)
 {
+	u64 tnum_next, tmax;
+	bool umin_in_tnum;
+
 	/* min signed is max(sign bit) | min(other bits) */
 	reg->smin_value = max_t(s64, reg->smin_value,
 				reg->var_off.value | (reg->var_off.mask & S64_MIN));
@@ -2388,6 +2391,33 @@ static void __update_reg64_bounds(struct bpf_reg_state *reg)
 	reg->umin_value = max(reg->umin_value, reg->var_off.value);
 	reg->umax_value = min(reg->umax_value,
 			      reg->var_off.value | reg->var_off.mask);
+
+	/* Check if u64 and tnum overlap in a single value */
+	tnum_next = tnum_step(reg->var_off, reg->umin_value);
+	umin_in_tnum = (reg->umin_value & ~reg->var_off.mask) == reg->var_off.value;
+	tmax = reg->var_off.value | reg->var_off.mask;
+	if (umin_in_tnum && tnum_next > reg->umax_value) {
+		/* The u64 range and the tnum only overlap in umin.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: --xx----------x-
+		 */
+		___mark_reg_known(reg, reg->umin_value);
+	} else if (!umin_in_tnum && tnum_next == tmax) {
+		/* The u64 range and the tnum only overlap in the maximum value
+		 * represented by the tnum, called tmax.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: xx-----x--------
+		 */
+		___mark_reg_known(reg, tmax);
+	} else if (!umin_in_tnum && tnum_next <= reg->umax_value &&
+		   tnum_step(reg->var_off, tnum_next) > reg->umax_value) {
+		/* The u64 range and the tnum only overlap in between umin
+		 * (excluded) and umax.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: xx----x-------x-
+		 */
+		___mark_reg_known(reg, tnum_next);
+	}
 }
 
 static void __update_reg_bounds(struct bpf_reg_state *reg)

From e6ad477d1bf8829973cddd9accbafa9d1a6cd15a Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:36:30 +0100
Subject: [PATCH 0573/1303] selftests/bpf: Test refinement of single-value tnum

This patch introduces selftests to cover the new bounds refinement
logic introduced in the previous patch. Without the previous patch,
the first two tests fail because of the invariant violation they
trigger. The last test fails because the R10 access is not detected as
dead code. In addition, all three tests fail because of R0 having a
non-constant value in the verifier logs.

In addition, the last two cases are covering the negative cases: when we
shouldn't refine the bounds because the u64 and tnum overlap in at least
two values.

Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/90d880c8cf587b9f7dc715d8961cd1b8111d01a8.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/verifier_bounds.c     | 137 ++++++++++++++++++
 1 file changed, 137 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 560531404bce..97065a26cf70 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1863,4 +1863,141 @@ l1_%=:	r0 = 1;				\
 	: __clobber_all);
 }
 
+/* This test covers the bounds deduction when the u64 range and the tnum
+ * overlap only at umax. After instruction 3, the ranges look as follows:
+ *
+ * 0    umin=0xe01     umax=0xf00                              U64_MAX
+ * |    [xxxxxxxxxxxxxx]                                       |
+ * |----------------------------|------------------------------|
+ * |   x               x                                       | tnum values
+ *
+ * The verifier can therefore deduce that the R0=0xf0=240.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum on umax")
+__msg("3: (15) if r0 == 0xe0 {{.*}} R0=240")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void bounds_refinement_tnum_umax(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 |= 0xe0;			\
+	r0 &= 0xf0;			\
+	if r0 == 0xe0 goto +2;		\
+	if r0 == 0xf0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction when the u64 range and the tnum
+ * overlap only at umin. After instruction 3, the ranges look as follows:
+ *
+ * 0    umin=0xe00     umax=0xeff                              U64_MAX
+ * |    [xxxxxxxxxxxxxx]                                       |
+ * |----------------------------|------------------------------|
+ * |    x               x                                      | tnum values
+ *
+ * The verifier can therefore deduce that the R0=0xe0=224.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum on umin")
+__msg("3: (15) if r0 == 0xf0 {{.*}} R0=224")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void bounds_refinement_tnum_umin(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 |= 0xe0;			\
+	r0 &= 0xf0;			\
+	if r0 == 0xf0 goto +2;		\
+	if r0 == 0xe0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction when the only possible tnum value is
+ * in the middle of the u64 range. After instruction 3, the ranges look as
+ * follows:
+ *
+ * 0    umin=0x7cf   umax=0x7df                                U64_MAX
+ * |    [xxxxxxxxxxxx]                                         |
+ * |----------------------------|------------------------------|
+ * |     x            x            x            x            x | tnum values
+ *       |            +--- 0x7e0
+ *       +--- 0x7d0
+ *
+ * Since the lower four bits are zero, the tnum and the u64 range only overlap
+ * in R0=0x7d0=2000. Instruction 5 is therefore dead code.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum in middle of range")
+__msg("3: (a5) if r0 < 0x7cf {{.*}} R0=2000")
+__success __log_level(2)
+__naked void bounds_refinement_tnum_middle(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 & 0x0f goto +4;		\
+	if r0 > 0x7df goto +3;		\
+	if r0 < 0x7cf goto +2;		\
+	if r0 == 0x7d0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test cover the negative case for the tnum/u64 overlap. Since
+ * they contain the same two values (i.e., {0, 1}), we can't deduce
+ * anything more.
+ */
+SEC("socket")
+__description("bounds refinement: several overlaps between tnum and u64")
+__msg("2: (25) if r0 > 0x1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=1,var_off=(0x0; 0x1))")
+__failure __log_level(2)
+__naked void bounds_refinement_several_overlaps(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 < 0 goto +3;		\
+	if r0 > 1 goto +2;		\
+	if r0 == 1 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test cover the negative case for the tnum/u64 overlap. Since
+ * they overlap in the two values contained by the u64 range (i.e.,
+ * {0xf, 0x10}), we can't deduce anything more.
+ */
+SEC("socket")
+__description("bounds refinement: multiple overlaps between tnum and u64")
+__msg("2: (25) if r0 > 0x10 {{.*}} R0=scalar(smin=umin=smin32=umin32=15,smax=umax=smax32=umax32=16,var_off=(0x0; 0x1f))")
+__failure __log_level(2)
+__naked void bounds_refinement_multiple_overlaps(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 < 0xf goto +3;		\
+	if r0 > 0x10 goto +2;		\
+	if r0 == 0x10 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";

From 024cea2d647ed8ab942f19544b892d324dba42b4 Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:42:45 +0100
Subject: [PATCH 0574/1303] selftests/bpf: Avoid simplification of crafted
 bounds test

The reg_bounds_crafted tests validate the verifier's range analysis
logic. They focus on the actual ranges and thus ignore the tnum. As a
consequence, they carry the assumption that the tested cases can be
reproduced in userspace without using the tnum information.

Unfortunately, the previous change the refinement logic breaks that
assumption for one test case:

  (u64)2147483648 (u32)<op> [4294967294; 0x100000000]

The tested bytecode is shown below. Without our previous improvement, on
the false branch of the condition, R7 is only known to have u64 range
[0xfffffffe; 0x100000000]. With our improvement, and using the tnum
information, we can deduce that R7 equals 0x100000000.

  19: (bc) w0 = w6                ; R6=0x80000000
  20: (bc) w0 = w7                ; R7=scalar(smin=umin=0xfffffffe,smax=umax=0x100000000,smin32=-2,smax32=0,var_off=(0x0; 0x1ffffffff))
  21: (be) if w6 <= w7 goto pc+3  ; R6=0x80000000 R7=0x100000000

R7's tnum is (0; 0x1ffffffff). On the false branch, regs_refine_cond_op
refines R7's u32 range to [0; 0x7fffffff]. Then, __reg32_deduce_bounds
refines the s32 range to 0 using u32 and finally also sets u32=0.
From this, __reg_bound_offset improves the tnum to (0; 0x100000000).
Finally, our previous patch uses this new tnum to deduce that it only
intersect with u64=[0xfffffffe; 0x100000000] in a single value:
0x100000000.

Because the verifier uses the tnum to reach this constant value, the
selftest is unable to reproduce it by only simulating ranges. The
solution implemented in this patch is to change the test case such that
there is more than one overlap value between u64 and the tnum. The max.
u64 value is thus changed from 0x100000000 to 0x300000000.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/50641c6a7ef39520595dcafa605692427c1006ec.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/reg_bounds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index d93a0c7b1786..0322f817d07b 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -2091,7 +2091,7 @@ static struct subtest_case crafted_cases[] = {
 	{U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}},
 
 	{U64, U32, {0, 0x100000000}, {0, 0}},
-	{U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}},
+	{U64, U32, {0xfffffffe, 0x300000000}, {0x80000000, 0x80000000}},
 
 	{U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}},
 	/* these are tricky cases where lower 32 bits allow to tighten 64

From 29252397bcc1e0a1f85e5c3bee59c325f5c26341 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 25 Feb 2026 20:35:45 +0000
Subject: [PATCH 0575/1303] inet: annotate data-races around isk->inet_num

UDP/TCP lookups are using RCU, thus isk->inet_num accesses
should use READ_ONCE() and WRITE_ONCE() where needed.

Fixes: 3ab5aee7fe84 ("net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260225203545.1512417-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet6_hashtables.h | 2 +-
 include/net/inet_hashtables.h  | 2 +-
 include/net/ip.h               | 2 +-
 net/ipv4/inet_hashtables.c     | 8 ++++----
 net/ipv4/tcp_diag.c            | 2 +-
 net/ipv6/inet6_hashtables.c    | 3 ++-
 6 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 282e29237d93..c16de5b7963f 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk,
 {
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_family != AF_INET6 ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
 	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 		return false;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ac05a52d9e13..5a979dcab538 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk,
 			      int dif, int sdif)
 {
 	if (!net_eq(sock_net(sk), net) ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    sk->sk_addrpair != cookie)
 	        return false;
 
diff --git a/include/net/ip.h b/include/net/ip.h
index 69d5cef46004..7f9abd457e01 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
-	ipcm->protocol = inet->inet_num;
+	ipcm->protocol = READ_ONCE(inet->inet_num);
 }
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index fca980772c81..9bfccc283fa6 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 		    struct inet_bind2_bucket *tb2, unsigned short port)
 {
-	inet_sk(sk)->inet_num = port;
+	WRITE_ONCE(inet_sk(sk)->inet_num, port);
 	inet_csk(sk)->icsk_bind_hash = tb;
 	inet_csk(sk)->icsk_bind2_hash = tb2;
 	sk_add_bind_node(sk, &tb2->owners);
@@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk)
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
 	inet_csk(sk)->icsk_bind_hash = NULL;
-	inet_sk(sk)->inet_num = 0;
+	WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 	sk->sk_userlocks &= ~SOCK_CONNECT_BIND;
 
 	spin_lock(&head2->lock);
@@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
+	if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum &&
 			!ipv6_only_sock(sk)) {
 		if (sk->sk_rcv_saddr != daddr)
 			return -1;
@@ -1206,7 +1206,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 		sk->sk_hash = 0;
 		inet_sk(sk)->inet_sport = 0;
-		inet_sk(sk)->inet_num = 0;
+		WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 
 		if (tw)
 			inet_twsk_bind_unhash(tw, hinfo);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index d83efd91f461..7935702e394b 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -509,7 +509,7 @@ static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
 				goto next_normal;
-			if (r->id.idiag_sport != htons(sk->sk_num) &&
+			if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) &&
 			    r->id.idiag_sport)
 				goto next_normal;
 			if (r->id.idiag_dport != sk->sk_dport &&
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 5e1da088d8e1..182d38e6d6d8 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
+	if (net_eq(sock_net(sk), net) &&
+	    READ_ONCE(inet_sk(sk)->inet_num) == hnum &&
 	    sk->sk_family == PF_INET6) {
 		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 			return -1;

From 0b3cd139be565b85f4a3579e376152b9def6256a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jonas=20K=C3=B6ppeler?= <j.koeppeler@tu-berlin.de>
Date: Thu, 26 Feb 2026 12:40:15 +0100
Subject: [PATCH 0576/1303] net/sched: sch_cake: avoid sync overhead when
 unlimited
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Skip inter-instance sync when no rate limit is configured, as it serves
no purpose and only adds overhead.

Fixes: 1bddd758bac2 ("net/sched: sch_cake: share shaper state across sub-instances of cake_mq")
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20260226-cake-mq-skip-sync-bandwidth-unlimited-v1-1-01830bb4db87@tu-berlin.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index a01f14b1c216..b23fc7d9fafe 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch)
 	u64 delay;
 	u32 len;
 
-	if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) {
+	if (q->config->is_shared && q->rate_ns &&
+	    now - q->last_checked_active >= q->config->sync_time) {
 		struct net_device *dev = qdisc_dev(sch);
 		struct cake_sched_data *other_priv;
 		u64 new_rate = q->config->rate_bps;

From 15c2715a52645fd8e6e18b7abc3449292d118c7c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jonas=20K=C3=B6ppeler?= <j.koeppeler@tu-berlin.de>
Date: Thu, 26 Feb 2026 12:40:16 +0100
Subject: [PATCH 0577/1303] net/sched: sch_cake: fixup cake_mq rate adjustment
 for diffserv config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cake_mq's rate adjustment during the sync periods did not adjust the
rates for every tin in a diffserv config. This lead to inconsistencies
of rates between the tins. Fix this by setting the rates for all tins
during synchronization.

Fixes: 1bddd758bac2 ("net/sched: sch_cake: share shaper state across sub-instances of cake_mq")
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20260226-cake-mq-skip-sync-bandwidth-unlimited-v1-2-01830bb4db87@tu-berlin.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 50 ++++++++++++++++++++------------------------
 1 file changed, 23 insertions(+), 27 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index b23fc7d9fafe..9efe23f8371b 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = {
 	1239850263, 1191209601, 1147878294, 1108955788
 };
 
-static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
-			  u64 target_ns, u64 rtt_est_ns);
+static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust);
+
 /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
  * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
  *
@@ -2040,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch)
 		if (num_active_qs > 1)
 			new_rate = div64_u64(q->config->rate_bps, num_active_qs);
 
-		/* mtu = 0 is used to only update the rate and not mess with cobalt params */
-		cake_set_rate(b, new_rate, 0, 0, 0);
+		cake_configure_rates(sch, new_rate, true);
 		q->last_checked_active = now;
 		q->active_queues = num_active_qs;
-		q->rate_ns = b->tin_rate_ns;
-		q->rate_shft = b->tin_rate_shft;
 	}
 
 begin:
@@ -2362,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
 	b->cparams.p_dec = 1 << 20; /* 1/4096 */
 }
 
-static int cake_config_besteffort(struct Qdisc *sch)
+static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct cake_tin_data *b = &q->tins[0];
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 
 	q->tin_cnt = 1;
 
@@ -2381,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_precedence(struct Qdisc *sch)
+static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 	/* convert high-level (user visible) parameters into internal format */
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 256;
 	u32 i;
 
@@ -2457,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch)
  *	Total 12 traffic classes.
  */
 
-static int cake_config_diffserv8(struct Qdisc *sch)
+static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*	Pruned list of traffic classes for typical applications:
  *
@@ -2474,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch)
  */
 
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 256;
 	u32 i;
 
@@ -2505,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_diffserv4(struct Qdisc *sch)
+static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*  Further pruned list of traffic classes for four-class system:
  *
@@ -2518,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch)
  */
 
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 1024;
 
 	q->tin_cnt = 4;
@@ -2547,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_diffserv3(struct Qdisc *sch)
+static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*  Simplified Diffserv structure with 3 tins.
  *		Latency Sensitive	(CS7, CS6, EF, VA, TOS4)
@@ -2555,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch)
  *		Low Priority		(LE, CS1)
  */
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 1024;
 
 	q->tin_cnt = 3;
@@ -2581,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch)
 	return 0;
 }
 
-static void cake_reconfigure(struct Qdisc *sch)
+static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust)
 {
+	u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch));
 	struct cake_sched_data *qd = qdisc_priv(sch);
 	struct cake_sched_config *q = qd->config;
 	int c, ft;
 
 	switch (q->tin_mode) {
 	case CAKE_DIFFSERV_BESTEFFORT:
-		ft = cake_config_besteffort(sch);
+		ft = cake_config_besteffort(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_PRECEDENCE:
-		ft = cake_config_precedence(sch);
+		ft = cake_config_precedence(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV8:
-		ft = cake_config_diffserv8(sch);
+		ft = cake_config_diffserv8(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV4:
-		ft = cake_config_diffserv4(sch);
+		ft = cake_config_diffserv4(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV3:
 	default:
-		ft = cake_config_diffserv3(sch);
+		ft = cake_config_diffserv3(sch, rate, mtu);
 		break;
 	}
 
@@ -2617,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch)
 
 	qd->rate_ns   = qd->tins[ft].tin_rate_ns;
 	qd->rate_shft = qd->tins[ft].tin_rate_shft;
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+	struct cake_sched_data *qd = qdisc_priv(sch);
+	struct cake_sched_config *q = qd->config;
+
+	cake_configure_rates(sch, qd->config->rate_bps, false);
 
 	if (q->buffer_config_limit) {
 		qd->buffer_limit = q->buffer_config_limit;

From ba14798653bb815b4dcd116c5265a9f748bc0c7f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 26 Feb 2026 17:19:17 +0100
Subject: [PATCH 0578/1303] selftests: netfilter: nft_queue.sh: avoid flakes on
 debug kernels

Jakub reports test flakes on debug kernels:
 FAIL: test_udp_gro_ct: Expected software segmentation to occur, had 23 and 17

This test assumes that the kernels nfnetlink_queue module sees N GSO
packets, segments them into M skbs and queues them to userspace for
reinjection.

Hence, if M >= N, no segmentation occurred.

However, its possible that this happens:
- nfnetlink_queue gets GSO packet
- segments that into n skbs
- userspace buffer is full, kernel drops the segmented skbs

-> "toqueue" counter incremented by 1, "fromqueue" is unchanged.

If this happens often enough in a single run, M >= N check triggers
incorrectly.

To solve this, allow the nf_queue.c test program to set the FAIL_OPEN
flag so that the segmented skbs bypass the queueing step in the kernel
if the receive buffer is full.

Also, reduce number of sending socat instances, decrease their priority
and increase nice value for the nf_queue program itself to reduce the
probability of overruns happening in the first place.

Fixes: 59ecffa3995e ("selftests: netfilter: nft_queue.sh: add udp fraglist gro test case")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20260218184114.0b405b72@kernel.org/
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260226161920.1205-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netfilter/nf_queue.c   | 10 ++++++++--
 tools/testing/selftests/net/netfilter/nft_queue.sh | 13 +++++++++----
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c
index 9e56b9d47037..116c0ca0eabb 100644
--- a/tools/testing/selftests/net/netfilter/nf_queue.c
+++ b/tools/testing/selftests/net/netfilter/nf_queue.c
@@ -18,6 +18,7 @@
 struct options {
 	bool count_packets;
 	bool gso_enabled;
+	bool failopen;
 	int verbose;
 	unsigned int queue_num;
 	unsigned int timeout;
@@ -30,7 +31,7 @@ static struct options opts;
 
 static void help(const char *p)
 {
-	printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
+	printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
 }
 
 static int parse_attr_cb(const struct nlattr *attr, void *data)
@@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void)
 
 	flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0;
 	flags |= NFQA_CFG_F_UID_GID;
+	if (opts.failopen)
+		flags |= NFQA_CFG_F_FAIL_OPEN;
 	mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags));
 	mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags));
 
@@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) {
+	while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) {
 		switch (c) {
 		case 'c':
 			opts.count_packets = true;
@@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv)
 		case 'G':
 			opts.gso_enabled = false;
 			break;
+		case 'o':
+			opts.failopen = true;
+			break;
 		case 'v':
 			opts.verbose++;
 			break;
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 139bc1211878..ea766bdc5d04 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -591,6 +591,7 @@ EOF
 test_udp_gro_ct()
 {
 	local errprefix="FAIL: test_udp_gro_ct:"
+	local timeout=5
 
 	ip netns exec "$nsrouter" conntrack -F 2>/dev/null
 
@@ -630,10 +631,10 @@ table inet udpq {
 	}
 }
 EOF
-	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
+	timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
 	local rpid=$!
 
-	ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" &
+	ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" &
 	local nfqpid=$!
 
 	ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on
@@ -643,8 +644,12 @@ EOF
 
 	local bs=512
 	local count=$(((32 * 1024 * 1024) / bs))
-	dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do
-		timeout 5 ip netns exec "$ns1" \
+
+	local nprocs=$(nproc)
+	[ $nprocs -gt 1 ] && nprocs=$((nprocs - 1))
+
+	dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do
+		timeout "$timeout" nice -n 19 ip netns exec "$ns1" \
 			socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 &
 	done
 

From 11cb63b0d1a0685e0831ae3c77223e002ef18189 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 25 Feb 2026 10:43:48 -0300
Subject: [PATCH 0579/1303] net/sched: Only allow act_ct to bind to
 clsact/ingress qdiscs and shared blocks

As Paolo said earlier [1]:

"Since the blamed commit below, classify can return TC_ACT_CONSUMED while
the current skb being held by the defragmentation engine. As reported by
GangMin Kim, if such packet is that may cause a UaF when the defrag engine
later on tries to tuch again such packet."

act_ct was never meant to be used in the egress path, however some users
are attaching it to egress today [2]. Attempting to reach a middle
ground, we noticed that, while most qdiscs are not handling
TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we
address the issue by only allowing act_ct to bind to clsact/ingress
qdiscs and shared blocks. That way it's still possible to attach act_ct to
egress (albeit only with clsact).

[1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/
[2] https://lore.kernel.org/netdev/cc6bfb4a-4a2b-42d8-b9ce-7ef6644fb22b@ovn.org/

Reported-by: GangMin Kim <km.kim1503@gmail.com>
Fixes: 3f14b377d01d ("net/sched: act_ct: fix skb leak and crash on ooo frags")
CC: stable@vger.kernel.org
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260225134349.1287037-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/act_api.h | 1 +
 net/sched/act_ct.c    | 6 ++++++
 net/sched/cls_api.c   | 7 +++++++
 3 files changed, 14 insertions(+)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index e1e8f0f7dacb..d11b79107930 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -70,6 +70,7 @@ struct tc_action {
 #define TCA_ACT_FLAGS_REPLACE	(1U << (TCA_ACT_FLAGS_USER_BITS + 2))
 #define TCA_ACT_FLAGS_NO_RTNL	(1U << (TCA_ACT_FLAGS_USER_BITS + 3))
 #define TCA_ACT_FLAGS_AT_INGRESS	(1U << (TCA_ACT_FLAGS_USER_BITS + 4))
+#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT	(1U << (TCA_ACT_FLAGS_USER_BITS + 5))
 
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index bd51522c7953..7d5e50c921a0 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
+	if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Attaching ct to a non ingress/clsact qdisc is unsupported");
+		return -EOPNOTSUPP;
+	}
+
 	err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
 	if (err < 0)
 		return err;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 343309e9009b..4829c27446e3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid)
 	return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS));
 }
 
+static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q)
+{
+	return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS));
+}
+
 static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 			  struct netlink_ext_ack *extack)
 {
@@ -2420,6 +2425,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 		flags |= TCA_ACT_FLAGS_NO_RTNL;
 	if (is_qdisc_ingress(parent))
 		flags |= TCA_ACT_FLAGS_AT_INGRESS;
+	if (is_ingress_or_clsact(block, q))
+		flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT;
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      flags, extack);
 	if (err == 0) {

From b14e82abf78affa50f4cabe8493e17f9adcfcec7 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 25 Feb 2026 10:43:49 -0300
Subject: [PATCH 0580/1303] selftests/tc-testing: Create tests to exercise
 act_ct binding restrictions

Add 4 test cases to exercise new act_ct binding restrictions:

- Try to attach act_ct to an ets qdisc
- Attach act_ct to an ingress qdisc
- Attach act_ct to a clsact/egress qdisc
- Attach act_ct to a shared block

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260225134349.1287037-2-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/actions/ct.json       | 159 ++++++++++++++++++
 1 file changed, 159 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
index 7d07c55bb668..33bb8f3ff8ed 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
@@ -505,5 +505,164 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "8883",
+        "name": "Try to attach act_ct to an ets qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 root handle 1: ets bands 2"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "2",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip",
+        "matchJSON": [],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 root"
+        ]
+    },
+    {
+        "id": "3b10",
+        "name": "Attach act_ct to an ingress qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0337",
+        "name": "Attach act_ct to a clsact/egress qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
+        "id": "4f60",
+        "name": "Attach act_ct to a shared block",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 ingress_block 21 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress_block 21 clsact"
+        ]
     }
 ]

From 15fba71533bcdfaa8eeba69a5a5a2927afdf664a Mon Sep 17 00:00:00 2001
From: Valentin Spreckels <valentin@spreckels.dev>
Date: Thu, 26 Feb 2026 20:54:09 +0100
Subject: [PATCH 0581/1303] net: usb: r8152: add TRENDnet TUC-ET2G

The TRENDnet TUC-ET2G is a RTL8156 based usb ethernet adapter. Add its
vendor and product IDs.

Signed-off-by: Valentin Spreckels <valentin@spreckels.dev>
Link: https://patch.msgid.link/20260226195409.7891-2-valentin@spreckels.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c   | 1 +
 include/linux/usb/r8152.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4af85728ac4f..0c83bbbea2e7 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
 	{ USB_DEVICE(VENDOR_ID_DELL,    0xb097) },
 	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
+	{ USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) },
 	{}
 };
 
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 2ca60828f28b..1502b2a355f9 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -32,6 +32,7 @@
 #define VENDOR_ID_DLINK			0x2001
 #define VENDOR_ID_DELL			0x413c
 #define VENDOR_ID_ASUS			0x0b05
+#define VENDOR_ID_TRENDNET		0x20f4
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);

From dabffd08545ffa1d7183bc45e387860984025291 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Thu, 26 Feb 2026 11:28:33 -0800
Subject: [PATCH 0582/1303] net: mana: Ring doorbell at 4 CQ wraparounds

MANA hardware requires at least one doorbell ring every 8 wraparounds
of the CQ. The driver rings the doorbell as a form of flow control to
inform hardware that CQEs have been consumed.

The NAPI poll functions mana_poll_tx_cq() and mana_poll_rx_cq() can
poll up to CQE_POLLING_BUFFER (512) completions per call. If the CQ
has fewer than 512 entries, a single poll call can process more than
4 wraparounds without ringing the doorbell. The doorbell threshold
check also uses ">" instead of ">=", delaying the ring by one extra
CQE beyond 4 wraparounds. Combined, these issues can cause the driver
to exceed the 8-wraparound hardware limit, leading to missed
completions and stalled queues.

Fix this by capping the number of CQEs polled per call to 4 wraparounds
of the CQ in both TX and RX paths. Also change the doorbell threshold
from ">" to ">=" so the doorbell is rung as soon as 4 wraparounds are
reached.

Cc: stable@vger.kernel.org
Fixes: 58a63729c957 ("net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings")
Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20260226192833.1050807-1-longli@microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 23 +++++++++++++++----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 933e9d681ded..9017e806ecda 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1770,8 +1770,14 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	ndev = txq->ndev;
 	apc = netdev_priv(ndev);
 
+	/* Limit CQEs polled to 4 wraparounds of the CQ to ensure the
+	 * doorbell can be rung in time for the hardware's requirement
+	 * of at least one doorbell ring every 8 wraparounds.
+	 */
 	comp_read = mana_gd_poll_cq(cq->gdma_cq, completions,
-				    CQE_POLLING_BUFFER);
+				    min((cq->gdma_cq->queue_size /
+					  COMP_ENTRY_SIZE) * 4,
+					 CQE_POLLING_BUFFER));
 
 	if (comp_read < 1)
 		return;
@@ -2156,7 +2162,14 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 	struct mana_rxq *rxq = cq->rxq;
 	int comp_read, i;
 
-	comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER);
+	/* Limit CQEs polled to 4 wraparounds of the CQ to ensure the
+	 * doorbell can be rung in time for the hardware's requirement
+	 * of at least one doorbell ring every 8 wraparounds.
+	 */
+	comp_read = mana_gd_poll_cq(cq->gdma_cq, comp,
+				    min((cq->gdma_cq->queue_size /
+					  COMP_ENTRY_SIZE) * 4,
+					 CQE_POLLING_BUFFER));
 	WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER);
 
 	rxq->xdp_flush = false;
@@ -2201,11 +2214,11 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 		mana_gd_ring_cq(gdma_queue, SET_ARM_BIT);
 		cq->work_done_since_doorbell = 0;
 		napi_complete_done(&cq->napi, w);
-	} else if (cq->work_done_since_doorbell >
-		   cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) {
+	} else if (cq->work_done_since_doorbell >=
+		   (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) {
 		/* MANA hardware requires at least one doorbell ring every 8
 		 * wraparounds of CQ even if there is no need to arm the CQ.
-		 * This driver rings the doorbell as soon as we have exceeded
+		 * This driver rings the doorbell as soon as it has processed
 		 * 4 wraparounds.
 		 */
 		mana_gd_ring_cq(gdma_queue, 0);

From 8168a7b72bdee3790b126f63bd30306759206b15 Mon Sep 17 00:00:00 2001
From: Ashish Kalra <ashish.kalra@amd.com>
Date: Fri, 6 Feb 2026 21:26:45 +0000
Subject: [PATCH 0583/1303] crypto: ccp - allow callers to use HV-Fixed page
 API when SEV is disabled

When SEV is disabled, the HV-Fixed page allocation call fails, which in
turn causes SFS initialization to fail.

Fix the HV-Fixed API so callers (for example, SFS) can use it even when
SEV is disabled by performing normal page allocation and freeing.

Fixes: e09701dcdd9c ("crypto: ccp - Add new HV-Fixed page allocation/free API")
Cc: stable@vger.kernel.org
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 096f993974d1..8b2dfc11289b 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -1105,15 +1105,12 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages)
 {
 	struct psp_device *psp_master = psp_get_master_device();
 	struct snp_hv_fixed_pages_entry *entry;
-	struct sev_device *sev;
 	unsigned int order;
 	struct page *page;
 
-	if (!psp_master || !psp_master->sev_data)
+	if (!psp_master)
 		return NULL;
 
-	sev = psp_master->sev_data;
-
 	order = get_order(PMD_SIZE * num_2mb_pages);
 
 	/*
@@ -1126,7 +1123,8 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages)
 	 * This API uses SNP_INIT_EX to transition allocated pages to HV_Fixed
 	 * page state, fail if SNP is already initialized.
 	 */
-	if (sev->snp_initialized)
+	if (psp_master->sev_data &&
+	    ((struct sev_device *)psp_master->sev_data)->snp_initialized)
 		return NULL;
 
 	/* Re-use freed pages that match the request */
@@ -1162,7 +1160,7 @@ void snp_free_hv_fixed_pages(struct page *page)
 	struct psp_device *psp_master = psp_get_master_device();
 	struct snp_hv_fixed_pages_entry *entry, *nentry;
 
-	if (!psp_master || !psp_master->sev_data)
+	if (!psp_master)
 		return;
 
 	/*

From 889b0e2721e793eb46cf7d17b965aa3252af3ec8 Mon Sep 17 00:00:00 2001
From: Alper Ak <alperyasinak1@gmail.com>
Date: Mon, 9 Feb 2026 13:30:42 +0300
Subject: [PATCH 0584/1303] crypto: ccp - Fix use-after-free on error path

In the error path of sev_tsm_init_locked(), the code dereferences 't'
after it has been freed with kfree(). The pr_err() statement attempts
to access t->tio_en and t->tio_init_done after the memory has been
released.

Move the pr_err() call before kfree(t) to access the fields while the
memory is still valid.

This issue reported by Smatch static analyser

Fixes:4be423572da1 ("crypto/ccp: Implement SEV-TIO PCIe IDE (phase1)")
Signed-off-by: Alper Ak <alperyasinak1@gmail.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev-tsm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/ccp/sev-dev-tsm.c b/drivers/crypto/ccp/sev-dev-tsm.c
index adc9542ae806..b07ae529b591 100644
--- a/drivers/crypto/ccp/sev-dev-tsm.c
+++ b/drivers/crypto/ccp/sev-dev-tsm.c
@@ -378,9 +378,9 @@ void sev_tsm_init_locked(struct sev_device *sev, void *tio_status_page)
 	return;
 
 error_exit:
-	kfree(t);
 	pr_err("Failed to enable SEV-TIO: ret=%d en=%d initdone=%d SEV=%d\n",
 	       ret, t->tio_en, t->tio_init_done, boot_cpu_has(X86_FEATURE_SEV));
+	kfree(t);
 }
 
 void sev_tsm_uninit(struct sev_device *sev)

From d240b079a37e90af03fd7dfec94930eb6c83936e Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 19 Feb 2026 00:54:00 +0100
Subject: [PATCH 0585/1303] crypto: atmel-sha204a - Fix OOM ->tfm_count leak

If memory allocation fails, decrement ->tfm_count to avoid blocking
future reads.

Cc: stable@vger.kernel.org
Fixes: da001fb651b0 ("crypto: atmel-i2c - add support for SHA204A random number generator")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/atmel-sha204a.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 8adc7fe71c04..98d1023007e3 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -52,9 +52,10 @@ static int atmel_sha204a_rng_read_nonblocking(struct hwrng *rng, void *data,
 		rng->priv = 0;
 	} else {
 		work_data = kmalloc_obj(*work_data, GFP_ATOMIC);
-		if (!work_data)
+		if (!work_data) {
+			atomic_dec(&i2c_priv->tfm_count);
 			return -ENOMEM;
-
+		}
 		work_data->ctx = i2c_priv;
 		work_data->client = i2c_priv->client;
 

From 89ff45359abbf9d8d3c4aa3f5a57ed0be82b5a12 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 26 Feb 2026 16:48:41 -0800
Subject: [PATCH 0586/1303] accel/amdxdna: Fill invalid payload for failed
 command

Newer userspace applications may read the payload of a failed command
to obtain detailed error information. However, the driver and old firmware
versions may not support returning advanced error information.
In this case, initialize the command payload with an invalid value so
userspace can detect that no detailed error information is available.

Fixes: aac243092b70 ("accel/amdxdna: Add command execution")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260227004841.3080241-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c    | 23 ++++++++---------------
 drivers/accel/amdxdna/amdxdna_ctx.c | 27 +++++++++++++++++++++++++++
 drivers/accel/amdxdna/amdxdna_ctx.h |  3 +++
 3 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 25845bd5e507..afee5e667f77 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -186,13 +186,13 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
 	cmd_abo = job->cmd_bo;
 
 	if (unlikely(job->job_timeout)) {
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT);
+		amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (unlikely(!data) || unlikely(size != sizeof(u32))) {
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -202,7 +202,7 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
 	if (status == AIE2_STATUS_SUCCESS)
 		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED);
 	else
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR);
+		amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ERROR);
 
 out:
 	aie2_sched_notify(job);
@@ -244,13 +244,13 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size)
 	cmd_abo = job->cmd_bo;
 
 	if (unlikely(job->job_timeout)) {
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT);
+		amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) {
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -270,19 +270,12 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size)
 		 fail_cmd_idx, fail_cmd_status);
 
 	if (fail_cmd_status == AIE2_STATUS_SUCCESS) {
-		amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
+		amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx, ERT_CMD_STATE_ABORT);
 		ret = -EINVAL;
-		goto out;
+	} else {
+		amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx, ERT_CMD_STATE_ERROR);
 	}
-	amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR);
 
-	if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) {
-		struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL);
-
-		cc->error_index = fail_cmd_idx;
-		if (cc->error_index >= cc->command_count)
-			cc->error_index = 0;
-	}
 out:
 	aie2_sched_notify(job);
 	return ret;
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
index 263d36072540..666dfd7b2a80 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -135,6 +135,33 @@ u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo)
 	return INVALID_CU_IDX;
 }
 
+int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo,
+			  struct amdxdna_sched_job *job, u32 cmd_idx,
+			  enum ert_cmd_state error_state)
+{
+	struct amdxdna_client *client = job->hwctx->client;
+	struct amdxdna_cmd *cmd = abo->mem.kva;
+	struct amdxdna_cmd_chain *cc = NULL;
+
+	cmd->header &= ~AMDXDNA_CMD_STATE;
+	cmd->header |= FIELD_PREP(AMDXDNA_CMD_STATE, error_state);
+
+	if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) {
+		cc = amdxdna_cmd_get_payload(abo, NULL);
+		cc->error_index = (cmd_idx < cc->command_count) ? cmd_idx : 0;
+		abo = amdxdna_gem_get_obj(client, cc->data[0], AMDXDNA_BO_CMD);
+		if (!abo)
+			return -EINVAL;
+		cmd = abo->mem.kva;
+	}
+
+	memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd));
+	if (cc)
+		amdxdna_gem_put_obj(abo);
+
+	return 0;
+}
+
 /*
  * This should be called in close() and remove(). DO NOT call in other syscalls.
  * This guarantee that when hwctx and resources will be released, if user
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h
index 16c85f08f03c..fbdf9d000871 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.h
+++ b/drivers/accel/amdxdna/amdxdna_ctx.h
@@ -167,6 +167,9 @@ amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo)
 
 void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size);
 u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo);
+int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo,
+			  struct amdxdna_sched_job *job, u32 cmd_idx,
+			  enum ert_cmd_state error_state);
 
 void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job);
 void amdxdna_hwctx_remove_all(struct amdxdna_client *client);

From 778031e1658d206a52bf9491c91ae5d4f4a2509d Mon Sep 17 00:00:00 2001
From: Matt DeVillier <matt.devillier@gmail.com>
Date: Thu, 26 Feb 2026 10:30:55 -0600
Subject: [PATCH 0587/1303] ALSA: hda/ca0132: Set HP/Speaker auto-detect
 default from headphone pin verb

HP/Speaker auto-detect (VNID_HP_ASEL) has been off by default for every
CA0132 device since the driver was added in 2012. vnode_lswitch is
always initialized to 0 in ca0132_init_chip(), and no quirk or other
code path enables it. As a result, headphone jack detection works only
after the user manually turns on "HP/Speaker Auto Detect" in alsamixer,
which is not obvious on laptops with combo jacks (e.g. Google Link,
Alienware).

Change the default to follow the headphone pin config: if the pin verb
has presence detect enabled (no AC_DEFCFG_MISC_NO_PRESENCE) and the
codec supports it (AC_PINCAP_PRES_DETECT), enable HP_ASEL by default.
This lets firmware (coreboot, UEFI, etc.) express whether the headphone
jack supports insertion detection. Devices with combo jacks can default
to auto-detect; devices with fixed/no jack leave it off.

Signed-off-by: Matt DeVillier <matt.devillier@gmail.com>
Link: https://patch.msgid.link/20260226163055.825167-1-matt.devillier@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/ca0132.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/codecs/ca0132.c b/sound/hda/codecs/ca0132.c
index bf342a76807c..a0677d7da8e2 100644
--- a/sound/hda/codecs/ca0132.c
+++ b/sound/hda/codecs/ca0132.c
@@ -9816,6 +9816,15 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->dig_in = 0x09;
 		break;
 	}
+
+	/* Default HP/Speaker auto-detect from headphone pin verb: enable if the
+	 * pin config indicates presence detect (not AC_DEFCFG_MISC_NO_PRESENCE).
+	 */
+	if (spec->unsol_tag_hp &&
+	    (snd_hda_query_pin_caps(codec, spec->unsol_tag_hp) & AC_PINCAP_PRES_DETECT) &&
+	    !(get_defcfg_misc(snd_hda_codec_get_pincfg(codec, spec->unsol_tag_hp)) &
+	      AC_DEFCFG_MISC_NO_PRESENCE))
+		spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID] = 1;
 }
 
 static int ca0132_prepare_verbs(struct hda_codec *codec)

From bd72a37b219b9b424bc5ec28f660ebdc129de7cb Mon Sep 17 00:00:00 2001
From: Lianqin Hu <hulianqin@vivo.com>
Date: Fri, 27 Feb 2026 02:11:02 +0000
Subject: [PATCH 0588/1303] ALSA: usb-audio: Add iface reset and delay quirk
 for AB13X USB Audio

Setting up the interface when suspended/resumeing fail on this card.
Adding a reset and delay quirk will eliminate this problem.

usb 1-1: New USB device found, idVendor=0624, idProduct=3d3f
usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
usb 1-1: Product: AB13X USB Audio
usb 1-1: Manufacturer: Generic
usb 1-1: SerialNumber: 20210726905926

Signed-off-by: Lianqin Hu <hulianqin@vivo.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/TYUPR06MB621795D087BF2D594027C235D273A@TYUPR06MB6217.apcprd06.prod.outlook.com
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index c6a78efbcaa3..d54a1a44a69b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2219,6 +2219,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x05e1, 0x0480, /* Hauppauge Woodbury */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x0624, 0x3d3f, /* AB13X USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x0644, 0x8043, /* TEAC UD-501/UD-501V2/UD-503/NT-503 */
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY |
 		   QUIRK_FLAG_IFACE_DELAY),

From 068641bc9dc3d680d1ec4f6ee9199d4812041dff Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 27 Feb 2026 20:13:27 +0800
Subject: [PATCH 0589/1303] ALSA: hda/realtek: Add quirk for HP Pavilion
 15-eh1xxx to enable mute LED

The HP Pavilion 15-eh1xxx series uses the HP mainboard 88D1 with ALC245
and needs the ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT quirk to make the
mute led working.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=215978
Cc: <stable@vger.kernel.org>
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260227121327.3751341-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 86bb22d19629..4c49f1195e1b 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6904,6 +6904,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88b3, "HP ENVY x360 Convertible 15-es0xxx", ALC245_FIXUP_HP_ENVY_X360_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x88d1, "HP Pavilion 15-eh1xxx (mainboard 88D1)", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88eb, "HP Victus 16-e0xxx", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),

From 05ac3846ffe53fc63e454eb195ce8a6bab7a6a88 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Fri, 27 Feb 2026 22:46:40 +0800
Subject: [PATCH 0590/1303] ALSA: hda/tas2781: A workaround solution to
 lower-vol issue among lower calibrated-impedance micro-speaker on TAS2781

On TAS2781, if the Speaker calibrated impedance is lower than default
value hard-coded inside the TAS2781, it will cuase vol lower than
normal. In order to fix this issue, the parameter of SineGainI need
updating.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Link: https://patch.msgid.link/20260227144641.1243-1-shenghao-ding@ti.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781.h                       |  1 +
 .../hda/codecs/side-codecs/tas2781_hda_i2c.c  | 15 +--
 sound/soc/codecs/tas2781-fmwlib.c             | 94 +++++++++++++++++++
 3 files changed, 98 insertions(+), 12 deletions(-)

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index 7c03bdc951bb..e847cf51878c 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -151,6 +151,7 @@ struct tasdevice {
 	struct bulk_reg_val *cali_data_backup;
 	struct bulk_reg_val alp_cali_bckp;
 	struct tasdevice_fw *cali_data_fmw;
+	void *cali_specific;
 	unsigned int dev_addr;
 	unsigned int err_code;
 	unsigned char cur_book;
diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 74c3cf1e45e1..67240ce184e1 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -60,7 +60,6 @@ struct tas2781_hda_i2c_priv {
 	int (*save_calibration)(struct tas2781_hda *h);
 
 	int hda_chip_id;
-	bool skip_calibration;
 };
 
 static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data)
@@ -479,8 +478,7 @@ static void tasdevice_dspfw_init(void *context)
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
-	if (!hda_priv->skip_calibration)
-		hda_priv->save_calibration(tas_hda);
+	hda_priv->save_calibration(tas_hda);
 }
 
 static void tasdev_fw_ready(const struct firmware *fmw, void *context)
@@ -535,7 +533,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 	void *master_data)
 {
 	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
-	struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv;
 	struct hda_component_parent *parent = master_data;
 	struct hda_component *comp;
 	struct hda_codec *codec;
@@ -564,14 +561,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 		break;
 	}
 
-	/*
-	 * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data
-	 * causes audio dropouts during playback, use fallback data
-	 * from DSP firmware as a workaround.
-	 */
-	if (codec->core.subsystem_id == 0x10431384)
-		hda_priv->skip_calibration = true;
-
 	guard(pm_runtime_active_auto)(dev);
 
 	comp->dev = dev;
@@ -643,6 +632,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 		 */
 		device_name = "TIAS2781";
 		hda_priv->hda_chip_id = HDA_TAS2781;
+		tas_hda->priv->chip_id = TAS2781;
 		hda_priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
 	} else if (strstarts(dev_name(&clt->dev), "i2c-TXNW2770")) {
@@ -656,6 +646,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 			     "i2c-TXNW2781:00-tas2781-hda.0")) {
 		device_name = "TXNW2781";
 		hda_priv->hda_chip_id = HDA_TAS2781;
+		tas_hda->priv->chip_id = TAS2781;
 		hda_priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
 	} else if (strstr(dev_name(&clt->dev), "INT8866")) {
diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index c969eb38704e..5798d518d94c 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -32,6 +32,10 @@
 #define TAS2781_YRAM1_PAGE			42
 #define TAS2781_YRAM1_START_REG			88
 
+#define TAS2781_PG_REG		TASDEVICE_REG(0x00, 0x00, 0x7c)
+#define TAS2781_PG_1_0		0xA0
+#define TAS2781_PG_2_0		0xA8
+
 #define TAS2781_YRAM2_START_PAGE		43
 #define TAS2781_YRAM2_END_PAGE			49
 #define TAS2781_YRAM2_START_REG			8
@@ -98,6 +102,12 @@ struct blktyp_devidx_map {
 	unsigned char dev_idx;
 };
 
+struct tas2781_cali_specific {
+	unsigned char sin_gni[4];
+	int sin_gni_reg;
+	bool is_sin_gn_flush;
+};
+
 static const char deviceNumber[TASDEVICE_DSP_TAS_MAX_DEVICE] = {
 	1, 2, 1, 2, 1, 1, 0, 2, 4, 3, 1, 2, 3, 4, 1, 2
 };
@@ -2454,6 +2464,84 @@ static int tasdevice_load_data(struct tasdevice_priv *tas_priv,
 	return ret;
 }
 
+static int tas2781_cali_preproc(struct tasdevice_priv *priv, int i)
+{
+	struct tas2781_cali_specific *spec = priv->tasdevice[i].cali_specific;
+	struct calidata *cali_data = &priv->cali_data;
+	struct cali_reg *p = &cali_data->cali_reg_array;
+	unsigned char *data = cali_data->data;
+	int rc;
+
+	/*
+	 * On TAS2781, if the Speaker calibrated impedance is lower than
+	 * default value hard-coded inside the TAS2781, it will cuase vol
+	 * lower than normal. In order to fix this issue, the parameter of
+	 * SineGainI need updating.
+	 */
+	if (spec == NULL) {
+		int k = i * (cali_data->cali_dat_sz_per_dev + 1);
+		int re_org, re_cal, corrected_sin_gn, pg_id;
+		unsigned char r0_deflt[4];
+
+		spec = devm_kzalloc(priv->dev, sizeof(*spec), GFP_KERNEL);
+		if (spec == NULL)
+			return -ENOMEM;
+		priv->tasdevice[i].cali_specific = spec;
+		rc = tasdevice_dev_bulk_read(priv, i, p->r0_reg, r0_deflt, 4);
+		if (rc < 0) {
+			dev_err(priv->dev, "invalid RE from %d = %d\n", i, rc);
+			return rc;
+		}
+		/*
+		 * SineGainI need to be re-calculated, calculate the high 16
+		 * bits.
+		 */
+		re_org = r0_deflt[0] << 8 | r0_deflt[1];
+		re_cal = data[k + 1] << 8 | data[k + 2];
+		if (re_org > re_cal) {
+			rc = tasdevice_dev_read(priv, i, TAS2781_PG_REG,
+						 &pg_id);
+			if (rc < 0) {
+				dev_err(priv->dev, "invalid PG id %d = %d\n",
+					i, rc);
+				return rc;
+			}
+
+			spec->sin_gni_reg = (pg_id == TAS2781_PG_1_0) ?
+				TASDEVICE_REG(0, 0x1b, 0x34) :
+				TASDEVICE_REG(0, 0x18, 0x1c);
+
+			rc = tasdevice_dev_bulk_read(priv, i,
+						      spec->sin_gni_reg,
+						      spec->sin_gni, 4);
+			if (rc < 0) {
+				dev_err(priv->dev, "wrong sinegaini %d = %d\n",
+					i, rc);
+				return rc;
+			}
+			corrected_sin_gn = re_org * ((spec->sin_gni[0] << 8) +
+						       spec->sin_gni[1]);
+			corrected_sin_gn /= re_cal;
+			spec->sin_gni[0] = corrected_sin_gn >> 8;
+			spec->sin_gni[1] = corrected_sin_gn & 0xff;
+
+			spec->is_sin_gn_flush = true;
+		}
+	}
+
+	if (spec->is_sin_gn_flush) {
+		rc = tasdevice_dev_bulk_write(priv, i, spec->sin_gni_reg,
+						       spec->sin_gni, 4);
+		if (rc < 0) {
+			dev_err(priv->dev, "update failed %d = %d\n",
+				i, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+
 static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 {
 	struct calidata *cali_data = &priv->cali_data;
@@ -2469,6 +2557,12 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 	}
 	k++;
 
+	if (priv->chip_id == TAS2781) {
+		rc = tas2781_cali_preproc(priv, i);
+		if (rc < 0)
+			return;
+	}
+
 	rc = tasdevice_dev_bulk_write(priv, i, p->r0_reg, &(data[k]), 4);
 	if (rc < 0) {
 		dev_err(priv->dev, "chn %d r0_reg bulk_wr err = %d\n", i, rc);

From d4d5633d8b19b0e745a7910aea49956b3b47900d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 27 Feb 2026 16:57:00 +0100
Subject: [PATCH 0591/1303] ALSA: firewire: dice: Fix printf warning with W=1

The use of snprintf() may cause a warning with W=1 due to the possibly
truncated string.  As the truncation doesn't really matter (and won't
happen practically) in the case of dice driver, just shut it up by
replacing with scnprintf().

Link: https://patch.msgid.link/20260227155705.1557224-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/dice/dice.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c
index 85d265c7d544..f7a50bae4b55 100644
--- a/sound/firewire/dice/dice.c
+++ b/sound/firewire/dice/dice.c
@@ -122,7 +122,7 @@ static void dice_card_strings(struct snd_dice *dice)
 	fw_csr_string(dev->config_rom + 5, CSR_VENDOR, vendor, sizeof(vendor));
 	strscpy(model, "?");
 	fw_csr_string(dice->unit->directory, CSR_MODEL, model, sizeof(model));
-	snprintf(card->longname, sizeof(card->longname),
+	scnprintf(card->longname, sizeof(card->longname),
 		 "%s %s (serial %u) at %s, S%d",
 		 vendor, model, dev->config_rom[4] & 0x3fffff,
 		 dev_name(&dice->unit->device), 100 << dev->max_speed);

From 0ed2e8bf61d6d5df1d78f4e24b682dff4c394e17 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 28 Feb 2026 04:56:20 -0700
Subject: [PATCH 0592/1303] io_uring: correct comment for
 IORING_SETUP_TASKRUN_FLAG

Sync with a recent liburing fix, which corrects the comment explaining
when the IORING_SETUP_TASKRUN_FLAG setup flag is valid to use. May be
use with COOP_TASKRUN or DEFER_TASKRUN, not useful without either of
this task_work mechanisms being used.

Link: https://github.com/axboe/liburing/pull/1543
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 6750c383a2ab..1ff16141c8a5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -188,7 +188,8 @@ enum io_uring_sqe_flags_bit {
 /*
  * If COOP_TASKRUN is set, get notified if task work is available for
  * running and a kernel transition would be needed to run it. This sets
- * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
+ * IORING_SQ_TASKRUN in the sq ring flags. Not valid without COOP_TASKRUN
+ * or DEFER_TASKRUN.
  */
 #define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
 #define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */

From 407fd8b8d8cce03856aa67329715de48b254b529 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Feb 2026 19:03:03 +0100
Subject: [PATCH 0593/1303] KVM: remove CONFIG_KVM_GENERIC_MMU_NOTIFIER

All architectures now use MMU notifier for KVM page table management.
Remove the Kconfig symbol and the code that is used when it is
disabled.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     |  1 -
 arch/loongarch/kvm/Kconfig |  1 -
 arch/mips/kvm/Kconfig      |  1 -
 arch/powerpc/kvm/Kconfig   |  4 ----
 arch/powerpc/kvm/powerpc.c |  1 -
 arch/riscv/kvm/Kconfig     |  1 -
 arch/s390/kvm/Kconfig      |  2 --
 arch/x86/kvm/Kconfig       |  1 -
 include/linux/kvm_host.h   |  7 +------
 virt/kvm/Kconfig           |  9 +--------
 virt/kvm/kvm_main.c        | 16 ----------------
 11 files changed, 2 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 4f803fd1c99a..7d1f22fd490b 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,7 +21,6 @@ menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index ed4f724db774..8e5213609975 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -28,7 +28,6 @@ config KVM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select VIRT_XFER_TO_GUEST_WORK
 	select SCHED_INFO
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index cc13cc35f208..b1b9a1d67758 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -23,7 +23,6 @@ config KVM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select HAVE_KVM_READONLY_MEM
 	help
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index c9a2d50ff1b0..9a0d1c1aca6c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -38,7 +38,6 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -81,7 +80,6 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_BOOK3S_HV_PMU
 	select CMA
 	help
@@ -203,7 +201,6 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -220,7 +217,6 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9a89a6d98f97..3da40ea8c562 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -625,7 +625,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 77379f77840a..ec2cee0a39e0 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -30,7 +30,6 @@ config KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select VIRT_XFER_TO_GUEST_WORK
-	select KVM_GENERIC_MMU_NOTIFIER
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	help
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 917ac740513e..5b835bc6a194 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -28,9 +28,7 @@ config KVM
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
 	select KVM_VFIO
-	select MMU_NOTIFIER
 	select VIRT_XFER_TO_GUEST_WORK
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMU_LOCKLESS_AGING
 	help
 	  Support hosting paravirtualized guest machines using the SIE
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index d916bd766c94..801bf9e520db 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM_X86
 	def_tristate KVM if (KVM_INTEL != n || KVM_AMD != n)
 	select KVM_COMMON
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_ELIDE_TLB_FLUSH_IF_YOUNG
 	select KVM_MMU_LOCKLESS_AGING
 	select HAVE_KVM_IRQCHIP
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index dde605cb894e..34759a262b28 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -253,7 +253,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	unsigned long attributes;
 };
@@ -275,7 +274,6 @@ struct kvm_gfn_range {
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
-#endif
 
 enum {
 	OUTSIDE_GUEST_MODE,
@@ -849,13 +847,12 @@ struct kvm {
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
 	gfn_t mmu_invalidate_range_start;
 	gfn_t mmu_invalidate_range_end;
-#endif
+
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
 	struct dentry *debugfs_dentry;
@@ -2118,7 +2115,6 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -2196,7 +2192,6 @@ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
 
 	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
 }
-#endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 267c7369c765..794976b88c6f 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -5,6 +5,7 @@ config KVM_COMMON
        bool
        select EVENTFD
        select INTERVAL_TREE
+       select MMU_NOTIFIER
        select PREEMPT_NOTIFIERS
 
 config HAVE_KVM_PFNCACHE
@@ -93,24 +94,16 @@ config HAVE_KVM_PM_NOTIFIER
 config KVM_GENERIC_HARDWARE_ENABLING
        bool
 
-config KVM_GENERIC_MMU_NOTIFIER
-       select MMU_NOTIFIER
-       bool
-
 config KVM_ELIDE_TLB_FLUSH_IF_YOUNG
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_MMU_LOCKLESS_AGING
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_GENERIC_MEMORY_ATTRIBUTES
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_GUEST_MEMFD
-       depends on KVM_GENERIC_MMU_NOTIFIER
        select XARRAY_MULTI
        bool
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 22f8a672e1fd..29ee01747347 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -502,7 +502,6 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_destroy_vcpus);
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
@@ -901,15 +900,6 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
-
-static int kvm_init_mmu_notifier(struct kvm *kvm)
-{
-	return 0;
-}
-
-#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
-
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
 				unsigned long state,
@@ -1226,10 +1216,8 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
-#endif
 out_err_no_mmu_notifier:
 	kvm_disable_virtualization();
 out_err_no_disable:
@@ -1292,7 +1280,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
@@ -1311,9 +1298,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->mn_active_invalidate_count = 0;
 	else
 		WARN_ON(kvm->mmu_invalidate_in_progress);
-#else
-	kvm_flush_shadow_all(kvm);
-#endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {

From 70295a479da684905c18d96656d781823f418ec2 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Feb 2026 19:06:31 +0100
Subject: [PATCH 0594/1303] KVM: always define KVM_CAP_SYNC_MMU

KVM_CAP_SYNC_MMU is provided by KVM's MMU notifiers, which are now always
available.  Move the definition from individual architectures to common
code.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 10 ++++------
 arch/arm64/kvm/arm.c           |  1 -
 arch/loongarch/kvm/vm.c        |  1 -
 arch/mips/kvm/mips.c           |  1 -
 arch/powerpc/kvm/powerpc.c     |  5 -----
 arch/riscv/kvm/vm.c            |  1 -
 arch/s390/kvm/kvm-s390.c       |  1 -
 arch/x86/kvm/x86.c             |  1 -
 virt/kvm/kvm_main.c            |  1 +
 9 files changed, 5 insertions(+), 17 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index fc5736839edd..6f85e1b321dd 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1396,7 +1396,10 @@ or its flags may be modified, but it may not be resized.
 Memory for the region is taken starting at the address denoted by the
 field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
-anonymous memory, ordinary files, and hugetlbfs.
+anonymous memory, ordinary files, and hugetlbfs.  Changes in the backing
+of the memory region are automatically reflected into the guest.
+For example, an mmap() that affects the region will be made visible
+immediately.  Another example is madvise(MADV_DROP).
 
 On architectures that support a form of address tagging, userspace_addr must
 be an untagged address.
@@ -1412,11 +1415,6 @@ use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
 to make a new slot read-only.  In this case, writes to this memory will be
 posted to userspace as KVM_EXIT_MMIO exits.
 
-When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
-the memory region are automatically reflected into the guest.  For example, an
-mmap() that affects the region will be made visible immediately.  Another
-example is madvise(MADV_DROP).
-
 For TDX guest, deleting/moving memory region loses guest memory contents.
 Read only region isn't supported.  Only as-id 0 is supported.
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 29f0326f7e00..410ffd41fd73 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -358,7 +358,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_USER_MEMORY:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ARM_PSCI:
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 63fd40530aa9..5282158b8122 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -118,7 +118,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_MP_STATE:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index b0fb92fda4d4..29d9f630edfb 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1035,7 +1035,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_IMMEDIATE_EXIT:
 		r = 1;
 		break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3da40ea8c562..00302399fc37 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -623,11 +623,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
 		       !kvmppc_hv_ops->enable_nested(NULL));
 		break;
-#endif
-	case KVM_CAP_SYNC_MMU:
-		r = 1;
-		break;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
 		r = hv_enabled;
 		break;
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 7cbd2340c190..58bce57dc55b 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -181,7 +181,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_USER_MEMORY:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_READONLY_MEM:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7a175d86cef0..bc7d6fa66eaf 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -601,7 +601,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
-	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_S390_UCONTROL
 	case KVM_CAP_S390_UCONTROL:
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3fb64905d190..a03530795707 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4805,7 +4805,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IOEVENTFD:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29ee01747347..1bc1da66b4b0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4870,6 +4870,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
+	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:

From 6996a2d2d0a64808c19c98002aeb5d9d1b2df6a4 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 27 Feb 2026 03:55:35 +0000
Subject: [PATCH 0595/1303] udp: Unhash auto-bound connected sk from 4-tuple
 hash table when disconnected.

Let's say we bind() an UDP socket to the wildcard address with a
non-zero port, connect() it to an address, and disconnect it from
the address.

bind() sets SOCK_BINDPORT_LOCK on sk->sk_userlocks (but not
SOCK_BINDADDR_LOCK), and connect() calls udp_lib_hash4() to put
the socket into the 4-tuple hash table.

Then, __udp_disconnect() calls sk->sk_prot->rehash(sk).

It computes a new hash based on the wildcard address and moves
the socket to a new slot in the 4-tuple hash table, leaving a
garbage in the chain that no packet hits.

Let's remove such a socket from 4-tuple hash table when disconnected.

Note that udp_sk(sk)->udp_portaddr_hash needs to be udpated after
udp_hash4_dec(hslot2) in udp_unhash4().

Fixes: 78c91ae2c6de ("ipv4/udp: Add 4-tuple hash for connected socket")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260227035547.3321327-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 014fdfdd331b..b60fad393e18 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2287,7 +2287,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 				     udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		nhslot2 = udp_hashslot2(udptable, newhash);
-		udp_sk(sk)->udp_portaddr_hash = newhash;
 
 		if (hslot2 != nhslot2 ||
 		    rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -2321,19 +2320,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 		if (udp_hashed4(sk)) {
 			spin_lock_bh(&hslot->lock);
 
-			udp_rehash4(udptable, sk, newhash4);
-			if (hslot2 != nhslot2) {
-				spin_lock(&hslot2->lock);
-				udp_hash4_dec(hslot2);
-				spin_unlock(&hslot2->lock);
+			if (inet_rcv_saddr_any(sk)) {
+				udp_unhash4(udptable, sk);
+			} else {
+				udp_rehash4(udptable, sk, newhash4);
+				if (hslot2 != nhslot2) {
+					spin_lock(&hslot2->lock);
+					udp_hash4_dec(hslot2);
+					spin_unlock(&hslot2->lock);
 
-				spin_lock(&nhslot2->lock);
-				udp_hash4_inc(nhslot2);
-				spin_unlock(&nhslot2->lock);
+					spin_lock(&nhslot2->lock);
+					udp_hash4_inc(nhslot2);
+					spin_unlock(&nhslot2->lock);
+				}
 			}
 
 			spin_unlock_bh(&hslot->lock);
 		}
+
+		udp_sk(sk)->udp_portaddr_hash = newhash;
 	}
 }
 EXPORT_IPV6_MOD(udp_lib_rehash);

From 026dfef287c07f37d4d4eef7a0b5a4bfdb29b32d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 26 Feb 2026 16:33:59 -0800
Subject: [PATCH 0596/1303] tcp: give up on stronger sk_rcvbuf checks (for now)

We hit another corner case which leads to TcpExtTCPRcvQDrop

Connections which send RPCs in the 20-80kB range over loopback
experience spurious drops. The exact conditions for most of
the drops I investigated are that:
 - socket exchanged >1MB of data so its not completely fresh
 - rcvbuf is around 128kB (default, hasn't grown)
 - there is ~60kB of data in rcvq
 - skb > 64kB arrives

The sum of skb->len (!) of both of the skbs (the one already
in rcvq and the arriving one) is larger than rwnd.
My suspicion is that this happens because __tcp_select_window()
rounds the rwnd up to (1 << wscale) if less than half of
the rwnd has been consumed.

Eric suggests that given the number of Fixes we already have
pointing to 1d2fbaad7cd8 it's probably time to give up on it,
until a bigger revamp of rmem management.

Also while we could risk tweaking the rwnd math, there are other
drops on workloads I investigated, after the commit in question,
not explained by this phenomenon.

Suggested-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/20260225122355.585fd57b@kernel.org
Fixes: 1d2fbaad7cd8 ("tcp: stronger sk_rcvbuf checks")
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260227003359.2391017-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6404e53382ca..7b03f2460751 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5374,25 +5374,11 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
-/* Check if this incoming skb can be added to socket receive queues
- * while satisfying sk->sk_rcvbuf limit.
- *
- * In theory we should use skb->truesize, but this can cause problems
- * when applications use too small SO_RCVBUF values.
- * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio,
- * allowing RWIN to be close to available space.
- * Whenever the receive queue gets full, we can receive a small packet
- * filling RWIN, but with a high skb->truesize, because most NIC use 4K page
- * plus sk_buff metadata even when receiving less than 1500 bytes of payload.
- *
- * Note that we use skb->len to decide to accept or drop this packet,
- * but sk->sk_rmem_alloc is the sum of all skb->truesize.
- */
 static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
 {
 	unsigned int rmem = atomic_read(&sk->sk_rmem_alloc);
 
-	return rmem + skb->len <= sk->sk_rcvbuf;
+	return rmem <= sk->sk_rcvbuf;
 }
 
 static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,

From 1cc93c48b5d7add5ea038860539893ce1310d72d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 26 Feb 2026 19:34:46 -0800
Subject: [PATCH 0597/1303] selftests/net: packetdrill: remove tests for
 tcp_rcv_*big

Since commit 1d2fbaad7cd8 ("tcp: stronger sk_rcvbuf checks")
has been reverted we need to remove the corresponding tests.

Link: https://lore.kernel.org/20260227003359.2391017-1-kuba@kernel.org
Link: https://patch.msgid.link/20260227033446.2596457-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_big_endseq.pkt    | 44 -------------------
 .../net/packetdrill/tcp_rcv_toobig.pkt        | 33 --------------
 2 files changed, 77 deletions(-)
 delete mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
 delete mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
deleted file mode 100644
index 3848b419e68c..000000000000
--- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
---mss=1000
-
-`./defaults.sh`
-
-    0 `nstat -n`
-
-// Establish a connection.
-   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
-   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
-   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
-   +0 bind(3, ..., ...) = 0
-   +0 listen(3, 1) = 0
-
-   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
-   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
-  +.1 < . 1:1(0) ack 1 win 257
-
-  +0 accept(3, ..., ...) = 4
-
-  +0 < P. 1:4001(4000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +0 < P. 4001:54001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +1 < P. 5001:55001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +0 < P. 70001:80001(10000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-  +0 read(4, ..., 100000) = 4000
-
-// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
-  +0 < P. 4001:54001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 54001 win 0
-
-// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
-+0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
deleted file mode 100644
index f575c0ff89da..000000000000
--- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
+++ /dev/null
@@ -1,33 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
---mss=1000
-
-`./defaults.sh`
-
-    0 `nstat -n`
-
-// Establish a connection.
-   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
-   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
-   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
-   +0 bind(3, ..., ...) = 0
-   +0 listen(3, 1) = 0
-
-   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
-   +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0>
-  +.1 < . 1:1(0) ack 1 win 257
-
-   +0 accept(3, ..., ...) = 4
-
-   +0 < P. 1:20001(20000) ack 1 win 257
- +.04 > .  1:1(0) ack 20001 win 18000
-
-   +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0
-   +0 < P. 20001:80001(60000) ack 1 win 257
-   +0 > .  1:1(0) ack 20001 win 18000
-
-   +0 read(4, ..., 20000) = 20000
-// A too big packet is accepted if the receive queue is empty
-   +0 < P. 20001:80001(60000) ack 1 win 257
-   +0 > .  1:1(0) ack 80001 win 0
-

From 60abb0ac11dccd6b98fd9182bc5f85b621688861 Mon Sep 17 00:00:00 2001
From: "Nikhil P. Rao" <nikhil.rao@amd.com>
Date: Wed, 25 Feb 2026 00:00:26 +0000
Subject: [PATCH 0598/1303] xsk: Fix fragment node deletion to prevent buffer
 leak

After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"),
the list_node field is reused for both the xskb pool list and the buffer
free list, this causes a buffer leak as described below.

xp_free() checks if a buffer is already on the free list using
list_empty(&xskb->list_node). When list_del() is used to remove a node
from the xskb pool list, it doesn't reinitialize the node pointers.
This means list_empty() will return false even after the node has been
removed, causing xp_free() to incorrectly skip adding the buffer to the
free list.

Fix this by using list_del_init() instead of list_del() in all fragment
handling paths, this ensures the list node is reinitialized after removal,
allowing the list_empty() to work correctly.

Fixes: b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node")
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-2-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 6 +++---
 net/xdp/xsk.c              | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 242e34f771cc..aefc368449d5 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -122,7 +122,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 		goto out;
 
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 		xp_free(pos);
 	}
 
@@ -157,7 +157,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
 					struct xdp_buff_xsk, list_node);
 	if (frag) {
-		list_del(&frag->list_node);
+		list_del_init(&frag->list_node);
 		ret = &frag->xdp;
 	}
 
@@ -168,7 +168,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	list_del(&xskb->list_node);
+	list_del_init(&xskb->list_node);
 }
 
 static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3b46bc635c43..be882a8d473c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -186,7 +186,7 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
 			goto err;
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 	}
 
 	return 0;

From f7387d6579d65efd490a864254101cb665f2e7a7 Mon Sep 17 00:00:00 2001
From: "Nikhil P. Rao" <nikhil.rao@amd.com>
Date: Wed, 25 Feb 2026 00:00:27 +0000
Subject: [PATCH 0599/1303] xsk: Fix zero-copy AF_XDP fragment drop

AF_XDP should ensure that only a complete packet is sent to application.
In the zero-copy case, if the Rx queue gets full as fragments are being
enqueued, the remaining fragments are dropped.

For the multi-buffer case, add a check to ensure that the Rx queue has
enough space for all fragments of a packet before starting to enqueue
them.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-3-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xdp/xsk.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index be882a8d473c..6149f6a79897 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,25 +167,31 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	struct xdp_buff_xsk *pos, *tmp;
 	struct list_head *xskb_list;
 	u32 contd = 0;
+	u32 num_desc;
 	int err;
 
-	if (frags)
-		contd = XDP_PKT_CONTD;
-
-	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err)
-		goto err;
-	if (likely(!frags))
+	if (likely(!frags)) {
+		err = __xsk_rcv_zc(xs, xskb, len, contd);
+		if (err)
+			goto err;
 		return 0;
+	}
 
+	contd = XDP_PKT_CONTD;
+	num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1;
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		err = -ENOBUFS;
+		goto err;
+	}
+
+	__xsk_rcv_zc(xs, xskb, len, contd);
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
 		if (list_is_singular(xskb_list))
 			contd = 0;
 		len = pos->xdp.data_end - pos->xdp.data;
-		err = __xsk_rcv_zc(xs, pos, len, contd);
-		if (err)
-			goto err;
+		__xsk_rcv_zc(xs, pos, len, contd);
 		list_del_init(&pos->list_node);
 	}
 

From 74badb9c20b1a9c02a95c735c6d3cd6121679c93 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 26 Feb 2026 21:58:12 -0800
Subject: [PATCH 0600/1303] dpaa2-switch: Fix interrupt storm after receiving
 bad if_id in IRQ handler

Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ
handler") introduces a range check for if_id to avoid an out-of-bounds
access. If an out-of-bounds if_id is detected, the interrupt status is
not cleared. This may result in an interrupt storm.

Clear the interrupt status after detecting an out-of-bounds if_id to avoid
the problem.

Found by an experimental AI code review agent at Google.

Fixes: 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler")
Cc: Junrui Luo <moonafterrain@outlook.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/20260227055812.1777915-1-linux@roeck-us.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index fc0e0f36186e..52c1cb9cb7e0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 	if_id = (status & 0xFFFF0000) >> 16;
 	if (if_id >= ethsw->sw_attr.num_ifs) {
 		dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id);
-		goto out;
+		goto out_clear;
 	}
 	port_priv = ethsw->ports[if_id];
 
@@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 			dpaa2_switch_port_connect_mac(port_priv);
 	}
 
+out_clear:
 	err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    DPSW_IRQ_INDEX_IF, status);
 	if (err)

From 101bacb303e89dc2e0640ae6a5e0fb97c4eb45bb Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:32:40 +0800
Subject: [PATCH 0601/1303] atm: lec: fix null-ptr-deref in lec_arp_clear_vccs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

syzkaller reported a null-ptr-deref in lec_arp_clear_vccs().
This issue can be easily reproduced using the syzkaller reproducer.

In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by
multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc).
When the underlying VCC is closed, lec_vcc_close() iterates over all
ARP entries and calls lec_arp_clear_vccs() for each matched entry.

For example, when lec_vcc_close() iterates through the hlists in
priv->lec_arp_empty_ones or other ARP tables:

1. In the first iteration, for the first matched ARP entry sharing the VCC,
lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back)
and sets vcc->user_back to NULL.
2. In the second iteration, for the next matched ARP entry sharing the same
VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from
vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it
via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash.

Fix this by adding a null check for vpriv before dereferencing
it. If vpriv is already NULL, it means the VCC has been cleared
by a previous call, so we can safely skip the cleanup and just
clear the entry's vcc/recv_vcc pointers.

The entire cleanup block (including vcc_release_async()) is placed inside
the vpriv guard because a NULL vpriv indicates the VCC has already been
fully released by a prior iteration — repeating the teardown would
redundantly set flags and trigger callbacks on an already-closing socket.

The Fixes tag points to the initial commit because the entry->vcc path has
been vulnerable since the original code. The entry->recv_vcc path was later
added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back")
with the same pattern, and both paths are fixed here.

Reported-by: syzbot+72e3ea390c305de0e259@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68c95a83.050a0220.3c6139.0e5c.GAE@google.com/T/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260225123250.189289-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/lec.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index a107375c0629..fb93c6e1c329 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 		struct net_device *dev = (struct net_device *)vcc->proto_data;
 
-		vcc->pop = vpriv->old_pop;
-		if (vpriv->xoff)
-			netif_wake_queue(dev);
-		kfree(vpriv);
-		vcc->user_back = NULL;
-		vcc->push = entry->old_push;
-		vcc_release_async(vcc, -EPIPE);
+		if (vpriv) {
+			vcc->pop = vpriv->old_pop;
+			if (vpriv->xoff)
+				netif_wake_queue(dev);
+			kfree(vpriv);
+			vcc->user_back = NULL;
+			vcc->push = entry->old_push;
+			vcc_release_async(vcc, -EPIPE);
+		}
 		entry->vcc = NULL;
 	}
 	if (entry->recv_vcc) {
 		struct atm_vcc *vcc = entry->recv_vcc;
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 
-		kfree(vpriv);
-		vcc->user_back = NULL;
+		if (vpriv) {
+			kfree(vpriv);
+			vcc->user_back = NULL;
 
-		entry->recv_vcc->push = entry->old_recv_push;
-		vcc_release_async(entry->recv_vcc, -EPIPE);
+			entry->recv_vcc->push = entry->old_recv_push;
+			vcc_release_async(entry->recv_vcc, -EPIPE);
+		}
 		entry->recv_vcc = NULL;
 	}
 }

From 9197e5949a41cfb5d44a6b8a860766266340d558 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Sat, 28 Feb 2026 11:56:03 +0900
Subject: [PATCH 0602/1303] firewire: ohci: initialize page array to use
 alloc_pages_bulk() correctly

The call of alloc_pages_bulk() skips to fill entries of page array when
the entries already have values. While, 1394 OHCI PCI driver passes the
page array without initializing. It could cause invalid state at PFN
validation in vmap().

Fixes: f2ae92780ab9 ("firewire: ohci: split page allocation from dma mapping")
Reported-by: John Ogness <john.ogness@linutronix.de>
Reported-and-tested-by: Harald Arnesen <linux@skogtun.org>
Reported-and-tested-by: David Gow <david@davidgow.net>
Closes: https://lore.kernel.org/lkml/87tsv1vig5.fsf@jogness.linutronix.de/
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/firewire/ohci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 1c868c1e4a49..8153d62c58f0 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -848,7 +848,7 @@ static int ar_context_init(struct ar_context *ctx, struct fw_ohci *ohci,
 {
 	struct device *dev = ohci->card.device;
 	unsigned int i;
-	struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES];
+	struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES] = { NULL };
 	dma_addr_t dma_addrs[AR_BUFFERS];
 	void *vaddr;
 	struct descriptor *d;

From dff8e3c025862001956b8edb29c1287c9efcd902 Mon Sep 17 00:00:00 2001
From: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Date: Wed, 4 Feb 2026 10:51:40 +0530
Subject: [PATCH 0603/1303] cpupower: fix swapped power/energy unit labels

Fix error where microWatts and microJoules units were interchanged.

Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/powercap-info.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/power/cpupower/utils/powercap-info.c b/tools/power/cpupower/utils/powercap-info.c
index 3ea4486f1a0e..e53033488218 100644
--- a/tools/power/cpupower/utils/powercap-info.c
+++ b/tools/power/cpupower/utils/powercap-info.c
@@ -38,11 +38,11 @@ static int powercap_print_one_zone(struct powercap_zone *zone)
 	printf(" (%s)\n", mode ? "enabled" : "disabled");
 
 	if (zone->has_power_uw)
-		printf(_("%sPower can be monitored in micro Jules\n"),
+		printf(_("%sPower can be monitored in micro Watts\n"),
 		       pr_prefix);
 
 	if (zone->has_energy_uj)
-		printf(_("%sPower can be monitored in micro Watts\n"),
+		printf(_("%sPower can be monitored in micro Jules\n"),
 		       pr_prefix);
 
 	printf("\n");

From 147792c395db870756a0dc87ce656c75ae7ab7e8 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 26 Feb 2026 15:53:56 +0530
Subject: [PATCH 0604/1303] net: ti: icssg-prueth: Fix ping failure after
 offload mode setup when link speed is not 1G

When both eth interfaces with links up are added to a bridge or hsr
interface, ping fails if the link speed is not 1Gbps (e.g., 100Mbps).

The issue is seen because when switching to offload (bridge/hsr) mode,
prueth_emac_restart() restarts the firmware and clears DRAM with
memset_io(), setting all memory to 0. This includes PORT_LINK_SPEED_OFFSET
which firmware reads for link speed. The value 0 corresponds to
FW_LINK_SPEED_1G (0x00), so for 1Gbps links the default value is correct
and ping works. For 100Mbps links, the firmware needs FW_LINK_SPEED_100M
(0x01) but gets 0 instead, causing ping to fail. The function
emac_adjust_link() is called to reconfigure, but it detects no state change
(emac->link is still 1, speed/duplex match PHY) so new_state remains false
and icssg_config_set_speed() is never called to correct the firmware speed
value.

The fix resets emac->link to 0 before calling emac_adjust_link() in
prueth_emac_common_start(). This forces new_state=true, ensuring
icssg_config_set_speed() is called to write the correct speed value to
firmware memory.

Fixes: 06feac15406f ("net: ti: icssg-prueth: Fix emac link speed handling")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20260226102356.2141871-1-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 0939994c932f..42a881bee109 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -273,6 +273,14 @@ static int prueth_emac_common_start(struct prueth *prueth)
 		if (ret)
 			goto disable_class;
 
+		/* Reset link state to force reconfiguration in
+		 * emac_adjust_link(). Without this, if the link was already up
+		 * before restart, emac_adjust_link() won't detect any state
+		 * change and will skip critical configuration like writing
+		 * speed to firmware.
+		 */
+		emac->link = 0;
+
 		mutex_lock(&emac->ndev->phydev->lock);
 		emac_adjust_link(emac->ndev);
 		mutex_unlock(&emac->ndev->phydev->lock);

From 9439a661c2e80485406ce2c90b107ca17858382d Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Thu, 26 Feb 2026 22:37:53 +0530
Subject: [PATCH 0605/1303] amd-xgbe: fix MAC_TCR_SS register width for 2.5G
 and 10M speeds

Extend the MAC_TCR_SS (Speed Select) register field width from 2 bits
to 3 bits to properly support all speed settings.

The MAC_TCR register's SS field encoding requires 3 bits to represent
all supported speeds:
  - 0x00: 10Gbps (XGMII)
  - 0x02: 2.5Gbps (GMII) / 100Mbps
  - 0x03: 1Gbps / 10Mbps
  - 0x06: 2.5Gbps (XGMII) - P100a only

With only 2 bits, values 0x04-0x07 cannot be represented, which breaks
2.5G XGMII mode on newer platforms and causes incorrect speed select
values to be programmed.

Fixes: 07445f3c7ca1 ("amd-xgbe: Add support for 10 Mbps speed")
Co-developed-by: Guruvendra Punugupati <Guruvendra.Punugupati@amd.com>
Signed-off-by: Guruvendra Punugupati <Guruvendra.Punugupati@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260226170753.250312-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 711f295eb777..80c2c27ac9dc 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -431,7 +431,7 @@
 #define MAC_SSIR_SSINC_INDEX		16
 #define MAC_SSIR_SSINC_WIDTH		8
 #define MAC_TCR_SS_INDEX		29
-#define MAC_TCR_SS_WIDTH		2
+#define MAC_TCR_SS_WIDTH		3
 #define MAC_TCR_TE_INDEX		0
 #define MAC_TCR_TE_WIDTH		1
 #define MAC_TCR_VNE_INDEX		24

From 1ac22c8eae81366101597d48360718dff9b9d980 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Mon, 23 Feb 2026 15:27:28 -0800
Subject: [PATCH 0606/1303] scsi: core: Fix refcount leak for tagset_refcnt

This leak will cause a hang when tearing down the SCSI host. For example,
iscsid hangs with the following call trace:

[130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured

PID: 2528     TASK: ffff9d0408974e00  CPU: 3    COMMAND: "iscsid"
 #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4
 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f
 #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0
 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f
 #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b
 #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp]
 #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi]
 #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi]
 #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6
 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef

Fixes: 8fe4ce5836e9 ("scsi: core: Fix a use-after-free")
Cc: stable@vger.kernel.org
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223232728.93350-1-junxiao.bi@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_scan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 60c06fa4ec32..2cfcf1f5d6a4 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -361,6 +361,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * since we use this queue depth most of times.
 	 */
 	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
+		kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
 		put_device(&starget->dev);
 		kfree(sdev);
 		goto out;

From dbd53975ed4132d161b6a97ebe785a262380182d Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Wed, 25 Feb 2026 13:56:22 +0530
Subject: [PATCH 0607/1303] scsi: mpi3mr: Clear reset history on ready and
 recheck state after timeout

The driver retains reset history even after the IOC has successfully
reached the READY state. That leaves stale reset information active during
normal operation and can mislead recovery and diagnostics.  In addition, if
the IOC becomes READY just as the ready timeout loop exits, the driver
still follows the failure path and may retry or report failure incorrectly.

Clear reset history once READY is confirmed so driver state matches actual
IOC status. After the timeout loop, recheck the IOC state and treat READY
as success instead of failing.

Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://patch.msgid.link/20260225082622.82588-1-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr_fw.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 5875065e2849..c744210cc901 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -1618,6 +1618,7 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc)
 			ioc_info(mrioc,
 			    "successfully transitioned to %s state\n",
 			    mpi3mr_iocstate_name(ioc_state));
+			mpi3mr_clear_reset_history(mrioc);
 			return 0;
 		}
 		ioc_status = readl(&mrioc->sysif_regs->ioc_status);
@@ -1637,6 +1638,15 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc)
 		elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000;
 	} while (elapsed_time_sec < mrioc->ready_timeout);
 
+	ioc_state = mpi3mr_get_iocstate(mrioc);
+	if (ioc_state == MRIOC_STATE_READY) {
+		ioc_info(mrioc,
+		    "successfully transitioned to %s state after %llu seconds\n",
+		    mpi3mr_iocstate_name(ioc_state), elapsed_time_sec);
+		mpi3mr_clear_reset_history(mrioc);
+		return 0;
+	}
+
 out_failed:
 	elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000;
 	if ((retry < 2) && (elapsed_time_sec < (mrioc->ready_timeout - 60))) {

From 80bf3b28d32b431f84f244a8469488eb6d96afbb Mon Sep 17 00:00:00 2001
From: Florian Fuchs <fuchsfl@gmail.com>
Date: Fri, 27 Feb 2026 19:18:23 +0100
Subject: [PATCH 0608/1303] scsi: devinfo: Add BLIST_SKIP_IO_HINTS for Iomega
 ZIP

The Iomega ZIP 100 (Z100P2) can't process IO Advice Hints Grouping mode
page query. It immediately switches to the status phase 0xb8 after
receiving the subpage code 0x05 of MODE_SENSE_10 command, which fails
imm_out() and turns into DID_ERROR of this command, which leads to unusable
device. This was tested with an Iomega ZIP 100 (Z100P2) connected with a
StarTech PEX1P2 AX99100 PCIe parallel port card.

Prior to this fix, Test Unit Ready fails and the drive can't be used:
        IMM: returned SCSI status b8
        sd 7:0:6:0: [sdh] Test Unit Ready failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK

Signed-off-by: Florian Fuchs <fuchsfl@gmail.com>
Link: https://patch.msgid.link/20260227181823.892932-1-fuchsfl@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_devinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 0dada89d8d99..68a992494b12 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -190,7 +190,7 @@ static struct {
 	{"IBM", "2076", NULL, BLIST_NO_VPD_SIZE},
 	{"IBM", "2105", NULL, BLIST_RETRY_HWERROR},
 	{"iomega", "jaz 1GB", "J.86", BLIST_NOTQ | BLIST_NOLUN},
-	{"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN},
+	{"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN | BLIST_SKIP_IO_HINTS},
 	{"IOMEGA", "Io20S         *F", NULL, BLIST_KEY},
 	{"INSITE", "Floptical   F*8I", NULL, BLIST_KEY},
 	{"INSITE", "I325VM", NULL, BLIST_KEY},

From 14d4ac19d1895397532eec407433c5d74d9da53b Mon Sep 17 00:00:00 2001
From: Prithvi Tambewagh <activprithvi@gmail.com>
Date: Mon, 16 Feb 2026 11:50:02 +0530
Subject: [PATCH 0609/1303] scsi: target: Fix recursive locking in
 __configfs_open_file()

In flush_write_buffer, &p->frag_sem is acquired and then the loaded store
function is called, which, here, is target_core_item_dbroot_store().  This
function called filp_open(), following which these functions were called
(in reverse order), according to the call trace:

  down_read
  __configfs_open_file
  do_dentry_open
  vfs_open
  do_open
  path_openat
  do_filp_open
  file_open_name
  filp_open
  target_core_item_dbroot_store
  flush_write_buffer
  configfs_write_iter

target_core_item_dbroot_store() tries to validate the new file path by
trying to open the file path provided to it; however, in this case, the bug
report shows:

db_root: not a directory: /sys/kernel/config/target/dbroot

indicating that the same configfs file was tried to be opened, on which it
is currently working on. Thus, it is trying to acquire frag_sem semaphore
of the same file of which it already holds the semaphore obtained in
flush_write_buffer(), leading to acquiring the semaphore in a nested manner
and a possibility of recursive locking.

Fix this by modifying target_core_item_dbroot_store() to use kern_path()
instead of filp_open() to avoid opening the file using filesystem-specific
function __configfs_open_file(), and further modifying it to make this fix
compatible.

Reported-by: syzbot+f6e8174215573a84b797@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f6e8174215573a84b797
Tested-by: syzbot+f6e8174215573a84b797@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Prithvi Tambewagh <activprithvi@gmail.com>
Reviewed-by: Dmitry Bogdanov <d.bogdanov@yadro.com>
Link: https://patch.msgid.link/20260216062002.61937-1-activprithvi@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_configfs.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 17608ea39d5a..a1c91d4515bc 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -108,8 +108,8 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 					const char *page, size_t count)
 {
 	ssize_t read_bytes;
-	struct file *fp;
 	ssize_t r = -EINVAL;
+	struct path path = {};
 
 	mutex_lock(&target_devices_lock);
 	if (target_devices) {
@@ -131,17 +131,14 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 		db_root_stage[read_bytes - 1] = '\0';
 
 	/* validate new db root before accepting it */
-	fp = filp_open(db_root_stage, O_RDONLY, 0);
-	if (IS_ERR(fp)) {
+	r = kern_path(db_root_stage, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (r) {
 		pr_err("db_root: cannot open: %s\n", db_root_stage);
+		if (r == -ENOTDIR)
+			pr_err("db_root: not a directory: %s\n", db_root_stage);
 		goto unlock;
 	}
-	if (!S_ISDIR(file_inode(fp)->i_mode)) {
-		filp_close(fp, NULL);
-		pr_err("db_root: not a directory: %s\n", db_root_stage);
-		goto unlock;
-	}
-	filp_close(fp, NULL);
+	path_put(&path);
 
 	strscpy(db_root, db_root_stage);
 	pr_debug("Target_Core_ConfigFS: db_root set to %s\n", db_root);

From 4478e8eeb87120c11e90041864c2233238b2155a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 26 Feb 2026 11:17:49 -0800
Subject: [PATCH 0610/1303] lib/crypto: tests: Depend on library options rather
 than selecting them

The convention for KUnit tests is to have the test kconfig options
visible only when the code they depend on is already enabled.  This way
only the tests that are relevant to the particular kernel build can be
enabled, either manually or via KUNIT_ALL_TESTS.

Update lib/crypto/tests/Kconfig to follow that convention, i.e. depend
on the corresponding library options rather than selecting them.  This
fixes an issue where enabling KUNIT_ALL_TESTS enabled non-test code.

This does mean that it becomes a bit more difficult to enable *all* the
crypto library tests (which is what I do as a maintainer of the code),
since doing so will now require enabling other options that select the
libraries.  Regardless, we should follow the standard KUnit convention.
I'll also add a .kunitconfig file that does enable all these options.

Note: currently most of the crypto library options are selected by
visible options in crypto/Kconfig, which can be used to enable them
without too much trouble.  If in the future we end up with more cases
like CRYPTO_LIB_CURVE25519 which is selected only by WIREGUARD (thus
making CRYPTO_LIB_CURVE25519_KUNIT_TEST effectively depend on WIREGUARD
after this commit), we could consider adding a new kconfig option that
enables all the library code specifically for testing.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/r/CAMuHMdULzMdxuTVfg8_4jdgzbzjfx-PHkcgbGSthcUx_sHRNMg@mail.gmail.com
Fixes: 4dcf6caddaa0 ("lib/crypto: tests: Add KUnit tests for SHA-224 and SHA-256")
Fixes: 571eaeddb67d ("lib/crypto: tests: Add KUnit tests for SHA-384 and SHA-512")
Fixes: 6dd4d9f7919e ("lib/crypto: tests: Add KUnit tests for Poly1305")
Fixes: 66b130607908 ("lib/crypto: tests: Add KUnit tests for SHA-1 and HMAC-SHA1")
Fixes: d6b6aac0cdb4 ("lib/crypto: tests: Add KUnit tests for MD5 and HMAC-MD5")
Fixes: afc4e4a5f122 ("lib/crypto: tests: Migrate Curve25519 self-test to KUnit")
Fixes: 6401fd334ddf ("lib/crypto: tests: Add KUnit tests for BLAKE2b")
Fixes: 15c64c47e484 ("lib/crypto: tests: Add SHA3 kunit tests")
Fixes: b3aed551b3fc ("lib/crypto: tests: Add KUnit tests for POLYVAL")
Fixes: ed894faccb8d ("lib/crypto: tests: Add KUnit tests for ML-DSA verification")
Fixes: 7246fe6cd644 ("lib/crypto: tests: Add KUnit tests for NH")
Cc: stable@vger.kernel.org
Reviewed-by: David Gow <david@davidgow.net>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260226191749.39397-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/tests/Kconfig | 35 ++++++++++++-----------------------
 1 file changed, 12 insertions(+), 23 deletions(-)

diff --git a/lib/crypto/tests/Kconfig b/lib/crypto/tests/Kconfig
index 4970463ea0aa..0de289b429a9 100644
--- a/lib/crypto/tests/Kconfig
+++ b/lib/crypto/tests/Kconfig
@@ -2,10 +2,9 @@
 
 config CRYPTO_LIB_BLAKE2B_KUNIT_TEST
 	tristate "KUnit tests for BLAKE2b" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_BLAKE2B
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_BLAKE2B
 	help
 	  KUnit tests for the BLAKE2b cryptographic hash function.
 
@@ -14,71 +13,64 @@ config CRYPTO_LIB_BLAKE2S_KUNIT_TEST
 	depends on KUNIT
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	# No need to select CRYPTO_LIB_BLAKE2S here, as that option doesn't
+	# No need to depend on CRYPTO_LIB_BLAKE2S here, as that option doesn't
 	# exist; the BLAKE2s code is always built-in for the /dev/random driver.
 	help
 	  KUnit tests for the BLAKE2s cryptographic hash function.
 
 config CRYPTO_LIB_CURVE25519_KUNIT_TEST
 	tristate "KUnit tests for Curve25519" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_CURVE25519
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_CURVE25519
 	help
 	  KUnit tests for the Curve25519 Diffie-Hellman function.
 
 config CRYPTO_LIB_MD5_KUNIT_TEST
 	tristate "KUnit tests for MD5" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_MD5
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_MD5
 	help
 	  KUnit tests for the MD5 cryptographic hash function and its
 	  corresponding HMAC.
 
 config CRYPTO_LIB_MLDSA_KUNIT_TEST
 	tristate "KUnit tests for ML-DSA" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_MLDSA
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_MLDSA
 	help
 	  KUnit tests for the ML-DSA digital signature algorithm.
 
 config CRYPTO_LIB_NH_KUNIT_TEST
 	tristate "KUnit tests for NH" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_NH
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
-	select CRYPTO_LIB_NH
 	help
 	  KUnit tests for the NH almost-universal hash function.
 
 config CRYPTO_LIB_POLY1305_KUNIT_TEST
 	tristate "KUnit tests for Poly1305" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_POLY1305
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_POLY1305
 	help
 	  KUnit tests for the Poly1305 library functions.
 
 config CRYPTO_LIB_POLYVAL_KUNIT_TEST
 	tristate "KUnit tests for POLYVAL" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_POLYVAL
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_POLYVAL
 	help
 	  KUnit tests for the POLYVAL library functions.
 
 config CRYPTO_LIB_SHA1_KUNIT_TEST
 	tristate "KUnit tests for SHA-1" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA1
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA1
 	help
 	  KUnit tests for the SHA-1 cryptographic hash function and its
 	  corresponding HMAC.
@@ -87,10 +79,9 @@ config CRYPTO_LIB_SHA1_KUNIT_TEST
 # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA256).
 config CRYPTO_LIB_SHA256_KUNIT_TEST
 	tristate "KUnit tests for SHA-224 and SHA-256" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA256
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA256
 	help
 	  KUnit tests for the SHA-224 and SHA-256 cryptographic hash functions
 	  and their corresponding HMACs.
@@ -99,20 +90,18 @@ config CRYPTO_LIB_SHA256_KUNIT_TEST
 # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA512).
 config CRYPTO_LIB_SHA512_KUNIT_TEST
 	tristate "KUnit tests for SHA-384 and SHA-512" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA512
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA512
 	help
 	  KUnit tests for the SHA-384 and SHA-512 cryptographic hash functions
 	  and their corresponding HMACs.
 
 config CRYPTO_LIB_SHA3_KUNIT_TEST
 	tristate "KUnit tests for SHA-3" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA3
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA3
 	help
 	  KUnit tests for the SHA3 cryptographic hash and XOF functions,
 	  including SHA3-224, SHA3-256, SHA3-384, SHA3-512, SHAKE128 and

From 11439c4635edd669ae435eec308f4ab8a0804808 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 1 Mar 2026 15:39:31 -0800
Subject: [PATCH 0611/1303] Linux 7.0-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index e944c6e71e81..2446085983f7 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 54a86cf48eaa6d1ab5130d756b718775e81e1748 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 5 Feb 2026 00:25:37 +0000
Subject: [PATCH 0612/1303] ASoC: fsl_easrc: Fix event generation in
 fsl_easrc_iec958_put_bits()

ALSA controls should return 1 if the value in the control changed but the
control put operation fsl_easrc_iec958_put_bits() unconditionally returns
0, causing ALSA to not generate any change events. This is detected by
mixer-test with large numbers of messages in the form:

    No event generated for Context 3 IEC958 CS5
    Context 3 IEC958 CS5.0 orig 5224 read 5225, is_volatile 0

Add a suitable check.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260205-asoc-fsl-easrc-fix-events-v1-1-39d4c766918b@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_easrc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c
index e64a0d97afd0..5b6204923e8a 100644
--- a/sound/soc/fsl/fsl_easrc.c
+++ b/sound/soc/fsl/fsl_easrc.c
@@ -52,10 +52,13 @@ static int fsl_easrc_iec958_put_bits(struct snd_kcontrol *kcontrol,
 	struct soc_mreg_control *mc =
 		(struct soc_mreg_control *)kcontrol->private_value;
 	unsigned int regval = ucontrol->value.integer.value[0];
+	int ret;
+
+	ret = (easrc_priv->bps_iec958[mc->regbase] != regval);
 
 	easrc_priv->bps_iec958[mc->regbase] = regval;
 
-	return 0;
+	return ret;
 }
 
 static int fsl_easrc_iec958_get_bits(struct snd_kcontrol *kcontrol,

From 31ddc62c1cd92e51b9db61d7954b85ae2ec224da Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 5 Feb 2026 00:25:38 +0000
Subject: [PATCH 0613/1303] ASoC: fsl_easrc: Fix event generation in
 fsl_easrc_iec958_set_reg()

ALSA controls should return 1 if the value in the control changed but the
control put operation fsl_easrc_set_reg() only returns 0 or a negative
error code, causing ALSA to not generate any change events. Add a suitable
check by using regmap_update_bits_check() with the underlying regmap, this
is more clearly and simply correct than trying to verify that one of the
generic ops is exactly equivalent to this one.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260205-asoc-fsl-easrc-fix-events-v1-2-39d4c766918b@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_easrc.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c
index 5b6204923e8a..6c56134c60cc 100644
--- a/sound/soc/fsl/fsl_easrc.c
+++ b/sound/soc/fsl/fsl_easrc.c
@@ -96,14 +96,17 @@ static int fsl_easrc_set_reg(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
 	struct soc_mreg_control *mc =
 		(struct soc_mreg_control *)kcontrol->private_value;
+	struct fsl_asrc *easrc = snd_soc_component_get_drvdata(component);
 	unsigned int regval = ucontrol->value.integer.value[0];
+	bool changed;
 	int ret;
 
-	ret = snd_soc_component_write(component, mc->regbase, regval);
-	if (ret < 0)
+	ret = regmap_update_bits_check(easrc->regmap, mc->regbase,
+				       GENMASK(31, 0), regval, &changed);
+	if (ret != 0)
 		return ret;
 
-	return 0;
+	return changed;
 }
 
 #define SOC_SINGLE_REG_RW(xname, xreg) \

From 9351cf3fd92dc1349bb75f2f7f7324607dcf596f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:01:37 +0000
Subject: [PATCH 0614/1303] ASoC: cs35l56: Only patch ASP registers if the DAI
 is part of a DAIlink

Move the ASP register patches to a separate struct and apply this from the
ASP DAI probe() function so that the registers are only patched if the DAI
is part of a DAI link.

Some systems use the ASP as a special-purpose interconnect and on these
systems the ASP registers are configured by a third party (the firmware,
the BIOS, or another device using the amp's secondary host control
interface).

If the machine driver does not hook up the ASP DAI then the ASP registers
must be omitted from the patch to prevent overwriting the third party
configuration.

If the machine driver includes the ASP DAI in a DAI link, this implies that
the machine driver and higher components (such as alsa-ucm) are taking
ownership of the ASP. In this case the ASP registers are patched to known
defaults and the machine driver should configure the ASP.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226110137.1664562-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  1 +
 sound/soc/codecs/cs35l56-shared.c | 16 +++++++++++++++-
 sound/soc/codecs/cs35l56.c        |  8 ++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index ae1e1489b671..28f9f5940ab6 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -406,6 +406,7 @@ extern const char * const cs35l56_cal_set_status_text[3];
 extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
 extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
 
+int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base);
 int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
 int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 4707f28bfca2..af87ebae98cb 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -26,7 +26,7 @@
 
 #include "cs35l56.h"
 
-static const struct reg_sequence cs35l56_patch[] = {
+static const struct reg_sequence cs35l56_asp_patch[] = {
 	/*
 	 * Firmware can change these to non-defaults to satisfy SDCA.
 	 * Ensure that they are at known defaults.
@@ -43,6 +43,20 @@ static const struct reg_sequence cs35l56_patch[] = {
 	{ CS35L56_ASP1TX2_INPUT,		0x00000000 },
 	{ CS35L56_ASP1TX3_INPUT,		0x00000000 },
 	{ CS35L56_ASP1TX4_INPUT,		0x00000000 },
+};
+
+int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base)
+{
+	return regmap_register_patch(cs35l56_base->regmap, cs35l56_asp_patch,
+				     ARRAY_SIZE(cs35l56_asp_patch));
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_set_asp_patch, "SND_SOC_CS35L56_SHARED");
+
+static const struct reg_sequence cs35l56_patch[] = {
+	/*
+	 * Firmware can change these to non-defaults to satisfy SDCA.
+	 * Ensure that they are at known defaults.
+	 */
 	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
 	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
 	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 2ff8b172b76e..3bf9e8fc34a2 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -348,6 +348,13 @@ static int cs35l56_dsp_event(struct snd_soc_dapm_widget *w,
 	return wm_adsp_event(w, kcontrol, event);
 }
 
+static int cs35l56_asp_dai_probe(struct snd_soc_dai *codec_dai)
+{
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
+
+	return cs35l56_set_asp_patch(&cs35l56->base);
+}
+
 static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
@@ -552,6 +559,7 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai,
 }
 
 static const struct snd_soc_dai_ops cs35l56_ops = {
+	.probe = cs35l56_asp_dai_probe,
 	.set_fmt = cs35l56_asp_dai_set_fmt,
 	.set_tdm_slot = cs35l56_asp_dai_set_tdm_slot,
 	.hw_params = cs35l56_asp_dai_hw_params,

From 986841dcad257615a6e3f89231bb38e1f3506b77 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Wed, 25 Feb 2026 17:12:10 +0800
Subject: [PATCH 0615/1303] ASoC: rt1321: fix DMIC ch2/3 mask issue

This patch fixed the DMIC ch2/3 mask missing problem.

Signed-off-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20260225091210.3648905-1-shumingf@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1320-sdw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c
index 50f65662e143..8bb7e8497c72 100644
--- a/sound/soc/codecs/rt1320-sdw.c
+++ b/sound/soc/codecs/rt1320-sdw.c
@@ -2629,7 +2629,7 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream,
 	struct sdw_port_config port_config;
 	struct sdw_port_config dmic_port_config[2];
 	struct sdw_stream_runtime *sdw_stream;
-	int retval;
+	int retval, num_channels;
 	unsigned int sampling_rate;
 
 	dev_dbg(dai->dev, "%s %s", __func__, dai->name);
@@ -2661,7 +2661,8 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream,
 				dmic_port_config[1].num = 10;
 				break;
 			case RT1321_DEV_ID:
-				dmic_port_config[0].ch_mask = BIT(0) | BIT(1);
+				num_channels = params_channels(params);
+				dmic_port_config[0].ch_mask = GENMASK(num_channels - 1, 0);
 				dmic_port_config[0].num = 8;
 				break;
 			default:

From 70eddf6a0a3fc6d3ab6f77251676da97cc7f12ae Mon Sep 17 00:00:00 2001
From: Oliver Freyermuth <o.freyermuth@googlemail.com>
Date: Tue, 24 Feb 2026 20:02:24 +0100
Subject: [PATCH 0616/1303] ASoC: Intel: sof_sdw: Add quirk for Alienware Area
 51 (2025) 0CCD SKU

This adds the necessary quirk for the Alienware 18 Area 51 (2025).
Complements commit 1b03391d073d ("ASoC: Intel: sof_sdw: Add quirk
for Alienware Area 51 (2025) 0CCC SKU").

Signed-off-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Tested-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Link: https://patch.msgid.link/20260224190224.30630-1-o.freyermuth@googlemail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index f230991f5f8e..c18ec607e029 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -763,6 +763,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 		},
 		.driver_data = (void *)(SOC_SDW_CODEC_SPKR),
 	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0CCD")
+		},
+		.driver_data = (void *)(SOC_SDW_CODEC_SPKR),
+	},
 	/* Pantherlake devices*/
 	{
 		.callback = sof_sdw_quirk_cb,

From fd13fc700e3e239826a46448bf7f01847dd26f5a Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Tue, 24 Feb 2026 13:03:07 +0000
Subject: [PATCH 0617/1303] ASoC: amd: acp: Add ACP6.3 match entries for Cirrus
 Logic parts

This adds some match entries for a few system configurations:

cs42l43 link 0 UID 0
cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs42l45 link 1 UID 0
cs35l63 link 0 UID 0
cs35l63 link 0 UID 2
cs35l63 link 0 UID 4
cs35l63 link 0 UID 6

cs42l45 link 0 UID 0
cs35l63 link 1 UID 0
cs35l63 link 1 UID 1

cs42l45 link 0 UID 0
cs35l63 link 1 UID 1
cs35l63 link 1 UID 3

cs42l45 link 1 UID 0
cs35l63 link 0 UID 0
cs35l63 link 0 UID 1

cs42l43 link 1 UID 0
cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs35l63 link 0 UID 0
cs35l63 link 0 UID 2
cs35l63 link 0 UID 4
cs35l63 link 0 UID 6

cs42l43 link 0 UID 1

cs42l43b link 0 UID 1

cs42l45 link 0 UID 0

cs42l45 link 1 UID 0

Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com>
Link: https://patch.msgid.link/20260224130307.526626-1-simont@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/amd-acp63-acpi-match.c | 413 +++++++++++++++++++++++
 1 file changed, 413 insertions(+)

diff --git a/sound/soc/amd/acp/amd-acp63-acpi-match.c b/sound/soc/amd/acp/amd-acp63-acpi-match.c
index 9b6a49c051cd..1dbbaba3c75b 100644
--- a/sound/soc/amd/acp/amd-acp63-acpi-match.c
+++ b/sound/soc/amd/acp/amd-acp63-acpi-match.c
@@ -30,6 +30,20 @@ static const struct snd_soc_acpi_endpoint spk_r_endpoint = {
 	.group_id = 1
 };
 
+static const struct snd_soc_acpi_endpoint spk_2_endpoint = {
+	.num = 0,
+	.aggregated = 1,
+	.group_position = 2,
+	.group_id = 1
+};
+
+static const struct snd_soc_acpi_endpoint spk_3_endpoint = {
+	.num = 0,
+	.aggregated = 1,
+	.group_position = 3,
+	.group_id = 1
+};
+
 static const struct snd_soc_acpi_adr_device rt711_rt1316_group_adr[] = {
 	{
 		.adr = 0x000030025D071101ull,
@@ -103,6 +117,345 @@ static const struct snd_soc_acpi_adr_device rt722_0_single_adr[] = {
 	}
 };
 
+static const struct snd_soc_acpi_endpoint cs42l43_endpoints[] = {
+	{ /* Jack Playback Endpoint */
+		.num = 0,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* DMIC Capture Endpoint */
+		.num = 1,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* Jack Capture Endpoint */
+		.num = 2,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* Speaker Playback Endpoint */
+		.num = 3,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l56x4_l1u3210_adr[] = {
+	{
+		.adr = 0x00013301FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013201FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00013101FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00013001FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l0u01_adr[] = {
+	{
+		.adr = 0x00003001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00003101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l1u01_adr[] = {
+	{
+		.adr = 0x00013001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l1u13_adr[] = {
+	{
+		.adr = 0x00013101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013301FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x4_l0u0246_adr[] = {
+	{
+		.adr = 0x00003001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00003201FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00003401FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00003601FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l0u0_adr[] = {
+	{
+		.adr = 0x00003001FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l0u1_adr[] = {
+	{
+		.adr = 0x00003101FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43b_l0u1_adr[] = {
+	{
+		.adr = 0x00003101FA2A3B01ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l1u0_cs35l56x4_l1u0123_adr[] = {
+	{
+		.adr = 0x00013001FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	},
+	{
+		.adr = 0x00013001FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013101FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00013201FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00013301FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs42l45_l0u0_adr[] = {
+	{
+		.adr = 0x00003001FA424501ull,
+		/* Re-use endpoints, but cs42l45 has no speaker */
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1,
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l45"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l45_l1u0_adr[] = {
+	{
+		.adr = 0x00013001FA424501ull,
+		/* Re-use endpoints, but cs42l45 has no speaker */
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1,
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l45"
+	}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs35l56x4_l1u3210[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr),
+		.adr_d = cs35l56x4_l1u3210_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs35l63x4_l0u0246[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr),
+		.adr_d = cs35l63x4_l0u0246_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u1[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43_l0u1_adr),
+		.adr_d = cs42l43_l0u1_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43b_l0u1[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43b_l0u1_adr),
+		.adr_d = cs42l43b_l0u1_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u0_cs35l56x4_l1u3210[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43_l0u0_adr),
+		.adr_d = cs42l43_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr),
+		.adr_d = cs35l56x4_l1u3210_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l1u0_cs35l56x4_l1u0123[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l43_l1u0_cs35l56x4_l1u0123_adr),
+		.adr_d = cs42l43_l1u0_cs35l56x4_l1u0123_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u01[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l1u01_adr),
+		.adr_d = cs35l63x2_l1u01_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u13[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l1u13_adr),
+		.adr_d = cs35l63x2_l1u13_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x2_l0u01[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l0u01_adr),
+		.adr_d = cs35l63x2_l0u01_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x4_l0u0246[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr),
+		.adr_d = cs35l63x4_l0u0246_adr,
+	},
+	{}
+};
+
 static const struct snd_soc_acpi_link_adr acp63_rt722_only[] = {
 	{
 		.mask = BIT(0),
@@ -135,6 +488,66 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp63_sdw_machines[] = {
 		.links = acp63_4_in_1_sdca,
 		.drv_name = "amd_sdw",
 	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l43_l0u0_cs35l56x4_l1u3210,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l1u0_cs35l63x4_l0u0246,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l0u0_cs35l63x2_l1u01,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l0u0_cs35l63x2_l1u13,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l1u0_cs35l63x2_l0u01,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs42l43_l1u0_cs35l56x4_l1u0123,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs35l56x4_l1u3210,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs35l63x4_l0u0246,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l43_l0u1,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l43b_l0u1,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l45_l0u0,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs42l45_l1u0,
+		.drv_name = "amd_sdw",
+	},
 	{},
 };
 EXPORT_SYMBOL(snd_soc_acpi_amd_acp63_sdw_machines);

From ca5056f5a78ce62588878d138e8141f01d70e61b Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:35:11 +0000
Subject: [PATCH 0618/1303] ASoC: cs35l56: Suppress pointless warning about
 number of GPIO pulls

In cs35l56_process_xu_onchip_speaker_id() the warning that the number
of pulls != number of GPIOs should only be printed if pulls are defined.

Pull settings are optional because there would normally be an external
resistor providing the pull. The warning would still be true if pulls
are not defined, but in that case is just log noise.

While we're changing that block of code, also fix the indenting of the
arguments to the dev_warn().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226113511.1768838-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 3bf9e8fc34a2..37909a319f88 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -1625,9 +1625,9 @@ static int cs35l56_process_xu_onchip_speaker_id(struct cs35l56_private *cs35l56,
 	if (num_pulls < 0)
 		return num_pulls;
 
-	if (num_pulls != num_gpios) {
+	if (num_pulls && (num_pulls != num_gpios)) {
 		dev_warn(cs35l56->base.dev, "%s count(%d) != %s count(%d)\n",
-			pull_name, num_pulls, gpio_name, num_gpios);
+			 pull_name, num_pulls, gpio_name, num_gpios);
 	}
 
 	ret = cs35l56_check_and_save_onchip_spkid_gpios(&cs35l56->base,

From 23942b71f07cc99e39d9216a5b370df494759d8c Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Feb 2026 02:24:34 +0800
Subject: [PATCH 0619/1303] regulator: mt6363: Fix incorrect and redundant IRQ
 disposal in probe

In mt6363_regulator_probe(), devm_add_action_or_reset() is used to
automatically dispose of the IRQ mapping if the probe fails or the
device is removed.

The manual call to irq_dispose_mapping() in the error path was redundant
as the reset action already triggers mt6363_irq_remove(). Furthermore,
the manual call incorrectly passed the hardware IRQ number (info->hwirq)
instead of the virtual IRQ mapping (info->virq).

Remove the redundant and incorrect manual disposal.

Fixes: 3c36965df808 ("regulator: Add support for MediaTek MT6363 SPMI PMIC Regulators")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260223-mt6363-v1-1-c99a2e8ac621@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mt6363-regulator.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/regulator/mt6363-regulator.c b/drivers/regulator/mt6363-regulator.c
index 03af5fa53600..0aebcbda0a19 100644
--- a/drivers/regulator/mt6363-regulator.c
+++ b/drivers/regulator/mt6363-regulator.c
@@ -899,10 +899,8 @@ static int mt6363_regulator_probe(struct platform_device *pdev)
 					     "Failed to map IRQ%d\n", info->hwirq);
 
 		ret = devm_add_action_or_reset(dev, mt6363_irq_remove, &info->virq);
-		if (ret) {
-			irq_dispose_mapping(info->hwirq);
+		if (ret)
 			return ret;
-		}
 
 		config.driver_data = info;
 		INIT_DELAYED_WORK(&info->oc_work, mt6363_oc_irq_enable_work);

From 7d0bf050a58747bb8f977a6281e63660a66d1c81 Mon Sep 17 00:00:00 2001
From: ChenXiaoSong <chenxiaosong@kylinos.cn>
Date: Sat, 21 Feb 2026 08:07:12 +0000
Subject: [PATCH 0620/1303] smb/client: make SMB2 maperror KUnit tests a
 separate module

Build the SMB2 maperror KUnit tests as `smb2maperror_test.ko`.

Link: https://lore.kernel.org/linux-cifs/20260210081040.4156383-1-geert@linux-m68k.org/
Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/Makefile            |  2 ++
 fs/smb/client/smb2glob.h          | 12 ++++++++++++
 fs/smb/client/smb2maperror.c      | 28 +++++++++++++++-------------
 fs/smb/client/smb2maperror_test.c | 12 +++++++++---
 4 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile
index 3abd357d6df6..26b6105f04d1 100644
--- a/fs/smb/client/Makefile
+++ b/fs/smb/client/Makefile
@@ -56,4 +56,6 @@ $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c
 quiet_cmd_gen_smb2_mapping = GEN     $@
       cmd_gen_smb2_mapping = perl $(src)/gen_smb2_mapping $< $@
 
+obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o
+
 clean-files	+= smb2_mapping_table.c
diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h
index e56e4d402f13..19da74b1edab 100644
--- a/fs/smb/client/smb2glob.h
+++ b/fs/smb/client/smb2glob.h
@@ -46,4 +46,16 @@ enum smb2_compound_ops {
 #define END_OF_CHAIN 4
 #define RELATED_REQUEST 8
 
+/*
+ *****************************************************************
+ * Struct definitions go here
+ *****************************************************************
+ */
+
+struct status_to_posix_error {
+	__u32 smb2_status;
+	int posix_error;
+	char *status_string;
+};
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index cd036365201f..f4cff44e2796 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -8,7 +8,6 @@
  *
  */
 #include <linux/errno.h>
-#include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "smb2proto.h"
@@ -16,12 +15,6 @@
 #include "../common/smb2status.h"
 #include "trace.h"
 
-struct status_to_posix_error {
-	__u32 smb2_status;
-	int posix_error;
-	char *status_string;
-};
-
 static const struct status_to_posix_error smb2_error_map_table[] = {
 /*
  * Automatically generated by the `gen_smb2_mapping` script,
@@ -115,10 +108,19 @@ int __init smb2_init_maperror(void)
 	return 0;
 }
 
-#define SMB_CLIENT_KUNIT_AVAILABLE \
-	((IS_MODULE(CONFIG_CIFS) && IS_ENABLED(CONFIG_KUNIT)) || \
-	 (IS_BUILTIN(CONFIG_CIFS) && IS_BUILTIN(CONFIG_KUNIT)))
+#if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
+/* Previous prototype for eliminating the build warning. */
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
 
-#if SMB_CLIENT_KUNIT_AVAILABLE && IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
-#include "smb2maperror_test.c"
-#endif /* CONFIG_SMB_KUNIT_TESTS */
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status)
+{
+	return smb2_get_err_map(smb2_status);
+}
+EXPORT_SYMBOL_GPL(smb2_get_err_map_test);
+
+const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table;
+EXPORT_SYMBOL_GPL(smb2_error_map_table_test);
+
+unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table);
+EXPORT_SYMBOL_GPL(smb2_error_map_num);
+#endif
diff --git a/fs/smb/client/smb2maperror_test.c b/fs/smb/client/smb2maperror_test.c
index 38ea6b846a99..8c47dea7a2c1 100644
--- a/fs/smb/client/smb2maperror_test.c
+++ b/fs/smb/client/smb2maperror_test.c
@@ -9,13 +9,18 @@
  */
 
 #include <kunit/test.h>
+#include "smb2glob.h"
+
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
+extern const struct status_to_posix_error *smb2_error_map_table_test;
+extern unsigned int smb2_error_map_num;
 
 static void
 test_cmp_map(struct kunit *test, const struct status_to_posix_error *expect)
 {
 	const struct status_to_posix_error *result;
 
-	result = smb2_get_err_map(expect->smb2_status);
+	result = smb2_get_err_map_test(expect->smb2_status);
 	KUNIT_EXPECT_PTR_NE(test, NULL, result);
 	KUNIT_EXPECT_EQ(test, expect->smb2_status, result->smb2_status);
 	KUNIT_EXPECT_EQ(test, expect->posix_error, result->posix_error);
@@ -26,8 +31,8 @@ static void maperror_test_check_search(struct kunit *test)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(smb2_error_map_table); i++)
-		test_cmp_map(test, &smb2_error_map_table[i]);
+	for (i = 0; i < smb2_error_map_num; i++)
+		test_cmp_map(test, &smb2_error_map_table_test[i]);
 }
 
 static struct kunit_case maperror_test_cases[] = {
@@ -43,3 +48,4 @@ static struct kunit_suite maperror_suite = {
 kunit_test_suite(maperror_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests of SMB2 maperror");

From 6f0402539b7da2b941a5a43754c15e53ac3cc276 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Wed, 25 Feb 2026 04:10:59 +0000
Subject: [PATCH 0621/1303] smb: update some doc references

To make it easier to locate the documentation during development.

Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.h | 7 +++++--
 fs/smb/server/smb2pdu.h | 5 ++++-
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index 78bb99f29d38..30d70097fe2f 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -224,7 +224,7 @@ struct smb2_file_reparse_point_info {
 	__le32 Tag;
 } __packed;
 
-/* See MS-FSCC 2.4.21 */
+/* See MS-FSCC 2.4.26 */
 struct smb2_file_id_information {
 	__le64	VolumeSerialNumber;
 	__u64  PersistentFileId; /* opaque endianness */
@@ -251,7 +251,10 @@ struct smb2_file_id_extd_directory_info {
 
 extern char smb2_padding[7];
 
-/* equivalent of the contents of SMB3.1.1 POSIX open context response */
+/*
+ * See POSIX-SMB2 2.2.14.2.16
+ * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md
+ */
 struct create_posix_rsp {
 	u32 nlink;
 	u32 reparse_tag;
diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h
index 257c6d26df26..8b6eafb70dca 100644
--- a/fs/smb/server/smb2pdu.h
+++ b/fs/smb/server/smb2pdu.h
@@ -83,7 +83,10 @@ struct create_durable_rsp {
 	} Data;
 } __packed;
 
-/* equivalent of the contents of SMB3.1.1 POSIX open context response */
+/*
+ * See POSIX-SMB2 2.2.14.2.16
+ * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md
+ */
 struct create_posix_rsp {
 	struct create_context_hdr ccontext;
 	__u8    Name[16];

From 48647d3f9a644d1e81af6558102d43cdb260597b Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2026 10:42:30 +0100
Subject: [PATCH 0622/1303] slab: distinguish lock and trylock for
 sheaf_flush_main()

sheaf_flush_main() can be called from __pcs_replace_full_main() where
it's fine if the trylock fails, and pcs_flush_all() where it's not
expected to and for some flush callers (when destroying the cache or
memory hotremove) it would be actually a problem if it failed and left
the main sheaf not flushed. The flush callers can however safely use
local_lock() instead of trylock.

The trylock failure should not happen in practice on !PREEMPT_RT, but
can happen on PREEMPT_RT. The impact is limited in practice because when
a trylock fails in the kmem_cache_destroy() path, it means someone is
using the cache while destroying it, which is a bug on its own. The memory
hotremove path is unlikely to be employed in a production RT config, but
it's possible.

To fix this, split the function into sheaf_flush_main() (using
local_lock()) and sheaf_try_flush_main() (using local_trylock()) where
both call __sheaf_flush_main_batch() to flush a single batch of objects.
This will also allow lockdep to verify our context assumptions.

The problem was raised in an off-list question by Marcelo.

Fixes: 2d517aa09bbc ("slab: add opt-in caching layer of percpu sheaves")
Cc: stable@vger.kernel.org
Reported-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Link: https://patch.msgid.link/20260211-b4-sheaf-flush-v1-1-4e7f492f0055@suse.cz
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 47 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 0c906fefc31b..b1e9f16ba435 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2858,19 +2858,19 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p);
  * object pointers are moved to a on-stack array under the lock. To bound the
  * stack usage, limit each batch to PCS_BATCH_MAX.
  *
- * returns true if at least partially flushed
+ * Must be called with s->cpu_sheaves->lock locked, returns with the lock
+ * unlocked.
+ *
+ * Returns how many objects are remaining to be flushed
  */
-static bool sheaf_flush_main(struct kmem_cache *s)
+static unsigned int __sheaf_flush_main_batch(struct kmem_cache *s)
 {
 	struct slub_percpu_sheaves *pcs;
 	unsigned int batch, remaining;
 	void *objects[PCS_BATCH_MAX];
 	struct slab_sheaf *sheaf;
-	bool ret = false;
 
-next_batch:
-	if (!local_trylock(&s->cpu_sheaves->lock))
-		return ret;
+	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
 	sheaf = pcs->main;
@@ -2888,10 +2888,37 @@ static bool sheaf_flush_main(struct kmem_cache *s)
 
 	stat_add(s, SHEAF_FLUSH, batch);
 
-	ret = true;
+	return remaining;
+}
 
-	if (remaining)
-		goto next_batch;
+static void sheaf_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+
+	do {
+		local_lock(&s->cpu_sheaves->lock);
+
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
+}
+
+/*
+ * Returns true if the main sheaf was at least partially flushed.
+ */
+static bool sheaf_try_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+	bool ret = false;
+
+	do {
+		if (!local_trylock(&s->cpu_sheaves->lock))
+			return ret;
+
+		ret = true;
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
 
 	return ret;
 }
@@ -5704,7 +5731,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	if (put_fail)
 		 stat(s, BARN_PUT_FAIL);
 
-	if (!sheaf_flush_main(s))
+	if (!sheaf_try_flush_main(s))
 		return NULL;
 
 	if (!local_trylock(&s->cpu_sheaves->lock))

From c35636e91e392e1540949bbc67932167cb48bc3a Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 18 Feb 2026 11:58:06 +0100
Subject: [PATCH 0623/1303] can: bcm: fix locking for bcm_op runtime updates

Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
added a locking for some variables that can be modified at runtime when
updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup().

Usually the RX_SETUP only handles and filters incoming traffic with one
exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is
sent when a specific RTR frame is received. Therefore the rx bcm_op uses
bcm_can_tx() which uses the bcm_tx_lock that was only initialized in
bcm_tx_setup(). Add the missing spin_lock_init() when allocating the
bcm_op in bcm_rx_setup() to handle the RTR case properly.

Fixes: c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
Reported-by: syzbot+5b11eccc403dd1cea9f8@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-can/699466e4.a70a0220.2c38d7.00ff.GAE@google.com/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260218-bcm_spin_lock_init-v1-1-592634c8a5b5@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b7324e9c955b..fd9fa072881e 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
+		spin_lock_init(&op->bcm_tx_lock);
 		op->can_id = msg_head->can_id;
 		op->nframes = msg_head->nframes;
 		op->cfsiz = CFSIZ(msg_head->flags);

From c77bfbdd6aac31b152ee81522cd90ad1de18738f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 26 Jan 2026 11:45:40 +0100
Subject: [PATCH 0624/1303] can: dummy_can: dummy_can_init(): fix packet
 statistics

The former implementation was only counting the tx_packets value but not
the tx_bytes as the skb was dropped on driver layer.

Enable CAN echo support (IFF_ECHO) in dummy_can_init(), which activates the
code for setting and retrieving the echo SKB and counts the tx_bytes
correctly.

Fixes: 816cf430e84b ("can: add dummy_can driver")
Cc: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20260126104540.21024-1-socketcan@hartkopp.net
[mkl: make commit message imperative]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dummy_can.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c
index 41953655e3d3..cd23de488edc 100644
--- a/drivers/net/can/dummy_can.c
+++ b/drivers/net/can/dummy_can.c
@@ -241,6 +241,7 @@ static int __init dummy_can_init(void)
 
 	dev->netdev_ops = &dummy_can_netdev_ops;
 	dev->ethtool_ops = &dummy_can_ethtool_ops;
+	dev->flags |= IFF_ECHO; /* enable echo handling */
 	priv = netdev_priv(dev);
 	priv->can.bittiming_const = &dummy_can_bittiming_const;
 	priv->can.bitrate_max = 20 * MEGA /* BPS */;

From ab3f894de216f4a62adc3b57e9191888cbf26885 Mon Sep 17 00:00:00 2001
From: Alban Bedel <alban.bedel@lht.dlh.de>
Date: Mon, 9 Feb 2026 15:47:05 +0100
Subject: [PATCH 0625/1303] can: mcp251x: fix deadlock in error path of
 mcp251x_open

The mcp251x_open() function call free_irq() in its error path with the
mpc_lock mutex held. But if an interrupt already occurred the
interrupt handler will be waiting for the mpc_lock and free_irq() will
deadlock waiting for the handler to finish.

This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can:
mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but
for the error path.

To solve this issue move the call to free_irq() after the lock is
released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ
handler will exit right away once it acquired the lock.

Signed-off-by: Alban Bedel <alban.bedel@lht.dlh.de>
Link: https://patch.msgid.link/20260209144706.2261954-1-alban.bedel@lht.dlh.de
Fixes: bf66f3736a94 ("can: mcp251x: Move to threaded interrupts instead of workqueues.")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/mcp251x.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index fa97adf25b73..bb7782582f40 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
+	bool release_irq = false;
 	unsigned long flags = 0;
 	int ret;
 
@@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net)
 	return 0;
 
 out_free_irq:
-	free_irq(spi->irq, priv);
+	/* The IRQ handler might be running, and if so it will be waiting
+	 * for the lock. But free_irq() must wait for the handler to finish
+	 * so calling it here would deadlock.
+	 *
+	 * Setting priv->force_quit will let the handler exit right away
+	 * without any access to the hardware. This make it safe to call
+	 * free_irq() after the lock is released.
+	 */
+	priv->force_quit = 1;
+	release_irq = true;
+
 	mcp251x_hw_sleep(spi);
 out_close:
 	mcp251x_power_enable(priv->transceiver, 0);
 	close_candev(net);
 	mutex_unlock(&priv->mcp_lock);
+	if (release_irq)
+		free_irq(spi->irq, priv);
 	return ret;
 }
 

From 5f4338e5633dc034a81000b2516a78cfb51c601d Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Mon, 2 Mar 2026 14:12:17 +0530
Subject: [PATCH 0626/1303] ALSA: hda/hdmi: Add Tegra238 HDA codec device ID

Add Tegra238 HDA codec device in hda_device_id list.

Signed-off-by: Sheetal <sheetal@nvidia.com>
Link: https://patch.msgid.link/20260302084217.3135982-1-sheetal@nvidia.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/hdmi/tegrahdmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/hdmi/tegrahdmi.c b/sound/hda/codecs/hdmi/tegrahdmi.c
index 5f6fe31aa202..ebb6410a4831 100644
--- a/sound/hda/codecs/hdmi/tegrahdmi.c
+++ b/sound/hda/codecs/hdmi/tegrahdmi.c
@@ -299,6 +299,7 @@ static const struct hda_device_id snd_hda_id_tegrahdmi[] = {
 	HDA_CODEC_ID_MODEL(0x10de002f, "Tegra194 HDMI/DP2",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0030, "Tegra194 HDMI/DP3",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0031, "Tegra234 HDMI/DP",	MODEL_TEGRA234),
+	HDA_CODEC_ID_MODEL(0x10de0032, "Tegra238 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0033, "SoC 33 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0034, "Tegra264 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0035, "SoC 35 HDMI/DP",	MODEL_TEGRA234),

From 968b098220e393a10488b6a5dddb302b2eaedf66 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Fri, 13 Feb 2026 20:39:27 +0000
Subject: [PATCH 0627/1303] can: esd_usb: add endpoint type validation

esd_usb_probe() constructs bulk pipes for two endpoints without
verifying their transfer types:

  - usb_rcvbulkpipe(dev->udev, 1) for RX (version reply, async RX data)
  - usb_sndbulkpipe(dev->udev, 2) for TX (version query, CAN frames)

A malformed USB device can present these endpoints with transfer types
that differ from what the driver assumes, triggering the WARNING in
usb_submit_urb().

Use usb_find_common_endpoints() to discover and validate the first
bulk IN and bulk OUT endpoints at probe time, before any allocation.
Found pipes are saved to struct esd_usb and code uses them directly
instead of making pipes in place.

Similar to
- commit 136bed0bfd3b ("can: mcba_usb: properly check endpoint type")
  which established the usb_find_common_endpoints() + stored pipes
  pattern for CAN USB drivers.

Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device")
Suggested-by: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20260213203927.599163-1-n7l8m4@u.northwestern.edu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/esd_usb.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 2892a68f510a..d257440fa01f 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -272,6 +272,9 @@ struct esd_usb {
 
 	struct usb_anchor rx_submitted;
 
+	unsigned int rx_pipe;
+	unsigned int tx_pipe;
+
 	int net_count;
 	u32 version;
 	int rxinitdone;
@@ -537,7 +540,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb)
 	}
 
 resubmit_urb:
-	usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1),
+	usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe,
 			  urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE,
 			  esd_usb_read_bulk_callback, dev);
 
@@ -626,9 +629,7 @@ static int esd_usb_send_msg(struct esd_usb *dev, union esd_usb_msg *msg)
 {
 	int actual_length;
 
-	return usb_bulk_msg(dev->udev,
-			    usb_sndbulkpipe(dev->udev, 2),
-			    msg,
+	return usb_bulk_msg(dev->udev, dev->tx_pipe, msg,
 			    msg->hdr.len * sizeof(u32), /* convert to # of bytes */
 			    &actual_length,
 			    1000);
@@ -639,12 +640,8 @@ static int esd_usb_wait_msg(struct esd_usb *dev,
 {
 	int actual_length;
 
-	return usb_bulk_msg(dev->udev,
-			    usb_rcvbulkpipe(dev->udev, 1),
-			    msg,
-			    sizeof(*msg),
-			    &actual_length,
-			    1000);
+	return usb_bulk_msg(dev->udev, dev->rx_pipe, msg,
+			    sizeof(*msg), &actual_length, 1000);
 }
 
 static int esd_usb_setup_rx_urbs(struct esd_usb *dev)
@@ -677,8 +674,7 @@ static int esd_usb_setup_rx_urbs(struct esd_usb *dev)
 
 		urb->transfer_dma = buf_dma;
 
-		usb_fill_bulk_urb(urb, dev->udev,
-				  usb_rcvbulkpipe(dev->udev, 1),
+		usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe,
 				  buf, ESD_USB_RX_BUFFER_SIZE,
 				  esd_usb_read_bulk_callback, dev);
 		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
@@ -903,7 +899,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb,
 	/* hnd must not be 0 - MSB is stripped in txdone handling */
 	msg->tx.hnd = BIT(31) | i; /* returned in TX done message */
 
-	usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf,
+	usb_fill_bulk_urb(urb, dev->udev, dev->tx_pipe, buf,
 			  msg->hdr.len * sizeof(u32), /* convert to # of bytes */
 			  esd_usb_write_bulk_callback, context);
 
@@ -1298,10 +1294,16 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 static int esd_usb_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_endpoint_descriptor *ep_in, *ep_out;
 	struct esd_usb *dev;
 	union esd_usb_msg *msg;
 	int i, err;
 
+	err = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out,
+					NULL, NULL);
+	if (err)
+		return err;
+
 	dev = kzalloc_obj(*dev);
 	if (!dev) {
 		err = -ENOMEM;
@@ -1309,6 +1311,8 @@ static int esd_usb_probe(struct usb_interface *intf,
 	}
 
 	dev->udev = interface_to_usbdev(intf);
+	dev->rx_pipe = usb_rcvbulkpipe(dev->udev, ep_in->bEndpointAddress);
+	dev->tx_pipe = usb_sndbulkpipe(dev->udev, ep_out->bEndpointAddress);
 
 	init_usb_anchor(&dev->rx_submitted);
 

From 38a01c9700b0dcafe97dfa9dc7531bf4a245deff Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:51:17 +0100
Subject: [PATCH 0628/1303] can: ems_usb: ems_usb_read_bulk_callback(): check
 the proper length of a message

When looking at the data in a USB urb, the actual_length is the size of
the buffer passed to the driver, not the transfer_buffer_length which is
set by the driver as the max size of the buffer.

When parsing the messages in ems_usb_read_bulk_callback() properly check
the size both at the beginning of parsing the message to make sure it is
big enough for the expected structure, and at the end of the message to
make sure we don't overflow past the end of the buffer for the next
message.

Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022316-answering-strainer-a5db@gregkh
Fixes: 702171adeed3 ("ems_usb: Added support for EMS CPC-USB/ARM7 CAN/USB interface")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ems_usb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 4c219a5b139b..9b25dda7c183 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 		start = CPC_HEADER_SIZE;
 
 		while (msg_count) {
+			if (start + CPC_MSG_HEADER_LEN > urb->actual_length) {
+				netdev_err(netdev, "format error\n");
+				break;
+			}
+
 			msg = (struct ems_cpc_msg *)&ibuf[start];
 
 			switch (msg->type) {
@@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 			start += CPC_MSG_HEADER_LEN + msg->length;
 			msg_count--;
 
-			if (start > urb->transfer_buffer_length) {
+			if (start > urb->actual_length) {
 				netdev_err(netdev, "format error\n");
 				break;
 			}

From 1e446fd0582ad8be9f6dafb115fc2e7245f9bea7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:30:20 +0100
Subject: [PATCH 0629/1303] can: ucan: Fix infinite loop from zero-length
 messages

If a broken ucan device gets a message with the message length field set
to 0, then the driver will loop for forever in
ucan_read_bulk_callback(), hanging the system.  If the length is 0, just
skip the message and go on to the next one.

This has been fixed in the kvaser_usb driver in the past in commit
0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in
command parsers"), so there must be some broken devices out there like
this somewhere.

Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022319-huff-absurd-6a18@gregkh
Fixes: 9f2d3eae88d2 ("can: ucan: add driver for Theobroma Systems UCAN devices")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ucan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index c79508b1c43e..0ea0ac75e42f 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -748,7 +748,7 @@ static void ucan_read_bulk_callback(struct urb *urb)
 		len = le16_to_cpu(m->len);
 
 		/* check sanity (length of content) */
-		if (urb->actual_length - pos < len) {
+		if ((len == 0) || (urb->actual_length - pos < len)) {
 			netdev_warn(up->netdev,
 				    "invalid message (short; no data; l:%d)\n",
 				    urb->actual_length);

From 5eaad4f768266f1f17e01232ffe2ef009f8129b7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:39:20 +0100
Subject: [PATCH 0630/1303] can: usb: etas_es58x: correctly anchor the urb in
 the read bulk callback

When submitting an urb, that is using the anchor pattern, it needs to be
anchored before submitting it otherwise it could be leaked if
usb_kill_anchored_urbs() is called.  This logic is correctly done
elsewhere in the driver, except in the read bulk callback so do that
here also.

Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Tested-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/2026022320-poser-stiffly-9d84@gregkh
Fixes: 8537257874e9 ("can: etas_es58x: add core support for ETAS ES58X CAN USB interfaces")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/etas_es58x/es58x_core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c
index 2d248deb69dc..b259f6109808 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.c
@@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb)
 	}
 
  resubmit_urb:
+	usb_anchor_urb(urb, &es58x_dev->rx_urbs);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV) {
 		for (i = 0; i < es58x_dev->num_can_ch; i++)
 			if (es58x_dev->netdev[i])
 				netif_device_detach(es58x_dev->netdev[i]);
-	} else if (ret)
+	} else
 		dev_err_ratelimited(dev,
 				    "Failed resubmitting read bulk urb: %pe\n",
 				    ERR_PTR(ret));

From 7299b1b39a255f6092ce4ec0b65f66e9d6a357af Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:30 +0100
Subject: [PATCH 0631/1303] can: usb: f81604: handle short interrupt urb
 messages properly

If an interrupt urb is received that is not the correct length, properly
detect it and don't attempt to treat the data as valid.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022331-opal-evaluator-a928@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index 76578063ac82..c61bd30d1765 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -620,6 +620,12 @@ static void f81604_read_int_callback(struct urb *urb)
 		netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__,
 			    ERR_PTR(urb->status));
 
+	if (urb->actual_length < sizeof(*data)) {
+		netdev_warn(netdev, "%s: short int URB: %u < %zu\n",
+			    __func__, urb->actual_length, sizeof(*data));
+		goto resubmit_urb;
+	}
+
 	switch (urb->status) {
 	case 0: /* success */
 		break;

From 51f94780720fa90c424f67e3e9784cb8ef8190e5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:31 +0100
Subject: [PATCH 0632/1303] can: usb: f81604: handle bulk write errors properly

If a write urb fails then more needs to be done other than just logging
the message, otherwise the transmission could be stalled.  Properly
increment the error counters and wake up the queues so that data will
continue to flow.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022334-slackness-dynamic-9195@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index c61bd30d1765..1cc927d79b6a 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -880,9 +880,27 @@ static void f81604_write_bulk_callback(struct urb *urb)
 	if (!netif_device_present(netdev))
 		return;
 
-	if (urb->status)
-		netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__,
-			    ERR_PTR(urb->status));
+	if (!urb->status)
+		return;
+
+	switch (urb->status) {
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+		return;
+	default:
+		break;
+	}
+
+	if (net_ratelimit())
+		netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__,
+			   ERR_PTR(urb->status));
+
+	can_free_echo_skb(netdev, 0, NULL);
+	netdev->stats.tx_dropped++;
+	netdev->stats.tx_errors++;
+
+	netif_wake_queue(netdev);
 }
 
 static void f81604_clear_reg_work(struct work_struct *work)

From 952caa5da10bed22be09612433964f6877ba0dde Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:32 +0100
Subject: [PATCH 0633/1303] can: usb: f81604: correctly anchor the urb in the
 read bulk callback

When submitting an urb, that is using the anchor pattern, it needs to be
anchored before submitting it otherwise it could be leaked if
usb_kill_anchored_urbs() is called.  This logic is correctly done
elsewhere in the driver, except in the read bulk callback so do that
here also.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022334-starlight-scaling-2cea@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index 1cc927d79b6a..f12318268e46 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb)
 {
 	struct f81604_can_frame *frame = urb->transfer_buffer;
 	struct net_device *netdev = urb->context;
+	struct f81604_port_priv *priv = netdev_priv(netdev);
 	int ret;
 
 	if (!netif_device_present(netdev))
@@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb)
 	f81604_process_rx_packet(netdev, frame);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev,
 			   "%s: failed to resubmit read bulk urb: %pe\n",
 			   __func__, ERR_PTR(ret));
@@ -652,10 +658,15 @@ static void f81604_read_int_callback(struct urb *urb)
 		f81604_handle_tx(priv, data);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n",
 			   __func__, ERR_PTR(ret));
 }

From 4ca191cec17a997d0e3b2cd312f3a884288acc27 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Wed, 4 Feb 2026 09:01:00 -0600
Subject: [PATCH 0634/1303] x86/boot/sev: Move SEV decompressor variables into
 the .data section

As part of the work to remove the dependency on calling into the decompressor
code (startup_64()) for a UEFI boot, a call to rmpadjust() was removed from
sev_enable() in favor of checking the value of the snp_vmpl variable.

When booting through a non-UEFI path and calling startup_64(), the call to
sev_enable() is performed before the BSS section is zeroed. With the removal
of the rmpadjust() call and the corresponding check of the return code, the
snp_vmpl variable is checked.

Since the kernel is running at VMPL0, the snp_vmpl variable will not have been
set and should be the default value of 0.  However, since the call occurs
before the BSS is zeroed, the snp_vmpl variable may not actually be zero,
which will cause the guest boot to fail.

Since the decompressor relocates itself, the BSS would need to be cleared both
before and after the relocation, but this would, in effect, cause all of the
changes to BSS variables before relocation to be lost after relocation.

Instead, move the snp_vmpl variable into the .data section so that it is
initialized and the value made safe during relocation. As a pre-caution
against future changes, move other SEV-related decompressor variables into the
.data section, too.

Fixes: 68a501d7fd82 ("x86/boot: Drop redundant RMPADJUST in SEV SVSM presence check")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Changyuan Lyu <changyuanl@google.com>
Tested-by: Kevin Hui <kevinhui@meta.com>
Tested-by: Changyuan Lyu <changyuanl@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/5648b7de5b0a5d0dfef3785f9582b718678c6448.1770217260.git.thomas.lendacky@amd.com
---
 arch/x86/boot/compressed/sev.c     | 8 ++++----
 arch/x86/boot/startup/sev-shared.c | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index c8c1464b3a56..46b54720d91d 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -28,17 +28,17 @@
 #include "sev.h"
 
 static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
-struct ghcb *boot_ghcb;
+struct ghcb *boot_ghcb __section(".data");
 
 #undef __init
 #define __init
 
 #define __BOOT_COMPRESSED
 
-u8 snp_vmpl;
-u16 ghcb_version;
+u8 snp_vmpl __section(".data");
+u16 ghcb_version __section(".data");
 
-u64 boot_svsm_caa_pa;
+u64 boot_svsm_caa_pa __section(".data");
 
 /* Include code for early handlers */
 #include "../../boot/startup/sev-shared.c"
diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c
index a0fa8bb2b945..d9ac3a929d33 100644
--- a/arch/x86/boot/startup/sev-shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -31,7 +31,7 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
-bool sev_snp_needs_sfw;
+bool sev_snp_needs_sfw __section(".data");
 
 void __noreturn
 sev_es_terminate(unsigned int set, unsigned int reason)

From 9073428bb204d921ae15326bb7d4558d9d269aab Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@amd.com>
Date: Tue, 3 Feb 2026 16:24:03 -0600
Subject: [PATCH 0635/1303] x86/sev: Allow IBPB-on-Entry feature for SNP guests

The SEV-SNP IBPB-on-Entry feature does not require a guest-side
implementation. It was added in Zen5 h/w, after the first SNP Zen
implementation, and thus was not accounted for when the initial set of SNP
features were added to the kernel.

In its abundant precaution, commit

  8c29f0165405 ("x86/sev: Add SEV-SNP guest feature negotiation support")

included SEV_STATUS' IBPB-on-Entry bit as a reserved bit, thereby masking
guests from using the feature.

Allow guests to make use of IBPB-on-Entry when supported by the hypervisor, as
the bit is now architecturally defined and safe to expose.

Fixes: 8c29f0165405 ("x86/sev: Add SEV-SNP guest feature negotiation support")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: stable@kernel.org
Link: https://patch.msgid.link/20260203222405.4065706-2-kim.phillips@amd.com
---
 arch/x86/boot/compressed/sev.c   | 1 +
 arch/x86/coco/sev/core.c         | 1 +
 arch/x86/include/asm/msr-index.h | 5 ++++-
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 46b54720d91d..e468476e9e4a 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -188,6 +188,7 @@ bool sev_es_check_ghcb_fault(unsigned long address)
 				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
 				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
 				 MSR_AMD64_SNP_SECURE_AVIC |		\
+				 MSR_AMD64_SNP_RESERVED_BITS19_22 |	\
 				 MSR_AMD64_SNP_RESERVED_MASK)
 
 #ifdef CONFIG_AMD_SECURE_AVIC
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 907981b94c40..7ed3da998489 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -89,6 +89,7 @@ static const char * const sev_status_feat_names[] = {
 	[MSR_AMD64_SNP_VMSA_REG_PROT_BIT]	= "VMSARegProt",
 	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
 	[MSR_AMD64_SNP_SECURE_AVIC_BIT]		= "SecureAVIC",
+	[MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT]	= "IBPBOnEntry",
 };
 
 /*
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index da5275d8eda6..6673601246b3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -740,7 +740,10 @@
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
 #define MSR_AMD64_SNP_SECURE_AVIC_BIT	18
 #define MSR_AMD64_SNP_SECURE_AVIC	BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT)
-#define MSR_AMD64_SNP_RESV_BIT		19
+#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19)
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT	23
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY	BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		24
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
 #define MSR_AMD64_SAVIC_CONTROL		0xc0010138
 #define MSR_AMD64_SAVIC_EN_BIT		0

From 2df6162785f31f1bbb598cfc3b08e4efc88f80b6 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 19 Feb 2026 13:57:34 +0100
Subject: [PATCH 0636/1303] can: gs_usb: gs_can_open(): always configure
 bitrates before starting device

So far the driver populated the struct can_priv::do_set_bittiming() and
struct can_priv::fd::do_set_data_bittiming() callbacks.

Before bringing up the interface, user space has to configure the bitrates.
With these callbacks the configuration is directly forwarded into the CAN
hardware. Then the interface can be brought up.

An ifdown-ifup cycle (without changing the bit rates) doesn't re-configure
the bitrates in the CAN hardware. This leads to a problem with the
CANable-2.5 [1] firmware, which resets the configured bit rates during
ifdown.

To fix the problem remove both bit timing callbacks and always configure
the bitrates in the struct net_device_ops::ndo_open() callback.

[1] https://github.com/Elmue/CANable-2.5-firmware-Slcan-and-Candlelight

Cc: stable@vger.kernel.org
Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices")
Link: https://patch.msgid.link/20260219-gs_usb-always-configure-bitrates-v2-1-671f8ba5b0a5@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 9d27d6f0c0b5..ec9a7cbbbc69 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -772,9 +772,8 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	}
 }
 
-static int gs_usb_set_bittiming(struct net_device *netdev)
+static int gs_usb_set_bittiming(struct gs_can *dev)
 {
-	struct gs_can *dev = netdev_priv(netdev);
 	struct can_bittiming *bt = &dev->can.bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
@@ -791,9 +790,8 @@ static int gs_usb_set_bittiming(struct net_device *netdev)
 				    GFP_KERNEL);
 }
 
-static int gs_usb_set_data_bittiming(struct net_device *netdev)
+static int gs_usb_set_data_bittiming(struct gs_can *dev)
 {
-	struct gs_can *dev = netdev_priv(netdev);
 	struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
@@ -1057,6 +1055,20 @@ static int gs_can_open(struct net_device *netdev)
 	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 		flags |= GS_CAN_MODE_HW_TIMESTAMP;
 
+	rc = gs_usb_set_bittiming(dev);
+	if (rc) {
+		netdev_err(netdev, "failed to set bittiming: %pe\n", ERR_PTR(rc));
+		goto out_usb_kill_anchored_urbs;
+	}
+
+	if (ctrlmode & CAN_CTRLMODE_FD) {
+		rc = gs_usb_set_data_bittiming(dev);
+		if (rc) {
+			netdev_err(netdev, "failed to set data bittiming: %pe\n", ERR_PTR(rc));
+			goto out_usb_kill_anchored_urbs;
+		}
+	}
+
 	/* finally start device */
 	dev->can.state = CAN_STATE_ERROR_ACTIVE;
 	dm.flags = cpu_to_le32(flags);
@@ -1370,7 +1382,6 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 	dev->can.state = CAN_STATE_STOPPED;
 	dev->can.clock.freq = le32_to_cpu(bt_const.fclk_can);
 	dev->can.bittiming_const = &dev->bt_const;
-	dev->can.do_set_bittiming = gs_usb_set_bittiming;
 
 	dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC;
 
@@ -1394,7 +1405,6 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		 * GS_CAN_FEATURE_BT_CONST_EXT is set.
 		 */
 		dev->can.fd.data_bittiming_const = &dev->bt_const;
-		dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming;
 	}
 
 	if (feature & GS_CAN_FEATURE_TERMINATION) {

From 7e1e6d6845329adb2da75110a061557e9c26d9b7 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 12 Feb 2026 11:30:00 -0500
Subject: [PATCH 0637/1303] dt-bindings: net: can: nxp,sja1000: add reference
 to mc-peripheral-props.yaml

Add a reference to mc-peripheral-props.yaml to allow vendor-specific
properties for memory access timings.

Fix below CHECK_DTBS warings:
arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dtb: can@4,0 (nxp,sja1000): Unevaluated properties are not allowed ('fsl,weim-cs-timing' was unexpected)
        from schema $id: http://devicetree.org/schemas/net/can/nxp,sja1000.yaml

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260212163000.1195586-1-Frank.Li@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
index ec0c2168e4b9..6bcfff970117 100644
--- a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
+++ b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
@@ -87,6 +87,7 @@ required:
 
 allOf:
   - $ref: can-controller.yaml#
+  - $ref: /schemas/memory-controllers/mc-peripheral-props.yaml
   - if:
       properties:
         compatible:

From fb797a70108f3fda83fde6dea30bee4be7d5df8b Mon Sep 17 00:00:00 2001
From: Chris Brandt <chris.brandt@renesas.com>
Date: Thu, 26 Feb 2026 20:52:16 -0500
Subject: [PATCH 0638/1303] drm: renesas: rz-du: mipi_dsi: Set DSI divider

Before the MIPI DSI clock source can be configured, the target divide
ratio needs to be set.

Signed-off-by: Chris Brandt <chris.brandt@renesas.com>
Reviewed-by: Biju Das <biju.das.jz@bp.renesas.com>
Tested-by: Biju Das <biju.das.jz@bp.renesas.com>
Fixes: 5a4326f2e3b1 ("clk: renesas: rzg2l: Remove DSI clock rate restrictions")
Link: https://patch.msgid.link/20260227015216.2721504-1-chris.brandt@renesas.com
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
 drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
index f74a0aa85ba8..29f2b7d24fe5 100644
--- a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
+++ b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
@@ -1122,6 +1122,7 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 				      struct mipi_dsi_device *device)
 {
 	struct rzg2l_mipi_dsi *dsi = host_to_rzg2l_mipi_dsi(host);
+	int bpp;
 	int ret;
 
 	if (device->lanes > dsi->num_data_lanes) {
@@ -1131,7 +1132,8 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 		return -EINVAL;
 	}
 
-	switch (mipi_dsi_pixel_format_to_bpp(device->format)) {
+	bpp = mipi_dsi_pixel_format_to_bpp(device->format);
+	switch (bpp) {
 	case 24:
 		break;
 	case 18:
@@ -1162,6 +1164,18 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 
 	drm_bridge_add(&dsi->bridge);
 
+	/*
+	 * Report the required division ratio setting for the MIPI clock dividers.
+	 *
+	 * vclk * bpp = hsclk * 8 * num_lanes
+	 *
+	 * vclk * DSI_AB_divider = hsclk * 16
+	 *
+	 *   which simplifies to...
+	 * DSI_AB_divider = bpp * 2 / num_lanes
+	 */
+	rzg2l_cpg_dsi_div_set_divider(bpp * 2 / dsi->lanes, PLL5_TARGET_DSI);
+
 	return 0;
 }
 

From d973b1039ccde6b241b438d53297edce4de45b5c Mon Sep 17 00:00:00 2001
From: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Date: Sat, 21 Feb 2026 17:28:04 +0100
Subject: [PATCH 0639/1303] wifi: rsi: Don't default to -EOPNOTSUPP in
 rsi_mac80211_config

This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected
behavior from the driver - other drivers default to 0 too.

Fixes: 0a44dfc07074 ("wifi: mac80211: simplify non-chanctx drivers")
Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Link: https://patch.msgid.link/20260221-rsi-config-ret-v1-1-9a8f805e2f31@puri.sm
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/rsi/rsi_91x_mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 8c8e074a3a70..c7ae8031436a 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
 	struct ieee80211_conf *conf = &hw->conf;
-	int status = -EOPNOTSUPP;
+	int status = 0;
 
 	mutex_lock(&common->mutex);
 

From a8df7892a9f42b2e2d5851f8835c734bd7fe8ad4 Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Mon, 2 Mar 2026 14:23:22 +0530
Subject: [PATCH 0640/1303] ASoC: dt-bindings: tegra: Add compatible for
 Tegra238 sound card

Tegra238 requires different PLLA and PLLA_OUT0 clock rates compared to
other Tegra platforms. Add Tegra238 compatible string to the APE
tegra-audio-graph-card bindings.

Signed-off-by: Sheetal <sheetal@nvidia.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260302085323.3139571-2-sheetal@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
index da89523ccf5f..92bc3ef56f2c 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
@@ -23,6 +23,7 @@ properties:
     enum:
       - nvidia,tegra210-audio-graph-card
       - nvidia,tegra186-audio-graph-card
+      - nvidia,tegra238-audio-graph-card
       - nvidia,tegra264-audio-graph-card
 
   clocks:

From 2d85ecd6fb0eb2fee0ffa040ec1ddea57b09bc38 Mon Sep 17 00:00:00 2001
From: Franz Schnyder <franz.schnyder@toradex.com>
Date: Wed, 18 Feb 2026 11:25:14 +0100
Subject: [PATCH 0641/1303] regulator: pf9453: Respect IRQ trigger settings
 from firmware

The datasheet specifies, that the IRQ_B pin is pulled low when any
unmasked interrupt bit status is changed, and it is released high once
the application processor reads the INT1 register. As it specifies a
level-low behavior, it should not force a falling-edge interrupt.

Remove the IRQF_TRIGGER_FALLING to not force the falling-edge interrupt
and instead rely on the flag from the device tree.

Fixes: 0959b6706325 ("regulator: pf9453: add PMIC PF9453 support")
Cc: stable@vger.kernel.org
Signed-off-by: Franz Schnyder <franz.schnyder@toradex.com>
Link: https://patch.msgid.link/20260218102518.238943-2-fra.schnyder@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pf9453-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/pf9453-regulator.c b/drivers/regulator/pf9453-regulator.c
index 779a6fdb0574..eed3055d1c1c 100644
--- a/drivers/regulator/pf9453-regulator.c
+++ b/drivers/regulator/pf9453-regulator.c
@@ -809,7 +809,7 @@ static int pf9453_i2c_probe(struct i2c_client *i2c)
 	}
 
 	ret = devm_request_threaded_irq(pf9453->dev, pf9453->irq, NULL, pf9453_irq_handler,
-					(IRQF_TRIGGER_FALLING | IRQF_ONESHOT),
+					IRQF_ONESHOT,
 					"pf9453-irq", pf9453);
 	if (ret)
 		return dev_err_probe(pf9453->dev, ret, "Failed to request IRQ: %d\n", pf9453->irq);

From e176ad7b57a1a15ece213251b7f3103bd929e26c Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Mon, 2 Mar 2026 13:24:52 +0100
Subject: [PATCH 0642/1303] dt-bindings: hwmon: sl28cpld: Drop sa67mcu
 compatible

I was just informed that this product is discontinued (without being
ever released to the market). Pull the plug and let's not waste any more
maintainers time and revert commit 0f6eae86e626 ("dt-bindings: hwmon:
sl28cpld: add sa67mcu compatible").

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Michael Walle <mwalle@kernel.org>
Link: https://lore.kernel.org/r/20260302122540.1377444-8-mwalle@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 .../devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml        | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
index 966b221b6caa..5803a1770cad 100644
--- a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
+++ b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
@@ -16,7 +16,6 @@ description: |
 properties:
   compatible:
     enum:
-      - kontron,sa67mcu-hwmon
       - kontron,sl28cpld-fan
 
   reg:

From 2e3649e237237258a08d75afef96648dd2b379f7 Mon Sep 17 00:00:00 2001
From: Julian Orth <ju.orth@gmail.com>
Date: Sun, 1 Mar 2026 13:34:42 +0100
Subject: [PATCH 0643/1303] drm/syncobj: Fix handle <-> fd ioctls with dirty
 stack
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Consider the following application:

    #include <fcntl.h>
    #include <string.h>
    #include <drm/drm.h>
    #include <sys/ioctl.h>

    int main(void) {
        int fd = open("/dev/dri/renderD128", O_RDWR);
        struct drm_syncobj_create arg1;
        ioctl(fd, DRM_IOCTL_SYNCOBJ_CREATE, &arg1);
        struct drm_syncobj_handle arg2;
        memset(&arg2, 1, sizeof(arg2)); // simulate dirty stack
        arg2.handle = arg1.handle;
        arg2.flags = 0;
        arg2.fd = 0;
        arg2.pad = 0;
        // arg2.point = 0; // userspace is required to set point to 0
        ioctl(fd, DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD, &arg2);
    }

The last ioctl returns EINVAL because args->point is not 0. However,
userspace developed against older kernel versions is not aware of the
new point field and might therefore not initialize it.

The correct check would be

    if (args->flags & DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE)
        return -EINVAL;

However, there might already be userspace that relies on this not
returning an error as long as point == 0. Therefore use the more lenient
check.

Fixes: c2d3a7300695 ("drm/syncobj: Extend EXPORT_SYNC_FILE for timeline syncobjs")
Signed-off-by: Julian Orth <ju.orth@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20260301-point-v1-1-21fc5fd98614@gmail.com
---
 drivers/gpu/drm/drm_syncobj.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 250734dee928..49eccb43ce63 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -875,7 +875,7 @@ drm_syncobj_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 		return drm_syncobj_export_sync_file(file_private, args->handle,
 						    point, &args->fd);
 
-	if (args->point)
+	if (point)
 		return -EINVAL;
 
 	return drm_syncobj_handle_to_fd(file_private, args->handle,
@@ -909,7 +909,7 @@ drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 							  args->handle,
 							  point);
 
-	if (args->point)
+	if (point)
 		return -EINVAL;
 
 	return drm_syncobj_fd_to_handle(file_private, args->fd,

From cdc8a1e11f4d5b480ec750e28010c357185b95a6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 14 Jan 2026 16:45:46 -0800
Subject: [PATCH 0644/1303] drm/xe: Do not preempt fence signaling CS
 instructions

If a batch buffer is complete, it makes little sense to preempt the
fence signaling instructions in the ring, as the largest portion of the
work (the batch buffer) is already done and fence signaling consists of
only a few instructions. If these instructions are preempted, the GuC
would need to perform a context switch just to signal the fence, which
is costly and delays fence signaling. Avoid this scenario by disabling
preemption immediately after the BB start instruction and re-enabling it
after executing the fence signaling instructions.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Carlos Santa <carlos.santa@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patch.msgid.link/20260115004546.58060-1-matthew.brost@intel.com
(cherry picked from commit 2bcbf2dcde0c839a73af664a3c77d4e77d58a3eb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_ring_ops.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 248620b0901d..53d420d72164 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -280,6 +280,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -345,6 +348,9 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -397,6 +403,9 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	i = emit_render_cache_flush(job, dw, i);
 
 	if (job->user_fence.used)

From e377182f0266f46f02d01838e6bde67b9dac0d66 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Wed, 25 Feb 2026 01:34:49 +0000
Subject: [PATCH 0645/1303] drm/xe/configfs: Free ctx_restore_mid_bb in release

ctx_restore_mid_bb memory is allocated in wa_bb_store(), but
xe_config_device_release() only frees ctx_restore_post_bb.

Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation
when the configfs device is removed.

Fixes: b30d5de3d40c ("drm/xe/configfs: Add mid context restore bb")
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Nitin Gote <nitin.r.gote@intel.com>
Link: https://patch.msgid.link/20260225013448.3547687-2-shuicheng.lin@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index c59b1414df22..7fd07d1280bb 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -830,6 +830,7 @@ static void xe_config_device_release(struct config_item *item)
 
 	mutex_destroy(&dev->lock);
 
+	kfree(dev->config.ctx_restore_mid_bb[0].cs);
 	kfree(dev->config.ctx_restore_post_bb[0].cs);
 	kfree(dev);
 }

From 99f9b5343cae80eb0dfe050baf6c86d722b3ba2e Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Thu, 26 Feb 2026 22:26:58 +0100
Subject: [PATCH 0646/1303] drm/xe/queue: Call fini on exec queue creation fail

Every call to queue init should have a corresponding fini call.
Skipping this would mean skipping removal of the queue from GuC list
(which is part of guc_id allocation). A damaged queue stored in
exec_queue_lookup list would lead to invalid memory reference,
sooner or later.

Call fini to free guc_id. This must be done before any internal
LRCs are freed.

Since the finalization with this extra call became very similar to
__xe_exec_queue_fini(), reuse that. To make this reuse possible,
alter xe_lrc_put() so it can survive NULL parameters, like other
similar functions.

v2: Reuse _xe_exec_queue_fini(). Make xe_lrc_put() aware of NULLs.

Fixes: 3c1fa4aa60b1 ("drm/xe: Move queue init before LRC creation")
Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com> (v1)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20260226212701.2937065-2-tomasz.lis@intel.com
(cherry picked from commit 393e5fea6f7d7054abc2c3d97a4cfe8306cd6079)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 23 +++++++++++------------
 drivers/gpu/drm/xe/xe_lrc.h        |  3 ++-
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0ddae7fcfc97..8ecdf949f9e4 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -266,6 +266,16 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 	return q;
 }
 
+static void __xe_exec_queue_fini(struct xe_exec_queue *q)
+{
+	int i;
+
+	q->ops->fini(q);
+
+	for (i = 0; i < q->width; ++i)
+		xe_lrc_put(q->lrc[i]);
+}
+
 static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags)
 {
 	int i, err;
@@ -320,21 +330,10 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags)
 	return 0;
 
 err_lrc:
-	for (i = i - 1; i >= 0; --i)
-		xe_lrc_put(q->lrc[i]);
+	__xe_exec_queue_fini(q);
 	return err;
 }
 
-static void __xe_exec_queue_fini(struct xe_exec_queue *q)
-{
-	int i;
-
-	q->ops->fini(q);
-
-	for (i = 0; i < q->width; ++i)
-		xe_lrc_put(q->lrc[i]);
-}
-
 struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm,
 					   u32 logical_mask, u16 width,
 					   struct xe_hw_engine *hwe, u32 flags,
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index c307a3fd9ea2..c1c615447c85 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -75,7 +75,8 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
  */
 static inline void xe_lrc_put(struct xe_lrc *lrc)
 {
-	kref_put(&lrc->refcount, xe_lrc_destroy);
+	if (lrc)
+		kref_put(&lrc->refcount, xe_lrc_destroy);
 }
 
 /**

From da46b5dfef48658d03347cda21532bcdbb521e67 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Sun, 1 Mar 2026 16:22:07 -0800
Subject: [PATCH 0647/1303] blktrace: fix __this_cpu_read/write in preemptible
 context

tracing_record_cmdline() internally uses __this_cpu_read() and
__this_cpu_write() on the per-CPU variable trace_cmdline_save, and
trace_save_cmdline() explicitly asserts preemption is disabled via
lockdep_assert_preemption_disabled(). These operations are only safe
when preemption is off, as they were designed to be called from the
scheduler context (probe_wakeup_sched_switch() / probe_wakeup()).

__blk_add_trace() was calling tracing_record_cmdline(current) early in
the blk_tracer path, before ring buffer reservation, from process
context where preemption is fully enabled. This triggers the following
using blktests/blktrace/002:

blktrace/002 (blktrace ftrace corruption with sysfs trace)   [failed]
    runtime  0.367s  ...  0.437s
    something found in dmesg:
    [   81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
    [   81.239580] null_blk: disk nullb1 created
    [   81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
    [   81.362842] caller is tracing_record_cmdline+0x10/0x40
    [   81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G                 N  7.0.0-rc1lblk+ #84 PREEMPT(full)
    [   81.362877] Tainted: [N]=TEST
    [   81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
    [   81.362881] Call Trace:
    [   81.362884]  <TASK>
    [   81.362886]  dump_stack_lvl+0x8d/0xb0
    ...
    (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message)

[   81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
[   81.239580] null_blk: disk nullb1 created
[   81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
[   81.362842] caller is tracing_record_cmdline+0x10/0x40
[   81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G                 N  7.0.0-rc1lblk+ #84 PREEMPT(full)
[   81.362877] Tainted: [N]=TEST
[   81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
[   81.362881] Call Trace:
[   81.362884]  <TASK>
[   81.362886]  dump_stack_lvl+0x8d/0xb0
[   81.362895]  check_preemption_disabled+0xce/0xe0
[   81.362902]  tracing_record_cmdline+0x10/0x40
[   81.362923]  __blk_add_trace+0x307/0x5d0
[   81.362934]  ? lock_acquire+0xe0/0x300
[   81.362940]  ? iov_iter_extract_pages+0x101/0xa30
[   81.362959]  blk_add_trace_bio+0x106/0x1e0
[   81.362968]  submit_bio_noacct_nocheck+0x24b/0x3a0
[   81.362979]  ? lockdep_init_map_type+0x58/0x260
[   81.362988]  submit_bio_wait+0x56/0x90
[   81.363009]  __blkdev_direct_IO_simple+0x16c/0x250
[   81.363026]  ? __pfx_submit_bio_wait_endio+0x10/0x10
[   81.363038]  ? rcu_read_lock_any_held+0x73/0xa0
[   81.363051]  blkdev_read_iter+0xc1/0x140
[   81.363059]  vfs_read+0x20b/0x330
[   81.363083]  ksys_read+0x67/0xe0
[   81.363090]  do_syscall_64+0xbf/0xf00
[   81.363102]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   81.363106] RIP: 0033:0x7f281906029d
[   81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec
[   81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[   81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d
[   81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000
[   81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000
[   81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000
[   81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a
[   81.363142]  </TASK>

The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(),
and blk_add_trace_rq() paths as well.

The purpose of tracing_record_cmdline() is to cache the task->comm for
a given PID so that the trace can later resolve it. It is only
meaningful when a trace event is actually being recorded. Ring buffer
reservation via ring_buffer_lock_reserve() disables preemption, and
preemption remains disabled until the event is committed :-

__blk_add_trace()
       	__trace_buffer_lock_reserve()
       		__trace_buffer_lock_reserve()
       			ring_buffer_lock_reserve()
       				preempt_disable_notrace();  <---

With this fix blktests for blktrace pass:

  blktests (master) # ./check blktrace
  blktrace/001 (blktrace zone management command tracing)      [passed]
      runtime  3.650s  ...  3.647s
  blktrace/002 (blktrace ftrace corruption with sysfs trace)   [passed]
      runtime  0.411s  ...  0.384s

Fixes: 7ffbd48d5cab ("tracing: Cache comms only after an event occurred")
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/trace/blktrace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index e6988929ead2..18a9b84cc768 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -383,8 +383,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	cpu = raw_smp_processor_id();
 
 	if (blk_tracer) {
-		tracing_record_cmdline(current);
-
 		buffer = blk_tr->array_buffer.buffer;
 		trace_ctx = tracing_gen_ctx_flags(0);
 		switch (bt->version) {
@@ -419,6 +417,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		if (!event)
 			return;
 
+		tracing_record_cmdline(current);
 		switch (bt->version) {
 		case 1:
 			record_blktrace_event(ring_buffer_event_data(event),

From c36e28becd0586ac98318fd335e5e91d19cd2623 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 2 Mar 2026 14:32:04 +0000
Subject: [PATCH 0648/1303] io_uring/net: reject SEND_VECTORIZED when
 unsupported

IORING_SEND_VECTORIZED with registered buffers is not implemented but
could be. Don't silently ignore the flag in this case but reject it with
an error. It only affects sendzc as normal sends don't support
registered buffers.

Fixes: 6f02527729bd3 ("io_uring/net: Allow to do vectorized send")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/net.c b/io_uring/net.c
index 8576c6cb2236..d27adbe3f20b 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -375,6 +375,8 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		kmsg->msg.msg_namelen = addr_len;
 	}
 	if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+		if (sr->flags & IORING_SEND_VECTORIZED)
+			return -EINVAL;
 		req->flags |= REQ_F_IMPORT_BUFFER;
 		return 0;
 	}

From 539d1b47e935e8384977dd7e5cec370c08b7a644 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Sun, 1 Mar 2026 18:29:43 +0530
Subject: [PATCH 0649/1303] block: break pcpu_alloc_mutex dependency on
 freeze_lock

While nr_hw_update allocates tagset tags it acquires ->pcpu_alloc_mutex
after ->freeze_lock is acquired or queue is frozen. This potentially
creates a circular dependency involving ->fs_reclaim if reclaim is
triggered simultaneously in a code path which first acquires ->pcpu_
alloc_mutex. As the queue is already frozen while nr_hw_queue update
allocates tagsets, the reclaim can't forward progress and thus it could
cause a potential deadlock as reported in lockdep splat[1].

Fix this by pre-allocating tagset tags before we freeze queue during
nr_hw_queue update. Later the allocated tagset tags could be safely
installed and used after queue is frozen.

Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/all/CAHj4cs8F=OV9s3La2kEQ34YndgfZP-B5PHS4Z8_b9euKG6J4mw@mail.gmail.com/ [1]
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Yu Kuai <yukuai@fnnas.com>
[axboe: fix brace style issue]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 45 ++++++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 15 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d5602ff62c7c..0b182013016a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4793,38 +4793,45 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
-static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
-				       int new_nr_hw_queues)
+static struct blk_mq_tags **blk_mq_prealloc_tag_set_tags(
+				struct blk_mq_tag_set *set,
+				int new_nr_hw_queues)
 {
 	struct blk_mq_tags **new_tags;
 	int i;
 
 	if (set->nr_hw_queues >= new_nr_hw_queues)
-		goto done;
+		return NULL;
 
 	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
 				GFP_KERNEL, set->numa_node);
 	if (!new_tags)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	if (set->tags)
 		memcpy(new_tags, set->tags, set->nr_hw_queues *
 		       sizeof(*set->tags));
-	kfree(set->tags);
-	set->tags = new_tags;
 
 	for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) {
-		if (!__blk_mq_alloc_map_and_rqs(set, i)) {
-			while (--i >= set->nr_hw_queues)
-				__blk_mq_free_map_and_rqs(set, i);
-			return -ENOMEM;
+		if (blk_mq_is_shared_tags(set->flags)) {
+			new_tags[i] = set->shared_tags;
+		} else {
+			new_tags[i] = blk_mq_alloc_map_and_rqs(set, i,
+					set->queue_depth);
+			if (!new_tags[i])
+				goto out_unwind;
 		}
 		cond_resched();
 	}
 
-done:
-	set->nr_hw_queues = new_nr_hw_queues;
-	return 0;
+	return new_tags;
+out_unwind:
+	while (--i >= set->nr_hw_queues) {
+		if (!blk_mq_is_shared_tags(set->flags))
+			blk_mq_free_map_and_rqs(set, new_tags[i], i);
+	}
+	kfree(new_tags);
+	return ERR_PTR(-ENOMEM);
 }
 
 /*
@@ -5113,6 +5120,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	unsigned int memflags;
 	int i;
 	struct xarray elv_tbl;
+	struct blk_mq_tags **new_tags;
 	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5147,11 +5155,18 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		if (blk_mq_elv_switch_none(q, &elv_tbl))
 			goto switch_back;
 
+	new_tags = blk_mq_prealloc_tag_set_tags(set, nr_hw_queues);
+	if (IS_ERR(new_tags))
+		goto switch_back;
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue_nomemsave(q);
 	queues_frozen = true;
-	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
-		goto switch_back;
+	if (new_tags) {
+		kfree(set->tags);
+		set->tags = new_tags;
+	}
+	set->nr_hw_queues = nr_hw_queues;
 
 fallback:
 	blk_mq_update_queue_map(set);

From b570f37a2ce480be26c665345c5514686a8a0274 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 10 Feb 2026 12:56:53 +0100
Subject: [PATCH 0650/1303] mm: Fix a hmm_range_fault() livelock / starvation
 problem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If hmm_range_fault() fails a folio_trylock() in do_swap_page,
trying to acquire the lock of a device-private folio for migration,
to ram, the function will spin until it succeeds grabbing the lock.

However, if the process holding the lock is depending on a work
item to be completed, which is scheduled on the same CPU as the
spinning hmm_range_fault(), that work item might be starved and
we end up in a livelock / starvation situation which is never
resolved.

This can happen, for example if the process holding the
device-private folio lock is stuck in
   migrate_device_unmap()->lru_add_drain_all()
sinc lru_add_drain_all() requires a short work-item
to be run on all online cpus to complete.

A prerequisite for this to happen is:
a) Both zone device and system memory folios are considered in
   migrate_device_unmap(), so that there is a reason to call
   lru_add_drain_all() for a system memory folio while a
   folio lock is held on a zone device folio.
b) The zone device folio has an initial mapcount > 1 which causes
   at least one migration PTE entry insertion to be deferred to
   try_to_migrate(), which can happen after the call to
   lru_add_drain_all().
c) No or voluntary only preemption.

This all seems pretty unlikely to happen, but indeed is hit by
the "xe_exec_system_allocator" igt test.

Resolve this by waiting for the folio to be unlocked if the
folio_trylock() fails in do_swap_page().

Rename migration_entry_wait_on_locked() to
softleaf_entry_wait_unlock() and update its documentation to
indicate the new use-case.

Future code improvements might consider moving
the lru_add_drain_all() call in migrate_device_unmap() to be
called *after* all pages have migration entries inserted.
That would eliminate also b) above.

v2:
- Instead of a cond_resched() in hmm_range_fault(),
  eliminate the problem by waiting for the folio to be unlocked
  in do_swap_page() (Alistair Popple, Andrew Morton)
v3:
- Add a stub migration_entry_wait_on_locked() for the
  !CONFIG_MIGRATION case. (Kernel Test Robot)
v4:
- Rename migrate_entry_wait_on_locked() to
  softleaf_entry_wait_on_locked() and update docs (Alistair Popple)
v5:
- Add a WARN_ON_ONCE() for the !CONFIG_MIGRATION
  version of softleaf_entry_wait_on_locked().
- Modify wording around function names in the commit message
  (Andrew Morton)

Suggested-by: Alistair Popple <apopple@nvidia.com>
Fixes: 1afaeb8293c9 ("mm/migrate: Trylock device page in do_swap_page")
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: linux-mm@kvack.org
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.15+
Reviewed-by: John Hubbard <jhubbard@nvidia.com> #v3
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Link: https://patch.msgid.link/20260210115653.92413-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit a69d1ab971a624c6f112cea61536569d579c3215)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 include/linux/migrate.h | 10 +++++++++-
 mm/filemap.c            | 15 ++++++++++-----
 mm/memory.c             |  3 ++-
 mm/migrate.c            |  8 ++++----
 mm/migrate_device.c     |  2 +-
 5 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 26ca00c325d9..d5af2b7f577b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 		struct folio *dst, struct folio *src);
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 		__releases(ptl);
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
@@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag
 	return -ENOSYS;
 }
 
+static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+	__releases(ptl)
+{
+	WARN_ON_ONCE(1);
+
+	spin_unlock(ptl);
+}
+
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/filemap.c b/mm/filemap.c
index 6cd7974d4ada..406cef06b684 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1379,14 +1379,16 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 
 #ifdef CONFIG_MIGRATION
 /**
- * migration_entry_wait_on_locked - Wait for a migration entry to be removed
- * @entry: migration swap entry.
+ * softleaf_entry_wait_on_locked - Wait for a migration entry or
+ * device_private entry to be removed.
+ * @entry: migration or device_private swap entry.
  * @ptl: already locked ptl. This function will drop the lock.
  *
- * Wait for a migration entry referencing the given page to be removed. This is
+ * Wait for a migration entry referencing the given page, or device_private
+ * entry referencing a dvice_private page to be unlocked. This is
  * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except
  * this can be called without taking a reference on the page. Instead this
- * should be called while holding the ptl for the migration entry referencing
+ * should be called while holding the ptl for @entry referencing
  * the page.
  *
  * Returns after unlocking the ptl.
@@ -1394,7 +1396,7 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
  * This follows the same logic as folio_wait_bit_common() so see the comments
  * there.
  */
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	__releases(ptl)
 {
 	struct wait_page_queue wait_page;
@@ -1428,6 +1430,9 @@ void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	 * If a migration entry exists for the page the migration path must hold
 	 * a valid reference to the page, and it must take the ptl to remove the
 	 * migration entry. So the page is valid until the ptl is dropped.
+	 * Similarly any path attempting to drop the last reference to a
+	 * device-private page needs to grab the ptl to remove the device-private
+	 * entry.
 	 */
 	spin_unlock(ptl);
 
diff --git a/mm/memory.c b/mm/memory.c
index 07778814b4a8..2f815a34d924 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4763,7 +4763,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				unlock_page(vmf->page);
 				put_page(vmf->page);
 			} else {
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				pte_unmap(vmf->pte);
+				softleaf_entry_wait_on_locked(entry, vmf->ptl);
 			}
 		} else if (softleaf_is_hwpoison(entry)) {
 			ret = VM_FAULT_HWPOISON;
diff --git a/mm/migrate.c b/mm/migrate.c
index 1bf2cf8c44dd..2c3d489ecf51 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -500,7 +500,7 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	if (!softleaf_is_migration(entry))
 		goto out;
 
-	migration_entry_wait_on_locked(entry, ptl);
+	softleaf_entry_wait_on_locked(entry, ptl);
 	return;
 out:
 	spin_unlock(ptl);
@@ -532,10 +532,10 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, p
 		 * If migration entry existed, safe to release vma lock
 		 * here because the pgtable page won't be freed without the
 		 * pgtable lock released.  See comment right above pgtable
-		 * lock release in migration_entry_wait_on_locked().
+		 * lock release in softleaf_entry_wait_on_locked().
 		 */
 		hugetlb_vma_unlock_read(vma);
-		migration_entry_wait_on_locked(entry, ptl);
+		softleaf_entry_wait_on_locked(entry, ptl);
 		return;
 	}
 
@@ -553,7 +553,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	ptl = pmd_lock(mm, pmd);
 	if (!pmd_is_migration_entry(*pmd))
 		goto unlock;
-	migration_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
+	softleaf_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
 	return;
 unlock:
 	spin_unlock(ptl);
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 0a8b31939640..8079676c8f1f 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -176,7 +176,7 @@ static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start,
 		}
 
 		if (softleaf_is_migration(entry)) {
-			migration_entry_wait_on_locked(entry, ptl);
+			softleaf_entry_wait_on_locked(entry, ptl);
 			spin_unlock(ptl);
 			return -EAGAIN;
 		}

From 03464a48cc8636b6de2febbc5ef39093a9a15e82 Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Tue, 10 Feb 2026 21:10:26 +0800
Subject: [PATCH 0651/1303] MAINTAINERS: Update email address for David Gow

Update my email address for KUnit related things in MAINTAINERS (and add
an entry to .mailmap so nothing gets lost).

Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..7d27cd78cfdb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -214,6 +214,7 @@ Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
 David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
+David Gow <david@davidgow.net> <davidgow@google.com>
 David Heidelberg <david@ixit.cz> <d.okias@gmail.com>
 David Hildenbrand <david@kernel.org> <david@redhat.com>
 David Rheinsberg <david@readahead.eu> <dh.herrmann@gmail.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..372ee16c24f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13943,7 +13943,7 @@ F:	fs/smb/server/
 
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendan.higgins@linux.dev>
-M:	David Gow <davidgow@google.com>
+M:	David Gow <david@davidgow.net>
 R:	Rae Moar <raemoar63@gmail.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
@@ -14763,7 +14763,7 @@ F:	drivers/misc/lis3lv02d/
 F:	drivers/platform/x86/hp/hp_accel.c
 
 LIST KUNIT TEST
-M:	David Gow <davidgow@google.com>
+M:	David Gow <david@davidgow.net>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained

From 7dd34dfc8dfa92a7244242098110388367996ac3 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 24 Feb 2026 19:37:56 +0900
Subject: [PATCH 0652/1303] rust: kunit: fix warning when !CONFIG_PRINTK

If `CONFIG_PRINTK` is not set, then the following warnings are issued
during build:

  warning: unused variable: `args`
    --> ../rust/kernel/kunit.rs:16:12
    |
  16 | pub fn err(args: fmt::Arguments<'_>) {
    |            ^^^^ help: if this is intentional, prefix it with an underscore: `_args`
    |
    = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default

  warning: unused variable: `args`
    --> ../rust/kernel/kunit.rs:32:13
    |
  32 | pub fn info(args: fmt::Arguments<'_>) {
    |             ^^^^ help: if this is intentional, prefix it with an underscore: `_args`

Fix this by adding a no-op assignment using `args` when `CONFIG_PRINTK`
is not set.

Fixes: a66d733da801 ("rust: support running Rust documentation tests as KUnit ones")
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: David Gow <david@davidgow.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 rust/kernel/kunit.rs | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs
index f93f24a60bdd..a1edf7491579 100644
--- a/rust/kernel/kunit.rs
+++ b/rust/kernel/kunit.rs
@@ -14,6 +14,10 @@
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn err(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]
@@ -30,6 +34,10 @@ pub fn err(args: fmt::Arguments<'_>) {
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn info(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]

From 40804c4974b8df2adab72f6475d343eaff72b7f6 Mon Sep 17 00:00:00 2001
From: Shuvam Pandey <shuvampandey1@gmail.com>
Date: Thu, 26 Feb 2026 21:14:10 +0545
Subject: [PATCH 0653/1303] kunit: tool: copy caller args in run_kernel to
 prevent mutation

run_kernel() appended KUnit flags directly to the caller-provided args
list. When exec_tests() calls run_kernel() repeatedly (e.g. with
--run_isolated), each call mutated the same list, causing later runs
to inherit stale filter_glob values and duplicate kunit.enable flags.

Fix this by copying args at the start of run_kernel(). Add a regression
test that calls run_kernel() twice with the same list and verifies the
original remains unchanged.

Fixes: ff9e09a3762f ("kunit: tool: support running each suite/test separately")
Signed-off-by: Shuvam Pandey <shuvampandey1@gmail.com>
Reviewed-by: David Gow <david@davidgow.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/kunit/kunit_kernel.py    |  6 ++++--
 tools/testing/kunit/kunit_tool_test.py | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 260d8d9aa1db..2998e1bc088b 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -346,8 +346,10 @@ class LinuxSourceTree:
 		return self.validate_config(build_dir)
 
 	def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]:
-		if not args:
-			args = []
+		# Copy to avoid mutating the caller-supplied list. exec_tests() reuses
+		# the same args across repeated run_kernel() calls (e.g. --run_isolated),
+		# so appending to the original would accumulate stale flags on each call.
+		args = list(args) if args else []
 		if filter_glob:
 			args.append('kunit.filter_glob=' + filter_glob)
 		if filter:
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index b67408147c1f..f6383884c599 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -503,6 +503,32 @@ class LinuxSourceTreeTest(unittest.TestCase):
 			with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile:
 				self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output')
 
+	def test_run_kernel_args_not_mutated(self):
+		"""Verify run_kernel() copies args so callers can reuse them."""
+		start_calls = []
+
+		def fake_start(start_args, unused_build_dir):
+			start_calls.append(list(start_args))
+			return subprocess.Popen(['printf', 'KTAP version 1\n'],
+						text=True, stdout=subprocess.PIPE)
+
+		with tempfile.TemporaryDirectory('') as build_dir:
+			tree = kunit_kernel.LinuxSourceTree(build_dir,
+					kunitconfig_paths=[os.devnull])
+			with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \
+			     mock.patch.object(kunit_kernel.subprocess, 'call'):
+				kernel_args = ['mem=1G']
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test1'):
+					pass
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test2'):
+					pass
+				self.assertEqual(kernel_args, ['mem=1G'],
+					'run_kernel() should not modify caller args')
+				self.assertIn('kunit.filter_glob=suite.test1', start_calls[0])
+				self.assertIn('kunit.filter_glob=suite.test2', start_calls[1])
+
 	def test_build_reconfig_no_config(self):
 		with tempfile.TemporaryDirectory('') as build_dir:
 			with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f:

From b11b9b6751b2cd74960dccd91667c5117fce743c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Feb 2026 10:48:53 +0100
Subject: [PATCH 0654/1303] kunit: reduce stack usage in kunit_run_tests()

Some of the recent changes to the kunit framework caused the stack usage
for kunit_run_tests() to grow higher than most other kernel functions,
which triggers a warning when CONFIG_FRAME_WARN is set to a relatively
low value:

lib/kunit/test.c: In function 'kunit_run_tests':
lib/kunit/test.c:801:1: error: the frame size of 1312 bytes is larger than 1280 bytes [-Werror=frame-larger-than=]

Split out the inner loop into a separate function to ensure that each
function remains under the limit, and pass the kunit_result_stats
structures by reference to avoid excessive copies.

Fixed checkpatch warnings at commit time:
Shuah Khan <skhan@linuxfoundation.org>

Cc: Carlos Llamas <cmllamas@google.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/test.c | 231 +++++++++++++++++++++++++----------------------
 1 file changed, 125 insertions(+), 106 deletions(-)

diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 62eb529824c6..41e1c89799b6 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -94,7 +94,7 @@ struct kunit_result_stats {
 	unsigned long total;
 };
 
-static bool kunit_should_print_stats(struct kunit_result_stats stats)
+static bool kunit_should_print_stats(struct kunit_result_stats *stats)
 {
 	if (kunit_stats_enabled == 0)
 		return false;
@@ -102,11 +102,11 @@ static bool kunit_should_print_stats(struct kunit_result_stats stats)
 	if (kunit_stats_enabled == 2)
 		return true;
 
-	return (stats.total > 1);
+	return (stats->total > 1);
 }
 
 static void kunit_print_test_stats(struct kunit *test,
-				   struct kunit_result_stats stats)
+				   struct kunit_result_stats *stats)
 {
 	if (!kunit_should_print_stats(stats))
 		return;
@@ -115,10 +115,10 @@ static void kunit_print_test_stats(struct kunit *test,
 		  KUNIT_SUBTEST_INDENT
 		  "# %s: pass:%lu fail:%lu skip:%lu total:%lu",
 		  test->name,
-		  stats.passed,
-		  stats.failed,
-		  stats.skipped,
-		  stats.total);
+		  stats->passed,
+		  stats->failed,
+		  stats->skipped,
+		  stats->total);
 }
 
 /* Append formatted message to log. */
@@ -600,26 +600,26 @@ static void kunit_run_case_catch_errors(struct kunit_suite *suite,
 }
 
 static void kunit_print_suite_stats(struct kunit_suite *suite,
-				    struct kunit_result_stats suite_stats,
-				    struct kunit_result_stats param_stats)
+				    struct kunit_result_stats *suite_stats,
+				    struct kunit_result_stats *param_stats)
 {
 	if (kunit_should_print_stats(suite_stats)) {
 		kunit_log(KERN_INFO, suite,
 			  "# %s: pass:%lu fail:%lu skip:%lu total:%lu",
 			  suite->name,
-			  suite_stats.passed,
-			  suite_stats.failed,
-			  suite_stats.skipped,
-			  suite_stats.total);
+			  suite_stats->passed,
+			  suite_stats->failed,
+			  suite_stats->skipped,
+			  suite_stats->total);
 	}
 
 	if (kunit_should_print_stats(param_stats)) {
 		kunit_log(KERN_INFO, suite,
 			  "# Totals: pass:%lu fail:%lu skip:%lu total:%lu",
-			  param_stats.passed,
-			  param_stats.failed,
-			  param_stats.skipped,
-			  param_stats.total);
+			  param_stats->passed,
+			  param_stats->failed,
+			  param_stats->skipped,
+			  param_stats->total);
 	}
 }
 
@@ -681,13 +681,116 @@ static void kunit_init_parent_param_test(struct kunit_case *test_case, struct ku
 	}
 }
 
-int kunit_run_tests(struct kunit_suite *suite)
+static noinline_for_stack void
+kunit_run_param_test(struct kunit_suite *suite, struct kunit_case *test_case,
+		     struct kunit *test,
+		     struct kunit_result_stats *suite_stats,
+		     struct kunit_result_stats *total_stats,
+		     struct kunit_result_stats *param_stats)
 {
 	char param_desc[KUNIT_PARAM_DESC_SIZE];
+	const void *curr_param;
+
+	kunit_init_parent_param_test(test_case, test);
+	if (test_case->status == KUNIT_FAILURE) {
+		kunit_update_stats(param_stats, test->status);
+		return;
+	}
+	/* Get initial param. */
+	param_desc[0] = '\0';
+	/* TODO: Make generate_params try-catch */
+	curr_param = test_case->generate_params(test, NULL, param_desc);
+	test_case->status = KUNIT_SKIPPED;
+	kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
+		  "KTAP version 1\n");
+	kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
+		  "# Subtest: %s", test_case->name);
+	if (test->params_array.params &&
+	    test_case->generate_params == kunit_array_gen_params) {
+		kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT
+			  KUNIT_SUBTEST_INDENT "1..%zd\n",
+			  test->params_array.num_params);
+	}
+
+	while (curr_param) {
+		struct kunit param_test = {
+			.param_value = curr_param,
+			.param_index = ++test->param_index,
+			.parent = test,
+		};
+		kunit_init_test(&param_test, test_case->name, NULL);
+		param_test.log = test_case->log;
+		kunit_run_case_catch_errors(suite, test_case, &param_test);
+
+		if (param_desc[0] == '\0') {
+			snprintf(param_desc, sizeof(param_desc),
+				 "param-%d", param_test.param_index);
+		}
+
+		kunit_print_ok_not_ok(&param_test, KUNIT_LEVEL_CASE_PARAM,
+				      param_test.status,
+				      param_test.param_index,
+				      param_desc,
+				      param_test.status_comment);
+
+		kunit_update_stats(param_stats, param_test.status);
+
+		/* Get next param. */
+		param_desc[0] = '\0';
+		curr_param = test_case->generate_params(test, curr_param,
+							param_desc);
+	}
+	/*
+	 * TODO: Put into a try catch. Since we don't need suite->exit
+	 * for it we can't reuse kunit_try_run_cleanup for this yet.
+	 */
+	if (test_case->param_exit)
+		test_case->param_exit(test);
+	/* TODO: Put this kunit_cleanup into a try-catch. */
+	kunit_cleanup(test);
+}
+
+static noinline_for_stack void
+kunit_run_one_test(struct kunit_suite *suite, struct kunit_case *test_case,
+		   struct kunit_result_stats *suite_stats,
+		   struct kunit_result_stats *total_stats)
+{
+	struct kunit test = { .param_value = NULL, .param_index = 0 };
+	struct kunit_result_stats param_stats = { 0 };
+
+	kunit_init_test(&test, test_case->name, test_case->log);
+	if (test_case->status == KUNIT_SKIPPED) {
+		/* Test marked as skip */
+		test.status = KUNIT_SKIPPED;
+		kunit_update_stats(&param_stats, test.status);
+	} else if (!test_case->generate_params) {
+		/* Non-parameterised test. */
+		test_case->status = KUNIT_SKIPPED;
+		kunit_run_case_catch_errors(suite, test_case, &test);
+		kunit_update_stats(&param_stats, test.status);
+	} else {
+		kunit_run_param_test(suite, test_case, &test, suite_stats,
+				     total_stats, &param_stats);
+	}
+	kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE);
+
+	kunit_print_test_stats(&test, &param_stats);
+
+	kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status,
+			      kunit_test_case_num(suite, test_case),
+			      test_case->name,
+			      test.status_comment);
+
+	kunit_update_stats(suite_stats, test_case->status);
+	kunit_accumulate_stats(total_stats, param_stats);
+}
+
+
+int kunit_run_tests(struct kunit_suite *suite)
+{
 	struct kunit_case *test_case;
 	struct kunit_result_stats suite_stats = { 0 };
 	struct kunit_result_stats total_stats = { 0 };
-	const void *curr_param;
 
 	/* Taint the kernel so we know we've run tests. */
 	add_taint(TAINT_TEST, LOCKDEP_STILL_OK);
@@ -703,97 +806,13 @@ int kunit_run_tests(struct kunit_suite *suite)
 
 	kunit_print_suite_start(suite);
 
-	kunit_suite_for_each_test_case(suite, test_case) {
-		struct kunit test = { .param_value = NULL, .param_index = 0 };
-		struct kunit_result_stats param_stats = { 0 };
-
-		kunit_init_test(&test, test_case->name, test_case->log);
-		if (test_case->status == KUNIT_SKIPPED) {
-			/* Test marked as skip */
-			test.status = KUNIT_SKIPPED;
-			kunit_update_stats(&param_stats, test.status);
-		} else if (!test_case->generate_params) {
-			/* Non-parameterised test. */
-			test_case->status = KUNIT_SKIPPED;
-			kunit_run_case_catch_errors(suite, test_case, &test);
-			kunit_update_stats(&param_stats, test.status);
-		} else {
-			kunit_init_parent_param_test(test_case, &test);
-			if (test_case->status == KUNIT_FAILURE) {
-				kunit_update_stats(&param_stats, test.status);
-				goto test_case_end;
-			}
-			/* Get initial param. */
-			param_desc[0] = '\0';
-			/* TODO: Make generate_params try-catch */
-			curr_param = test_case->generate_params(&test, NULL, param_desc);
-			test_case->status = KUNIT_SKIPPED;
-			kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
-				  "KTAP version 1\n");
-			kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
-				  "# Subtest: %s", test_case->name);
-			if (test.params_array.params &&
-			    test_case->generate_params == kunit_array_gen_params) {
-				kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT
-					  KUNIT_SUBTEST_INDENT "1..%zd\n",
-					  test.params_array.num_params);
-			}
-
-			while (curr_param) {
-				struct kunit param_test = {
-					.param_value = curr_param,
-					.param_index = ++test.param_index,
-					.parent = &test,
-				};
-				kunit_init_test(&param_test, test_case->name, NULL);
-				param_test.log = test_case->log;
-				kunit_run_case_catch_errors(suite, test_case, &param_test);
-
-				if (param_desc[0] == '\0') {
-					snprintf(param_desc, sizeof(param_desc),
-						 "param-%d", param_test.param_index);
-				}
-
-				kunit_print_ok_not_ok(&param_test, KUNIT_LEVEL_CASE_PARAM,
-						      param_test.status,
-						      param_test.param_index,
-						      param_desc,
-						      param_test.status_comment);
-
-				kunit_update_stats(&param_stats, param_test.status);
-
-				/* Get next param. */
-				param_desc[0] = '\0';
-				curr_param = test_case->generate_params(&test, curr_param,
-									param_desc);
-			}
-			/*
-			 * TODO: Put into a try catch. Since we don't need suite->exit
-			 * for it we can't reuse kunit_try_run_cleanup for this yet.
-			 */
-			if (test_case->param_exit)
-				test_case->param_exit(&test);
-			/* TODO: Put this kunit_cleanup into a try-catch. */
-			kunit_cleanup(&test);
-		}
-test_case_end:
-		kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE);
-
-		kunit_print_test_stats(&test, param_stats);
-
-		kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status,
-				      kunit_test_case_num(suite, test_case),
-				      test_case->name,
-				      test.status_comment);
-
-		kunit_update_stats(&suite_stats, test_case->status);
-		kunit_accumulate_stats(&total_stats, param_stats);
-	}
+	kunit_suite_for_each_test_case(suite, test_case)
+		kunit_run_one_test(suite, test_case, &suite_stats, &total_stats);
 
 	if (suite->suite_exit)
 		suite->suite_exit(suite);
 
-	kunit_print_suite_stats(suite, suite_stats, total_stats);
+	kunit_print_suite_stats(suite, &suite_stats, &total_stats);
 suite_end:
 	kunit_print_suite_end(suite);
 

From 9adfcef334bf9c6ef68eaecfca5f45d18614efe0 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 2 Mar 2026 17:14:39 +0800
Subject: [PATCH 0655/1303] sched_ext: Use READ_ONCE() for the read side of
 dsq->nr update

scx_bpf_dsq_nr_queued() reads dsq->nr via READ_ONCE() without holding
any lock, making dsq->nr a lock-free concurrently accessed variable.
However, dsq_mod_nr(), the sole writer of dsq->nr, only uses
WRITE_ONCE() on the write side without the matching READ_ONCE() on the
read side:

    WRITE_ONCE(dsq->nr, dsq->nr + delta);
                        ^^^^^^^
                        plain read -- KCSAN data race

The KCSAN documentation requires that if one accessor uses READ_ONCE()
or WRITE_ONCE() on a variable to annotate lock-free access, all other
accesses must also use the appropriate accessor. A plain read on the
right-hand side of WRITE_ONCE() leaves the pair incomplete and will
trigger KCSAN warnings.

Fix by using READ_ONCE() for the read side of the update:

    WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta);

This is consistent with scx_bpf_dsq_nr_queued() and makes the
concurrent access annotation complete and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 9280381f8923..4c2cf0d7d495 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -976,8 +976,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a,
 
 static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
 {
-	/* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
-	WRITE_ONCE(dsq->nr, dsq->nr + delta);
+	/*
+	 * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE()
+	 * on the read side and WRITE_ONCE() on the write side to properly
+	 * annotate the concurrent lockless access and avoid KCSAN warnings.
+	 */
+	WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta);
 }
 
 static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)

From 494eaf4651975127d34d5ae6555c72dedba092c9 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 2 Mar 2026 17:14:40 +0800
Subject: [PATCH 0656/1303] sched_ext: Replace naked scx_root dereferences in
 kobject callbacks

scx_attr_ops_show() and scx_uevent() access scx_root->ops.name directly.
This is problematic for two reasons:

1. The file-level comment explicitly identifies naked scx_root
   dereferences as a temporary measure that needs to be replaced
   with proper per-instance access.

2. scx_attr_events_show(), the neighboring sysfs show function in
   the same group, already uses the correct pattern:

       struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);

   Having inconsistent access patterns in the same sysfs/uevent
   group is error-prone.

The kobject embedded in struct scx_sched is initialized as:

    kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root");

so container_of(kobj, struct scx_sched, kobj) correctly retrieves
the owning scx_sched instance in both callbacks.

Replace the naked scx_root dereferences with container_of()-based
access, consistent with scx_attr_events_show() and in preparation
for proper multi-instance scx_sched support.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4c2cf0d7d495..a566d2cc8a43 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3712,7 +3712,9 @@ static void scx_kobj_release(struct kobject *kobj)
 static ssize_t scx_attr_ops_show(struct kobject *kobj,
 				 struct kobj_attribute *ka, char *buf)
 {
-	return sysfs_emit(buf, "%s\n", scx_root->ops.name);
+	struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return sysfs_emit(buf, "%s\n", sch->ops.name);
 }
 SCX_ATTR(ops);
 
@@ -3756,7 +3758,9 @@ static const struct kobj_type scx_ktype = {
 
 static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
-	return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name);
+	const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return add_uevent_var(env, "SCXOPS=%s", sch->ops.name);
 }
 
 static const struct kset_uevent_ops scx_uevent_ops = {

From af4e9ef3d78420feb8fe58cd9a1ab80c501b3c08 Mon Sep 17 00:00:00 2001
From: David Laight <david.laight.linux@gmail.com>
Date: Mon, 2 Mar 2026 13:27:51 +0000
Subject: [PATCH 0657/1303] uaccess: Fix scoped_user_read_access() for 'pointer
 to const'

If a 'const struct foo __user *ptr' is used for the address passed to
scoped_user_read_access() then you get a warning/error

  uaccess.h:691:1: error: initialization discards 'const' qualifier from pointer target type [-Werror=discarded-qualifiers]

for the

  void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl)

assignment.

Fix by using 'auto' for both _tmpptr and the redeclaration of uptr.
Replace the CLASS() with explicit __cleanup() functions on uptr.

Fixes: e497310b4ffb ("uaccess: Provide scoped user access regions")
Signed-off-by: David Laight <david.laight.linux@gmail.com>
Reviewed-and-tested-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/uaccess.h | 54 +++++++++++++++--------------------------
 1 file changed, 20 insertions(+), 34 deletions(-)

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1f3804245c06..809e4f7dfdbd 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { }
 /* Define RW variant so the below _mode macro expansion works */
 #define masked_user_rw_access_begin(u)	masked_user_access_begin(u)
 #define user_rw_access_begin(u, s)	user_access_begin(u, s)
-#define user_rw_access_end()		user_access_end()
 
 /* Scoped user access */
-#define USER_ACCESS_GUARD(_mode)				\
-static __always_inline void __user *				\
-class_user_##_mode##_begin(void __user *ptr)			\
-{								\
-	return ptr;						\
-}								\
-								\
-static __always_inline void					\
-class_user_##_mode##_end(void __user *ptr)			\
-{								\
-	user_##_mode##_access_end();				\
-}								\
-								\
-DEFINE_CLASS(user_ ##_mode## _access, void __user *,		\
-	     class_user_##_mode##_end(_T),			\
-	     class_user_##_mode##_begin(ptr), void __user *ptr)	\
-								\
-static __always_inline class_user_##_mode##_access_t		\
-class_user_##_mode##_access_ptr(void __user *scope)		\
-{								\
-	return scope;						\
-}
 
-USER_ACCESS_GUARD(read)
-USER_ACCESS_GUARD(write)
-USER_ACCESS_GUARD(rw)
-#undef USER_ACCESS_GUARD
+/* Cleanup wrapper functions */
+static __always_inline void __scoped_user_read_access_end(const void *p)
+{
+	user_read_access_end();
+};
+static __always_inline void __scoped_user_write_access_end(const void *p)
+{
+	user_write_access_end();
+};
+static __always_inline void __scoped_user_rw_access_end(const void *p)
+{
+	user_access_end();
+};
 
 /**
  * __scoped_user_access_begin - Start a scoped user access
@@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw)
  *
  * Don't use directly. Use scoped_masked_user_$MODE_access() instead.
  */
-#define __scoped_user_access(mode, uptr, size, elbl)					\
-for (bool done = false; !done; done = true)						\
-	for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \
-	     !done; done = true)							\
-		for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true)	\
-			/* Force modified pointer usage within the scope */		\
-			for (const typeof(uptr) uptr = _tmpptr; !done; done = true)
+#define __scoped_user_access(mode, uptr, size, elbl)				\
+for (bool done = false; !done; done = true)					\
+	for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl);	\
+	     !done; done = true)						\
+		/* Force modified pointer usage within the scope */		\
+		for (const auto uptr  __cleanup(__scoped_user_##mode##_access_end) = \
+		     _tmpptr; !done; done = true)
 
 /**
  * scoped_user_read_access_size - Start a scoped user read access with given size

From 6270ee26e1edd862ea17e3eba148ca8fb2c99dc9 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Thu, 26 Feb 2026 13:38:57 -0800
Subject: [PATCH 0658/1303] accel/amdxdna: Fix NULL pointer dereference of
 mgmt_chann

mgmt_chann may be set to NULL if the firmware returns an unexpected
error in aie2_send_mgmt_msg_wait(). This can later lead to a NULL
pointer dereference in aie2_hw_stop().

Fix this by introducing a dedicated helper to destroy mgmt_chann
and by adding proper NULL checks before accessing it.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260226213857.3068474-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_message.c | 21 ++++++++++++++++-----
 drivers/accel/amdxdna/aie2_pci.c     |  7 ++-----
 drivers/accel/amdxdna/aie2_pci.h     |  1 +
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 277a27bce850..22e1a85a7ae0 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -40,11 +40,8 @@ static int aie2_send_mgmt_msg_wait(struct amdxdna_dev_hdl *ndev,
 		return -ENODEV;
 
 	ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg);
-	if (ret == -ETIME) {
-		xdna_mailbox_stop_channel(ndev->mgmt_chann);
-		xdna_mailbox_destroy_channel(ndev->mgmt_chann);
-		ndev->mgmt_chann = NULL;
-	}
+	if (ret == -ETIME)
+		aie2_destroy_mgmt_chann(ndev);
 
 	if (!ret && *hdl->status != AIE2_STATUS_SUCCESS) {
 		XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x",
@@ -914,6 +911,20 @@ void aie2_msg_init(struct amdxdna_dev_hdl *ndev)
 		ndev->exec_msg_ops = &legacy_exec_message_ops;
 }
 
+void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev)
+{
+	struct amdxdna_dev *xdna = ndev->xdna;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	if (!ndev->mgmt_chann)
+		return;
+
+	xdna_mailbox_stop_channel(ndev->mgmt_chann);
+	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+	ndev->mgmt_chann = NULL;
+}
+
 static inline struct amdxdna_gem_obj *
 aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job)
 {
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 85079b6fc5d9..977ce21eaf9f 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -330,9 +330,7 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna)
 
 	aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, NULL);
 	aie2_mgmt_fw_fini(ndev);
-	xdna_mailbox_stop_channel(ndev->mgmt_chann);
-	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
-	ndev->mgmt_chann = NULL;
+	aie2_destroy_mgmt_chann(ndev);
 	drmm_kfree(&xdna->ddev, ndev->mbox);
 	ndev->mbox = NULL;
 	aie2_psp_stop(ndev->psp_hdl);
@@ -441,8 +439,7 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 	return 0;
 
 destroy_mgmt_chann:
-	xdna_mailbox_stop_channel(ndev->mgmt_chann);
-	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+	aie2_destroy_mgmt_chann(ndev);
 stop_psp:
 	aie2_psp_stop(ndev->psp_hdl);
 fini_smu:
diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h
index b20a3661078c..e72311c77996 100644
--- a/drivers/accel/amdxdna/aie2_pci.h
+++ b/drivers/accel/amdxdna/aie2_pci.h
@@ -303,6 +303,7 @@ int aie2_get_array_async_error(struct amdxdna_dev_hdl *ndev,
 
 /* aie2_message.c */
 void aie2_msg_init(struct amdxdna_dev_hdl *ndev);
+void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev);
 int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev);
 int aie2_resume_fw(struct amdxdna_dev_hdl *ndev);
 int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value);

From 3ebc98c1ae7efda949a015990280a097f4a5453a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 2 Mar 2026 09:16:22 +0100
Subject: [PATCH 0659/1303] ftrace: Add missing ftrace_lock to
 update_ftrace_direct_add/del

Ihor and Kumar reported splat from ftrace_get_addr_curr [1], which happened
because of the missing ftrace_lock in update_ftrace_direct_add/del functions
allowing concurrent access to ftrace internals.

The ftrace_update_ops function must be guarded by ftrace_lock, adding that.

Fixes: 05dc5e9c1fe1 ("ftrace: Add update_ftrace_direct_add function")
Fixes: 8d2c1233f371 ("ftrace: Add update_ftrace_direct_del function")
Reported-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Closes: https://lore.kernel.org/bpf/1b58ffb2-92ae-433a-ba46-95294d6edea2@linux.dev/
Tested-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20260302081622.165713-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/ftrace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..8baf61c9be6d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6404,6 +6404,7 @@ int update_ftrace_direct_add(struct ftrace_ops *ops, struct ftrace_hash *hash)
 			new_filter_hash = old_filter_hash;
 		}
 	} else {
+		guard(mutex)(&ftrace_lock);
 		err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH);
 		/*
 		 * new_filter_hash is dup-ed, so we need to release it anyway,
@@ -6530,6 +6531,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 			ops->func_hash->filter_hash = NULL;
 		}
 	} else {
+		guard(mutex)(&ftrace_lock);
 		err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH);
 		/*
 		 * new_filter_hash is dup-ed, so we need to release it anyway,

From f8211e95dfda702ba81ea2e3e7a8c6c967f385fa Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 2 Mar 2026 09:02:39 -0800
Subject: [PATCH 0660/1303] Documentation: KVM: Formalizing taking vcpu->mutex
 *outside* of kvm->slots_lock

Explicitly document the ordering of vcpu->mutex being taken *outside* of
kvm->slots_lock.  While somewhat unintuitive since vCPUs conceptually have
narrower scope than VMs, the scope of the owning object (vCPU versus VM)
doesn't automatically carry over to the lock.  In this case, vcpu->mutex
has far broader scope than kvm->slots_lock.  As Paolo put it, it's a
"don't worry about multiple ioctls at the same time" mutex that's intended
to be taken at the outer edges of KVM.

More importantly, arm64 and x86 have gained flows that take kvm->slots_lock
inside of vcpu->mutex.  x86's kvm_inhibit_apic_access_page() is particularly
nasty, as slots_lock is taken quite deep within KVM_RUN, i.e. simply
swapping the ordering isn't an option.

Commit to the vcpu->mutex => kvm->slots_lock ordering, as vcpu->mutex
really is intended to be a "top-level" lock, whereas kvm->slots_lock is
"just" a helper lock.

Opportunistically document that vcpu->mutex is also taken outside of
slots_arch_lock, e.g. when allocating shadow roots on x86 (which is the
entire reason slots_arch_lock exists, as shadow roots must be allocated
while holding kvm->srcu)

  kvm_mmu_new_pgd()
  |
  -> kvm_mmu_reload()
     |
     -> kvm_mmu_load()
        |
        -> mmu_alloc_shadow_roots()
           |
           -> mmu_first_shadow_root_alloc()

but also when manipulating memslots in vCPU context, e.g. when inhibiting
the APIC-access page via the aforementioned kvm_inhibit_apic_access_page()

  kvm_inhibit_apic_access_page()
  |
  -> __x86_set_memory_region()
     |
     -> kvm_set_internal_memslot()
        |
        -> kvm_set_memory_region()
           |
           -> kvm_set_memslot()

Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://patch.msgid.link/20260302170239.596810-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/locking.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index ae8bce7fecbe..662231e958a0 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -17,6 +17,8 @@ The acquisition orders for mutexes are as follows:
 
 - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
 
+- vcpu->mutex is taken outside kvm->slots_lock and kvm->slots_arch_lock
+
 - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
   them together is quite rare.
 

From 800ca7b88a0c0eba6fa721e043eb3ed5b10ecc4f Mon Sep 17 00:00:00 2001
From: Saket Dumbre <saket.dumbre@intel.com>
Date: Sat, 21 Feb 2026 12:36:39 +0100
Subject: [PATCH 0661/1303] ACPICA: Update the _CPC definition to match ACPI
 6.6

Update the _CPC definition to also support return package sub-type of
a Package (with Integer and Buffer) as per ACPI Spec 6.6.

Link: https://github.com/acpica/acpica/commit/17a761944cc2
Signed-off-by: Saket Dumbre <saket.dumbre@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/2829238.mvXUDI8C0e@rafael.j.wysocki
---
 drivers/acpi/acpica/acpredef.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 5f70b196e0aa..6c9b5bf7d392 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -379,8 +379,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 
 	{{"_CPC", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (Ints/Bufs) */
-	PACKAGE_INFO(ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER, 0,
-		     0, 0, 0),
+	PACKAGE_INFO(ACPI_PTYPE1_VAR,
+		     ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER |
+		     ACPI_RTYPE_PACKAGE, 0, 0, 0, 0),
 
 	{{"_CR3", METHOD_0ARGS,	/* ACPI 6.0 */
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},

From fdb12c8a24a453bdd6759979b6ef1e04ebd4beb4 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 27 Feb 2026 22:40:48 -0700
Subject: [PATCH 0662/1303] kbuild: Leave objtool binary around with 'make
 clean'

The difference between 'make clean' and 'make mrproper' is documented in
'make help' as:

  clean     - Remove most generated files but keep the config and
              enough build support to build external modules
  mrproper  - Remove all generated files + config + various backup files

After commit 68b4fe32d737 ("kbuild: Add objtool to top-level clean
target"), running 'make clean' then attempting to build an external
module with the resulting build directory fails with

  $ make ARCH=x86_64 O=build clean

  $ make -C build M=... MO=...
  ...
  /bin/sh: line 1: .../build/tools/objtool/objtool: No such file or directory

as 'make clean' removes the objtool binary.

Split the objtool clean target into mrproper and clean like Kbuild does
and remove all generated artifacts with 'make clean' except for the
objtool binary, which is removed with 'make mrproper'. To avoid a small
race when running the objtool clean target through both objtool_mrproper
and objtool_clean when running 'make mrproper', modify objtool's clean
up find command to avoid using find's '-delete' command by piping the
files into 'xargs rm -f' like the rest of Kbuild does.

Cc: stable@vger.kernel.org
Fixes: 68b4fe32d737 ("kbuild: Add objtool to top-level clean target")
Reported-by: Michal Suchanek <msuchanek@suse.de>
Closes: https://lore.kernel.org/20260225112633.6123-1-msuchanek@suse.de/
Reported-by: Rainer Fiebig <jrf@mailbox.org>
Closes: https://lore.kernel.org/62d12399-76e5-3d40-126a-7490b4795b17@mailbox.org/
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Tested-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20260227-avoid-objtool-binary-removal-clean-v1-1-122f3e55eae9@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 Makefile               | 8 ++++----
 tools/objtool/Makefile | 8 +++++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index e944c6e71e81..d76d706a5580 100644
--- a/Makefile
+++ b/Makefile
@@ -1497,13 +1497,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),)
 	$(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean
 endif
 
-PHONY += objtool_clean
+PHONY += objtool_clean objtool_mrproper
 
 objtool_O = $(abspath $(objtree))/tools/objtool
 
-objtool_clean:
+objtool_clean objtool_mrproper:
 ifneq ($(wildcard $(objtool_O)),)
-	$(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) clean
+	$(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) $(patsubst objtool_%,%,$@)
 endif
 
 tools/: FORCE
@@ -1686,7 +1686,7 @@ PHONY += $(mrproper-dirs) mrproper
 $(mrproper-dirs):
 	$(Q)$(MAKE) $(clean)=$(patsubst _mrproper_%,%,$@)
 
-mrproper: clean $(mrproper-dirs)
+mrproper: clean objtool_mrproper $(mrproper-dirs)
 	$(call cmd,rmfiles)
 	@find . $(RCS_FIND_IGNORE) \
 		\( -name '*.rmeta' \) \
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6964175abdfd..76bcd4e85de3 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -142,13 +142,15 @@ $(LIBSUBCMD)-clean:
 	$(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT)
 
 clean: $(LIBSUBCMD)-clean
-	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
-	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)find $(OUTPUT) \( -name '*.o' -o -name '\.*.cmd' -o -name '\.*.d' \) -type f -print | xargs $(RM)
 	$(Q)$(RM) $(OUTPUT)arch/x86/lib/cpu-feature-names.c $(OUTPUT)fixdep
 	$(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.objtool
 	$(Q)$(RM) -r -- $(OUTPUT)feature
 
+mrproper: clean
+	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
+
 FORCE:
 
-.PHONY: clean FORCE
+.PHONY: clean mrproper FORCE

From c28b3ec3ca034fd1abc832fef46ce36eb13f8fad Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Fri, 27 Feb 2026 12:26:04 -0700
Subject: [PATCH 0663/1303] drm/amd/display: Use mpc.preblend flag to indicate
 3D LUT

[WHAT]
New ASIC's 3D LUT is indicated by mpc.preblend.

Fixes: 0de2b1afea8d ("drm/amd/display: add 3D LUT colorop")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 43175f6164d32cb96362d16e357689f74298145c)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c   | 6 ++++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 2ba98f384685..cd1e58b8defc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1706,6 +1706,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func;
 	struct drm_atomic_state *state = plane_state->state;
 	const struct amdgpu_device *adev = drm_to_adev(colorop->dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	const struct drm_device *dev = colorop->dev;
 	const struct drm_color_lut32 *lut3d;
 	uint32_t lut3d_size;
@@ -1722,7 +1723,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	}
 
 	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) {
-		if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+		if (!has_3dlut) {
 			drm_dbg(dev, "3D LUT is not supported by hardware\n");
 			return -EINVAL;
 		}
@@ -1875,6 +1876,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	struct drm_colorop *colorop = plane_state->color_pipeline;
 	struct drm_device *dev = plane_state->plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 
 	/* 1D Curve - DEGAM TF */
@@ -1907,7 +1909,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	if (ret)
 		return ret;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D Curve & LUT - SHAPER TF & LUT */
 		colorop = colorop->next;
 		if (!colorop) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
index f25c0ede7199..d59ba82d3d7c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
@@ -60,6 +60,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 	struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS];
 	struct drm_device *dev = plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 	int i = 0;
 
@@ -112,7 +113,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 
 	i++;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D curve - SHAPER TF */
 		ops[i] = kzalloc_obj(*ops[0]);
 		if (!ops[i]) {

From a4fa2355e0add57253468ef13bd08f11285f3b6e Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Fri, 27 Feb 2026 12:30:38 -0700
Subject: [PATCH 0664/1303] drm/amd/display: Enable DEGAMMA and reject
 COLOR_PIPELINE+DEGAMMA_LUT

[WHAT]
Create DEGAMMA properties even if color pipeline is enabled, and enforce
the mutual exclusion in atomic check by rejecting any commit that
attempts to enable both COLOR_PIPELINE on the plane and DEGAMMA_LUT on
the CRTC simultaneously.

Fixes: 18a4127e9315 ("drm/amd/display: Disable CRTC degamma when color pipeline is enabled")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4963
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 196a6aa727f1f15eb54dda5e60a41543ea9397ee)
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c   | 16 ++++++++--------
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c  |  8 ++++++++
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 130190e8a1b2..304437c2284d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -765,15 +765,15 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	dm->adev->mode_info.crtcs[crtc_index] = acrtc;
 
 	/* Don't enable DRM CRTC degamma property for
-	 * 1. Degamma is replaced by color pipeline.
-	 * 2. DCE since it doesn't support programmable degamma anywhere.
-	 * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * 1. DCE since it doesn't support programmable degamma anywhere.
+	 * 2. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * Note: DEGAMMA properties are created even if the primary plane has the
+	 * COLOR_PIPELINE property. User space can use either the DEGAMMA properties
+	 * or the COLOR_PIPELINE property. An atomic commit which attempts to enable
+	 * both is rejected.
 	 */
-	if (plane->color_pipeline_property)
-		has_degamma = false;
-	else
-		has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
-			      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
+	has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
+		      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
 
 	drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0,
 				   true, MAX_COLOR_LUT_ENTRIES);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 70587e5a8d46..127207e18dcb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1256,6 +1256,14 @@ static int amdgpu_dm_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
+	/* Reject commits that attempt to use both COLOR_PIPELINE and CRTC DEGAMMA_LUT */
+	if (new_plane_state->color_pipeline && new_crtc_state->degamma_lut) {
+		drm_dbg_atomic(plane->dev,
+			       "[PLANE:%d:%s] COLOR_PIPELINE and CRTC DEGAMMA_LUT cannot be enabled simultaneously\n",
+			       plane->base.id, plane->name);
+		return -EINVAL;
+	}
+
 	ret = amdgpu_dm_plane_fill_dc_scaling_info(adev, new_plane_state, &scaling_info);
 	if (ret)
 		return ret;

From 389c2024cab817366e6b8345f679f41064fa94d6 Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Sat, 21 Feb 2026 10:47:59 +0530
Subject: [PATCH 0665/1303] drm/amdgpu: Enable DPG support for VCN5

This will set DPG flags for enabling power gating on GFX11_5_4

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a503c266d70d3363ba6bffb883cd6ecdb092670c)
---
 drivers/gpu/drm/amd/amdgpu/soc21.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 8122a5cacf07..a0ad1f8a76f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -858,7 +858,9 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block)
 			AMD_CG_SUPPORT_IH_CG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_VCN |
+		adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG_DPG |
 			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_GFX_PG;
 		adev->external_rev_id = adev->rev_id + 0x1;

From 30d937f63bd19bbcaafa4b892eb251f8bbbf04ef Mon Sep 17 00:00:00 2001
From: Dillon Varone <Dillon.Varone@amd.com>
Date: Wed, 18 Feb 2026 14:34:28 -0500
Subject: [PATCH 0666/1303] drm/amd/display: Fallback to boot snapshot for
 dispclk

[WHY & HOW]
If the dentist is unavailable, fallback to reading CLKIP via the boot
snapshot to get the current dispclk.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Dillon Varone <Dillon.Varone@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2ab77600d1e55a042c02437326d3c7563e853c6c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index b91517b9fedc..eb198d52a115 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -72,7 +72,11 @@ void dcn401_initialize_min_clocks(struct dc *dc)
 		 * audio corruption. Read current DISPCLK from DENTIST and request the same
 		 * freq to ensure that the timing is valid and unchanged.
 		 */
-		clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		if (dc->clk_mgr->funcs->get_dispclk_from_dentist) {
+			clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		} else {
+			clocks->dispclk_khz = dc->clk_mgr->boot_snapshot.dispclk * 1000;
+		}
 	}
 	clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000;
 	clocks->fclk_p_state_change_support = true;

From 3b46d61890632c8f8b117147b6923bff4b42ccb7 Mon Sep 17 00:00:00 2001
From: Vladimir Yakovlev <vovchkir@gmail.com>
Date: Tue, 3 Mar 2026 01:20:17 +0300
Subject: [PATCH 0667/1303] spi: spi-dw-dma: fix print error log when wait
 finish transaction

If an error occurs, the device may not have a current message. In this
case, the system will crash.

In this case, it's better to use dev from the struct ctlr (struct spi_controller*).

Signed-off-by: Vladimir Yakovlev <vovchkir@gmail.com>
Link: https://patch.msgid.link/20260302222017.992228-2-vovchkir@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw-dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c
index 65adec7c7524..fe726b9b1780 100644
--- a/drivers/spi/spi-dw-dma.c
+++ b/drivers/spi/spi-dw-dma.c
@@ -271,7 +271,7 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed)
 					 msecs_to_jiffies(ms));
 
 	if (ms == 0) {
-		dev_err(&dws->ctlr->cur_msg->spi->dev,
+		dev_err(&dws->ctlr->dev,
 			"DMA transaction timed out\n");
 		return -ETIMEDOUT;
 	}

From 20d6f07004d639967dcb00994d56ce6d16118e9e Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 28 Feb 2026 20:01:40 -0800
Subject: [PATCH 0668/1303] lib/crypto: tests: Add a .kunitconfig file

Add a .kunitconfig file to the lib/crypto/ directory so that the crypto
library tests can be run more easily using kunit.py.  Example with UML:

    tools/testing/kunit/kunit.py run --kunitconfig=lib/crypto

Example with QEMU:

    tools/testing/kunit/kunit.py run --kunitconfig=lib/crypto --arch=arm64 --make_options LLVM=1

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260301040140.490310-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/.kunitconfig | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 lib/crypto/.kunitconfig

diff --git a/lib/crypto/.kunitconfig b/lib/crypto/.kunitconfig
new file mode 100644
index 000000000000..6b2ce28ae509
--- /dev/null
+++ b/lib/crypto/.kunitconfig
@@ -0,0 +1,34 @@
+CONFIG_KUNIT=y
+
+# These kconfig options select all the CONFIG_CRYPTO_LIB_* symbols that have a
+# corresponding KUnit test.  Those symbols cannot be directly enabled here,
+# since they are hidden symbols.
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ADIANTUM=y
+CONFIG_CRYPTO_BLAKE2B=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_CRYPTO_HCTR2=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MLDSA=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_SHA3=y
+CONFIG_INET=y
+CONFIG_IPV6=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_WIREGUARD=y
+
+CONFIG_CRYPTO_LIB_BLAKE2B_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_BLAKE2S_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_CURVE25519_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_MD5_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_MLDSA_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_NH_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_POLY1305_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_POLYVAL_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA1_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA256_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA512_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA3_KUNIT_TEST=y

From 5d75c7bcc40a90f77f315e1c91dfb2f1b189a435 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:05 +0100
Subject: [PATCH 0669/1303] crypto: Clean up help text for CRYPTO_BLAKE2B

Btrfs stopped using this BLAKE2b implementation in commit
fe11ac191ce0ad91 ("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/98b983d2f2bddf0e5e8e1c970446c3c64527ef89.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index e2b4106ac961..8bc95e69faa5 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -876,8 +876,6 @@ config CRYPTO_BLAKE2B
 	  - blake2b-384
 	  - blake2b-512
 
-	  Used by the btrfs filesystem.
-
 	  See https://blake2.net for further information.
 
 config CRYPTO_CMAC

From a70d9d655fd0549dd7cd9de437eb3fbe2e78c8ab Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:06 +0100
Subject: [PATCH 0670/1303] crypto: Clean up help text for CRYPTO_SHA256

NFS, Ceph, SMB, and Btrfs stopped using this SHA-256 implementation in
commits c2c90a8b2620626c ("nfsd: use SHA-256 library API instead of
crypto_shash API"), 27c0a7b05d13a0dc ("libceph: Use HMAC-SHA256 library
instead of crypto_shash"), 924067ef183bd17f ("ksmbd: Use HMAC-SHA256
library for message signing and key generation"), and fe11ac191ce0ad91
("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/bf8e1c229b36fc5349e29701e962d0dfd4fd21b6.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 8bc95e69faa5..c84fda3acdbd 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -963,7 +963,6 @@ config CRYPTO_SHA256
 	  10118-3), including HMAC support.
 
 	  This is required for IPsec AH (XFRM_AH) and IPsec ESP (XFRM_ESP).
-	  Used by the btrfs filesystem, Ceph, NFS, and SMB.
 
 config CRYPTO_SHA512
 	tristate "SHA-384 and SHA-512"

From a9ad29b7ad6c5e36ffa543ceb3c4439e63186339 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:07 +0100
Subject: [PATCH 0671/1303] crypto: Clean up help text for CRYPTO_XXHASH

Btrfs stopped using this xxHash implementation in commit
fe11ac191ce0ad91 ("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/3b632975201074ccaa129f4901a66aff87b19742.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index c84fda3acdbd..49293b656aff 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1036,8 +1036,6 @@ config CRYPTO_XXHASH
 
 	  Extremely fast, working at speeds close to RAM limits.
 
-	  Used by the btrfs filesystem.
-
 endmenu
 
 menu "CRCs (cyclic redundancy checks)"

From 0ef6eb10f2e0fe38bb795b2ecdb01b8c9b536ea8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:08 +0100
Subject: [PATCH 0672/1303] crypto: Clean up help text for CRYPTO_CRC32C

Ext4, jbd2, iSCSI, NVMeoF/TCP, and Btrfs stopped using this CRC32c
implementation in commits f2b4fa19647e18a2 ("ext4: switch to using the
crc32c library"), dd348f054b24a3f5 ("jbd2: switch to using the crc32c
library"), 92186c1455a2d356 ("scsi: iscsi_tcp: Switch to using the
crc32c library"), 427fff9aff295e2c ("nvme-tcp: use crc32c() and
skb_copy_and_crc32c_datagram_iter()"), and fe11ac191ce0ad91 ("btrfs:
switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/f567add7840bc612382237b3e76f3a8bdbd671e6.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 49293b656aff..5e66de2948ed 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1053,8 +1053,6 @@ config CRYPTO_CRC32C
 	  on Communications, Vol. 41, No. 6, June 1993, selected for use with
 	  iSCSI.
 
-	  Used by btrfs, ext4, jbd2, NVMeoF/TCP, and iSCSI.
-
 config CRYPTO_CRC32
 	tristate "CRC32"
 	select CRYPTO_HASH

From f33ac74f9cc1cdadd3921246832b2084a5dec53a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:09 +0100
Subject: [PATCH 0673/1303] crypto: Clean up help text for CRYPTO_CRC32

F2fs and RoCEv2 stopped using this CRC32 implementation in commits
3ca4bec40ee211cd ("f2fs: switch to using the crc32 library") and
ccca5e8aa1457231 ("RDMA/rxe: switch to using the crc32 library").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/0f76ebf05bb1b6ca50db97988f9ac20944534b4c.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 5e66de2948ed..b4bb85e8e226 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1060,8 +1060,6 @@ config CRYPTO_CRC32
 	help
 	  CRC32 CRC algorithm (IEEE 802.3)
 
-	  Used by RoCEv2 and f2fs.
-
 endmenu
 
 menu "Compression"

From 7cbe98f7bef965241a5908d50d557008cf998aee Mon Sep 17 00:00:00 2001
From: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Date: Sun, 1 Mar 2026 18:13:14 -0300
Subject: [PATCH 0674/1303] net: dsa: realtek: rtl8365mb: fix
 rtl8365mb_phy_ocp_write return value

Function rtl8365mb_phy_ocp_write() always returns 0, even when an error
occurs during register access. This patch fixes the return value to
propagate the actual error code from regmap operations.

Link: https://lore.kernel.org/netdev/a2dfde3c-d46f-434b-9d16-1e251e449068@yahoo.com/
Fixes: 2796728460b8 ("net: dsa: realtek: rtl8365mb: serialize indirect PHY register access")
Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260301-realtek_namiltd_fix1-v1-1-43a6bb707f9c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8365mb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index c575e164368c..f938a3f701cc 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy,
 out:
 	rtl83xx_unlock(priv);
 
-	return 0;
+	return ret;
 }
 
 static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum)

From 3f10543c5bdd11568d1a54f5b1d955f5652e3095 Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Sun, 1 Mar 2026 09:41:33 +0100
Subject: [PATCH 0675/1303] selftests/net: packetdrill: restore
 tcp_rcv_big_endseq.pkt

Commit 1cc93c48b5d7 ("selftests/net: packetdrill: remove tests for
tcp_rcv_*big") removed the test for the reverted commit 1d2fbaad7cd8
("tcp: stronger sk_rcvbuf checks") but also the one for commit
9ca48d616ed7 ("tcp: do not accept packets beyond window").

Restore the test with the necessary adaptation: expect a delayed ACK
instead of an immediate one, since tcp_can_ingest() does not fail
anymore for the last data packet.

Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Link: https://patch.msgid.link/20260301-tcp_rcv_big_endseq-v1-1-86ab7415ab58@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_big_endseq.pkt    | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
new file mode 100644
index 000000000000..6c0f32c40f19
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+    0 `nstat -n`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+  +.1 < . 1:1(0) ack 1 win 257
+
+  +0 accept(3, ..., ...) = 4
+
+  +0 < P. 1:4001(4000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 4001:54001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +1 < P. 5001:55001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 70001:80001(10000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+  +0 read(4, ..., 100000) = 4000
+
+// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
+  +0 < P. 4001:54001(50000) ack 1 win 257
+   * > .  1:1(0) ack 54001 win 0
+
+// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`

From 1939d9816dbfc057508267f0c5214f9478fbd6d1 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 1 Mar 2026 19:16:51 +0000
Subject: [PATCH 0676/1303] MAINTAINERS: ena: update AMAZON ETHERNET
 maintainers

Remove Shay Agroskin and Saeed Bishara.
Promote David Arinzon to maintainer.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Link: https://patch.msgid.link/20260301191652.5916-1-akiyano@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2265e2c9bfbe..7829ff2180ae 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -993,10 +993,8 @@ F:	Documentation/devicetree/bindings/thermal/amazon,al-thermal.yaml
 F:	drivers/thermal/thermal_mmio.c
 
 AMAZON ETHERNET DRIVERS
-M:	Shay Agroskin <shayagr@amazon.com>
 M:	Arthur Kiyanovski <akiyano@amazon.com>
-R:	David Arinzon <darinzon@amazon.com>
-R:	Saeed Bishara <saeedb@amazon.com>
+M:	David Arinzon <darinzon@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/device_drivers/ethernet/amazon/ena.rst

From a300000233a9ff842e2fb450fb9a79f7827a586d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 21 Feb 2026 12:45:25 -0800
Subject: [PATCH 0677/1303] fsverity: add dependency on 64K or smaller pages

Currently, all filesystems that support fsverity (ext4, f2fs, and btrfs)
cache the Merkle tree in the pagecache at a 64K aligned offset after the
end of the file data.  This offset needs to be a multiple of the page
size, which is guaranteed only when the page size is 64K or smaller.

64K was chosen to be the "largest reasonable page size".  But it isn't
the largest *possible* page size: the hexagon and powerpc ports of Linux
support 256K pages, though that configuration is rarely used.

For now, just disable support for FS_VERITY in these odd configurations
to ensure it isn't used in cases where it would have incorrect behavior.

Fixes: 671e67b47e9f ("fs-verity: add Kconfig and the helper functions for hashing")
Reported-by: Christoph Hellwig <hch@lst.de>
Closes: https://lore.kernel.org/r/20260119063349.GA643@lst.de
Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20260221204525.30426-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 fs/verity/Kconfig | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 76d1c5971b82..b20882963ffb 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -2,6 +2,9 @@
 
 config FS_VERITY
 	bool "FS Verity (read-only file-based authenticity protection)"
+	# Filesystems cache the Merkle tree at a 64K aligned offset in the
+	# pagecache.  That approach assumes the page size is at most 64K.
+	depends on PAGE_SHIFT <= 16
 	select CRYPTO_HASH_INFO
 	select CRYPTO_LIB_SHA256
 	select CRYPTO_LIB_SHA512

From 93992667d0ab695ac30ceec91a516fd4bf725d75 Mon Sep 17 00:00:00 2001
From: Rong Zhang <i@rong.moe>
Date: Tue, 3 Mar 2026 01:32:59 +0800
Subject: [PATCH 0678/1303] ALSA: doc: usb-audio: Add doc for
 QUIRK_FLAG_SKIP_IFACE_SETUP

QUIRK_FLAG_SKIP_IFACE_SETUP was introduced into usb-audio before without
appropriate documentation, so add it.

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Cc: stable@vger.kernel.org
Signed-off-by: Rong Zhang <i@rong.moe>
Link: https://patch.msgid.link/20260302173300.322673-1-i@rong.moe
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/alsa-configuration.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index 0a4eaa7d66dd..55b845d38236 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -2372,6 +2372,10 @@ quirk_flags
           audible volume
         * bit 25: ``mixer_capture_min_mute``
           Similar to bit 24 but for capture streams
+        * bit 26: ``skip_iface_setup``
+          Skip the probe-time interface setup (usb_set_interface,
+          init_pitch, init_sample_rate); redundant with
+          snd_usb_endpoint_prepare() at stream-open time
 
 This module supports multiple devices, autoprobe and hotplugging.
 

From 83307aebe6a1a4fddf5dec6071716ce251da9cc9 Mon Sep 17 00:00:00 2001
From: wangdicheng <wangdicheng@kylinos.cn>
Date: Tue, 3 Mar 2026 13:42:42 +0800
Subject: [PATCH 0679/1303] ALSA: hda/senary: Use codec->core.afg for GPIO
 access

Replace the hardcoded GPIO node ID (0x01) with codec->core.afg.
This follows the standard HDA driver practice and makes the driver
more robust against different hardware configurations.

Signed-off-by: wangdicheng <wangdicheng@kylinos.cn>
Link: https://patch.msgid.link/20260303054242.318062-1-wangdich9700@163.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/senarytech.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/hda/codecs/senarytech.c b/sound/hda/codecs/senarytech.c
index 3a50d4b3a064..8822d4dc5e36 100644
--- a/sound/hda/codecs/senarytech.c
+++ b/sound/hda/codecs/senarytech.c
@@ -19,9 +19,6 @@
 #include "hda_jack.h"
 #include "generic.h"
 
-/* GPIO node ID */
-#define SENARY_GPIO_NODE	0x01
-
 struct senary_spec {
 	struct hda_gen_spec gen;
 
@@ -123,11 +120,11 @@ static void senary_init_gpio_led(struct hda_codec *codec)
 	unsigned int mask = spec->gpio_mute_led_mask | spec->gpio_mic_led_mask;
 
 	if (mask) {
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_MASK,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_MASK,
 				    mask);
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DIRECTION,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DIRECTION,
 				    mask);
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DATA,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DATA,
 				    spec->gpio_led);
 	}
 }

From 8fb54c7307f6add04246d2f7845e42ecd41950fe Mon Sep 17 00:00:00 2001
From: MeiChia Chiu <MeiChia.Chiu@mediatek.com>
Date: Tue, 3 Mar 2026 13:47:25 +0800
Subject: [PATCH 0680/1303] wifi: mac80211: fix missing ieee80211_eml_params
 member initialization

The missing initialization causes driver to misinterpret the EML control bitmap,
resulting in incorrect link bitmap handling.

Fixes: 0d95280a2d54e ("wifi: mac80211: Add eMLSR/eMLMR action frame parsing support")
Signed-off-by: MeiChia Chiu <MeiChia.Chiu@mediatek.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260303054725.471548-1-MeiChia.Chiu@mediatek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/eht.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c
index 75096b2195d2..078e1e23d8d1 100644
--- a/net/mac80211/eht.c
+++ b/net/mac80211/eht.c
@@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata,
 	u8 *ptr = mgmt->u.action.u.eml_omn.variable;
 	struct ieee80211_eml_params eml_params = {
 		.link_id = status->link_id,
+		.control = control,
 	};
 	struct sta_info *sta;
 	int opt_len = 0;

From a116bac87118903925108e57781bbfc7a7eea27b Mon Sep 17 00:00:00 2001
From: "Isaac J. Manjarres" <isaacmanjarres@google.com>
Date: Mon, 2 Mar 2026 16:23:09 -0800
Subject: [PATCH 0681/1303] dma-buf: Include ioctl.h in UAPI header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

include/uapi/linux/dma-buf.h uses several macros from ioctl.h to define
its ioctl commands. However, it does not include ioctl.h itself. So,
if userspace source code tries to include the dma-buf.h file without
including ioctl.h, it can result in build failures.

Therefore, include ioctl.h in the dma-buf UAPI header.

Signed-off-by: Isaac J. Manjarres <isaacmanjarres@google.com>
Reviewed-by: T.J. Mercier <tjmercier@google.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20260303002309.1401849-1-isaacmanjarres@google.com
---
 include/uapi/linux/dma-buf.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h
index 5a6fda66d9ad..e827c9d20c5d 100644
--- a/include/uapi/linux/dma-buf.h
+++ b/include/uapi/linux/dma-buf.h
@@ -20,6 +20,7 @@
 #ifndef _DMA_BUF_UAPI_H_
 #define _DMA_BUF_UAPI_H_
 
+#include <linux/ioctl.h>
 #include <linux/types.h>
 
 /**

From 3f27958b729a2337336a6b50e0d9aee5fbbce816 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Tue, 3 Mar 2026 14:09:58 +0800
Subject: [PATCH 0682/1303] sched_ext: Use READ_ONCE() for plain reads of
 scx_watchdog_timeout

scx_watchdog_timeout is written with WRITE_ONCE() in scx_enable():

    WRITE_ONCE(scx_watchdog_timeout, timeout);

However, three read-side accesses use plain reads without the matching
READ_ONCE():

    /* check_rq_for_timeouts() - L2824 */
    last_runnable + scx_watchdog_timeout

    /* scx_watchdog_workfn() - L2852 */
    scx_watchdog_timeout / 2

    /* scx_enable() - L5179 */
    scx_watchdog_timeout / 2

The KCSAN documentation requires that if one accessor uses WRITE_ONCE()
to annotate lock-free access, all other accesses must also use the
appropriate accessor. Plain reads alongside WRITE_ONCE() leave the pair
incomplete and can trigger KCSAN warnings.

Note that scx_tick() already uses the correct READ_ONCE() annotation:

    last_check + READ_ONCE(scx_watchdog_timeout)

Fix the three remaining plain reads to match, making all accesses to
scx_watchdog_timeout consistently annotated and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index a566d2cc8a43..2ba69b302368 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2739,7 +2739,7 @@ static bool check_rq_for_timeouts(struct rq *rq)
 		unsigned long last_runnable = p->scx.runnable_at;
 
 		if (unlikely(time_after(jiffies,
-					last_runnable + scx_watchdog_timeout))) {
+					last_runnable + READ_ONCE(scx_watchdog_timeout)))) {
 			u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);
 
 			scx_exit(sch, SCX_EXIT_ERROR_STALL, 0,
@@ -2767,7 +2767,7 @@ static void scx_watchdog_workfn(struct work_struct *work)
 		cond_resched();
 	}
 	queue_delayed_work(system_unbound_wq, to_delayed_work(work),
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 }
 
 void scx_tick(struct rq *rq)
@@ -5081,7 +5081,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	WRITE_ONCE(scx_watchdog_timeout, timeout);
 	WRITE_ONCE(scx_watchdog_timestamp, jiffies);
 	queue_delayed_work(system_unbound_wq, &scx_watchdog_work,
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 
 	/*
 	 * Once __scx_enabled is set, %current can be switched to SCX anytime.

From 9af832c0a76eedce169c4c6360e4e20d8a0c9ab1 Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:15 +0800
Subject: [PATCH 0683/1303] tools/sched_ext: Add -fms-extensions to bpf build
 flags

Similar to commit 835a50753579 ("selftests/bpf: Add -fms-extensions to
bpf build flags") and commit 639f58a0f480 ("bpftool: Fix build warnings
due to MS extensions")

The kernel is now built with -fms-extensions, therefore
generated vmlinux.h contains types like:
struct aes_key {
        struct aes_enckey;
        union aes_invkey_arch inv_k;
};

struct ns_common {
	...
        union {
                struct ns_tree;
                struct callback_head ns_rcu;
        };
};

Which raise warning like below when building scx scheduler:

tools/sched_ext/build/include/vmlinux.h:50533:3: warning:
declaration does not declare anything [-Wmissing-declarations]
 50533 |                 struct ns_tree;
       |                 ^
Fix it by using -fms-extensions and -Wno-microsoft-anon-tag flags
to build bpf programs that #include "vmlinux.h"

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile
index 47ad7444677e..21554f089692 100644
--- a/tools/sched_ext/Makefile
+++ b/tools/sched_ext/Makefile
@@ -122,6 +122,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     -I../../include							\
 	     $(call get_sys_includes,$(CLANG))					\
 	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building

From 01a867c2e090cb440c8f27158e8650c8ddefec8e Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:16 +0800
Subject: [PATCH 0684/1303] selftests/sched_ext: Add -fms-extensions to bpf
 build flags

Similar to commit 835a50753579 ("selftests/bpf: Add -fms-extensions to
bpf build flags") and commit 639f58a0f480 ("bpftool: Fix build warnings
due to MS extensions")

Fix "declaration does not declare anything" warning by using
-fms-extensions and -Wno-microsoft-anon-tag flags to build bpf programs
that #include "vmlinux.h"

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 2c601a7eaff5..006300ac6dff 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     $(CLANG_SYS_INCLUDES) 						\
 	     -Wall -Wno-compare-distinct-pointer-types				\
 	     -Wno-incompatible-function-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building

From 75ad51825933575906394d0d5db04586b02db00a Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:17 +0800
Subject: [PATCH 0685/1303] selftests/sched_ext: Fix peek_dsq.bpf.c compile
 error for clang 17

When compiling sched_ext selftests using clang 17.0.6, it raised
compiler crash and build error:

Error at line 68: Unsupport signed division for DAG: 0x55b2f9a60240:
i64 = sdiv 0x55b2f9a609b0, Constant:i64<100>, peek_dsq.bpf.c:68:25 @[
peek_dsq.bpf.c:95:4 @[ peek_dsq.bpf.c:169:8 @[ peek
_dsq.bpf.c:140:6 ] ] ]Please convert to unsigned div/mod

After digging, it's not a compiler error, clang supported Signed division
only when using -mcpu=v4, while we use -mcpu=v3 currently, the better way
is to use unsigned div, see [1] for details.

[1] https://github.com/llvm/llvm-project/issues/70433

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/peek_dsq.bpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
index a3faf5bb49d6..784f2f6c1af9 100644
--- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
@@ -58,14 +58,14 @@ static void record_peek_result(long pid)
 {
 	u32 slot_key;
 	long *slot_pid_ptr;
-	int ix;
+	u32 ix;
 
 	if (pid <= 0)
 		return;
 
 	/* Find an empty slot or one with the same PID */
 	bpf_for(ix, 0, 10) {
-		slot_key = (pid + ix) % MAX_SAMPLES;
+		slot_key = ((u64)pid + ix) % MAX_SAMPLES;
 		slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key);
 		if (!slot_pid_ptr)
 			continue;

From 7ae0d8f1abbbba6f98cac735145e1206927c67d9 Mon Sep 17 00:00:00 2001
From: wangdicheng <wangdicheng@kylinos.cn>
Date: Tue, 3 Mar 2026 16:15:16 +0800
Subject: [PATCH 0686/1303] ALSA: hda/senary: Ensure EAPD is enabled during
 init

The driver sets spec->gen.own_eapd_ctl to take manual control of the
EAPD (External Amplifier). However, senary_init does not turn on the
EAPD, while senary_shutdown turns it off.

Since the generic driver skips EAPD handling when own_eapd_ctl is set,
the EAPD remains off after initialization (e.g., after resume), leaving
the codec in a non-functional state.

Explicitly call senary_auto_turn_eapd in senary_init to ensure the EAPD
is enabled and the codec is functional.

Signed-off-by: wangdicheng <wangdicheng@kylinos.cn>
Link: https://patch.msgid.link/20260303081516.583438-1-wangdich9700@163.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/senarytech.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/hda/codecs/senarytech.c b/sound/hda/codecs/senarytech.c
index 8822d4dc5e36..6239a25bb8f3 100644
--- a/sound/hda/codecs/senarytech.c
+++ b/sound/hda/codecs/senarytech.c
@@ -25,6 +25,7 @@ struct senary_spec {
 	/* extra EAPD pins */
 	unsigned int num_eapds;
 	hda_nid_t eapds[4];
+	bool dynamic_eapd;
 	hda_nid_t mute_led_eapd;
 
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
@@ -131,8 +132,12 @@ static void senary_init_gpio_led(struct hda_codec *codec)
 
 static int senary_init(struct hda_codec *codec)
 {
+	struct senary_spec *spec = codec->spec;
+
 	snd_hda_gen_init(codec);
 	senary_init_gpio_led(codec);
+	if (!spec->dynamic_eapd)
+		senary_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT);
 
 	return 0;

From 479d589b40b836442bbdadc3fdb37f001bb67f26 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 26 Feb 2026 16:03:01 +0800
Subject: [PATCH 0687/1303] bpf/bonding: reject vlan+srcmac xmit_hash_policy
 change when XDP is loaded

bond_option_mode_set() already rejects mode changes that would make a
loaded XDP program incompatible via bond_xdp_check().  However,
bond_option_xmit_hash_policy_set() has no such guard.

For 802.3ad and balance-xor modes, bond_xdp_check() returns false when
xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually
absent due to hardware offload.  This means a user can:

1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode
   with a compatible xmit_hash_policy (e.g. layer2+3).
2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.

This leaves bond->xdp_prog set but bond_xdp_check() now returning false
for the same device.  When the bond is later destroyed, dev_xdp_uninstall()
calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits
the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering:

WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL))

Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an
XDP program is loaded on a bond in 802.3ad or balance-xor mode.

commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP")
introduced bond_xdp_check() which returns false for 802.3ad/balance-xor
modes when xmit_hash_policy is vlan+srcmac.  The check was wired into
bond_xdp_set() to reject XDP attachment with an incompatible policy, but
the symmetric path -- preventing xmit_hash_policy from being changed to an
incompatible value after XDP is already loaded -- was left unguarded in
bond_option_xmit_hash_policy_set().

Note:
commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode")
later added a similar guard to bond_option_mode_set(), but
bond_option_xmit_hash_policy_set() remained unprotected.

Reported-by: syzbot+5a287bcdc08104bc3132@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6995aff6.050a0220.2eeac1.014e.GAE@google.com/T/
Fixes: 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP")
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260226080306.98766-2-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c    | 9 +++++++--
 drivers/net/bonding/bond_options.c | 2 ++
 include/net/bonding.h              | 1 +
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a1de08ee3815..14ed91391fcc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-bool bond_xdp_check(struct bonding *bond, int mode)
+bool __bond_xdp_check(int mode, int xmit_policy)
 {
 	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
@@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 		/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
 		 * payload is not in the packet due to hardware offload.
 		 */
-		if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
+		if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
 			return true;
 		fallthrough;
 	default:
@@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 	}
 }
 
+bool bond_xdp_check(struct bonding *bond, int mode)
+{
+	return __bond_xdp_check(mode, bond->params.xmit_policy);
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index dcee384c2f06..7380cc4ee75a 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1575,6 +1575,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond,
 static int bond_option_xmit_hash_policy_set(struct bonding *bond,
 					    const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value))
+		return -EOPNOTSUPP;
 	netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.xmit_policy = newval->value;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 4ad5521e7731..395c6e281c5f 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool __bond_xdp_check(int mode, int xmit_policy);
 bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);

From 181cafbd8a01d22f3078a84f079c4a7cc0653068 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 26 Feb 2026 16:03:02 +0800
Subject: [PATCH 0688/1303] selftests/bpf: add test for xdp_bonding
 xmit_hash_policy compat

Add a selftest to verify that changing xmit_hash_policy to vlan+srcmac
is rejected when a native XDP program is loaded on a bond in 802.3ad
mode.  Without the fix in bond_option_xmit_hash_policy_set(), the change
succeeds silently, creating an inconsistent state that triggers a kernel
WARNING in dev_xdp_uninstall() when the bond is torn down.

The test attaches native XDP to a bond0 (802.3ad, layer2+3), then
attempts to switch xmit_hash_policy to vlan+srcmac and asserts the
operation fails.  It also verifies the change succeeds after XDP is
detached, confirming the rejection is specific to the XDP-loaded state.

Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260226080306.98766-3-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/bpf/prog_tests/xdp_bonding.c    | 58 +++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index fb952703653e..e8ea26464349 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -610,6 +610,61 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	system("ip link del bond");
 }
 
+/*
+ * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a
+ * native XDP program is loaded on a bond in 802.3ad or balance-xor mode.
+ * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely
+ * changing the policy creates an inconsistency that triggers a WARNING in
+ * dev_xdp_uninstall() during device teardown.
+ */
+static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons)
+{
+	struct nstoken *nstoken = NULL;
+	int bond_ifindex = -1;
+	int xdp_fd, err;
+
+	SYS(out, "ip netns add ns_xmit_policy");
+	nstoken = open_netns("ns_xmit_policy");
+	if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy"))
+		goto out;
+
+	/* 802.3ad with layer2+3 policy: native XDP is supported */
+	SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3");
+	SYS(out, "ip link add veth0 type veth peer name veth0p");
+	SYS(out, "ip link set veth0 master bond0");
+	SYS(out, "ip link set bond0 up");
+
+	bond_ifindex = if_nametoindex("bond0");
+	if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex"))
+		goto out;
+
+	xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog);
+	if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd"))
+		goto out;
+
+	err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL);
+	if (!ASSERT_OK(err, "attach XDP to bond0"))
+		goto out;
+
+	/* With XDP loaded, switching to vlan+srcmac must be rejected */
+	err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null");
+	ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail");
+
+	/* Detach XDP first, then the same change must succeed */
+	ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL),
+		  "detach XDP from bond0");
+
+	bond_ifindex = -1;
+	err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null");
+	ASSERT_OK(err, "vlan+srcmac change without XDP should succeed");
+
+out:
+	if (bond_ifindex > 0)
+		bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL);
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del ns_xmit_policy");
+}
+
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
@@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void)
 				test_case->xmit_policy);
 	}
 
+	if (test__start_subtest("xdp_bonding_xmit_policy_compat"))
+		test_xdp_bonding_xmit_policy_compat(&skeletons);
+
 	if (test__start_subtest("xdp_bonding_redirect_multi"))
 		test_xdp_bonding_redirect_multi(&skeletons);
 

From 18c04a808c436d629d5812ce883e3822a5f5a47f Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:57 +0000
Subject: [PATCH 0689/1303] octeon_ep: Relocate counter updates before NAPI

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion,
and replace napi_complete with napi_complete_done.

Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly
   synchronized.
napi_complete_done (vs napi_complete) allows for better
interrupt coalescing.

Fixes: 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-2-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeon_ep/octep_main.c   | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index ec55eb2a6c04..bb5f21b33508 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -554,12 +554,12 @@ static void octep_clean_irqs(struct octep_device *oct)
 }
 
 /**
- * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -575,7 +575,17 @@ static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
-	wmb();
+	smp_wmb();
+}
+
+/**
+ * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+{
 	writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -601,7 +611,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
-	napi_complete(napi);
+	octep_update_pkt(ioq_vector->iq, ioq_vector->oq);
+	napi_complete_done(napi, rx_done);
 	octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 	return rx_done;
 }

From 43b3160cb639079a15daeb5f080120afbfbfc918 Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:58 +0000
Subject: [PATCH 0690/1303] octeon_ep: avoid compiler and IQ/OQ reordering

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx
variable access to prevent compiler optimization and reordering.
Additionally, ensure IO queue OUT/IN_CNT registers are flushed
by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count,
etc., causing stale values to be used when calculating packets to process
or register updates to send to hardware. The Octeon hardware requires a
read-back after writing to OUT_CNT/IN_CNT registers to ensure the write
has been flushed through any posted write buffers before the interrupt
resend bit is set. Without this, we have observed cases where the hardware
didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler
from performing optimizations like caching in registers, load tearing etc.

Fixes: 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-3-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeon_ep/octep_main.c   | 21 +++++++++------
 .../net/ethernet/marvell/octeon_ep/octep_rx.c | 27 +++++++++++++------
 2 files changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index bb5f21b33508..028dd55604ea 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -561,17 +561,22 @@ static void octep_clean_irqs(struct octep_device *oct)
  */
 static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index f2a7c6a76c74..74de19166488 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 				      struct octep_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
 
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
 	 * reached half its max value.
@@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 	u16 rx_ol_flags;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_device *oct = oq->octep_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_oq_process_rx(oct, oq,
 						       pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 

From 2ae7d20fb24f598f60faa8f6ecc856dac782261a Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:59 +0000
Subject: [PATCH 0691/1303] octeon_ep_vf: Relocate counter updates before NAPI

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion.
Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly
   synchronized.

Fixes: 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-4-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../marvell/octeon_ep_vf/octep_vf_main.c        | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 562fe945b422..0e76f671a226 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -286,12 +286,13 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 }
 
 /**
- * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
+
+static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -308,6 +309,17 @@ static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *
 
 	/* Flush the previous wrties before writing to RESEND bit */
 	smp_wmb();
+}
+
+/**
+ * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq,
+				    struct octep_vf_oq *oq)
+{
 	writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -333,6 +345,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
+	octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq);
 	if (likely(napi_complete_done(napi, rx_done)))
 		octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 

From 6c73126ecd1080351b468fe43353b2f705487f44 Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:14:00 +0000
Subject: [PATCH 0692/1303] octeon_ep_vf: avoid compiler and IQ/OQ reordering

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx
variable access to prevent compiler optimization and reordering.
Additionally, ensure IO queue OUT/IN_CNT registers are flushed
by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count,
etc., causing stale values to be used when calculating packets to process
or register updates to send to hardware. The Octeon hardware requires a
read-back after writing to OUT_CNT/IN_CNT registers to ensure the write
has been flushed through any posted write buffers before the interrupt
resend bit is set. Without this, we have observed cases where the hardware
didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler
from performing optimizations like caching in registers, load tearing etc.

Fixes: 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-5-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../marvell/octeon_ep_vf/octep_vf_main.c      | 21 ++++++++------
 .../marvell/octeon_ep_vf/octep_vf_rx.c        | 28 +++++++++++++------
 2 files changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 0e76f671a226..7f1b93cffb98 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -294,17 +294,22 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 
 static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
index 6f865dbbba6c..b579d5b545c4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
@@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 					 struct octep_vf_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
+
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
@@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 	struct sk_buff *skb;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_vf_device *oct = oq->octep_vf_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_vf_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_vf_oq_process_rx(oct, oq,
 							  pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 

From d98c24617a831e92e7224a07dcaed2dd0b02af96 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:24 -0800
Subject: [PATCH 0693/1303] wifi: cw1200: Fix locking in error paths

cw1200_wow_suspend() must only return with priv->conf_mutex locked if it
returns zero. This mutex must be unlocked if an error is returned. Add
mutex_unlock() calls to the error paths from which that call is missing.
This has been detected by the Clang thread-safety analyzer.

Fixes: a910e4a94f69 ("cw1200: add driver for the ST-E CW1100 & CW1200 WLAN chipsets")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223220102.2158611-25-bart.vanassche@linux.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/st/cw1200/pm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c
index 120f0379f81d..84eb15d729c7 100644
--- a/drivers/net/wireless/st/cw1200/pm.c
+++ b/drivers/net/wireless/st/cw1200/pm.c
@@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		wiphy_err(priv->hw->wiphy,
 			  "PM request failed: %d. WoW is disabled.\n", ret);
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EBUSY;
 	}
 
 	/* Force resume if event is coming from the device. */
 	if (atomic_read(&priv->bh_rx)) {
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EAGAIN;
 	}
 

From 72c6df8f284b3a49812ce2ac136727ace70acc7c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:25 -0800
Subject: [PATCH 0694/1303] wifi: wlcore: Fix a locking bug

Make sure that wl->mutex is locked before it is unlocked. This has been
detected by the Clang thread-safety analyzer.

Fixes: 45aa7f071b06 ("wlcore: Use generic runtime pm calls for wowlan elp configuration")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223220102.2158611-26-bart.vanassche@linux.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wlcore/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 17dd417756f2..1c340a4a0930 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -1875,6 +1875,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		     wl->wow_enabled);
 	WARN_ON(!wl->wow_enabled);
 
+	mutex_lock(&wl->mutex);
+
 	ret = pm_runtime_force_resume(wl->dev);
 	if (ret < 0) {
 		wl1271_error("ELP wakeup failure!");
@@ -1891,8 +1893,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		run_irq_work = true;
 	spin_unlock_irqrestore(&wl->wl_lock, flags);
 
-	mutex_lock(&wl->mutex);
-
 	/* test the recovery flag before calling any SDIO functions */
 	pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS,
 				    &wl->flags);

From 60862846308627e9e15546bb647a00de44deb27b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:14 +0100
Subject: [PATCH 0695/1303] wifi: mt76: mt7996: Fix possible oob access in
 mt7996_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes: 98686cd21624c ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-1-b0f6d1ad4850@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 2560e2f46e89..d4f3ee943b47 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -800,6 +800,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
 		if (is_mt7990(&dev->mt76))

From c41a9abd6ae31d130e8f332e7c8800c4c866234b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:15 +0100
Subject: [PATCH 0696/1303] wifi: mt76: mt7925: Fix possible oob access in
 mt7925_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes: c948b5da6bbec ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-2-b0f6d1ad4850@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index 871b67101976..0d9435900423 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -668,6 +668,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ)
 		tid = MT_TX_ADDBA;

From 4e10a730d1b511ff49723371ed6d694dd1b2c785 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:16 +0100
Subject: [PATCH 0697/1303] wifi: mt76: Fix possible oob access in
 mt76_connac2_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob
access.

Fixes: 577dbc6c656d ("mt76: mt7915: enable offloading of sequence number assignment")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-3-b0f6d1ad4850@kernel.org
[fix check to also cover mgmt->u.action.u.addba_req.capab,
correct Fixes tag]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index 3304b5971be0..b41ca1410da9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -413,6 +413,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + 1 + 2 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
 		u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab);

From 710f5c76580306cdb9ec51fac8fcf6a8faff7821 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 27 Feb 2026 17:26:03 +0000
Subject: [PATCH 0698/1303] indirect_call_wrapper: do not reevaluate function
 pointer

We have an increasing number of READ_ONCE(xxx->function)
combined with INDIRECT_CALL_[1234]() helpers.

Unfortunately this forces INDIRECT_CALL_[1234]() to read
xxx->function many times, which is not what we wanted.

Fix these macros so that xxx->function value is not reloaded.

$ scripts/bloat-o-meter -t vmlinux.0 vmlinux
add/remove: 0/0 grow/shrink: 1/65 up/down: 122/-1084 (-962)
Function                                     old     new   delta
ip_push_pending_frames                        59     181    +122
ip6_finish_output                            687     681      -6
__udp_enqueue_schedule_skb                  1078    1072      -6
ioam6_output                                2319    2312      -7
xfrm4_rcv_encap_finish2                       64      56      -8
xfrm4_output                                 297     289      -8
vrf_ip_local_out                             278     270      -8
vrf_ip6_local_out                            278     270      -8
seg6_input_finish                             64      56      -8
rpl_output                                   700     692      -8
ipmr_forward_finish                          124     116      -8
ip_forward_finish                            143     135      -8
ip6mr_forward2_finish                        100      92      -8
ip6_forward_finish                            73      65      -8
input_action_end_bpf                        1091    1083      -8
dst_input                                     52      44      -8
__xfrm6_output                               801     793      -8
__xfrm4_output                                83      75      -8
bpf_input                                    500     491      -9
__tcp_check_space                            530     521      -9
input_action_end_dt6                         291     280     -11
vti6_tnl_xmit                               1634    1622     -12
bpf_xmit                                    1203    1191     -12
rpl_input                                    497     483     -14
rawv6_send_hdrinc                           1355    1341     -14
ndisc_send_skb                              1030    1016     -14
ipv6_srh_rcv                                1377    1363     -14
ip_send_unicast_reply                       1253    1239     -14
ip_rcv_finish                                226     212     -14
ip6_rcv_finish                               300     286     -14
input_action_end_x_core                      205     191     -14
input_action_end_x                           355     341     -14
input_action_end_t                           205     191     -14
input_action_end_dx6_finish                  127     113     -14
input_action_end_dx4_finish                  373     359     -14
input_action_end_dt4                         426     412     -14
input_action_end_core                        186     172     -14
input_action_end_b6_encap                    292     278     -14
input_action_end_b6                          198     184     -14
igmp6_send                                  1332    1318     -14
ip_sublist_rcv                               864     848     -16
ip6_sublist_rcv                             1091    1075     -16
ipv6_rpl_srh_rcv                            1937    1920     -17
xfrm_policy_queue_process                   1246    1228     -18
seg6_output_core                             903     885     -18
mld_sendpack                                 856     836     -20
NF_HOOK                                      756     736     -20
vti_tunnel_xmit                             1447    1426     -21
input_action_end_dx6                         664     642     -22
input_action_end                            1502    1480     -22
sock_sendmsg_nosec                           134     111     -23
ip6mr_forward2                               388     364     -24
sock_recvmsg_nosec                           134     109     -25
seg6_input_core                              836     810     -26
ip_send_skb                                  172     146     -26
ip_local_out                                 140     114     -26
ip6_local_out                                140     114     -26
__sock_sendmsg                               162     136     -26
__ip_queue_xmit                             1196    1170     -26
__ip_finish_output                           405     379     -26
ipmr_queue_fwd_xmit                          373     346     -27
sock_recvmsg                                 173     145     -28
ip6_xmit                                    1635    1607     -28
xfrm_output_resume                          1418    1389     -29
ip_build_and_send_pkt                        625     591     -34
dst_output                                   504     432     -72
Total: Before=25217686, After=25216724, chg -0.00%

Fixes: 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up indirect calls of builtin")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260227172603.1700433-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/indirect_call_wrapper.h | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 35227d47cfc9..dc272b514a01 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -16,22 +16,26 @@
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
 	({								\
-		likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__);	\
+		typeof(f) __f1 = (f);					\
+		likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_2(f, f2, f1, ...)					\
 	({								\
-		likely(f == f2) ? f2(__VA_ARGS__) :			\
-				  INDIRECT_CALL_1(f, f1, __VA_ARGS__);	\
+		typeof(f) __f2 = (f);					\
+		likely(__f2 == f2) ? f2(__VA_ARGS__) :			\
+				  INDIRECT_CALL_1(__f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_3(f, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f3) ? f3(__VA_ARGS__) :				\
-				  INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f3 = (f);						\
+		likely(__f3 == f3) ? f3(__VA_ARGS__) :				\
+				  INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f4) ? f4(__VA_ARGS__) :				\
-				  INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f4 = (f);						\
+		likely(__f4 == f4) ? f4(__VA_ARGS__) :				\
+				  INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__);	\
 	})
 
 #define INDIRECT_CALLABLE_DECLARE(f)	f

From 6a877ececd6daa002a9a0002cd0fbca6592a9244 Mon Sep 17 00:00:00 2001
From: Allison Henderson <achender@kernel.org>
Date: Fri, 27 Feb 2026 13:23:36 -0700
Subject: [PATCH 0699/1303] net/rds: Fix circular locking dependency in
 rds_tcp_tune

syzbot reported a circular locking dependency in rds_tcp_tune() where
sk_net_refcnt_upgrade() is called while holding the socket lock:

======================================================
WARNING: possible circular locking dependency detected
======================================================
kworker/u10:8/15040 is trying to acquire lock:
ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0},
at: __kmalloc_cache_noprof+0x4b/0x6f0

but task is already holding lock:
ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0},
at: rds_tcp_tune+0xd7/0x930

The issue occurs because sk_net_refcnt_upgrade() performs memory
allocation (via get_net_track() -> ref_tracker_alloc()) while the
socket lock is held, creating a circular dependency with fs_reclaim.

Fix this by moving sk_net_refcnt_upgrade() outside the socket lock
critical section. This is safe because the fields modified by the
sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not
accessed by any concurrent code path at this point.

v2:
  - Corrected fixes tag
  - check patch line wrap nits
  - ai commentary nits

Reported-by: syzbot+2e2cf5331207053b8106@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2e2cf5331207053b8106
Fixes: 3a58f13a881e ("net: rds: acquire refcount on TCP sockets")
Signed-off-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260227202336.167757-1-achender@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rds/tcp.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 04f310255692..654e23d13e3d 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock)
 	struct rds_tcp_net *rtn;
 
 	tcp_sock_set_nodelay(sock->sk);
-	lock_sock(sk);
 	/* TCP timer functions might access net namespace even after
 	 * a process which created this net namespace terminated.
 	 */
 	if (!sk->sk_net_refcnt) {
-		if (!maybe_get_net(net)) {
-			release_sock(sk);
+		if (!maybe_get_net(net))
 			return false;
-		}
+		/*
+		 * sk_net_refcnt_upgrade() must be called before lock_sock()
+		 * because it does a GFP_KERNEL allocation, which can trigger
+		 * fs_reclaim and create a circular lock dependency with the
+		 * socket lock.  The fields it modifies (sk_net_refcnt,
+		 * ns_tracker) are not accessed by any concurrent code path
+		 * at this point.
+		 */
 		sk_net_refcnt_upgrade(sk);
 		put_net(net);
 	}
+	lock_sock(sk);
 	rtn = net_generic(net, rds_tcp_netid);
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;

From 9de68394a61528d40f575c3e6719cc75c56f62c3 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 2 Mar 2026 01:25:44 +0100
Subject: [PATCH 0700/1303] Revert "driver core: enforce device_lock for
 driver_match_device()"

This reverts commit dc23806a7c47 ("driver core: enforce device_lock for
driver_match_device()") and commit 289b14592cef ("driver core: fix
inverted "locked" suffix of driver_match_device()").

While technically correct, there is a major downside to this approach:

When a device is already present in the system and a driver is
registered on the same bus, we iterate over all devices registered on
this bus to see if one of them matches. If we come across an already
bound one where the corresponding driver crashed while holding the
device lock (e.g. in probe()) we can't make any progress anymore.

However, drivers are typically the least tested code in the kernel and
hence it is a case that is likely to happen regularly. Besides hurting
developer ergonomics, it potentially decreases chances of shutting
things down cleanly and obtaining logs in production environments as
well [1].

This came up in the context of a firewire bug, which only in combination
with the reverted commit, caused the machine to hang [2]. Additionally,
it was observed in [3].

Thus, revert commit dc23806a7c47 ("driver core: enforce device_lock for
driver_match_device()") and add a brief note clarifying that an
implementer of struct bus_type must not expect match() to be called with
the device lock held.

Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1]
Link: https://lore.kernel.org/all/67f655bb-4d81-4609-b008-68d200255dd2@davidgow.net/ [2]
Link: https://lore.kernel.org/lkml/CALbr=LZ4v7N=tO1vgOsyj9AS+XuNbn6kG-QcF+PacdMjSo0iyw@mail.gmail.com/ [3]
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Closes: https://lore.kernel.org/driver-core/CAHk-=wgJ_L1C=HjcYJotg_zrZEmiLFJaoic+PWthjuQrutrfJw@mail.gmail.com/
Reviewed-by: Gui-Dong Han <hanguidong02@gmail.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260302002545.19389-1-dakr@kernel.org
[ Add additional Link: reference. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/base.h        | 11 +----------
 drivers/base/dd.c          |  2 +-
 include/linux/device/bus.h |  2 ++
 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/base/base.h b/drivers/base/base.h
index 79d031d2d845..1af95ac68b77 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -179,19 +179,10 @@ void device_release_driver_internal(struct device *dev, const struct device_driv
 void driver_detach(const struct device_driver *drv);
 void driver_deferred_probe_del(struct device *dev);
 void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf);
-static inline int driver_match_device_locked(const struct device_driver *drv,
-					     struct device *dev)
-{
-	device_lock_assert(dev);
-
-	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
-}
-
 static inline int driver_match_device(const struct device_driver *drv,
 				      struct device *dev)
 {
-	guard(device)(dev);
-	return driver_match_device_locked(drv, dev);
+	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
 }
 
 static inline void dev_sync_state(struct device *dev)
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 0354f209529c..bea8da5f8a3a 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -928,7 +928,7 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 	bool async_allowed;
 	int ret;
 
-	ret = driver_match_device_locked(drv, dev);
+	ret = driver_match_device(drv, dev);
 	if (ret == 0) {
 		/* no match */
 		return 0;
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 99c3c83ea520..63de5f053c33 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -35,6 +35,8 @@ struct fwnode_handle;
  *		otherwise. It may also return error code if determining that
  *		the driver supports the device is not possible. In case of
  *		-EPROBE_DEFER it will queue the device for deferred probing.
+ *		Note: This callback may be invoked with or without the device
+ *		lock held.
  * @uevent:	Called when a device is added, removed, or a few other things
  *		that generate uevents to add the environment variables.
  * @probe:	Called when a new device or driver add to this bus, and callback

From 1a86a1f7d88996085934139fa4c063b6299a2dd3 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Fri, 27 Feb 2026 22:19:37 +0000
Subject: [PATCH 0701/1303] net: Fix rcu_tasks stall in threaded busypoll

I was debugging a NIC driver when I noticed that when I enable
threaded busypoll, bpftrace hangs when starting up. dmesg showed:

  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 10658 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 40793 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 131273 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 402058 jiffies old.
  INFO: rcu_tasks detected stalls on tasks:
  00000000769f52cd: .N nvcsw: 2/2 holdout: 1 idle_cpu: -1/64
  task:napi/eth2-8265  state:R  running task     stack:0     pid:48300 tgid:48300 ppid:2      task_flags:0x208040 flags:0x00004000
  Call Trace:
   <TASK>
   ? napi_threaded_poll_loop+0x27c/0x2c0
   ? __pfx_napi_threaded_poll+0x10/0x10
   ? napi_threaded_poll+0x26/0x80
   ? kthread+0xfa/0x240
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork+0x31/0x50
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork_asm+0x1a/0x30
   </TASK>

The cause is that in threaded busypoll, the main loop is in
napi_threaded_poll rather than napi_threaded_poll_loop, where the
latter rarely iterates more than once within its loop. For
rcu_softirq_qs_periodic inside napi_threaded_poll_loop to report its
qs state, the last_qs must be 100ms behind, and this can't happen
because napi_threaded_poll_loop rarely iterates in threaded busypoll,
and each time napi_threaded_poll_loop is called last_qs is reset to
latest jiffies.

This patch changes so that in threaded busypoll, last_qs is saved
in the outer napi_threaded_poll, and whether busy_poll_last_qs
is NULL indicates whether napi_threaded_poll_loop is called for
busypoll. This way last_qs would not reset to latest jiffies on
each invocation of napi_threaded_poll_loop.

Fixes: c18d4b190a46 ("net: Extend NAPI threaded polling to allow kthread based busy polling")
Cc: stable@vger.kernel.org
Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20260227221937.1060857-1-zhuyifei@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c1a9f7fdcffa..4af4cf2d63a4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7794,11 +7794,12 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
-static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
+static void napi_threaded_poll_loop(struct napi_struct *napi,
+				    unsigned long *busy_poll_last_qs)
 {
+	unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies;
 	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
-	unsigned long last_qs = jiffies;
 
 	for (;;) {
 		bool repoll = false;
@@ -7827,12 +7828,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 		/* When busy poll is enabled, the old packets are not flushed in
 		 * napi_complete_done. So flush them here.
 		 */
-		if (busy_poll)
+		if (busy_poll_last_qs)
 			gro_flush_normal(&napi->gro, HZ >= 1000);
 		local_bh_enable();
 
 		/* Call cond_resched here to avoid watchdog warnings. */
-		if (repoll || busy_poll) {
+		if (repoll || busy_poll_last_qs) {
 			rcu_softirq_qs_periodic(last_qs);
 			cond_resched();
 		}
@@ -7840,11 +7841,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 		if (!repoll)
 			break;
 	}
+
+	if (busy_poll_last_qs)
+		*busy_poll_last_qs = last_qs;
 }
 
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	unsigned long last_qs = jiffies;
 	bool want_busy_poll;
 	bool in_busy_poll;
 	unsigned long val;
@@ -7862,7 +7867,7 @@ static int napi_threaded_poll(void *data)
 			assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state,
 				   want_busy_poll);
 
-		napi_threaded_poll_loop(napi, want_busy_poll);
+		napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL);
 	}
 
 	return 0;
@@ -13175,7 +13180,7 @@ static void run_backlog_napi(unsigned int cpu)
 {
 	struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
 
-	napi_threaded_poll_loop(&sd->backlog, false);
+	napi_threaded_poll_loop(&sd->backlog, NULL);
 }
 
 static void backlog_napi_setup(unsigned int cpu)

From d1a196e0a6dcddd03748468a0e9e3100790fc85c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 12:30:51 +0100
Subject: [PATCH 0702/1303] platform/x86: dell-wmi-sysman: Don't hex dump
 plaintext password data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

set_new_password() hex dumps the entire buffer, which contains plaintext
password data, including current and new passwords. Remove the hex dump
to avoid leaking credentials.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: stable@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20260303113050.58127-2-thorsten.blum@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c   | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
index 86ec962aace9..e586f7957946 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
@@ -93,7 +93,6 @@ int set_new_password(const char *password_type, const char *new)
 	if (ret < 0)
 		goto out;
 
-	print_hex_dump_bytes("set new password data: ", DUMP_PREFIX_NONE, buffer, buffer_size);
 	ret = call_password_interface(wmi_priv.password_attr_wdev, buffer, buffer_size);
 	/* on success copy the new password to current password */
 	if (!ret)

From 63dc2c34a91642d9ae615a9609841fa317a36c92 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Thu, 22 Jan 2026 18:06:14 +0800
Subject: [PATCH 0703/1303] x86/xen: Build identity mapping page tables
 dynamically for XENPV

After commit 47ffe0578aee ("x86/pvh: Add 64bit relocation page tables"),
the PVH entry uses a new set of page tables instead of the
preconstructed page tables in head64.S. Since those preconstructed page
tables are only used in XENPV now and XENPV does not actually need the
preconstructed identity page tables directly, they can be filled in
xen_setup_kernel_pagetable(). Therefore, build the identity mapping page
table dynamically to remove the preconstructed page tables and make the
code cleaner.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: "Borislav Petkov (AMD)" <bp@alien8.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <453981eae7e8158307f971d1632d5023adbe03c3.1769074722.git.houwenlong.hwl@antgroup.com>
---
 arch/x86/include/asm/pgtable_64.h |  2 --
 arch/x86/kernel/head_64.S         | 28 ----------------------------
 arch/x86/xen/mmu_pv.c             |  9 +++++++++
 3 files changed, 9 insertions(+), 30 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index f06e5d6a2747..ce45882ccd07 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -19,10 +19,8 @@
 extern p4d_t level4_kernel_pgt[512];
 extern p4d_t level4_ident_pgt[512];
 extern pud_t level3_kernel_pgt[512];
-extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
-extern pmd_t level2_ident_pgt[512];
 extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
 extern pgd_t init_top_pgt[];
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 21816b48537c..85d4a5094f6b 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -616,38 +616,10 @@ SYM_DATA(early_recursion_flag, .long 0)
 
 	.data
 
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH)
-SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.org    init_top_pgt + L4_PAGE_OFFSET*8, 0
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.org    init_top_pgt + L4_START_KERNEL*8, 0
-	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
-	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-	.fill	PTI_USER_PGD_FILL,8,0
-SYM_DATA_END(init_top_pgt)
-
-SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt)
-	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.fill	511, 8, 0
-SYM_DATA_END(level3_ident_pgt)
-SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt)
-	/*
-	 * Since I easily can, map the first 1G.
-	 * Don't set NX because code runs from these pages.
-	 *
-	 * Note: This sets _PAGE_GLOBAL despite whether
-	 * the CPU supports it or it is enabled.  But,
-	 * the CPU should ignore the bit.
-	 */
-	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
-SYM_DATA_END(level2_ident_pgt)
-#else
 SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
 	.fill	512,8,0
 	.fill	PTI_USER_PGD_FILL,8,0
 SYM_DATA_END(init_top_pgt)
-#endif
 
 SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
 	.fill	511,8,0
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index aa6755385887..50172d64aed6 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -105,6 +105,9 @@ pte_t xen_make_pte_init(pteval_t pte);
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 #endif
 
+static pud_t level3_ident_pgt[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t level2_ident_pgt[PTRS_PER_PMD] __page_aligned_bss;
+
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
  * Also protects non-atomic updates of current_pages and balloon lists.
@@ -1777,6 +1780,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Zap identity mapping */
 	init_top_pgt[0] = __pgd(0);
 
+	init_top_pgt[pgd_index(__PAGE_OFFSET_BASE_L4)].pgd =
+		__pa_symbol(level3_ident_pgt) + _KERNPG_TABLE_NOENC;
+	init_top_pgt[pgd_index(__START_KERNEL_map)].pgd =
+		__pa_symbol(level3_kernel_pgt) + _PAGE_TABLE_NOENC;
+	level3_ident_pgt[0].pud = __pa_symbol(level2_ident_pgt) + _KERNPG_TABLE_NOENC;
+
 	/* Pre-constructed entries are in pfn, so convert to mfn */
 	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */

From 8b57227d59a86fc06d4f09de08f98133680f2cae Mon Sep 17 00:00:00 2001
From: David Thomson <dt@linux-mail.net>
Date: Tue, 24 Feb 2026 09:37:11 +0000
Subject: [PATCH 0704/1303] xen/acpi-processor: fix _CST detection using
 undersized evaluation buffer

read_acpi_id() attempts to evaluate _CST using a stack buffer of
sizeof(union acpi_object) (48 bytes), but _CST returns a nested Package
of sub-Packages (one per C-state, each containing a register descriptor,
type, latency, and power) requiring hundreds of bytes. The evaluation
always fails with AE_BUFFER_OVERFLOW.

On modern systems using FFH/MWAIT entry (where pblk is zero), this
causes the function to return before setting the acpi_id_cst_present
bit. In check_acpi_ids(), flags.power is then zero for all Phase 2 CPUs
(physical CPUs beyond dom0's vCPU count), so push_cxx_to_hypervisor() is
never called for them.

On a system with dom0_max_vcpus=2 and 8 physical CPUs, only PCPUs 0-1
receive C-state data. PCPUs 2-7 are stuck in C0/C1 idle, unable to
enter C2/C3. This costs measurable wall power (4W observed on an Intel
Core Ultra 7 265K with Xen 4.20).

The function never uses the _CST return value -- it only needs to know
whether _CST exists. Replace the broken acpi_evaluate_object() call with
acpi_has_method(), which correctly detects _CST presence using
acpi_get_handle() without any buffer allocation. This brings C-state
detection to parity with the P-state path, which already works correctly
for Phase 2 CPUs.

Fixes: 59a568029181 ("xen/acpi-processor: C and P-state driver that uploads said data to hypervisor.")
Signed-off-by: David Thomson <dt@linux-mail.net>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260224093707.19679-1-dt@linux-mail.net>
---
 drivers/xen/xen-acpi-processor.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index f2e8eaf684ba..8d1860bd5d57 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -379,11 +379,8 @@ read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv)
 			 acpi_psd[acpi_id].domain);
 	}
 
-	status = acpi_evaluate_object(handle, "_CST", NULL, &buffer);
-	if (ACPI_FAILURE(status)) {
-		if (!pblk)
-			return AE_OK;
-	}
+	if (!pblk && !acpi_has_method(handle, "_CST"))
+		return AE_OK;
 	/* .. and it has a C-state */
 	__set_bit(acpi_id, acpi_id_cst_present);
 

From b8c460a045985a8cb7a7c34912d2db91afee242f Mon Sep 17 00:00:00 2001
From: kexinsun <kexinsun@smail.nju.edu.cn>
Date: Tue, 24 Feb 2026 10:24:24 +0800
Subject: [PATCH 0705/1303] x86/xen: update outdated comment

The function xen_flush_tlb_others() was renamed xen_flush_tlb_multi()
by commit 4ce94eabac16 ("x86/mm/tlb: Flush remote and local TLBs
concurrently").  Update the comment accordingly.

Signed-off-by: kexinsun <kexinsun@smail.nju.edu.cn>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260224022424.1718-1-kexinsun@smail.nju.edu.cn>
---
 arch/x86/xen/enlighten_pv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index b74ff8bc7f2a..fde5f44460ee 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -392,7 +392,7 @@ static void __init xen_init_capabilities(void)
 
 	/*
 	 * Xen PV would need some work to support PCID: CR3 handling as well
-	 * as xen_flush_tlb_others() would need updating.
+	 * as xen_flush_tlb_multi() would need updating.
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 

From 7271cb98e4981e32c9b2a5f9eb5ad0cd0cdd5bf3 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Sun, 1 Mar 2026 13:04:52 +0800
Subject: [PATCH 0706/1303] x86/PVH: Use boot params to pass RSDP address in
 start_info page

After commit e6e094e053af75 ("x86/acpi, x86/boot: Take RSDP address from
boot params if available"), the RSDP address can be passed in boot
params. Therefore, store the RSDP address in start_info page into boot
params in the PVH entry instead of registering a different callback.
This removes an absolute reference during the PVH entry and is more
standardized.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <76675c4d49d3a8f72252076812ef8f22276230c2.1772282441.git.houwenlong.hwl@antgroup.com>
---
 arch/x86/platform/pvh/enlighten.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 2263885d16ba..f2053cbe9b0c 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -25,11 +25,6 @@ struct hvm_start_info __initdata pvh_start_info;
 
 const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info);
 
-static u64 __init pvh_get_root_pointer(void)
-{
-	return pvh_start_info.rsdp_paddr;
-}
-
 /*
  * Xen guests are able to obtain the memory map from the hypervisor via the
  * HYPERVISOR_memory_op hypercall.
@@ -95,7 +90,7 @@ static void __init init_pvh_bootparams(bool xen_guest)
 	pvh_bootparams.hdr.version = (2 << 8) | 12;
 	pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0;
 
-	x86_init.acpi.get_root_pointer = pvh_get_root_pointer;
+	pvh_bootparams.acpi_rsdp_addr = pvh_start_info.rsdp_paddr;
 }
 
 /*

From 27990181031fdcdbe0f7c46011f6404e5d116386 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 3 Mar 2026 14:17:07 +0000
Subject: [PATCH 0707/1303] ASoC: SDCA: Add allocation failure check for Entity
 name

Currently find_sdca_entity_iot() can allocate a string for the
Entity name but it doesn't check if that allocation succeeded.
Add the missing NULL check after the allocation.

Fixes: 48fa77af2f4a ("ASoC: SDCA: Add terminal type into input/output widget name")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260303141707.3841635-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdca/sdca_functions.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c
index 95b67bb904c3..e0ed593697ba 100644
--- a/sound/soc/sdca/sdca_functions.c
+++ b/sound/soc/sdca/sdca_functions.c
@@ -1156,9 +1156,12 @@ static int find_sdca_entity_iot(struct device *dev,
 	if (!terminal->is_dataport) {
 		const char *type_name = sdca_find_terminal_name(terminal->type);
 
-		if (type_name)
+		if (type_name) {
 			entity->label = devm_kasprintf(dev, GFP_KERNEL, "%s %s",
 						       entity->label, type_name);
+			if (!entity->label)
+				return -ENOMEM;
+		}
 	}
 
 	ret = fwnode_property_read_u32(entity_node,

From 00fd9aad55e7ced494a738a07662155d058b872f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 3 Mar 2026 15:26:31 +0100
Subject: [PATCH 0708/1303] Revert "ACPI: PM: Let acpi_dev_pm_attach() skip
 devices without ACPI PM"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Revert commit 88fad6ce090b ("ACPI: PM: Let acpi_dev_pm_attach() skip
devices without ACPI PM") that introduced a SoundWire suspend regression
[1].

It is actually not true that the commit above doesn't make a functional
difference because acpi_subsys_suspend(), for example, may resume
devices in runtime-suspend which affects the subsequent handling of
those devices during the suspend transition.  For this reason, the
devices that were handled by the ACPI PM domain before that commit may
be handled differently now which may lead to suspend-resume issues.

Fixes: 88fad6ce090b ("ACPI: PM: Let acpi_dev_pm_attach() skip devices without ACPI PM")
Reported-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Closes: https://github.com/thesofproject/linux/pull/5677#issuecomment-3984375077 [1]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/2829615.mvXUDI8C0e@rafael.j.wysocki
---
 drivers/acpi/device_pm.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f2579611e0a5..aa55ecfc2923 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1456,15 +1456,6 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	if (!adev || !acpi_match_device_ids(adev, special_pm_ids))
 		return 0;
 
-	/*
-	 * Skip devices whose ACPI companions don't support power management and
-	 * don't have a wakeup GPE.
-	 */
-	if (!acpi_device_power_manageable(adev) && !acpi_device_can_wakeup(adev)) {
-		dev_dbg(dev, "No ACPI power management or wakeup GPE\n");
-		return 0;
-	}
-
 	/*
 	 * Only attach the power domain to the first device if the
 	 * companion is shared by multiple. This is to prevent doing power

From b85cfdf46b2402a9e57d6b7d43e2c977f9554645 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Mon, 9 Feb 2026 18:00:14 +0000
Subject: [PATCH 0709/1303] btrfs: print-tree: add remap tree definitions

Add the definitions for the remap tree to print-tree.c, so that we get
more useful information if a tree is dumped to dmesg.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/print-tree.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index f189bf09ce6a..b7dfe877cf8d 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -38,6 +38,7 @@ static const struct root_name_map root_map[] = {
 	{ BTRFS_BLOCK_GROUP_TREE_OBJECTID,	"BLOCK_GROUP_TREE"	},
 	{ BTRFS_DATA_RELOC_TREE_OBJECTID,	"DATA_RELOC_TREE"	},
 	{ BTRFS_RAID_STRIPE_TREE_OBJECTID,	"RAID_STRIPE_TREE"	},
+	{ BTRFS_REMAP_TREE_OBJECTID,		"REMAP_TREE"		},
 };
 
 const char *btrfs_root_name(const struct btrfs_key *key, char *buf)
@@ -415,6 +416,9 @@ static void key_type_string(const struct btrfs_key *key, char *buf, int buf_size
 		[BTRFS_UUID_KEY_SUBVOL]			= "UUID_KEY_SUBVOL",
 		[BTRFS_UUID_KEY_RECEIVED_SUBVOL]	= "UUID_KEY_RECEIVED_SUBVOL",
 		[BTRFS_RAID_STRIPE_KEY]			= "RAID_STRIPE",
+		[BTRFS_IDENTITY_REMAP_KEY]		= "IDENTITY_REMAP",
+		[BTRFS_REMAP_KEY]			= "REMAP",
+		[BTRFS_REMAP_BACKREF_KEY]		= "REMAP_BACKREF",
 	};
 
 	if (key->type == 0 && key->objectid == BTRFS_FREE_SPACE_OBJECTID)
@@ -435,6 +439,7 @@ void btrfs_print_leaf(const struct extent_buffer *l)
 	struct btrfs_extent_data_ref *dref;
 	struct btrfs_shared_data_ref *sref;
 	struct btrfs_dev_extent *dev_extent;
+	struct btrfs_remap_item *remap;
 	struct btrfs_key key;
 
 	if (!l)
@@ -569,6 +574,11 @@ void btrfs_print_leaf(const struct extent_buffer *l)
 			print_raid_stripe_key(l, btrfs_item_size(l, i),
 				btrfs_item_ptr(l, i, struct btrfs_stripe_extent));
 			break;
+		case BTRFS_REMAP_KEY:
+		case BTRFS_REMAP_BACKREF_KEY:
+			remap = btrfs_item_ptr(l, i, struct btrfs_remap_item);
+			pr_info("\t\taddress %llu\n", btrfs_remap_address(l, remap));
+			break;
 		}
 	}
 }

From b8883b61f2fc50dcf22938cbed40fec05020552f Mon Sep 17 00:00:00 2001
From: Sun YangKai <sunk67188@gmail.com>
Date: Mon, 9 Feb 2026 20:53:39 +0800
Subject: [PATCH 0710/1303] btrfs: hold space_info->lock when clearing periodic
 reclaim ready

btrfs_set_periodic_reclaim_ready() requires space_info->lock to be held,
as enforced by lockdep_assert_held(). However, btrfs_reclaim_sweep() was
calling it after do_reclaim_sweep() returns, at which point
space_info->lock is no longer held.

Fix this by explicitly acquiring space_info->lock before clearing the
periodic reclaim ready flag in btrfs_reclaim_sweep().

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208182556.891815-1-clm@meta.com/
Fixes: 19eff93dc738 ("btrfs: fix periodic reclaim condition")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Sun YangKai <sunk67188@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/space-info.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index bb5aac7ee9d2..36bfd2385b2a 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -2194,8 +2194,11 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info)
 		if (!btrfs_should_periodic_reclaim(space_info))
 			continue;
 		for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) {
-			if (do_reclaim_sweep(space_info, raid))
+			if (do_reclaim_sweep(space_info, raid)) {
+				spin_lock(&space_info->lock);
 				btrfs_set_periodic_reclaim_ready(space_info, false);
+				spin_unlock(&space_info->lock);
+			}
 		}
 	}
 }

From 17da926ca8757cc0432ce3e13230759894a6b017 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Tue, 24 Feb 2026 13:51:13 +0100
Subject: [PATCH 0711/1303] btrfs: zoned: move
 btrfs_zoned_reserve_data_reloc_bg() after kthread start

btrfs_zoned_reserve_data_reloc_bg() is called on each mount of a file
system and allocates a new block-group, to assign it to be the dedicated
relocation target, if no pre-existing usable block-group for this task is
found.

If for some reason the transaction is aborted, btrfs_end_transaction()
will wake up the transaction kthread. But the transaction kthread is not
yet initialized at the time btrfs_zoned_reserve_data_reloc_bg() is
called, leading to the following NULL-pointer dereference:

  RSP: 0018:ffffc9000c617c98 EFLAGS: 00010046
  RAX: 0000000000000000 RBX: 000000000000073c RCX: 0000000000000002
  RDX: 0000000000000001 RSI: 0000000000000003 RDI: 0000000000000001
  RBP: 0000000000000207 R08: ffffffff8223c71d R09: 0000000000000635
  R10: ffff888108588000 R11: 0000000000000003 R12: 0000000000000003
  R13: 000000000000073c R14: 0000000000000000 R15: ffff888114dd6000
  FS:  00007f2993745840(0000) GS:ffff8882b508d000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000000000000073c CR3: 0000000121a82006 CR4: 0000000000770eb0
  PKRU: 55555554
  Call Trace:
   <TASK>
   try_to_wake_up (./include/linux/spinlock.h:557 kernel/sched/core.c:4106)
   __btrfs_end_transaction (fs/btrfs/transaction.c:1115 (discriminator 2))
   btrfs_zoned_reserve_data_reloc_bg (fs/btrfs/zoned.c:2840)
   open_ctree (fs/btrfs/disk-io.c:3588)
   btrfs_get_tree.cold (fs/btrfs/super.c:982 fs/btrfs/super.c:1944 fs/btrfs/super.c:2087 fs/btrfs/super.c:2121)
   vfs_get_tree (fs/super.c:1752)
   __do_sys_fsconfig (fs/fsopen.c:231 fs/fsopen.c:295 fs/fsopen.c:473)
   do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
   entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
  RIP: 0033:0x7f299392740e

Move the call to btrfs_zoned_reserve_data_reloc_bg() after the
transaction_kthread has been initialized to fix this problem.

Fixes: 694ce5e143d6 ("btrfs: zoned: reserve data_reloc block group on mount")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 49987334dd15..2aeb85e3ece9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3594,7 +3594,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		}
 	}
 
-	btrfs_zoned_reserve_data_reloc_bg(fs_info);
 	btrfs_free_zone_cache(fs_info);
 
 	btrfs_check_active_zone_reservation(fs_info);
@@ -3622,6 +3621,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_cleaner;
 	}
 
+	/*
+	 * Starts a transaction, must be called after the transaction kthread
+	 * is initialized.
+	 */
+	btrfs_zoned_reserve_data_reloc_bg(fs_info);
+
 	ret = btrfs_read_qgroup_config(fs_info);
 	if (ret)
 		goto fail_trans_kthread;

From 5131fa077f9bb386a1b901bf5b247041f0ec8f80 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Tue, 24 Feb 2026 14:25:35 -0800
Subject: [PATCH 0712/1303] btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol
 create

We have recently observed a number of subvolumes with broken dentries.
ls-ing the parent dir looks like:

drwxrwxrwt 1 root root 16 Jan 23 16:49 .
drwxr-xr-x 1 root root 24 Jan 23 16:48 ..
d????????? ? ?    ?     ?            ? broken_subvol

and similarly stat-ing the file fails.

In this state, deleting the subvol fails with ENOENT, but attempting to
create a new file or subvol over it errors out with EEXIST and even
aborts the fs. Which leaves us a bit stuck.

dmesg contains a single notable error message reading:
"could not do orphan cleanup -2"

2 is ENOENT and the error comes from the failure handling path of
btrfs_orphan_cleanup(), with the stack leading back up to
btrfs_lookup().

btrfs_lookup
btrfs_lookup_dentry
btrfs_orphan_cleanup // prints that message and returns -ENOENT

After some detailed inspection of the internal state, it became clear
that:
- there are no orphan items for the subvol
- the subvol is otherwise healthy looking, it is not half-deleted or
  anything, there is no drop progress, etc.
- the subvol was created a while ago and does the meaningful first
  btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much
  later.
- after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT,
  which results in a negative dentry for the subvolume via
  d_splice_alias(NULL, dentry), leading to the observed behavior. The
  bug can be mitigated by dropping the dentry cache, at which point we
  can successfully delete the subvolume if we want.

i.e.,
btrfs_lookup()
  btrfs_lookup_dentry()
    if (!sb_rdonly(inode->vfs_inode)->vfs_inode)
    btrfs_orphan_cleanup(sub_root)
      test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP)
      btrfs_search_slot() // finds orphan item for inode N
      ...
      prints "could not do orphan cleanup -2"
  if (inode == ERR_PTR(-ENOENT))
    inode = NULL;
  return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume

btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP)
on the root when it runs, so it cannot run more than once on a given
root, so something else must run concurrently. However, the obvious
routes to deleting an orphan when nlinks goes to 0 should not be able to
run without first doing a lookup into the subvolume, which should run
btrfs_orphan_cleanup() and set the bit.

The final important observation is that create_subvol() calls
d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if
the dentry cache gets dropped, the next lookup into the subvolume will
make a real call into btrfs_orphan_cleanup() for the first time. This
opens up the possibility of concurrently deleting the inode/orphan items
but most typical evict() paths will be holding a reference on the parent
dentry (child dentry holds parent->d_lockref.count via dget in
d_alloc(), released in __dentry_kill()) and prevent the parent from
being removed from the dentry cache.

The one exception is delayed iputs. Ordered extent creation calls
igrab() on the inode. If the file is unlinked and closed while those
refs are held, iput() in __dentry_kill() decrements i_count but does
not trigger eviction (i_count > 0). The child dentry is freed and the
subvol dentry's d_lockref.count drops to 0, making it evictable while
the inode is still alive.

Since there are two races (the race between writeback and unlink and
the race between lookup and delayed iputs), and there are too many moving
parts, the following three diagrams show the complete picture.
(Only the second and third are races)

Phase 1:
Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set

btrfs_mksubvol()
  lookup_one_len()
    __lookup_slow()
      d_alloc_parallel()
        __d_alloc() // d_lockref.count = 1
  create_subvol(dentry)
    // doesn't touch the bit..
    d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.count == 1

Phase 2:
Create a delayed iput for a file in the subvol but leave the subvol in
state where its dentry can be evicted (d_lockref.count == 0)

T1 (task)                    T2 (writeback)                   T3 (OE workqueue)

write() // dirty pages
                              btrfs_writepages()
                                btrfs_run_delalloc_range()
                                  cow_file_range()
                                    btrfs_alloc_ordered_extent()
                                      igrab() // i_count: 1 -> 2
btrfs_unlink_inode()
  btrfs_orphan_add()
close()
  __fput()
    dput()
      finish_dput()
        __dentry_kill()
          dentry_unlink_inode()
            iput() // 2 -> 1
          --parent->d_lockref.count // 1 -> 0; evictable
                                                                finish_ordered_fn()
                                                                  btrfs_finish_ordered_io()
                                                                    btrfs_put_ordered_extent()
                                                                      btrfs_add_delayed_iput()

Phase 3:
Once the delayed iput is pending and the subvol dentry is evictable,
the shrinker can free it, causing the next lookup to go through
btrfs_lookup() and call btrfs_orphan_cleanup() for the first time.
If the cleaner kthread processes the delayed iput concurrently, the
two race:

  T1 (shrinker)              T2 (cleaner kthread)                          T3 (lookup)

  super_cache_scan()
    prune_dcache_sb()
      __dentry_kill()
      // subvol dentry freed
                              btrfs_run_delayed_iputs()
                                iput()  // i_count -> 0
                                  evict()  // sets I_FREEING
                                    btrfs_evict_inode()
                                      // truncation loop
                                                                            btrfs_lookup()
                                                                              btrfs_lookup_dentry()
                                                                                btrfs_orphan_cleanup()
                                                                                  // first call (bit never set)
                                                                                  btrfs_iget()
                                                                                    // blocks on I_FREEING

                                      btrfs_orphan_del()
                                      // inode freed
                                                                                    // returns -ENOENT
                                                                                  btrfs_del_orphan_item()
                                                                                    // -ENOENT
                                                                                // "could not do orphan cleanup -2"
                                                                            d_splice_alias(NULL, dentry)
                                                                            // negative dentry for valid subvol

The most straightforward fix is to ensure the invariant that a dentry
for a subvolume can exist if and only if that subvolume has
BTRFS_ROOT_ORPHAN_CLEANUP set on its root (and is known to have no
orphans or ran btrfs_orphan_cleanup()).

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dadf9bf30f08..1d22c5c05b50 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -672,6 +672,13 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 		goto out;
 	}
 
+	/*
+	 * Subvolumes have orphans cleaned on first dentry lookup. A new
+	 * subvolume cannot have any orphans, so we should set the bit before we
+	 * add the subvolume dentry to the dentry cache, so that it is in the
+	 * same state as a subvolume after first lookup.
+	 */
+	set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &new_root->state);
 	d_instantiate_new(dentry, new_inode_args.inode);
 	new_inode_args.inode = NULL;
 

From 5f25805303e201f3afaff0a90f7c7ce257468704 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 2 Mar 2026 19:03:34 +0100
Subject: [PATCH 0713/1303] s390/xor: Fix xor_xc_5() inline assembly

xor_xc_5() contains a larl 1,2f that is not used by the asm and is not
declared as a clobber. This can corrupt a compiler-allocated value in %r1
and lead to miscompilation. Remove the instruction.

Fixes: 745600ed6965 ("s390/lib: Use exrl instead of ex in xor functions")
Cc: stable@vger.kernel.org
Reviewed-by: Juergen Christ <jchrist@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 1721b73b7803..a4d8b51beb95 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -96,7 +96,6 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1,
 		     const unsigned long * __restrict p5)
 {
 	asm volatile(
-		"	larl	1,2f\n"
 		"	aghi	%0,-1\n"
 		"	jm	6f\n"
 		"	srlg	0,%0,8\n"

From f775276edc0c505dc0f782773796c189f31a1123 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:34:58 +0100
Subject: [PATCH 0714/1303] s390/xor: Fix xor_xc_2() inline assembly
 constraints

The inline assembly constraints for xor_xc_2() are incorrect. "bytes",
"p1", and "p2" are input operands, while all three of them are modified
within the inline assembly. Given that the function consists only of this
inline assembly it seems unlikely that this may cause any problems, however
fix this in any case.

Fixes: 2cfc5f9ce7f5 ("s390/xor: optimized xor routing using the XC instruction")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-2-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index a4d8b51beb95..81c0235c0466 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -28,8 +28,8 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1,
 		"	j	3f\n"
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:"
-		: : "d" (bytes), "a" (p1), "a" (p2)
-		: "0", "cc", "memory");
+		: "+d" (bytes), "+a" (p1), "+a" (p2)
+		: : "0", "cc", "memory");
 }
 
 static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1,

From 87ff6da3001b2a35d241c5d965b82536f6418277 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:34:59 +0100
Subject: [PATCH 0715/1303] s390/xor: Improve inline assembly constraints

The inline assembly constraint for the "bytes" operand is "d" for all xor()
inline assemblies. "d" means that any register from 0 to 15 can be used. If
the compiler would use register 0 then the exrl instruction would not or
the value of "bytes" into the executed instruction - resulting in an
incorrect result.

However all the xor() inline assemblies make hard-coded use of register 0,
and it is correctly listed in the clobber list, so that this cannot happen.

Given that this is quite subtle use the better "a" constraint, which
excludes register 0 from register allocation in any case.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-3-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 81c0235c0466..5363e4c2462d 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -28,7 +28,7 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1,
 		"	j	3f\n"
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2)
+		: "+a" (bytes), "+a" (p1), "+a" (p2)
 		: : "0", "cc", "memory");
 }
 
@@ -54,7 +54,7 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1,
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:	xc	0(1,%1),0(%3)\n"
 		"4:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
 		: : "0", "cc", "memory");
 }
 
@@ -85,7 +85,7 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1,
 		"3:	xc	0(1,%1),0(%3)\n"
 		"4:	xc	0(1,%1),0(%4)\n"
 		"5:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
 		: : "0", "cc", "memory");
 }
 
@@ -121,7 +121,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1,
 		"4:	xc	0(1,%1),0(%4)\n"
 		"5:	xc	0(1,%1),0(%5)\n"
 		"6:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
 		  "+a" (p5)
 		: : "0", "cc", "memory");
 }

From 674c5ff0f440a051ebf299d29a4c013133d81a65 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:35:00 +0100
Subject: [PATCH 0716/1303] s390/stackleak: Fix __stackleak_poison() inline
 assembly constraint

The __stackleak_poison() inline assembly comes with a "count" operand where
the "d" constraint is used. "count" is used with the exrl instruction and
"d" means that the compiler may allocate any register from 0 to 15.

If the compiler would allocate register 0 then the exrl instruction would
not or the value of "count" into the executed instruction - resulting in a
stackframe which is only partially poisoned.

Use the correct "a" constraint, which excludes register 0 from register
allocation.

Fixes: 2a405f6bb3a5 ("s390/stackleak: provide fast __stackleak_poison() implementation")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-4-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/processor.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index cc187afa07b3..78195ee5e99f 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -159,7 +159,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low,
 		"	j	4f\n"
 		"3:	mvc	8(1,%[addr]),0(%[addr])\n"
 		"4:"
-		: [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp)
+		: [addr] "+&a" (erase_low), [count] "+&a" (count), [tmp] "=&a" (tmp)
 		: [poison] "d" (poison)
 		: "memory", "cc"
 		);

From b2840e33127ce0eea880504b7f133e780f567a9b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 25 Feb 2026 11:59:58 -0800
Subject: [PATCH 0717/1303] btrfs: add missing RCU unlock in error path in
 try_release_subpage_extent_buffer()

Call rcu_read_lock() before exiting the loop in
try_release_subpage_extent_buffer() because there is a rcu_read_unlock()
call past the loop.

This has been detected by the Clang thread-safety analyzer.

Fixes: ad580dfa388f ("btrfs: fix subpage deadlock in try_release_subpage_extent_buffer()")
CC: stable@vger.kernel.org # 6.18+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3df399dc8856..051309e90079 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4494,6 +4494,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 		 */
 		if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
 			spin_unlock(&eb->refs_lock);
+			rcu_read_lock();
 			break;
 		}
 

From ae1238b77feafa2f7f10bcd0432a99e098a98ec6 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Wed, 25 Feb 2026 10:36:06 +0000
Subject: [PATCH 0718/1303] btrfs: read key again after incrementing slot in
 move_existing_remaps()

Fix move_existing_remaps() so that if we increment the slot because the
key we encounter isn't a REMAP_BACKREF, we don't reuse the objectid and
offset of the old item.

Link: https://lore.kernel.org/linux-btrfs/20260125123908.2096548-1-clm@meta.com/
Reported-by: Chris Mason <clm@fb.com>
Fixes: bbea42dfb91f ("btrfs: move existing remaps before relocating block group")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cdb53c0b26ec..fcfbe1b1dab4 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4399,6 +4399,8 @@ static int move_existing_remaps(struct btrfs_fs_info *fs_info,
 
 				leaf = path->nodes[0];
 			}
+
+			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 		}
 
 		remap = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_remap_item);

From 2d1ababdedd4ba38867c2500eb7f95af5ddeeef7 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 26 Feb 2026 11:05:43 +0000
Subject: [PATCH 0719/1303] btrfs: fix transaction abort on file creation due
 to name hash collision

If we attempt to create several files with names that result in the same
hash, we have to pack them in same dir item and that has a limit inherent
to the leaf size. However if we reach that limit, we trigger a transaction
abort and turns the filesystem into RO mode. This allows for a malicious
user to disrupt a system, without the need to have administration
privileges/capabilities.

Reproducer:

  $ cat exploit-hash-collisions.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi

  # Use smallest node size to make the test faster and require fewer file
  # names that result in hash collision.
  mkfs.btrfs -f --nodesize 4K $DEV
  mount $DEV $MNT

  # List of names that result in the same crc32c hash for btrfs.
  declare -a names=(
   'foobar'
   '%a8tYkxfGMLWRGr55QSeQc4PBNH9PCLIvR6jZnkDtUUru1t@RouaUe_L:@xGkbO3nCwvLNYeK9vhE628gss:T$yZjZ5l-Nbd6CbC$M=hqE-ujhJICXyIxBvYrIU9-TDC'
   'AQci3EUB%shMsg-N%frgU:02ByLs=IPJU0OpgiWit5nexSyxZDncY6WB:=zKZuk5Zy0DD$Ua78%MelgBuMqaHGyKsJUFf9s=UW80PcJmKctb46KveLSiUtNmqrMiL9-Y0I_l5Fnam04CGIg=8@U:Z'
   'CvVqJpJzueKcuA$wqwePfyu7VxuWNN3ho$p0zi2H8QFYK$7YlEqOhhb%:hHgjhIjW5vnqWHKNP4'
   'ET:vk@rFU4tsvMB0$C_p=xQHaYZjvoF%-BTc%wkFW8yaDAPcCYoR%x$FH5O:'
   'HwTon%v7SGSP4FE08jBwwiu5aot2CFKXHTeEAa@38fUcNGOWvE@Mz6WBeDH_VooaZ6AgsXPkVGwy9l@@ZbNXabUU9csiWrrOp0MWUdfi$EZ3w9GkIqtz7I_eOsByOkBOO'
   'Ij%2VlFGXSuPvxJGf5UWy6O@1svxGha%b@=%wjkq:CIgE6u7eJOjmQY5qTtxE2Rjbis9@us'
   'KBkjG5%9R8K9sOG8UTnAYjxLNAvBmvV5vz3IiZaPmKuLYO03-6asI9lJ_j4@6Xo$KZicaLWJ3Pv8XEwVeUPMwbHYWwbx0pYvNlGMO9F:ZhHAwyctnGy%_eujl%WPd4U2BI7qooOSr85J-C2V$LfY'
   'NcRfDfuUQ2=zP8K3CCF5dFcpfiOm6mwenShsAb_F%n6GAGC7fT2JFFn:c35X-3aYwoq7jNX5$ZJ6hI3wnZs$7KgGi7wjulffhHNUxAT0fRRLF39vJ@NvaEMxsMO'
   'Oj42AQAEzRoTxa5OuSKIr=A_lwGMy132v4g3Pdq1GvUG9874YseIFQ6QU'
   'Ono7avN5GjC:_6dBJ_'
   'WHmN2gnmaN-9dVDy4aWo:yNGFzz8qsJyJhWEWcud7$QzN2D9R0efIWWEdu5kwWr73NZm4=@CoCDxrrZnRITr-kGtU_cfW2:%2_am'
   'WiFnuTEhAG9FEC6zopQmj-A-$LDQ0T3WULz%ox3UZAPybSV6v1Z$b4L_XBi4M4BMBtJZpz93r9xafpB77r:lbwvitWRyo$odnAUYlYMmU4RvgnNd--e=I5hiEjGLETTtaScWlQp8mYsBovZwM2k'
   'XKyH=OsOAF3p%uziGF_ZVr$ivrvhVgD@1u%5RtrV-gl_vqAwHkK@x7YwlxX3qT6WKKQ%PR56NrUBU2dOAOAdzr2=5nJuKPM-T-$ZpQfCL7phxQbUcb:BZOTPaFExc-qK-gDRCDW2'
   'd3uUR6OFEwZr%ns1XH_@tbxA@cCPmbBRLdyh7p6V45H$P2$F%w0RqrD3M0g8aGvWpoTFMiBdOTJXjD:JF7=h9a_43xBywYAP%r$SPZi%zDg%ql-KvkdUCtF9OLaQlxmd'
   'ePTpbnit%hyNm@WELlpKzNZYOzOTf8EQ$sEfkMy1VOfIUu3coyvIr13-Y7Sv5v-Ivax2Go_GQRFMU1b3362nktT9WOJf3SpT%z8sZmM3gvYQBDgmKI%%RM-G7hyrhgYflOw%z::ZRcv5O:lDCFm'
   'evqk743Y@dvZAiG5J05L_ROFV@$2%rVWJ2%3nxV72-W7$e$-SK3tuSHA2mBt$qloC5jwNx33GmQUjD%akhBPu=VJ5g$xhlZiaFtTrjeeM5x7dt4cHpX0cZkmfImndYzGmvwQG:$euFYmXn$_2rA9mKZ'
   'gkgUtnihWXsZQTEkrMAWIxir09k3t7jk_IK25t1:cy1XWN0GGqC%FrySdcmU7M8MuPO_ppkLw3=Dfr0UuBAL4%GFk2$Ma10V1jDRGJje%Xx9EV2ERaWKtjpwiZwh0gCSJsj5UL7CR8RtW5opCVFKGGy8Cky'
   'hNgsG_8lNRik3PvphqPm0yEH3P%%fYG:kQLY=6O-61Wa6nrV_WVGR6TLB09vHOv%g4VQRP8Gzx7VXUY1qvZyS'
   'isA7JVzN12xCxVPJZ_qoLm-pTBuhjjHMvV7o=F:EaClfYNyFGlsfw-Kf%uxdqW-kwk1sPl2vhbjyHU1A6$hz'
   'kiJ_fgcdZFDiOptjgH5PN9-PSyLO4fbk_:u5_2tz35lV_iXiJ6cx7pwjTtKy-XGaQ5IefmpJ4N_ZqGsqCsKuqOOBgf9LkUdffHet@Wu'
   'lvwtxyhE9:%Q3UxeHiViUyNzJsy:fm38pg_b6s25JvdhOAT=1s0$pG25x=LZ2rlHTszj=gN6M4zHZYr_qrB49i=pA--@WqWLIuX7o1S_SfS@2FSiUZN'
   'rC24cw3UBDZ=5qJBUMs9e$=S4Y94ni%Z8639vnrGp=0Hv4z3dNFL0fBLmQ40=EYIY:Z=SLc@QLMSt2zsss2ZXrP7j4='
   'uwGl2s-fFrf@GqS=DQqq2I0LJSsOmM%xzTjS:lzXguE3wChdMoHYtLRKPvfaPOZF2fER@j53evbKa7R%A7r4%YEkD=kicJe@SFiGtXHbKe4gCgPAYbnVn'
   'UG37U6KKua2bgc:IHzRs7BnB6FD:2Mt5Cc5NdlsW%$1tyvnfz7S27FvNkroXwAW:mBZLA1@qa9WnDbHCDmQmfPMC9z-Eq6QT0jhhPpqyymaD:R02ghwYo%yx7SAaaq-:x33LYpei$5g8DMl3C'
   'y2vjek0FE1PDJC0qpfnN:x8k2wCFZ9xiUF2ege=JnP98R%wxjKkdfEiLWvQzmnW'
   '8-HCSgH5B%K7P8_jaVtQhBXpBk:pE-$P7ts58U0J@iR9YZntMPl7j$s62yAJO@_9eanFPS54b=UTw$94C-t=HLxT8n6o9P=QnIxq-f1=Ne2dvhe6WbjEQtc'
   'YPPh:IFt2mtR6XWSmjHptXL_hbSYu8bMw-JP8@PNyaFkdNFsk$M=xfL6LDKCDM-mSyGA_2MBwZ8Dr4=R1D%7-mCaaKGxb990jzaagRktDTyp'
   '9hD2ApKa_t_7x-a@GCG28kY:7$M@5udI1myQ$x5udtggvagmCQcq9QXWRC5hoB0o-_zHQUqZI5rMcz_kbMgvN5jr63LeYA4Cj-c6F5Ugmx6DgVf@2Jqm%MafecpgooqreJ53P-QTS'
  )

  # Now create files with all those names in the same parent directory.
  # It should not fail since a 4K leaf has enough space for them.
  for name in "${names[@]}"; do
       touch $MNT/$name
  done

  # Now add one more file name that causes a crc32c hash collision.
  # This should fail, but it should not turn the filesystem into RO mode
  # (which could be exploited by malicious users) due to a transaction
  # abort.
  touch $MNT/'W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt'

  # Check that we are able to create another file, with a name that does not cause
  # a crc32c hash collision.
  echo -n "hello world" > $MNT/baz

  # Unmount and mount again, verify file baz exists and with the right content.
  umount $MNT
  mount $DEV $MNT
  echo "File baz content: $(cat $MNT/baz)"

  umount $MNT

When running the reproducer:

  $ ./exploit-hash-collisions.sh
  (...)
  touch: cannot touch '/mnt/sdi/W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt': Value too large for defined data type
  ./exploit-hash-collisions.sh: line 57: /mnt/sdi/baz: Read-only file system
  cat: /mnt/sdi/baz: No such file or directory
  File baz content:

And the transaction abort stack trace in dmesg/syslog:

  $ dmesg
  (...)
  [758240.509761] ------------[ cut here ]------------
  [758240.510668] BTRFS: Transaction aborted (error -75)
  [758240.511577] WARNING: fs/btrfs/inode.c:6854 at btrfs_create_new_inode+0x805/0xb50 [btrfs], CPU#6: touch/888644
  [758240.513513] Modules linked in: btrfs dm_zero (...)
  [758240.523221] CPU: 6 UID: 0 PID: 888644 Comm: touch Tainted: G        W           6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full)
  [758240.524621] Tainted: [W]=WARN
  [758240.525037] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
  [758240.526331] RIP: 0010:btrfs_create_new_inode+0x80b/0xb50 [btrfs]
  [758240.527093] Code: 0f 82 cf (...)
  [758240.529211] RSP: 0018:ffffce64418fbb48 EFLAGS: 00010292
  [758240.529935] RAX: 00000000ffffffd3 RBX: 0000000000000000 RCX: 00000000ffffffb5
  [758240.531040] RDX: 0000000d04f33e06 RSI: 00000000ffffffb5 RDI: ffffffffc0919dd0
  [758240.531920] RBP: ffffce64418fbc10 R08: 0000000000000000 R09: 00000000ffffffb5
  [758240.532928] R10: 0000000000000000 R11: ffff8e52c0000000 R12: ffff8e53eee7d0f0
  [758240.533818] R13: ffff8e57f70932a0 R14: ffff8e5417629568 R15: 0000000000000000
  [758240.534664] FS:  00007f1959a2a740(0000) GS:ffff8e5b27cae000(0000) knlGS:0000000000000000
  [758240.535821] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [758240.536644] CR2: 00007f1959b10ce0 CR3: 000000012a2cc005 CR4: 0000000000370ef0
  [758240.537517] Call Trace:
  [758240.537828]  <TASK>
  [758240.538099]  btrfs_create_common+0xbf/0x140 [btrfs]
  [758240.538760]  path_openat+0x111a/0x15b0
  [758240.539252]  do_filp_open+0xc2/0x170
  [758240.539699]  ? preempt_count_add+0x47/0xa0
  [758240.540200]  ? __virt_addr_valid+0xe4/0x1a0
  [758240.540800]  ? __check_object_size+0x1b3/0x230
  [758240.541661]  ? alloc_fd+0x118/0x180
  [758240.542315]  do_sys_openat2+0x70/0xd0
  [758240.543012]  __x64_sys_openat+0x50/0xa0
  [758240.543723]  do_syscall_64+0x50/0xf20
  [758240.544462]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [758240.545397] RIP: 0033:0x7f1959abc687
  [758240.546019] Code: 48 89 fa (...)
  [758240.548522] RSP: 002b:00007ffe16ff8690 EFLAGS: 00000202 ORIG_RAX: 0000000000000101
  [758240.566278] RAX: ffffffffffffffda RBX: 00007f1959a2a740 RCX: 00007f1959abc687
  [758240.567068] RDX: 0000000000000941 RSI: 00007ffe16ffa333 RDI: ffffffffffffff9c
  [758240.567860] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  [758240.568707] R10: 00000000000001b6 R11: 0000000000000202 R12: 0000561eec7c4b90
  [758240.569712] R13: 0000561eec7c311f R14: 00007ffe16ffa333 R15: 0000000000000000
  [758240.570758]  </TASK>
  [758240.571040] ---[ end trace 0000000000000000 ]---
  [758240.571681] BTRFS: error (device sdi state A) in btrfs_create_new_inode:6854: errno=-75 unknown
  [758240.572899] BTRFS info (device sdi state EA): forced readonly

Fix this by checking for hash collision, and if the adding a new name is
possible, early in btrfs_create_new_inode() before we do any tree updates,
so that we don't need to abort the transaction if we cannot add the new
name due to the leaf size limit.

A test case for fstests will be sent soon.

Fixes: caae78e03234 ("btrfs: move common inode creation code into btrfs_create_new_inode()")
CC: stable@vger.kernel.org # 6.1+
Reviewed-by: Boris Burkov <boris@bur.io>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d28d55beaacd..b409efe1857e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6610,6 +6610,25 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	int ret;
 	bool xa_reserved = false;
 
+	if (!args->orphan && !args->subvol) {
+		/*
+		 * Before anything else, check if we can add the name to the
+		 * parent directory. We want to avoid a dir item overflow in
+		 * case we have an existing dir item due to existing name
+		 * hash collisions. We do this check here before we call
+		 * btrfs_add_link() down below so that we can avoid a
+		 * transaction abort (which could be exploited by malicious
+		 * users).
+		 *
+		 * For subvolumes we already do this in btrfs_mksubvol().
+		 */
+		ret = btrfs_check_dir_item_collision(BTRFS_I(dir)->root,
+						     btrfs_ino(BTRFS_I(dir)),
+						     name);
+		if (ret < 0)
+			return ret;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;

From e1b18b959025e6b5dbad668f391f65d34b39595a Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 23 Feb 2026 16:19:31 +0000
Subject: [PATCH 0720/1303] btrfs: fix transaction abort when snapshotting
 received subvolumes

Currently a user can trigger a transaction abort by snapshotting a
previously received snapshot a bunch of times until we reach a
BTRFS_UUID_KEY_RECEIVED_SUBVOL item overflow (the maximum item size we
can store in a leaf). This is very likely not common in practice, but
if it happens, it turns the filesystem into RO mode. The snapshot, send
and set_received_subvol and subvol_setflags (used by receive) don't
require CAP_SYS_ADMIN, just inode_owner_or_capable(). A malicious user
could use this to turn a filesystem into RO mode and disrupt a system.

Reproducer script:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi

  # Use smallest node size to make the test faster.
  mkfs.btrfs -f --nodesize 4K $DEV
  mount $DEV $MNT

  # Create a subvolume and set it to RO so that it can be used for send.
  btrfs subvolume create $MNT/sv
  touch $MNT/sv/foo
  btrfs property set $MNT/sv ro true

  # Send and receive the subvolume into snaps/sv.
  mkdir $MNT/snaps
  btrfs send $MNT/sv | btrfs receive $MNT/snaps

  # Now snapshot the received subvolume, which has a received_uuid, a
  # lot of times to trigger the leaf overflow.
  total=500
  for ((i = 1; i <= $total; i++)); do
      echo -ne "\rCreating snapshot $i/$total"
      btrfs subvolume snapshot -r $MNT/snaps/sv $MNT/snaps/sv_$i > /dev/null
  done
  echo

  umount $MNT

When running the test:

  $ ./test.sh
  (...)
  Create subvolume '/mnt/sdi/sv'
  At subvol /mnt/sdi/sv
  At subvol sv
  Creating snapshot 496/500ERROR: Could not create subvolume: Value too large for defined data type
  Creating snapshot 497/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 498/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 499/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 500/500ERROR: Could not create subvolume: Read-only file system

And in dmesg/syslog:

  $ dmesg
  (...)
  [251067.627338] BTRFS warning (device sdi): insert uuid item failed -75 (0x4628b21c4ac8d898, 0x2598bee2b1515c91) type 252!
  [251067.629212] ------------[ cut here ]------------
  [251067.630033] BTRFS: Transaction aborted (error -75)
  [251067.630871] WARNING: fs/btrfs/transaction.c:1907 at create_pending_snapshot.cold+0x52/0x465 [btrfs], CPU#10: btrfs/615235
  [251067.632851] Modules linked in: btrfs dm_zero (...)
  [251067.644071] CPU: 10 UID: 0 PID: 615235 Comm: btrfs Tainted: G        W           6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full)
  [251067.646165] Tainted: [W]=WARN
  [251067.646733] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
  [251067.648735] RIP: 0010:create_pending_snapshot.cold+0x55/0x465 [btrfs]
  [251067.649984] Code: f0 48 0f (...)
  [251067.653313] RSP: 0018:ffffce644908fae8 EFLAGS: 00010292
  [251067.653987] RAX: 00000000ffffff01 RBX: ffff8e5639e63a80 RCX: 00000000ffffffd3
  [251067.655042] RDX: ffff8e53faa76b00 RSI: 00000000ffffffb5 RDI: ffffffffc0919750
  [251067.656077] RBP: ffffce644908fbd8 R08: 0000000000000000 R09: ffffce644908f820
  [251067.657068] R10: ffff8e5adc1fffa8 R11: 0000000000000003 R12: ffff8e53c0431bd0
  [251067.658050] R13: ffff8e5414593600 R14: ffff8e55efafd000 R15: 00000000ffffffb5
  [251067.659019] FS:  00007f2a4944b3c0(0000) GS:ffff8e5b27dae000(0000) knlGS:0000000000000000
  [251067.660115] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [251067.660943] CR2: 00007ffc5aa57898 CR3: 00000005813a2003 CR4: 0000000000370ef0
  [251067.661972] Call Trace:
  [251067.662292]  <TASK>
  [251067.662653]  create_pending_snapshots+0x97/0xc0 [btrfs]
  [251067.663413]  btrfs_commit_transaction+0x26e/0xc00 [btrfs]
  [251067.664257]  ? btrfs_qgroup_convert_reserved_meta+0x35/0x390 [btrfs]
  [251067.665238]  ? _raw_spin_unlock+0x15/0x30
  [251067.665837]  ? record_root_in_trans+0xa2/0xd0 [btrfs]
  [251067.666531]  btrfs_mksubvol+0x330/0x580 [btrfs]
  [251067.667145]  btrfs_mksnapshot+0x74/0xa0 [btrfs]
  [251067.667827]  __btrfs_ioctl_snap_create+0x194/0x1d0 [btrfs]
  [251067.668595]  btrfs_ioctl_snap_create_v2+0x107/0x130 [btrfs]
  [251067.669479]  btrfs_ioctl+0x1580/0x2690 [btrfs]
  [251067.670093]  ? count_memcg_events+0x6d/0x180
  [251067.670849]  ? handle_mm_fault+0x1a0/0x2a0
  [251067.671652]  __x64_sys_ioctl+0x92/0xe0
  [251067.672406]  do_syscall_64+0x50/0xf20
  [251067.673129]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [251067.674096] RIP: 0033:0x7f2a495648db
  [251067.674812] Code: 00 48 89 (...)
  [251067.678227] RSP: 002b:00007ffc5aa57840 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  [251067.679691] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f2a495648db
  [251067.681145] RDX: 00007ffc5aa588b0 RSI: 0000000050009417 RDI: 0000000000000004
  [251067.682511] RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000
  [251067.683842] R10: 000000000000000a R11: 0000000000000246 R12: 00007ffc5aa59910
  [251067.685176] R13: 00007ffc5aa588b0 R14: 0000000000000004 R15: 0000000000000006
  [251067.686524]  </TASK>
  [251067.686972] ---[ end trace 0000000000000000 ]---
  [251067.687890] BTRFS: error (device sdi state A) in create_pending_snapshot:1907: errno=-75 unknown
  [251067.689049] BTRFS info (device sdi state EA): forced readonly
  [251067.689054] BTRFS warning (device sdi state EA): Skipping commit of aborted transaction.
  [251067.690119] BTRFS: error (device sdi state EA) in cleanup_transaction:2043: errno=-75 unknown
  [251067.702028] BTRFS info (device sdi state EA): last unmount of filesystem 46dc3975-30a2-4a69-a18f-418b859cccda

Fix this by ignoring -EOVERFLOW errors from btrfs_uuid_tree_add() in the
snapshot creation code when attempting to add the
BTRFS_UUID_KEY_RECEIVED_SUBVOL item. This is OK because it's not critical
and we are still able to delete the snapshot, as snapshot/subvolume
deletion ignores if a BTRFS_UUID_KEY_RECEIVED_SUBVOL is missing (see
inode.c:btrfs_delete_subvolume()). As for send/receive, we can still do
send/receive operations since it always peeks the first root ID in the
existing BTRFS_UUID_KEY_RECEIVED_SUBVOL (it could peek any since all
snapshots have the same content), and even if the key is missing, it
falls back to searching by BTRFS_UUID_KEY_SUBVOL key.

A test case for fstests will be sent soon.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Boris Burkov <boris@bur.io>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/transaction.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 463238ca8a4d..8d887ffcdba1 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1905,6 +1905,22 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  objectid);
+		/*
+		 * We are creating of lot of snapshots of the same root that was
+		 * received (has a received UUID) and reached a leaf's limit for
+		 * an item. We can safely ignore this and avoid a transaction
+		 * abort. A deletion of this snapshot will still work since we
+		 * ignore if an item with a BTRFS_UUID_KEY_RECEIVED_SUBVOL key
+		 * is missing (see btrfs_delete_subvolume()). Send/receive will
+		 * work too since it peeks the first root id from the existing
+		 * item (it could peek any), and in case it's missing it
+		 * falls back to search by BTRFS_UUID_KEY_SUBVOL keys.
+		 * Creation of a snapshot does not require CAP_SYS_ADMIN, so
+		 * we don't want users triggering transaction aborts, either
+		 * intentionally or not.
+		 */
+		if (ret == -EOVERFLOW)
+			ret = 0;
 		if (unlikely(ret && ret != -EEXIST)) {
 			btrfs_abort_transaction(trans, ret);
 			goto fail;

From 87f2c46003fce4d739138aab4af1942b1afdadac Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 26 Feb 2026 23:41:07 +0000
Subject: [PATCH 0721/1303] btrfs: fix transaction abort on set received ioctl
 due to item overflow

If the set received ioctl fails due to an item overflow when attempting to
add the BTRFS_UUID_KEY_RECEIVED_SUBVOL we have to abort the transaction
since we did some metadata updates before.

This means that if a user calls this ioctl with the same received UUID
field for a lot of subvolumes, we will hit the overflow, trigger the
transaction abort and turn the filesystem into RO mode. A malicious user
could exploit this, and this ioctl does not even requires that a user
has admin privileges (CAP_SYS_ADMIN), only that he/she owns the subvolume.

Fix this by doing an early check for item overflow before starting a
transaction. This is also race safe because we are holding the subvol_sem
semaphore in exclusive (write) mode.

A test case for fstests will follow soon.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c     | 21 +++++++++++++++++++--
 fs/btrfs/uuid-tree.c | 38 ++++++++++++++++++++++++++++++++++++++
 fs/btrfs/uuid-tree.h |  2 ++
 3 files changed, 59 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1d22c5c05b50..56d17eedaf90 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3929,6 +3929,25 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 		goto out;
 	}
 
+	received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
+				       BTRFS_UUID_SIZE);
+
+	/*
+	 * Before we attempt to add the new received uuid, check if we have room
+	 * for it in case there's already an item. If the size of the existing
+	 * item plus this root's ID (u64) exceeds the maximum item size, we can
+	 * return here without the need to abort a transaction. If we don't do
+	 * this check, the btrfs_uuid_tree_add() call below would fail with
+	 * -EOVERFLOW and result in a transaction abort. Malicious users could
+	 * exploit this to turn the fs into RO mode.
+	 */
+	if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
+		ret = btrfs_uuid_tree_check_overflow(fs_info, sa->uuid,
+						     BTRFS_UUID_KEY_RECEIVED_SUBVOL);
+		if (ret < 0)
+			goto out;
+	}
+
 	/*
 	 * 1 - root item
 	 * 2 - uuid items (received uuid + subvol uuid)
@@ -3944,8 +3963,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	sa->rtime.sec = ct.tv_sec;
 	sa->rtime.nsec = ct.tv_nsec;
 
-	received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
-				       BTRFS_UUID_SIZE);
 	if (received_uuid_changed &&
 	    !btrfs_is_empty_uuid(root_item->received_uuid)) {
 		ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid,
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index f24c14b9bb2f..43c17a1d3451 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -199,6 +199,44 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8
 	return 0;
 }
 
+/*
+ * Check if we can add one root ID to a UUID key.
+ * If the key does not yet exists, we can, otherwise only if extended item does
+ * not exceeds the maximum item size permitted by the leaf size.
+ *
+ * Returns 0 on success, negative value on error.
+ */
+int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info,
+				   const u8 *uuid, u8 type)
+{
+	BTRFS_PATH_AUTO_FREE(path);
+	int ret;
+	u32 item_size;
+	struct btrfs_key key;
+
+	if (WARN_ON_ONCE(!fs_info->uuid_root))
+		return -EINVAL;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	btrfs_uuid_to_key(uuid, type, &key);
+	ret = btrfs_search_slot(NULL, fs_info->uuid_root, &key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	item_size = btrfs_item_size(path->nodes[0], path->slots[0]);
+
+	if (sizeof(struct btrfs_item) + item_size + sizeof(u64) >
+	    BTRFS_LEAF_DATA_SIZE(fs_info))
+		return -EOVERFLOW;
+
+	return 0;
+}
+
 static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
 			       u64 subid)
 {
diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h
index c60ad20325cc..02b235a3653f 100644
--- a/fs/btrfs/uuid-tree.h
+++ b/fs/btrfs/uuid-tree.h
@@ -12,6 +12,8 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ
 			u64 subid);
 int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 type,
 			u64 subid);
+int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info,
+				   const u8 *uuid, u8 type);
 int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info);
 int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info);
 int btrfs_uuid_scan_kthread(void *data);

From 0f475ee0ebce5c9492b260027cd95270191675fa Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 00:02:33 +0000
Subject: [PATCH 0722/1303] btrfs: abort transaction on failure to update root
 in the received subvol ioctl

If we failed to update the root we don't abort the transaction, which is
wrong since we already used the transaction to remove an item from the
uuid tree.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 56d17eedaf90..5805ac2078f2 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3984,7 +3984,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 
 	ret = btrfs_update_root(trans, fs_info->tree_root,
 				&root->root_key, &root->root_item);
-	if (ret < 0) {
+	if (unlikely(ret < 0)) {
+		btrfs_abort_transaction(trans, ret);
 		btrfs_end_transaction(trans);
 		goto out;
 	}

From 8dd0e6807b54a2411ed7263018139c60d1406e39 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 00:05:08 +0000
Subject: [PATCH 0723/1303] btrfs: remove unnecessary transaction abort in the
 received subvol ioctl

If we fail to remove an item from the uuid tree, we don't need to abort
the transaction since we have not done any change before. So remove that
transaction abort.

Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5805ac2078f2..7d86e9c8909e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3969,7 +3969,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  btrfs_root_id(root));
 		if (unlikely(ret && ret != -ENOENT)) {
-		        btrfs_abort_transaction(trans, ret);
 		        btrfs_end_transaction(trans);
 		        goto out;
 		}

From 0749cab6174dc035b1628fb6db03abf758cfda6f Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 12:09:47 +0000
Subject: [PATCH 0724/1303] btrfs: remove duplicated definition of
 btrfs_printk_in_rcu()

It's defined twice in a row for the !CONFIG_PRINTK case, so remove one
of the duplicates.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/messages.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h
index 943e53980945..c8e92efce405 100644
--- a/fs/btrfs/messages.h
+++ b/fs/btrfs/messages.h
@@ -28,9 +28,6 @@ void _btrfs_printk(const struct btrfs_fs_info *fs_info, unsigned int level, cons
 
 #else
 
-#define btrfs_printk_in_rcu(fs_info, level, fmt, args...)		\
-	btrfs_no_printk(fs_info, fmt, ##args)
-
 #define btrfs_printk_in_rcu(fs_info, level, fmt, args...)		\
 	btrfs_no_printk(fs_info, fmt, ##args)
 

From 1336b579f6079fb8520be03624fcd9ba443c930b Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 3 Mar 2026 22:35:30 +0800
Subject: [PATCH 0725/1303] sched_ext: Remove redundant css_put() in
 scx_cgroup_init()

The iterator css_for_each_descendant_pre() walks the cgroup hierarchy
under cgroup_lock(). It does not increment the reference counts on
yielded css structs.

According to the cgroup documentation, css_put() should only be used
to release a reference obtained via css_get() or css_tryget_online().
Since the iterator does not use either of these to acquire a reference,
calling css_put() in the error path of scx_cgroup_init() causes a
refcount underflow.

Remove the unbalanced css_put() to prevent a potential Use-After-Free
(UAF) vulnerability.

Fixes: 819513666966 ("sched_ext: Add cgroup support")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2ba69b302368..eab6e09b6442 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3589,7 +3589,6 @@ static int scx_cgroup_init(struct scx_sched *sch)
 		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
-			css_put(css);
 			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}

From 2185904ff8b5da76a4353e5d1236caa78e0d98e3 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Fri, 20 Feb 2026 12:32:27 +0530
Subject: [PATCH 0726/1303] powerpc/pci: Initialize msi_addr_mask for
 OF-created PCI devices

Recent changes replaced the use of no_64bit_msi with msi_addr_mask.  As a
result, msi_addr_mask is now expected to be initialized to DMA_BIT_MASK(64)
when a pci_dev is set up. However, this initialization was missed on
powerpc due to differences in the device initialization path compared to
other (x86) architecture. Due to this, now PCI device probe method fails on
powerpc system.

On powerpc systems, struct pci_dev instances are created from device tree
nodes via of_create_pci_dev(). Because msi_addr_mask was not initialized
there, it remained zero. Later, during MSI setup, msi_verify_entries()
validates the programmed MSI address against pdev->msi_addr_mask. Since the
mask was not set correctly, the validation fails, causing PCI driver probe
failures for devices on powerpc systems.

Initialize pdev->msi_addr_mask to DMA_BIT_MASK(64) in of_create_pci_dev()
so that MSI address validation succeeds and device probe works as expected.

Fixes: 386ced19e9a3 ("PCI/MSI: Convert the boolean no_64bit_msi flag to a DMA address mask")
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Tested-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Vivian Wang <wangruikang@iscas.ac.cn>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260220070239.1693303-2-nilay@linux.ibm.com
---
 arch/powerpc/kernel/pci_of_scan.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 756043dd06e9..fb9fbf0d1796 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -212,6 +212,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	dev->error_state = pci_channel_io_normal;
 	dev->dma_mask = 0xffffffff;
 
+	/*
+	 * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit
+	 * if MSI (rather than MSI-X) capability does not have
+	 * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver.
+	 */
+	dev->msi_addr_mask = DMA_BIT_MASK(64);
+
 	/* Early fixups, before probing the BARs */
 	pci_fixup_device(pci_fixup_early, dev);
 

From 147dae12985947cdb9e1918142f06482c5077a81 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Fri, 20 Feb 2026 12:32:28 +0530
Subject: [PATCH 0727/1303] sparc/PCI: Initialize msi_addr_mask for OF-created
 PCI devices

Recent changes replaced the use of no_64bit_msi with msi_addr_mask, which
is now expected to be initialized to DMA_BIT_MASK(64) during PCI device
setup. On SPARC systems, this initialization was inadvertently missed for
devices instantiated from device tree nodes, leaving msi_addr_mask unset
for OF-created pci_dev instances. As a result, MSI address validation fails
during probe, causing affected devices to fail initialization.

Initialize pdev->msi_addr_mask to DMA_BIT_MASK(64) in of_create_pci_dev()
so that MSI address validation succeeds and PCI device probing works as
expected.

Fixes: 386ced19e9a3 ("PCI/MSI: Convert the boolean no_64bit_msi flag to a DMA address mask")
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Han Gao <gaohan@iscas.ac.cn> # SPARC Enterprise T5220
Tested-by: Nathaniel Roach <nroach44@nroach44.id.au> # SPARC T5-2
Reviewed-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260220070239.1693303-3-nilay@linux.ibm.com
---
 arch/sparc/kernel/pci.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 7e41574634b3..1603d50fdcad 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -355,6 +355,13 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 	dev->error_state = pci_channel_io_normal;
 	dev->dma_mask = 0xffffffff;
 
+	/*
+	 * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit
+	 * if MSI (rather than MSI-X) capability does not have
+	 * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver.
+	 */
+	dev->msi_addr_mask = DMA_BIT_MASK(64);
+
 	if (of_node_name_eq(node, "pci")) {
 		/* a PCI-PCI bridge */
 		dev->hdr_type = PCI_HEADER_TYPE_BRIDGE;

From 50ad1a31bed898787e12b73cb5716fe7960cdde4 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Sat, 21 Feb 2026 07:21:55 +0100
Subject: [PATCH 0728/1303] cpupower: Add support for setting EPP via systemd
 service

Extend the systemd service so that it can be used for tuning the Energy
Performance Preference (EPP) as well. Available options can be read from
/sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences.
The desired one can then be set in cpupower-service.conf.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/cpupower-service.conf | 5 +++++
 tools/power/cpupower/cpupower.sh           | 6 ++++++
 2 files changed, 11 insertions(+)

diff --git a/tools/power/cpupower/cpupower-service.conf b/tools/power/cpupower/cpupower-service.conf
index 02eabe8e3614..abbb46967565 100644
--- a/tools/power/cpupower/cpupower-service.conf
+++ b/tools/power/cpupower/cpupower-service.conf
@@ -30,3 +30,8 @@
 # its policy for the relative importance of performance versus energy savings to
 # the processor. See man CPUPOWER-SET(1) for additional details
 #PERF_BIAS=
+
+# Set the Energy Performance Preference
+# Available options can be read from
+# /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences
+#EPP=
diff --git a/tools/power/cpupower/cpupower.sh b/tools/power/cpupower/cpupower.sh
index a37dd4cfdb2b..6283e8bf275d 100644
--- a/tools/power/cpupower/cpupower.sh
+++ b/tools/power/cpupower/cpupower.sh
@@ -23,4 +23,10 @@ then
     cpupower set -b "$PERF_BIAS" > /dev/null || ESTATUS=1
 fi
 
+# apply Energy Performance Preference
+if test -n "$EPP"
+then
+    cpupower set -e "$EPP" > /dev/null || ESTATUS=1
+fi
+
 exit $ESTATUS

From 3817b1d34432d3d83a61576719570d04c341b7cd Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Mon, 9 Feb 2026 11:24:41 +0800
Subject: [PATCH 0729/1303] cpupower: Add intel_pstate turbo boost support for
 Intel platforms

On modern Intel platforms, the intel_pstate driver is commonly used and
it provides turbo boost control via
/sys/devices/system/cpu/intel_pstate/no_turbo.

However, cpupower doesn't handle this. it
1. shows turbo boost as "active" blindly for Intel platforms
2. controls turbo boost functionality via the generic
   /sys/devices/system/cpu/cpufreq/boost sysfs interface only.

Enhance the cpupower tool to ensure the "--boost" command works
seamlessly on Intel platforms with intel_pstate driver running.

Without this patch,
   $ echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo
   1
   $ sudo cpupower frequency-info --boost
   analyzing CPU 21:
     boost state support:
       Supported: yes
       Active: yes
   $ sudo cpupower set --boost 0
   Error setting turbo-boost
   $ sudo cpupower set --boost 1
   Error setting turbo-boost

With this patch,
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   0
   $ sudo cpupower set --boost 0
   $ sudo cpupower frequency-info --boost
   analyzing CPU 21:
     boost state support:
       Supported: yes
       Active: no
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   1
   $ sudo cpupower set --boost 1
   $ sudo cpupower frequency-info --boost
   analyzing CPU 28:
     boost state support:
       Supported: yes
       Active: yes
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   0

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/cpupower-set.c    |  6 ++-
 tools/power/cpupower/utils/helpers/helpers.h |  5 ++-
 tools/power/cpupower/utils/helpers/misc.c    | 41 +++++++++++++++++++-
 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index c2117e5650dd..550a942e72ce 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -124,7 +124,11 @@ int cmd_set(int argc, char **argv)
 	}
 
 	if (params.turbo_boost) {
-		ret = cpupower_set_turbo_boost(turbo_boost);
+		if (cpupower_cpu_info.vendor == X86_VENDOR_INTEL)
+			ret = cpupower_set_intel_turbo_boost(turbo_boost);
+		else
+			ret = cpupower_set_generic_turbo_boost(turbo_boost);
+
 		if (ret)
 			fprintf(stderr, "Error setting turbo-boost\n");
 	}
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 82ea62bdf5a2..a3ad80b9c2c2 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -104,7 +104,7 @@ extern struct cpupower_cpu_info cpupower_cpu_info;
 /* cpuid and cpuinfo helpers  **************************/
 
 int cpufreq_has_generic_boost_support(bool *active);
-int cpupower_set_turbo_boost(int turbo_boost);
+int cpupower_set_generic_turbo_boost(int turbo_boost);
 
 /* X86 ONLY ****************************************/
 #if defined(__i386__) || defined(__x86_64__)
@@ -143,6 +143,7 @@ extern int decode_pstates(unsigned int cpu, int boost_states,
 
 int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
 				  int *active, int *states);
+int cpupower_set_intel_turbo_boost(int turbo_boost);
 
 /* AMD P-State stuff **************************/
 bool cpupower_amd_pstate_enabled(void);
@@ -189,6 +190,8 @@ static inline int cpupower_set_amd_pstate_mode(char *mode)
 static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
 						int *active, int *states)
 { return -1; }
+static inline int cpupower_set_intel_turbo_boost(int turbo_boost)
+{ return -1; }
 
 static inline bool cpupower_amd_pstate_enabled(void)
 { return false; }
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index 166dc1e470ea..eebfc79a4889 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -19,6 +19,9 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active,
 {
 	int ret;
 	unsigned long long val;
+	char linebuf[MAX_LINE_LEN];
+	char path[SYSFS_PATH_MAX];
+	char *endp;
 
 	*support = *active = *states = 0;
 
@@ -42,8 +45,42 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active,
 		}
 	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) {
 		amd_pstate_boost_init(cpu, support, active);
-	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA)
+	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) {
 		*support = *active = 1;
+
+		snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo");
+
+		if (!is_valid_path(path))
+			return 0;
+
+		if (cpupower_read_sysfs(path, linebuf, MAX_LINE_LEN) == 0)
+			return -1;
+
+		val = strtol(linebuf, &endp, 0);
+		if (endp == linebuf || errno == ERANGE)
+			return -1;
+
+		*active = !val;
+	}
+	return 0;
+}
+
+int cpupower_set_intel_turbo_boost(int turbo_boost)
+{
+	char path[SYSFS_PATH_MAX];
+	char linebuf[2] = {};
+
+	snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo");
+
+	/* Fallback to generic solution when intel_pstate driver not running */
+	if (!is_valid_path(path))
+		return cpupower_set_generic_turbo_boost(turbo_boost);
+
+	snprintf(linebuf, sizeof(linebuf), "%d", !turbo_boost);
+
+	if (cpupower_write_sysfs(path, linebuf, 2) <= 0)
+		return -1;
+
 	return 0;
 }
 
@@ -274,7 +311,7 @@ void print_speed(unsigned long speed, int no_rounding)
 	}
 }
 
-int cpupower_set_turbo_boost(int turbo_boost)
+int cpupower_set_generic_turbo_boost(int turbo_boost)
 {
 	char path[SYSFS_PATH_MAX];
 	char linebuf[2] = {};

From 20f644f42e3b8e729d3c3199d48e75c0b257de8f Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Wed, 25 Feb 2026 13:11:57 +0530
Subject: [PATCH 0730/1303] drm/msm/a6xx: Fix the bogus protect error on X2-85

Update the X2-85 gpu's register protect count configuration with the
correct count_max value to avoid blocking the entire MMIO region from the
UMD.

Protect configurations are a bit complicated on A8xx. There are 2 set of
protect registers with different counts: Global and Pipe-specific. The
last-span-unbound feature is available only on the Pipe-specific protect
registers. Due to this, we cannot use the BUILD_BUG sanity check for A8x
protect configurations, so remove the A840 entry from there.

Fixes: 01ff3bf27215 ("drm/msm/a8xx: Add support for Adreno X2-85 GPU")
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/706944/
Message-ID: <20260225-glymur-protect-fix-v1-1-0deddedf9277@oss.qualcomm.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_catalog.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
index 550a53a7865e..38561f26837e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
@@ -1759,7 +1759,7 @@ static const u32 x285_protect_regs[] = {
 	A6XX_PROTECT_NORDWR(0x27c06, 0x0000),
 };
 
-DECLARE_ADRENO_PROTECT(x285_protect, 64);
+DECLARE_ADRENO_PROTECT(x285_protect, 15);
 
 static const struct adreno_reglist_pipe a840_nonctxt_regs[] = {
 	{ REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) },
@@ -1966,5 +1966,4 @@ static inline __always_unused void __build_asserts(void)
 	BUILD_BUG_ON(a660_protect.count > a660_protect.count_max);
 	BUILD_BUG_ON(a690_protect.count > a690_protect.count_max);
 	BUILD_BUG_ON(a730_protect.count > a730_protect.count_max);
-	BUILD_BUG_ON(a840_protect.count > a840_protect.count_max);
 }

From e4eb6e4dd6348dd00e19c2275e3fbaed304ca3bd Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Thu, 26 Feb 2026 10:57:11 +0100
Subject: [PATCH 0731/1303] drm/msm: Fix dma_free_attrs() buffer size

The gpummu->table buffer is alloc'd with size TABLE_SIZE + 32 in
a2xx_gpummu_new() but freed with size TABLE_SIZE in
a2xx_gpummu_destroy().

Change the free size to match the allocation.

Fixes: c2052a4e5c99 ("drm/msm: implement a2xx mmu")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707340/
Message-ID: <20260226095714.12126-2-fourier.thomas@gmail.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a2xx_gpummu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
index 0407c9bc8c1b..4467b04527cd 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
@@ -78,7 +78,7 @@ static void a2xx_gpummu_destroy(struct msm_mmu *mmu)
 {
 	struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu);
 
-	dma_free_attrs(mmu->dev, TABLE_SIZE, gpummu->table, gpummu->pt_base,
+	dma_free_attrs(mmu->dev, TABLE_SIZE + 32, gpummu->table, gpummu->pt_base,
 		DMA_ATTR_FORCE_CONTIGUOUS);
 
 	kfree(gpummu);

From 3875ceb592d3cb23dc932165cc1eeb74cf4dc319 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 15:48:56 -0800
Subject: [PATCH 0732/1303] crypto: testmgr - Fix stale references to
 aes-generic

Due to commit a2484474272e ("crypto: aes - Replace aes-generic with
wrapper around lib"), the "aes-generic" driver name has been replaced
with "aes-lib".  Update a couple testmgr entries that were added
concurrently with this change.

Fixes: a22d48cbe558 ("crypto: testmgr - Add test vectors for authenc(hmac(sha224),cbc(aes))")
Fixes: 030218dedee2 ("crypto: testmgr - Add test vectors for authenc(hmac(sha384),cbc(aes))")
Acked-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Link: https://lore.kernel.org/r/20260302234856.30569-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/testmgr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 49b607f65f63..4985411dedae 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4132,7 +4132,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 	}, {
 		.alg = "authenc(hmac(sha224),cbc(aes))",
-		.generic_driver = "authenc(hmac-sha224-lib,cbc(aes-generic))",
+		.generic_driver = "authenc(hmac-sha224-lib,cbc(aes-lib))",
 		.test = alg_test_aead,
 		.suite = {
 			.aead = __VECS(hmac_sha224_aes_cbc_tv_temp)
@@ -4194,7 +4194,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 	}, {
 		.alg = "authenc(hmac(sha384),cbc(aes))",
-		.generic_driver = "authenc(hmac-sha384-lib,cbc(aes-generic))",
+		.generic_driver = "authenc(hmac-sha384-lib,cbc(aes-lib))",
 		.test = alg_test_aead,
 		.suite = {
 			.aead = __VECS(hmac_sha384_aes_cbc_tv_temp)

From eef33aa44935d001747ca97703c08dd6f9031162 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Wed, 3 Dec 2025 14:29:48 +0100
Subject: [PATCH 0733/1303] ice: fix adding AQ LLDP filter for VF

The referenced commit came from a misunderstanding of the FW LLDP filter
AQ (Admin Queue) command due to the error in the internal documentation.
Contrary to the assumptions in the original commit, VFs can be added and
deleted from this filter without any problems. Introduced dev_info message
proved to be useful, so reverting the whole commit does not make sense.

Without this fix, trusted VFs do not receive LLDP traffic, if there is an
AQ LLDP filter on PF. When trusted VF attempts to add an LLDP multicast
MAC address, the following message can be seen in dmesg on host:

ice 0000:33:00.0: Failed to add Rx LLDP rule on VSI 20 error: -95

Revert checking VSI type when adding LLDP filter through AQ.

Fixes: 4d5a1c4e6d49 ("ice: do not add LLDP-specific filter if not necessary")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 6cd63190f55d..74fe74225277 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -6391,7 +6391,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 	struct ice_aqc_lldp_filter_ctrl *cmd;
 	struct libie_aq_desc desc;
 
-	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
+	if (!ice_fw_supports_lldp_fltr_ctrl(hw))
 		return -EOPNOTSUPP;
 
 	cmd = libie_aq_raw(&desc);

From 326256c0a72d4877cec1d4df85357da106233128 Mon Sep 17 00:00:00 2001
From: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Date: Tue, 13 Jan 2026 20:38:16 +0100
Subject: [PATCH 0734/1303] ice: reintroduce retry mechanism for indirect AQ

Add retry mechanism for indirect Admin Queue (AQ) commands. To do so we
need to keep the command buffer.

This technically reverts commit 43a630e37e25
("ice: remove unused buffer copy code in ice_sq_send_cmd_retry()"),
but combines it with a fix in the logic by using a kmemdup() call,
making it more robust and less likely to break in the future due to
programmer error.

Cc: Michal Schmidt <mschmidt@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 3056df93f7a8 ("ice: Re-send some AQ commands, as result of EBUSY AQ error")
Signed-off-by: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Co-developed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Signed-off-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 74fe74225277..fd32c318d3f5 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1841,6 +1841,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 {
 	struct libie_aq_desc desc_cpy;
 	bool is_cmd_for_retry;
+	u8 *buf_cpy = NULL;
 	u8 idx = 0;
 	u16 opcode;
 	int status;
@@ -1850,8 +1851,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	memset(&desc_cpy, 0, sizeof(desc_cpy));
 
 	if (is_cmd_for_retry) {
-		/* All retryable cmds are direct, without buf. */
-		WARN_ON(buf);
+		if (buf) {
+			buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL);
+			if (!buf_cpy)
+				return -ENOMEM;
+		}
 
 		memcpy(&desc_cpy, desc, sizeof(desc_cpy));
 	}
@@ -1863,12 +1867,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		    hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY)
 			break;
 
+		if (buf_cpy)
+			memcpy(buf, buf_cpy, buf_size);
 		memcpy(desc, &desc_cpy, sizeof(desc_cpy));
-
 		msleep(ICE_SQ_SEND_DELAY_TIME_MS);
 
 	} while (++idx < ICE_SQ_SEND_MAX_EXECUTE);
 
+	kfree(buf_cpy);
 	return status;
 }
 

From fb4903b3354aed4a2301180cf991226f896c87ed Mon Sep 17 00:00:00 2001
From: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Date: Tue, 13 Jan 2026 20:38:17 +0100
Subject: [PATCH 0735/1303] ice: fix retry for AQ command 0x06EE

Executing ethtool -m can fail reporting a netlink I/O error while firmware
link management holds the i2c bus used to communicate with the module.

According to Intel(R) Ethernet Controller E810 Datasheet Rev 2.8 [1]
Section 3.3.10.4 Read/Write SFF EEPROM (0x06EE)
request should to be retried upon receiving EBUSY from firmware.

Commit e9c9692c8a81 ("ice: Reimplement module reads used by ethtool")
implemented it only for part of ice_get_module_eeprom(), leaving all other
calls to ice_aq_sff_eeprom() vulnerable to returning early on getting
EBUSY without retrying.

Remove the retry loop from ice_get_module_eeprom() and add Admin Queue
(AQ) command with opcode 0x06EE to the list of commands that should be
retried on receiving EBUSY from firmware.

Cc: stable@vger.kernel.org
Fixes: e9c9692c8a81 ("ice: Reimplement module reads used by ethtool")
Signed-off-by: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Co-developed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Signed-off-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://www.intel.com/content/www/us/en/content-details/613875/intel-ethernet-controller-e810-datasheet.html [1]
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c  |  1 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 35 ++++++++------------
 2 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index fd32c318d3f5..ce11fea122d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode)
 	case ice_aqc_opc_lldp_stop:
 	case ice_aqc_opc_lldp_start:
 	case ice_aqc_opc_lldp_filter_ctrl:
+	case ice_aqc_opc_sff_eeprom:
 		return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3c1a084c2a4b..29e341251754 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4509,7 +4509,7 @@ ice_get_module_eeprom(struct net_device *netdev,
 	u8 addr = ICE_I2C_EEPROM_DEV_ADDR;
 	struct ice_hw *hw = &pf->hw;
 	bool is_sfp = false;
-	unsigned int i, j;
+	unsigned int i;
 	u16 offset = 0;
 	u8 page = 0;
 	int status;
@@ -4551,26 +4551,19 @@ ice_get_module_eeprom(struct net_device *netdev,
 		if (page == 0 || !(data[0x2] & 0x4)) {
 			u32 copy_len;
 
-			/* If i2c bus is busy due to slow page change or
-			 * link management access, call can fail. This is normal.
-			 * So we retry this a few times.
-			 */
-			for (j = 0; j < 4; j++) {
-				status = ice_aq_sff_eeprom(hw, 0, addr, offset, page,
-							   !is_sfp, value,
-							   SFF_READ_BLOCK_SIZE,
-							   0, NULL);
-				netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n",
-					   addr, offset, page, is_sfp,
-					   value[0], value[1], value[2], value[3],
-					   value[4], value[5], value[6], value[7],
-					   status);
-				if (status) {
-					usleep_range(1500, 2500);
-					memset(value, 0, SFF_READ_BLOCK_SIZE);
-					continue;
-				}
-				break;
+			status = ice_aq_sff_eeprom(hw, 0, addr, offset, page,
+						   !is_sfp, value,
+						   SFF_READ_BLOCK_SIZE,
+						   0, NULL);
+			netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n",
+				   addr, offset, page, is_sfp,
+				   value[0], value[1], value[2], value[3],
+				   value[4], value[5], value[6], value[7],
+				   ERR_PTR(status));
+			if (status) {
+				netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n",
+					   __func__, ERR_PTR(status));
+				return status;
 			}
 
 			/* Make sure we have enough room for the new block */

From fe868b499d16f55bbeea89992edb98043c9de416 Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Thu, 22 Jan 2026 03:26:44 +0000
Subject: [PATCH 0736/1303] ice: Fix memory leak in ice_set_ringparam()

In ice_set_ringparam, tx_rings and xdp_rings are allocated before
rx_rings. If the allocation of rx_rings fails, the code jumps to
the done label leaking both tx_rings and xdp_rings. Furthermore, if
the setup of an individual Rx ring fails during the loop, the code jumps
to the free_tx label which releases tx_rings but leaks xdp_rings.

Fix this by introducing a free_xdp label and updating the error paths to
ensure both xdp_rings and tx_rings are properly freed if rx_rings
allocation or setup fails.

Compile tested only. Issue found using a prototype static analysis tool
and code review.

Fixes: fcea6f3da546 ("ice: Add stats and ethtool support")
Fixes: efc2214b6047 ("ice: Add support for XDP")
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 29e341251754..b9be10b58856 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3332,7 +3332,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq);
 	if (!rx_rings) {
 		err = -ENOMEM;
-		goto done;
+		goto free_xdp;
 	}
 
 	ice_for_each_rxq(vsi, i) {
@@ -3359,7 +3359,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 			}
 			kfree(rx_rings);
 			err = -ENOMEM;
-			goto free_tx;
+			goto free_xdp;
 		}
 	}
 
@@ -3411,6 +3411,13 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	}
 	goto done;
 
+free_xdp:
+	if (xdp_rings) {
+		ice_for_each_xdp_txq(vsi, i)
+			ice_free_tx_ring(&xdp_rings[i]);
+		kfree(xdp_rings);
+	}
+
 free_tx:
 	/* error cleanup if the Rx allocations failed after getting Tx */
 	if (tx_rings) {

From 636cc3bd12f499c74eaf5dc9a7d5b832f1bb24ed Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 11 Feb 2026 10:11:40 +0100
Subject: [PATCH 0737/1303] libie: don't unroll if fwlog isn't supported

The libie_fwlog_deinit() function can be called during driver unload
even when firmware logging was never properly initialized. This led to call
trace:

[  148.576156] Oops: Oops: 0000 [#1] SMP NOPTI
[  148.576167] CPU: 80 UID: 0 PID: 12843 Comm: rmmod Kdump: loaded Not tainted 6.17.0-rc7next-queue-3oct-01915-g06d79d51cf51 #1 PREEMPT(full)
[  148.576177] Hardware name: HPE ProLiant DL385 Gen10 Plus/ProLiant DL385 Gen10 Plus, BIOS A42 07/18/2020
[  148.576182] RIP: 0010:__dev_printk+0x16/0x70
[  148.576196] Code: 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 55 41 54 49 89 d4 55 48 89 fd 53 48 85 f6 74 3c <4c> 8b 6e 50 48 89 f3 4d 85 ed 75 03 4c 8b 2e 48 89 df e8 f3 27 98
[  148.576204] RSP: 0018:ffffd2fd7ea17a48 EFLAGS: 00010202
[  148.576211] RAX: ffffd2fd7ea17aa0 RBX: ffff8eb288ae2000 RCX: 0000000000000000
[  148.576217] RDX: ffffd2fd7ea17a70 RSI: 00000000000000c8 RDI: ffffffffb68d3d88
[  148.576222] RBP: ffffffffb68d3d88 R08: 0000000000000000 R09: 0000000000000000
[  148.576227] R10: 00000000000000c8 R11: ffff8eb2b1a49400 R12: ffffd2fd7ea17a70
[  148.576231] R13: ffff8eb3141fb000 R14: ffffffffc1215b48 R15: ffffffffc1215bd8
[  148.576236] FS:  00007f5666ba6740(0000) GS:ffff8eb2472b9000(0000) knlGS:0000000000000000
[  148.576242] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  148.576247] CR2: 0000000000000118 CR3: 000000011ad17000 CR4: 0000000000350ef0
[  148.576252] Call Trace:
[  148.576258]  <TASK>
[  148.576269]  _dev_warn+0x7c/0x96
[  148.576290]  libie_fwlog_deinit+0x112/0x117 [libie_fwlog]
[  148.576303]  ixgbe_remove+0x63/0x290 [ixgbe]
[  148.576342]  pci_device_remove+0x42/0xb0
[  148.576354]  device_release_driver_internal+0x19c/0x200
[  148.576365]  driver_detach+0x48/0x90
[  148.576372]  bus_remove_driver+0x6d/0xf0
[  148.576383]  pci_unregister_driver+0x2e/0xb0
[  148.576393]  ixgbe_exit_module+0x1c/0xd50 [ixgbe]
[  148.576430]  __do_sys_delete_module.isra.0+0x1bc/0x2e0
[  148.576446]  do_syscall_64+0x7f/0x980

It can be reproduced by trying to unload ixgbe driver in recovery mode.

Fix that by checking if fwlog is supported before doing unroll.

Fixes: 641585bc978e ("ixgbe: fwlog support for e610")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/libie/fwlog.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c
index 79020d990859..4d0c8370386b 100644
--- a/drivers/net/ethernet/intel/libie/fwlog.c
+++ b/drivers/net/ethernet/intel/libie/fwlog.c
@@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog)
 {
 	int status;
 
+	/* if FW logging isn't supported it means no configuration was done */
+	if (!libie_fwlog_supported(fwlog))
+		return;
+
 	/* make sure FW logging is disabled to not put the FW in a weird state
 	 * for the next driver load
 	 */

From b84852170153671bb0fa6737a6e48370addd8e1a Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Tue, 10 Feb 2026 15:57:14 +0000
Subject: [PATCH 0738/1303] iavf: fix netdev->max_mtu to respect actual
 hardware limit

iavf sets LIBIE_MAX_MTU as netdev->max_mtu, ignoring vf_res->max_mtu
from PF [1]. This allows setting an MTU beyond the actual hardware
limit, causing TX queue timeouts [2].

Set correct netdev->max_mtu using vf_res->max_mtu from the PF.

Note that currently PF drivers such as ice/i40e set the frame size in
vf_res->max_mtu, not MTU. Convert vf_res->max_mtu to MTU before setting
netdev->max_mtu.

[1]
 # ip -j -d link show $DEV | jq '.[0].max_mtu'
 16356

[2]
 iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 1: transmit queue 0 timed out 5692 ms
 iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex
 iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 6: transmit queue 3 timed out 5312 ms
 iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex
 ...

Fixes: 5fa4caff59f2 ("iavf: switch to Page Pool")
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index bceaf4b1b85d..86c1964f42e1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	netdev->watchdog_timeo = 5 * HZ;
 
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = LIBIE_MAX_MTU;
+
+	/* PF/VF API: vf_res->max_mtu is max frame size (not MTU).
+	 * Convert to MTU.
+	 */
+	if (!adapter->vf_res->max_mtu) {
+		netdev->max_mtu = LIBIE_MAX_MTU;
+	} else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU ||
+		   adapter->vf_res->max_mtu >
+			   LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) {
+		netdev_warn_once(adapter->netdev,
+				 "invalid max frame size %d from PF, using default MTU %d",
+				 adapter->vf_res->max_mtu, LIBIE_MAX_MTU);
+		netdev->max_mtu = LIBIE_MAX_MTU;
+	} else {
+		netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN;
+	}
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",

From d4c13ab36273a8c318ba06799793cc1f5d9c6fa1 Mon Sep 17 00:00:00 2001
From: Vivek Behera <vivek.behera@siemens.com>
Date: Thu, 22 Jan 2026 15:16:52 +0100
Subject: [PATCH 0739/1303] igb: Fix trigger of incorrect irq in igb_xsk_wakeup

The current implementation in the igb_xsk_wakeup expects
the Rx and Tx queues to share the same irq. This would lead
to triggering of incorrect irq in split irq configuration.
This patch addresses this issue which could impact environments
with 2 active cpu cores
or when the number of queues is reduced to 2 or less

cat /proc/interrupts | grep eno2
 167:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 0-edge      eno2
 168:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 1-edge      eno2-rx-0
 169:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 2-edge      eno2-rx-1
 170:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 3-edge      eno2-tx-0
 171:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 4-edge      eno2-tx-1

Furthermore it uses the flags input argument to trigger either rx, tx or
both rx and tx irqs as specified in the ndo_xsk_wakeup api documentation

Fixes: 80f6ccf9f116 ("igb: Introduce XSK data structures and helpers")
Signed-off-by: Vivek Behera <vivek.behera@siemens.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Saritha Sanigani <sarithax.sanigani@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_xsk.c | 38 +++++++++++++++++++-----
 1 file changed, 30 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
index 30ce5fbb5b77..ce4a7b58cad2 100644
--- a/drivers/net/ethernet/intel/igb/igb_xsk.c
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
 	return nb_pkts < budget;
 }
 
+static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector)
+{
+	u32 eics = 0;
+
+	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
+		eics = q_vector->eims_value;
+
+	return eics;
+}
+
 int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
 	struct igb_adapter *adapter = netdev_priv(dev);
@@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 
 	ring = adapter->tx_ring[qid];
 
-	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
-		return -ENETDOWN;
-
 	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
-	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+	if (flags & XDP_WAKEUP_TX) {
+		if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
+			return -ENETDOWN;
+
+		eics |= igb_sw_irq_prep(ring->q_vector);
+	}
+
+	if (flags & XDP_WAKEUP_RX) {
+		/* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector
+		 * and NAPI is shared between RX and TX.
+		 * If NAPI is already running it would be marked as missed
+		 * from the TX path, making this RX call a NOP
+		 */
+		ring = adapter->rx_ring[qid];
+		eics |= igb_sw_irq_prep(ring->q_vector);
+	}
+
+	if (eics) {
 		/* Cause software interrupt */
-		if (adapter->flags & IGB_FLAG_HAS_MSIX) {
-			eics |= ring->q_vector->eims_value;
+		if (adapter->flags & IGB_FLAG_HAS_MSIX)
 			wr32(E1000_EICS, eics);
-		} else {
+		else
 			wr32(E1000_ICS, E1000_ICS_RXDMT0);
-		}
 	}
 
 	return 0;

From 554a1c34c11a057d01819ce9bb04653a8ffc8071 Mon Sep 17 00:00:00 2001
From: Vivek Behera <vivek.behera@siemens.com>
Date: Tue, 20 Jan 2026 08:52:16 +0100
Subject: [PATCH 0740/1303] igc: Fix trigger of incorrect irq in igc_xsk_wakeup
 function

This patch addresses the issue where the igc_xsk_wakeup function
was triggering an incorrect IRQ for tx-0 when the i226 is configured
with only 2 combined queues or in an environment with 2 active CPU cores.
This prevented XDP Zero-copy send functionality in such split IRQ
configurations.

The fix implements the correct logic for extracting q_vectors saved
during rx and tx ring allocation and utilizes flags provided by the
ndo_xsk_wakeup API to trigger the appropriate IRQ.

Fixes: fc9df2a0b520 ("igc: Enable RX via AF_XDP zero-copy")
Fixes: 15fd021bc427 ("igc: Add Tx hardware timestamp request for AF_XDP zero-copy packet")
Signed-off-by: Vivek Behera <vivek.behera@siemens.com>
Reviewed-by: Jacob Keller <jacob.keller@intel.com>
Reviewed-by: Aleksandr loktinov <aleksandr.loktionov@intel.com>
Reviewed-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 34 ++++++++++++++++-------
 drivers/net/ethernet/intel/igc/igc_ptp.c  |  3 +-
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 27e5c2109138..b2e8d0c0f827 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	return nxmit;
 }
 
-static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter,
-					struct igc_q_vector *q_vector)
+static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector)
 {
-	struct igc_hw *hw = &adapter->hw;
 	u32 eics = 0;
 
-	eics |= q_vector->eims_value;
-	wr32(IGC_EICS, eics);
+	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
+		eics = q_vector->eims_value;
+
+	return eics;
 }
 
 int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
-	struct igc_q_vector *q_vector;
+	struct igc_hw *hw = &adapter->hw;
 	struct igc_ring *ring;
+	u32 eics = 0;
 
 	if (test_bit(__IGC_DOWN, &adapter->state))
 		return -ENETDOWN;
 
 	if (!igc_xdp_is_enabled(adapter))
 		return -ENXIO;
-
+	/* Check if queue_id is valid. Tx and Rx queue numbers are always same */
 	if (queue_id >= adapter->num_rx_queues)
 		return -EINVAL;
 
@@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	if (!ring->xsk_pool)
 		return -ENXIO;
 
-	q_vector = adapter->q_vector[queue_id];
-	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
-		igc_trigger_rxtxq_interrupt(adapter, q_vector);
+	if (flags & XDP_WAKEUP_RX)
+		eics |= igc_sw_irq_prep(ring->q_vector);
+
+	if (flags & XDP_WAKEUP_TX) {
+		/* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector
+		 * and NAPI is shared between RX and TX.
+		 * If NAPI is already running it would be marked as missed
+		 * from the RX path, making this TX call a NOP
+		 */
+		ring = adapter->tx_ring[queue_id];
+		eics |= igc_sw_irq_prep(ring->q_vector);
+	}
+
+	if (eics)
+		/* Cause software interrupt */
+		wr32(IGC_EICS, eics);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 7aae83c108fd..44ee19386766 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter,
 		tstamp->buffer_type = 0;
 
 		/* Trigger txrx interrupt for transmit completion */
-		igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0);
+		igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index,
+			       XDP_WAKEUP_TX);
 
 		return;
 	}

From b06ccbabe2506fd70b9167a644978b049150224a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 3 Mar 2026 01:01:15 -1000
Subject: [PATCH 0741/1303] sched_ext: Fix starvation of scx_enable() under
 fair-class saturation

During scx_enable(), the READY -> ENABLED task switching loop changes the
calling thread's sched_class from fair to ext. Since fair has higher
priority than ext, saturating fair-class workloads can indefinitely starve
the enable thread, hanging the system. This was introduced when the enable
path switched from preempt_disable() to scx_bypass() which doesn't protect
against fair-class starvation. Note that the original preempt_disable()
protection wasn't complete either - in partial switch modes, the calling
thread could still be starved after preempt_enable() as it may have been
switched to ext class.

Fix it by offloading the enable body to a dedicated system-wide RT
(SCHED_FIFO) kthread which cannot be starved by either fair or ext class
tasks. scx_enable() lazily creates the kthread on first use and passes the
ops pointer through a struct scx_enable_cmd containing the kthread_work,
then synchronously waits for completion.

The workfn runs on a different kthread from sch->helper (which runs
disable_work), so it can safely flush disable_work on the error path
without deadlock.

Fixes: 8c2090c504e9 ("sched_ext: Initialize in bypass mode")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 66 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 56 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index eab6e09b6442..ba51969718f5 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4975,20 +4975,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	return 0;
 }
 
-static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+/*
+ * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
+ * starvation. During the READY -> ENABLED task switching loop, the calling
+ * thread's sched_class gets switched from fair to ext. As fair has higher
+ * priority than ext, the calling thread can be indefinitely starved under
+ * fair-class saturation, leading to a system hang.
+ */
+struct scx_enable_cmd {
+	struct kthread_work	work;
+	struct sched_ext_ops	*ops;
+	int			ret;
+};
+
+static void scx_enable_workfn(struct kthread_work *work)
 {
+	struct scx_enable_cmd *cmd =
+		container_of(work, struct scx_enable_cmd, work);
+	struct sched_ext_ops *ops = cmd->ops;
 	struct scx_sched *sch;
 	struct scx_task_iter sti;
 	struct task_struct *p;
 	unsigned long timeout;
 	int i, cpu, ret;
 
-	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
-			   cpu_possible_mask)) {
-		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
-		return -EINVAL;
-	}
-
 	mutex_lock(&scx_enable_mutex);
 
 	if (scx_enable_state() != SCX_DISABLED) {
@@ -5205,13 +5215,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	atomic_long_inc(&scx_enable_seq);
 
-	return 0;
+	cmd->ret = 0;
+	return;
 
 err_free_ksyncs:
 	free_kick_syncs();
 err_unlock:
 	mutex_unlock(&scx_enable_mutex);
-	return ret;
+	cmd->ret = ret;
+	return;
 
 err_disable_unlock_all:
 	scx_cgroup_unlock();
@@ -5230,7 +5242,41 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 */
 	scx_error(sch, "scx_enable() failed (%d)", ret);
 	kthread_flush_work(&sch->disable_work);
-	return 0;
+	cmd->ret = 0;
+}
+
+static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+{
+	static struct kthread_worker *helper;
+	static DEFINE_MUTEX(helper_mutex);
+	struct scx_enable_cmd cmd;
+
+	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
+			   cpu_possible_mask)) {
+		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
+		return -EINVAL;
+	}
+
+	if (!READ_ONCE(helper)) {
+		mutex_lock(&helper_mutex);
+		if (!helper) {
+			helper = kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(helper)) {
+				helper = NULL;
+				mutex_unlock(&helper_mutex);
+				return -ENOMEM;
+			}
+			sched_set_fifo(helper->task);
+		}
+		mutex_unlock(&helper_mutex);
+	}
+
+	kthread_init_work(&cmd.work, scx_enable_workfn);
+	cmd.ops = ops;
+
+	kthread_queue_work(READ_ONCE(helper), &cmd.work);
+	kthread_flush_work(&cmd.work);
+	return cmd.ret;
 }
 
 

From 56145d237385ca0e7ca9ff7b226aaf2eb8ef368b Mon Sep 17 00:00:00 2001
From: Lang Xu <xulang@uniontech.com>
Date: Tue, 3 Mar 2026 17:52:17 +0800
Subject: [PATCH 0742/1303] bpf: Fix a UAF issue in
 bpf_trampoline_link_cgroup_shim

The root cause of this bug is that when 'bpf_link_put' reduces the
refcount of 'shim_link->link.link' to zero, the resource is considered
released but may still be referenced via 'tr->progs_hlist' in
'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in
'bpf_shim_tramp_link_release' is deferred. During this window, another
process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.

Based on Martin KaFai Lau's suggestions, I have created a simple patch.

To fix this:
   Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'.
   Only increment the refcount if it is not already zero.

Testing:
   I verified the fix by adding a delay in
   'bpf_shim_tramp_link_release' to make the bug easier to trigger:

static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
	/* ... */
	if (!shim_link->trampoline)
		return;

+	msleep(100);
	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link,
		shim_link->trampoline, NULL));
	bpf_trampoline_put(shim_link->trampoline);
}

Before the patch, running a PoC easily reproduced the crash(almost 100%)
with a call trace similar to KaiyanM's report.
After the patch, the bug no longer occurs even after millions of
iterations.

Fixes: 69fd337a975c ("bpf: per-cgroup lsm flavor")
Reported-by: Kaiyan Mei <M202472210@hust.edu.cn>
Closes: https://lore.kernel.org/bpf/3c4ebb0b.46ff8.19abab8abe2.Coremail.kaiyanm@hust.edu.cn/
Signed-off-by: Lang Xu <xulang@uniontech.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/279EEE1BA1DDB49D+20260303095217.34436-1-xulang@uniontech.com
---
 kernel/bpf/trampoline.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 84db9e658e52..f02254a21585 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1002,10 +1002,8 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
 	mutex_lock(&tr->mutex);
 
 	shim_link = cgroup_shim_find(tr, bpf_func);
-	if (shim_link) {
+	if (shim_link && !IS_ERR(bpf_link_inc_not_zero(&shim_link->link.link))) {
 		/* Reusing existing shim attached by the other program. */
-		bpf_link_inc(&shim_link->link.link);
-
 		mutex_unlock(&tr->mutex);
 		bpf_trampoline_put(tr); /* bpf_trampoline_get above */
 		return 0;

From 12c43a062acb0ac137fc2a4a106d4d084b8c5416 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:11 +0000
Subject: [PATCH 0743/1303] smb/client: fix buffer size for smb311_posix_qinfo
 in smb2_compound_op()

Use `sizeof(struct smb311_posix_qinfo)` instead of sizeof its pointer,
so the allocated buffer matches the actual struct size.

Fixes: 6a5f6592a0b6 ("SMB311: Add support for query info using posix extensions (level 100)")
Reported-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 195a38fd61e8..1c4663ed7e69 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -325,7 +325,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 							  cfile->fid.volatile_fid,
 							  SMB_FIND_FILE_POSIX_INFO,
 							  SMB2_O_INFO_FILE, 0,
-							  sizeof(struct smb311_posix_qinfo *) +
+							  sizeof(struct smb311_posix_qinfo) +
 							  (PATH_MAX * 2) +
 							  (sizeof(struct smb_sid) * 2), 0, NULL);
 			} else {
@@ -335,7 +335,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 							  COMPOUND_FID,
 							  SMB_FIND_FILE_POSIX_INFO,
 							  SMB2_O_INFO_FILE, 0,
-							  sizeof(struct smb311_posix_qinfo *) +
+							  sizeof(struct smb311_posix_qinfo) +
 							  (PATH_MAX * 2) +
 							  (sizeof(struct smb_sid) * 2), 0, NULL);
 			}

From 9621b996e4db1dbc2b3dc5d5910b7d6179397320 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:12 +0000
Subject: [PATCH 0744/1303] smb/client: fix buffer size for smb311_posix_qinfo
 in SMB311_posix_query_info()

SMB311_posix_query_info() is currently unused, but it may still be used in
some stable versions, so these changes are submitted as a separate patch.

Use `sizeof(struct smb311_posix_qinfo)` instead of sizeof its pointer,
so the allocated buffer matches the actual struct size.

Fixes: b1bc1874b885 ("smb311: Add support for SMB311 query info (non-compounded)")
Reported-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 04e361ed2356..8a1fcc097606 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3996,7 +3996,7 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			u64 persistent_fid, u64 volatile_fid,
 			struct smb311_posix_qinfo *data, u32 *plen)
 {
-	size_t output_len = sizeof(struct smb311_posix_qinfo *) +
+	size_t output_len = sizeof(struct smb311_posix_qinfo) +
 			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);
 	*plen = 0;
 

From 8098179dc981c361c4ff238bc3935329a93bbdfb Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:13 +0000
Subject: [PATCH 0745/1303] smb/client: remove unused SMB311_posix_query_info()

It is currently unused, as now we are doing compounding instead
(see smb2_query_path_info()).

Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c   | 18 ------------------
 fs/smb/client/smb2proto.h |  3 ---
 2 files changed, 21 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 8a1fcc097606..c43ca74e8704 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3989,24 +3989,6 @@ int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			  NULL);
 }
 
-#if 0
-/* currently unused, as now we are doing compounding instead (see smb311_posix_query_path_info) */
-int
-SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
-			u64 persistent_fid, u64 volatile_fid,
-			struct smb311_posix_qinfo *data, u32 *plen)
-{
-	size_t output_len = sizeof(struct smb311_posix_qinfo) +
-			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);
-	*plen = 0;
-
-	return query_info(xid, tcon, persistent_fid, volatile_fid,
-			  SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0,
-			  output_len, sizeof(struct smb311_posix_qinfo), (void **)&data, plen);
-	/* Note caller must free "data" (passed in above). It may be allocated in query_info call */
-}
-#endif
-
 int
 SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 	       u64 persistent_fid, u64 volatile_fid,
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 881e42cf66ce..230bb1e9f4e1 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -167,9 +167,6 @@ int SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst,
 		    struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 		    u64 persistent_fid, u64 volatile_fid);
 void SMB2_flush_free(struct smb_rqst *rqst);
-int SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
-			    u64 persistent_fid, u64 volatile_fid,
-			    struct smb311_posix_qinfo *data, u32 *plen);
 int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 		    u64 persistent_fid, u64 volatile_fid,
 		    struct smb2_file_all_info *data);

From 3ac88a9948792b092a4b11323e2abd1ecbe0cc68 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 24 Feb 2026 11:25:34 +0900
Subject: [PATCH 0746/1303] rust: str: make NullTerminatedFormatter public

If `CONFIG_BLOCK` is disabled, the following warnings are displayed
during build:

  warning: struct `NullTerminatedFormatter` is never constructed
    --> ../rust/kernel/str.rs:667:19
      |
  667 | pub(crate) struct NullTerminatedFormatter<'a> {
      |                   ^^^^^^^^^^^^^^^^^^^^^^^
      |
      = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default

  warning: associated function `new` is never used
    --> ../rust/kernel/str.rs:673:19
      |
  671 | impl<'a> NullTerminatedFormatter<'a> {
      | ------------------------------------ associated function in this implementation
  672 |     /// Create a new [`Self`] instance.
  673 |     pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {

Fix them by making `NullTerminatedFormatter` public, as it could be
useful for drivers anyway.

Fixes: cdde7a1951ff ("rust: str: introduce `NullTerminatedFormatter`")
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260224-nullterminatedformatter-v1-1-5bef7b9b3d4c@nvidia.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/str.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index fa87779d2253..3f8918764640 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -664,13 +664,13 @@ fn write_str(&mut self, s: &str) -> fmt::Result {
 ///
 /// * The first byte of `buffer` is always zero.
 /// * The length of `buffer` is at least 1.
-pub(crate) struct NullTerminatedFormatter<'a> {
+pub struct NullTerminatedFormatter<'a> {
     buffer: &'a mut [u8],
 }
 
 impl<'a> NullTerminatedFormatter<'a> {
     /// Create a new [`Self`] instance.
-    pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {
+    pub fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {
         *(buffer.first_mut()?) = 0;
 
         // INVARIANT:

From 2ffb4f5c2ccb2fa1c049dd11899aee7967deef5a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 1 Mar 2026 11:45:48 -0800
Subject: [PATCH 0747/1303] ipv6: fix NULL pointer deref in
 ip6_rt_get_dev_rcu()

l3mdev_master_dev_rcu() can return NULL when the slave device is being
un-slaved from a VRF. All other callers deal with this, but we lost
the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu()
with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on
device with address").

  KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f]
  RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418)
  Call Trace:
   ip6_pol_route (net/ipv6/route.c:2318)
   fib6_rule_lookup (net/ipv6/fib6_rules.c:115)
   ip6_route_output_flags (net/ipv6/route.c:2607)
   vrf_process_v6_outbound (drivers/net/vrf.c:437)

I was tempted to rework the un-slaving code to clear the flag first
and insert synchronize_rcu() before we remove the upper. But looks like
the explicit fallback to loopback_dev is an established pattern.
And I guess avoiding the synchronize_rcu() is nice, too.

Fixes: 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address")
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260301194548.927324-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 85df25c36409..7db0c837196c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
 		 */
 		if (netif_is_l3_slave(dev) &&
 		    !rt6_need_strict(&res->f6i->fib6_dst.addr))
-			dev = l3mdev_master_dev_rcu(dev);
+			dev = l3mdev_master_dev_rcu(dev) ? :
+			      dev_net(dev)->loopback_dev;
 		else if (!netif_is_l3_master(dev))
 			dev = dev_net(dev)->loopback_dev;
 		/* last case is netif_is_l3_master(dev) is true in which

From 67edfec516d30d3e62925c397be4a1e5185802fc Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 12:36:00 -0800
Subject: [PATCH 0748/1303] net/tcp-ao: Fix MAC comparison to be constant-time

To prevent timing attacks, MACs need to be compared in constant
time.  Use the appropriate helper function for this.

Fixes: 0a3a809089eb ("net/tcp: Verify inbound TCP-AO signed segments")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20260302203600.13561-1-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/Kconfig  | 1 +
 net/ipv4/tcp_ao.c | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index b71c22475c51..3ab6247be585 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -748,6 +748,7 @@ config TCP_SIGPOOL
 config TCP_AO
 	bool "TCP: Authentication Option (RFC5925)"
 	select CRYPTO
+	select CRYPTO_LIB_UTILS
 	select TCP_SIGPOOL
 	depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64)
 	help
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 4980caddb0fc..a97cdf3e6af4 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) "TCP: " fmt
 
 #include <crypto/hash.h>
+#include <crypto/utils.h>
 #include <linux/inetdevice.h>
 #include <linux/tcp.h>
 
@@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb,
 	/* XXX: make it per-AF callback? */
 	tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key,
 			(phash - (u8 *)th), sne);
-	if (memcmp(phash, hash_buf, maclen)) {
+	if (crypto_memneq(phash, hash_buf, maclen)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
 		atomic64_inc(&info->counters.pkt_bad);
 		atomic64_inc(&key->pkt_bad);

From 4ee7fa6cf78ff26d783d39e2949d14c4c1cd5e7f Mon Sep 17 00:00:00 2001
From: Yung Chih Su <yuuchihsu@gmail.com>
Date: Mon, 2 Mar 2026 14:02:47 +0800
Subject: [PATCH 0749/1303] net: ipv4: fix ARM64 alignment fault in multipath
 hash seed

`struct sysctl_fib_multipath_hash_seed` contains two u32 fields
(user_seed and mp_seed), making it an 8-byte structure with a 4-byte
alignment requirement.

In `fib_multipath_hash_from_keys()`, the code evaluates the entire
struct atomically via `READ_ONCE()`:

    mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;

While this silently works on GCC by falling back to unaligned regular
loads which the ARM64 kernel tolerates, it causes a fatal kernel panic
when compiled with Clang and LTO enabled.

Commit e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire
when CONFIG_LTO=y") strengthens `READ_ONCE()` to use Load-Acquire
instructions (`ldar` / `ldapr`) to prevent compiler reordering bugs
under Clang LTO. Since the macro evaluates the full 8-byte struct,
Clang emits a 64-bit `ldar` instruction. ARM64 architecture strictly
requires `ldar` to be naturally aligned, thus executing it on a 4-byte
aligned address triggers a strict Alignment Fault (FSC = 0x21).

Fix the read side by moving the `READ_ONCE()` directly to the `u32`
member, which emits a safe 32-bit `ldar Wn`.

Furthermore, Eric Dumazet pointed out that `WRITE_ONCE()` on the entire
struct in `proc_fib_multipath_hash_set_seed()` is also flawed. Analysis
shows that Clang splits this 8-byte write into two separate 32-bit
`str` instructions. While this avoids an alignment fault, it destroys
atomicity and exposes a tear-write vulnerability. Fix this by
explicitly splitting the write into two 32-bit `WRITE_ONCE()`
operations.

Finally, add the missing `READ_ONCE()` when reading `user_seed` in
`proc_fib_multipath_hash_seed()` to ensure proper pairing and
concurrency safety.

Fixes: 4ee2a8cace3f ("net: ipv4: Add a sysctl to set multipath hash seed")
Signed-off-by: Yung Chih Su <yuuchihsu@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260302060247.7066-1-yuuchihsu@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_fib.h       | 2 +-
 net/ipv4/sysctl_net_ipv4.c | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b4495c38e0a0..318593743b6e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net,
 	siphash_aligned_key_t hash_key;
 	u32 mp_seed;
 
-	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;
+	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed);
 	fib_multipath_hash_construct_key(&hash_key, mp_seed);
 
 	return flow_hash_from_keys_seed(keys, &hash_key);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 643763bc2142..5654cc9c8a0b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed)
 			    proc_fib_multipath_hash_rand_seed),
 	};
 
-	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new);
+	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed);
+	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed);
 }
 
 static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write,
@@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write
 	int ret;
 
 	mphs = &net->ipv4.sysctl_fib_multipath_hash_seed;
-	user_seed = mphs->user_seed;
+	user_seed = READ_ONCE(mphs->user_seed);
 
 	tmp = *table;
 	tmp.data = &user_seed;

From 5af6e8b54927f7a8d3c7fd02b1bdc09e93d5c079 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 2 Mar 2026 03:40:46 -0800
Subject: [PATCH 0750/1303] netconsole: fix sysdata_release_enabled_show
 checking wrong flag

sysdata_release_enabled_show() checks SYSDATA_TASKNAME instead of
SYSDATA_RELEASE, causing the configfs release_enabled attribute to
reflect the taskname feature state rather than the release feature
state. This is a copy-paste error from the adjacent
sysdata_taskname_enabled_show() function.

The corresponding _store function already uses the correct
SYSDATA_RELEASE flag.

Fixes: 343f90227070 ("netconsole: implement configfs for release_enabled")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260302-sysdata_release_fix-v1-1-e5090f677c7c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 2db116fb1a7c..3c9acd6e49e8 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -617,7 +617,7 @@ static ssize_t sysdata_release_enabled_show(struct config_item *item,
 	bool release_enabled;
 
 	dynamic_netconsole_mutex_lock();
-	release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME);
+	release_enabled = !!(nt->sysdata_fields & SYSDATA_RELEASE);
 	dynamic_netconsole_mutex_unlock();
 
 	return sysfs_emit(buf, "%d\n", release_enabled);

From e2f27363aa6d983504c6836dd0975535e2e9dba0 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Mon, 2 Mar 2026 09:51:24 +0530
Subject: [PATCH 0751/1303] amd-xgbe: fix sleep while atomic on suspend/resume

The xgbe_powerdown() and xgbe_powerup() functions use spinlocks
(spin_lock_irqsave) while calling functions that may sleep:
- napi_disable() can sleep waiting for NAPI polling to complete
- flush_workqueue() can sleep waiting for pending work items

This causes a "BUG: scheduling while atomic" error during suspend/resume
cycles on systems using the AMD XGBE Ethernet controller.

The spinlock protection in these functions is unnecessary as these
functions are called from suspend/resume paths which are already serialized
by the PM core

Fix this by removing the spinlock. Since only code that takes this lock
is xgbe_powerdown() and xgbe_powerup(), remove it completely.

Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260302042124.1386445-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c  | 10 ----------
 drivers/net/ethernet/amd/xgbe/xgbe-main.c |  1 -
 drivers/net/ethernet/amd/xgbe/xgbe.h      |  3 ---
 3 files changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 62bb4b8a68e1..8b79d88480db 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1120,7 +1120,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	unsigned long flags;
 
 	DBGPR("-->xgbe_powerdown\n");
 
@@ -1131,8 +1130,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&pdata->lock, flags);
-
 	if (caller == XGMAC_DRIVER_CONTEXT)
 		netif_device_detach(netdev);
 
@@ -1148,8 +1145,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 
 	pdata->power_down = 1;
 
-	spin_unlock_irqrestore(&pdata->lock, flags);
-
 	DBGPR("<--xgbe_powerdown\n");
 
 	return 0;
@@ -1159,7 +1154,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	unsigned long flags;
 
 	DBGPR("-->xgbe_powerup\n");
 
@@ -1170,8 +1164,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&pdata->lock, flags);
-
 	pdata->power_down = 0;
 
 	xgbe_napi_enable(pdata, 0);
@@ -1186,8 +1178,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 
 	xgbe_start_timers(pdata);
 
-	spin_unlock_irqrestore(&pdata->lock, flags);
-
 	DBGPR("<--xgbe_powerup\n");
 
 	return 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d1f0419edb23..7d45ea22a02e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -76,7 +76,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev)
 	pdata->netdev = netdev;
 	pdata->dev = dev;
 
-	spin_lock_init(&pdata->lock);
 	spin_lock_init(&pdata->xpcs_lock);
 	mutex_init(&pdata->rss_mutex);
 	spin_lock_init(&pdata->tstamp_lock);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 1269b8ce9249..e1d7d7150e16 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1004,9 +1004,6 @@ struct xgbe_prv_data {
 	unsigned int pp3;
 	unsigned int pp4;
 
-	/* Overall device lock */
-	spinlock_t lock;
-
 	/* XPCS indirect addressing lock */
 	spinlock_t xpcs_lock;
 	unsigned int xpcs_window_def_reg;

From 7f5d8e63f3d4dc952548502a2227de780cbcd21f Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 2 Mar 2026 11:50:20 -0800
Subject: [PATCH 0752/1303] MAINTAINERS: update the skge/sky2 maintainers

Mark the skge and sky2 drivers as orphan.
I no longer have any Marvell/SysKonnect boards to test with and
mail to Mirko Lindner bounced because Marvell sold off that divsion.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://patch.msgid.link/20260302195120.187183-1-stephen@networkplumber.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7829ff2180ae..bee85351120e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15372,10 +15372,8 @@ F:	drivers/crypto/marvell/
 F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
-M:	Mirko Lindner <mlindner@marvell.com>
-M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netdev@vger.kernel.org
-S:	Odd fixes
+S:	Orphan
 F:	drivers/net/ethernet/marvell/sk*
 
 MARVELL LIBERTAS WIRELESS DRIVER

From 46d0d6f50dab706637f4c18a470aac20a21900d3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 12:34:09 -0800
Subject: [PATCH 0753/1303] net/tcp-md5: Fix MAC comparison to be constant-time

To prevent timing attacks, MACs need to be compared in constant
time.  Use the appropriate helper function for this.

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Fixes: 658ddaaf6694 ("tcp: md5: RST: getting md5 key from listener")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Link: https://patch.msgid.link/20260302203409.13388-1-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/Kconfig    | 1 +
 net/ipv4/tcp.c      | 3 ++-
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 3 ++-
 4 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 3ab6247be585..df922f9f5289 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -762,6 +762,7 @@ config TCP_AO
 config TCP_MD5SIG
 	bool "TCP: MD5 Signature Option support (RFC2385)"
 	select CRYPTO_LIB_MD5
+	select CRYPTO_LIB_UTILS
 	help
 	  RFC2385 specifies a method of giving MD5 protection to TCP sessions.
 	  Its main (only?) use is to protect BGP sessions between core routers
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8cdc26e8ad68..202a4e57a218 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -244,6 +244,7 @@
 #define pr_fmt(fmt) "TCP: " fmt
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -4970,7 +4971,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 	else
 		tp->af_specific->calc_md5_hash(newhash, key, NULL, skb);
-	if (memcmp(hash_location, newhash, 16) != 0) {
+	if (crypto_memneq(hash_location, newhash, 16)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
 		trace_tcp_hash_md5_mismatch(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d53d39be291a..910c25cb24e1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -88,6 +88,7 @@
 #include <linux/skbuff_ref.h>
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 
 #include <trace/events/tcp.h>
 
@@ -839,7 +840,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 			goto out;
 
 		tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
-		if (memcmp(md5_hash_location, newhash, 16) != 0)
+		if (crypto_memneq(md5_hash_location, newhash, 16))
 			goto out;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e46a0efae012..5195a46b951e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -68,6 +68,7 @@
 #include <linux/seq_file.h>
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 
 #include <trace/events/tcp.h>
 
@@ -1048,7 +1049,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
 		key.type = TCP_KEY_MD5;
 
 		tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb);
-		if (memcmp(md5_hash_location, newhash, 16) != 0)
+		if (crypto_memneq(md5_hash_location, newhash, 16))
 			goto out;
 	}
 #endif

From 9e7dc228bb6d4afa74dd6bab4f3aad43126cc2db Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Wed, 4 Mar 2026 01:42:57 +0100
Subject: [PATCH 0754/1303] io_uring/mock: Fix typo in help text
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the spelling of "subsystem".

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index e95d43457851..74f07212db85 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1897,7 +1897,7 @@ config IO_URING_MOCK_FILE
 	default n
 	depends on IO_URING
 	help
-	  Enable mock files for io_uring subststem testing. The ABI might
+	  Enable mock files for io_uring subsystem testing. The ABI might
 	  still change, so it's still experimental and should only be enabled
 	  for specific test purposes.
 

From 26bc83b88bbbf054f0980a4a42047a8d1e210e4c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Tue, 17 Feb 2026 20:27:02 -0800
Subject: [PATCH 0755/1303] smb: client: Compare MACs in constant time

To prevent timing attacks, MAC comparisons need to be constant-time.
Replace the memcmp() with the correct function, crypto_memneq().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1encrypt.c   | 3 ++-
 fs/smb/client/smb2transport.c | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb1encrypt.c b/fs/smb/client/smb1encrypt.c
index 0dbbce2431ff..bf10fdeeedca 100644
--- a/fs/smb/client/smb1encrypt.c
+++ b/fs/smb/client/smb1encrypt.c
@@ -11,6 +11,7 @@
 
 #include <linux/fips.h>
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 #include "cifsproto.h"
 #include "smb1proto.h"
 #include "cifs_debug.h"
@@ -131,7 +132,7 @@ int cifs_verify_signature(struct smb_rqst *rqst,
 /*	cifs_dump_mem("what we think it should be: ",
 		      what_we_think_sig_should_be, 16); */
 
-	if (memcmp(server_response_sig, what_we_think_sig_should_be, 8))
+	if (crypto_memneq(server_response_sig, what_we_think_sig_should_be, 8))
 		return -EACCES;
 	else
 		return 0;
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 8b9000a83181..81be2b226e26 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <crypto/aead.h>
 #include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "smb2proto.h"
@@ -617,7 +618,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(server_response_sig, shdr->Signature,
+			  SMB2_SIGNATURE_SIZE)) {
 		cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n",
 			shdr->Command, shdr->MessageId);
 		return -EACCES;

From 6ca8379b5d36e22b04e6315c3e49a6083377c862 Mon Sep 17 00:00:00 2001
From: Shengming Hu <hu.shengming@zte.com.cn>
Date: Sat, 21 Feb 2026 11:30:07 +0800
Subject: [PATCH 0756/1303] fgraph: Fix thresh_return clear per-task notrace

When tracing_thresh is enabled, function graph tracing uses
trace_graph_thresh_return() as the return handler. Unlike
trace_graph_return(), it did not clear the per-task TRACE_GRAPH_NOTRACE
flag set by the entry handler for set_graph_notrace addresses. This could
leave the task permanently in "notrace" state and effectively disable
function graph tracing for that task.

Mirror trace_graph_return()'s per-task notrace handling by clearing
TRACE_GRAPH_NOTRACE and returning early when set.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260221113007819YgrZsMGABff4Rc-O_fZxL@zte.com.cn
Fixes: b84214890a9bc ("function_graph: Move graph notrace bit to shadow stack global var")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3d8239fee004..817d0f1696b6 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -400,14 +400,15 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops,
 				      struct ftrace_regs *fregs)
 {
+	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
 	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
 
-	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
-		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+	if (*task_var & TRACE_GRAPH_NOTRACE) {
+		*task_var &= ~TRACE_GRAPH_NOTRACE;
 		return;
 	}
 

From b96d0c59cdbb2a22b2545f6f3d5c6276b05761dd Mon Sep 17 00:00:00 2001
From: Shengming Hu <hu.shengming@zte.com.cn>
Date: Sat, 21 Feb 2026 11:33:14 +0800
Subject: [PATCH 0757/1303] fgraph: Fix thresh_return nosleeptime double-adjust

trace_graph_thresh_return() called handle_nosleeptime() and then delegated
to trace_graph_return(), which calls handle_nosleeptime() again. When
sleep-time accounting is disabled this double-adjusts calltime and can
produce bogus durations (including underflow).

Fix this by computing rettime once, applying handle_nosleeptime() only
once, using the adjusted calltime for threshold comparison, and writing
the return event directly via __trace_graph_return() when the threshold is
met.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260221113314048jE4VRwIyZEALiYByGK0My@zte.com.cn
Fixes: 3c9880f3ab52b ("ftrace: Use a running sleeptime instead of saving on shadow stack")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 817d0f1696b6..0d2d3a2ea7dd 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -403,8 +403,12 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
+	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	int size;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (*task_var & TRACE_GRAPH_NOTRACE) {
@@ -419,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	tr = gops->private;
 	handle_nosleeptime(tr, trace, ftimes, size);
 
-	if (tracing_thresh &&
-	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
+	calltime = ftimes->calltime;
+
+	if (tracing_thresh && (rettime - calltime < tracing_thresh))
 		return;
-	else
-		trace_graph_return(trace, gops, fregs);
+
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static struct fgraph_ops funcgraph_ops = {

From 0a663b764dbdf135a126284f454c9f01f95a87d4 Mon Sep 17 00:00:00 2001
From: Huiwen He <hehuiwen@kylinos.cn>
Date: Tue, 24 Feb 2026 10:35:44 +0800
Subject: [PATCH 0758/1303] tracing: Fix syscall events activation by ensuring
 refcount hits zero

When multiple syscall events are specified in the kernel command line
(e.g., trace_event=syscalls:sys_enter_openat,syscalls:sys_enter_close),
they are often not captured after boot, even though they appear enabled
in the tracing/set_event file.

The issue stems from how syscall events are initialized. Syscall
tracepoints require the global reference count (sys_tracepoint_refcount)
to transition from 0 to 1 to trigger the registration of the syscall
work (TIF_SYSCALL_TRACEPOINT) for tasks, including the init process (pid 1).

The current implementation of early_enable_events() with disable_first=true
used an interleaved sequence of "Disable A -> Enable A -> Disable B -> Enable B".
If multiple syscalls are enabled, the refcount never drops to zero,
preventing the 0->1 transition that triggers actual registration.

Fix this by splitting early_enable_events() into two distinct phases:
1. Disable all events specified in the buffer.
2. Enable all events specified in the buffer.

This ensures the refcount hits zero before re-enabling, allowing syscall
events to be properly activated during early boot.

The code is also refactored to use a helper function to avoid logic
duplication between the disable and enable phases.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260224023544.1250787-1-hehuiwen@kylinos.cn
Fixes: ce1039bd3a89 ("tracing: Fix enabling of syscall events on the command line")
Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 52 ++++++++++++++++++++++++++-----------
 1 file changed, 37 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9928da636c9d..9c7f26cbe171 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -4668,26 +4668,22 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
-__init void
-early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+/*
+ * Helper function to enable or disable a comma-separated list of events
+ * from the bootup buffer.
+ */
+static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable)
 {
 	char *token;
-	int ret;
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
 
+	while ((token = strsep(&buf, ","))) {
 		if (*token) {
-			/* Restarting syscalls requires that we stop them first */
-			if (disable_first)
+			if (enable) {
+				if (ftrace_set_clr_event(tr, token, 1))
+					pr_warn("Failed to enable trace event: %s\n", token);
+			} else {
 				ftrace_set_clr_event(tr, token, 0);
-
-			ret = ftrace_set_clr_event(tr, token, 1);
-			if (ret)
-				pr_warn("Failed to enable trace event: %s\n", token);
+			}
 		}
 
 		/* Put back the comma to allow this to be called again */
@@ -4696,6 +4692,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
 	}
 }
 
+/**
+ * early_enable_events - enable events from the bootup buffer
+ * @tr: The trace array to enable the events in
+ * @buf: The buffer containing the comma separated list of events
+ * @disable_first: If true, disable all events in @buf before enabling them
+ *
+ * This function enables events from the bootup buffer. If @disable_first
+ * is true, it will first disable all events in the buffer before enabling
+ * them.
+ *
+ * For syscall events, which rely on a global refcount to register the
+ * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must
+ * ensure the refcount hits zero before re-enabling them. A simple
+ * "disable then enable" per-event is not enough if multiple syscalls are
+ * used, as the refcount will stay above zero. Thus, we need a two-phase
+ * approach: disable all, then enable all.
+ */
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+{
+	if (disable_first)
+		__early_set_events(tr, buf, false);
+
+	__early_set_events(tr, buf, true);
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();

From cc337974cd1084f9821179eb66f4e470d9fd2ed8 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 2 Mar 2026 21:35:46 -0500
Subject: [PATCH 0759/1303] ftrace: Disable preemption in the tracepoint
 callbacks handling filtered pids

When function trace PID filtering is enabled, the function tracer will
attach a callback to the fork tracepoint as well as the exit tracepoint
that will add the forked child PID to the PID filtering list as well as
remove the PID that is exiting.

Commit a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of
__DO_TRACE_CALL() with SRCU-fast") removed the disabling of preemption
when calling tracepoint callbacks.

The callbacks used for the PID filtering accounting depended on preemption
being disabled, and now the trigger a "suspicious RCU usage" warning message.

Make them explicitly disable preemption.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260302213546.156e3e4f@gandalf.local.home
Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/ftrace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..2f72af0357e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 

From a5dd6f58666f22ae16b98a2177bebc3340d38fe9 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 3 Mar 2026 21:57:38 -0500
Subject: [PATCH 0760/1303] tracing: Disable preemption in the tracepoint
 callbacks handling filtered pids

Filtering PIDs for events triggered the following during selftests:

[37] event tracing - restricts events based on pid notrace filtering
[  155.874095]
[  155.874869] =============================
[  155.876037] WARNING: suspicious RCU usage
[  155.877287] 7.0.0-rc1-00004-g8cd473a19bc7 #7 Not tainted
[  155.879263] -----------------------------
[  155.882839] kernel/trace/trace_events.c:1057 suspicious rcu_dereference_check() usage!
[  155.889281]
[  155.889281] other info that might help us debug this:
[  155.889281]
[  155.894519]
[  155.894519] rcu_scheduler_active = 2, debug_locks = 1
[  155.898068] no locks held by ftracetest/4364.
[  155.900524]
[  155.900524] stack backtrace:
[  155.902645] CPU: 1 UID: 0 PID: 4364 Comm: ftracetest Not tainted 7.0.0-rc1-00004-g8cd473a19bc7 #7 PREEMPT(lazy)
[  155.902648] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[  155.902651] Call Trace:
[  155.902655]  <TASK>
[  155.902659]  dump_stack_lvl+0x67/0x90
[  155.902665]  lockdep_rcu_suspicious+0x154/0x1a0
[  155.902672]  event_filter_pid_sched_process_fork+0x9a/0xd0
[  155.902678]  kernel_clone+0x367/0x3a0
[  155.902689]  __x64_sys_clone+0x116/0x140
[  155.902696]  do_syscall_64+0x158/0x460
[  155.902700]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  155.902702]  ? trace_irq_disable+0x1d/0xc0
[  155.902709]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  155.902711] RIP: 0033:0x4697c3
[  155.902716] Code: 1f 84 00 00 00 00 00 64 48 8b 04 25 10 00 00 00 45 31 c0 31 d2 31 f6 bf 11 00 20 01 4c 8d 90 d0 02 00 00 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 89 c2 85 c0 75 2c 64 48 8b 04 25 10 00 00
[  155.902718] RSP: 002b:00007ffc41150428 EFLAGS: 00000246 ORIG_RAX: 0000000000000038
[  155.902721] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004697c3
[  155.902722] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011
[  155.902724] RBP: 0000000000000000 R08: 0000000000000000 R09: 000000003fccf990
[  155.902725] R10: 000000003fccd690 R11: 0000000000000246 R12: 0000000000000001
[  155.902726] R13: 000000003fce8103 R14: 0000000000000001 R15: 0000000000000000
[  155.902733]  </TASK>
[  155.902747]

The tracepoint callbacks recently were changed to allow preemption. The
event PID filtering callbacks that were attached to the fork and exit
tracepoints expected preemption disabled in order to access the RCU
protected PID lists.

Add a guard(preempt)() to protect the references to the PID list.

Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260303215738.6ab275af@fedora
Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast")
Link: https://patch.msgid.link/20260303131706.96057f61a48a34c43ce1e396@kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9c7f26cbe171..b7343fdfd7b0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
@@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 

From e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Fri, 27 Feb 2026 10:58:42 +0800
Subject: [PATCH 0761/1303] tracing: Fix WARN_ON in tracing_buffers_mmap_close

When a process forks, the child process copies the parent's VMAs but the
user_mapped reference count is not incremented. As a result, when both the
parent and child processes exit, tracing_buffers_mmap_close() is called
twice. On the second call, user_mapped is already 0, causing the function to
return -ENODEV and triggering a WARN_ON.

Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set.
But this is only a hint, and the application can call
madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the
application does that, it can trigger this issue on fork.

Fix it by incrementing the user_mapped reference count without re-mapping
the pages in the VMA's open callback.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://patch.msgid.link/20260227025842.1085206-1-wangqing7171@gmail.com
Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer")
Reported-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=3b5dd2030fe08afdf65d
Tested-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 21 +++++++++++++++++++++
 kernel/trace/trace.c        | 13 +++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 876358cfe1b1..d862fa610270 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
 
 int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		    struct vm_area_struct *vma);
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f16f053ef77d..17d0ea0cc3e6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23de3719f495..1e7c032a72d2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };

From b9e7e3ea605f23d342c67fc5bded99bcaa32d93b Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 6 Jan 2026 18:40:19 +0100
Subject: [PATCH 0762/1303] powerpc/e500: Always use 64 bits PTE

Today there are two PTE formats for e500:
- The 64 bits format, used
 - On 64 bits kernel
 - On 32 bits kernel with 64 bits physical addresses
 - On 32 bits kernel with support of huge pages
- The 32 bits format, used in other cases

Maintaining two PTE formats means unnecessary maintenance burden
because every change needs to be implemented and tested for both
formats.

Remove the 32 bits PTE format. The memory usage increase due to
larger PTEs is minimal (approx. 0,1% of memory).

This also means that from now on huge pages are supported also
with 32 bits physical addresses.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/04a658209ea78dcc0f3dbde6b2c29cf1939adfe9.1767721208.git.chleroy@kernel.org
---
 arch/powerpc/include/asm/nohash/32/pgtable.h  |  4 +-
 arch/powerpc/include/asm/nohash/32/pte-85xx.h | 59 -------------------
 arch/powerpc/include/asm/pgtable-types.h      |  2 +-
 arch/powerpc/kernel/head_85xx.S               | 46 +--------------
 arch/powerpc/platforms/Kconfig.cputype        |  4 +-
 5 files changed, 5 insertions(+), 110 deletions(-)
 delete mode 100644 arch/powerpc/include/asm/nohash/32/pte-85xx.h

diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 2d71e4b7cd09..496ecc65ac25 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -120,10 +120,8 @@
 
 #if defined(CONFIG_44x)
 #include <asm/nohash/32/pte-44x.h>
-#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
-#include <asm/nohash/pte-e500.h>
 #elif defined(CONFIG_PPC_85xx)
-#include <asm/nohash/32/pte-85xx.h>
+#include <asm/nohash/pte-e500.h>
 #elif defined(CONFIG_PPC_8xx)
 #include <asm/nohash/32/pte-8xx.h>
 #endif
diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
deleted file mode 100644
index 14d64b4f3f14..000000000000
--- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H
-#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H
-#ifdef __KERNEL__
-
-/* PTE bit definitions for Freescale BookE SW loaded TLB MMU based
- * processors
- *
-   MMU Assist Register 3:
-
-   32 33 34 35 36  ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63
-   RPN......................  0  0 U0 U1 U2 U3 UX SX UW SW UR SR
-
-   - PRESENT *must* be in the bottom two bits because swap PTEs use
-     the top 30 bits.
-
-*/
-
-/* Definitions for FSL Book-E Cores */
-#define _PAGE_READ	0x00001	/* H: Read permission (SR) */
-#define _PAGE_PRESENT	0x00002	/* S: PTE contains a translation */
-#define _PAGE_WRITE	0x00004	/* S: Write permission (SW) */
-#define _PAGE_DIRTY	0x00008	/* S: Page dirty */
-#define _PAGE_EXEC	0x00010	/* H: SX permission */
-#define _PAGE_ACCESSED	0x00020	/* S: Page referenced */
-
-#define _PAGE_ENDIAN	0x00040	/* H: E bit */
-#define _PAGE_GUARDED	0x00080	/* H: G bit */
-#define _PAGE_COHERENT	0x00100	/* H: M bit */
-#define _PAGE_NO_CACHE	0x00200	/* H: I bit */
-#define _PAGE_WRITETHRU	0x00400	/* H: W bit */
-#define _PAGE_SPECIAL	0x00800 /* S: Special page */
-
-#define _PMD_PRESENT	0
-#define _PMD_PRESENT_MASK (PAGE_MASK)
-#define _PMD_BAD	(~PAGE_MASK)
-#define _PMD_USER	0
-
-#define _PTE_NONE_MASK	0
-
-#define PTE_WIMGE_SHIFT (6)
-
-/*
- * We define 2 sets of base prot bits, one for basic pages (ie,
- * cacheable kernel and user pages) and one for non cacheable
- * pages. We always set _PAGE_COHERENT when SMP is enabled or
- * the processor might need it for DMA coherency.
- */
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
-#else
-#define _PAGE_BASE	(_PAGE_BASE_NC)
-#endif
-
-#include <asm/pgtable-masks.h>
-
-#endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index f3086e39e7d2..e8dec885b6e4 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -49,7 +49,7 @@ static inline unsigned long pud_val(pud_t x)
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
-#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
+#if defined(CONFIG_PPC_85xx)
 typedef struct { unsigned long long pgd; } pgd_t;
 
 static inline unsigned long long pgd_val(pgd_t x)
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index f9a73fae6464..8867596d35ad 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -305,7 +305,6 @@ set_ivor:
  *   r12 is pointer to the pte
  *   r10 is the pshift from the PGD, if we're a hugepage
  */
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_HUGETLB_PAGE
 #define FIND_PTE	\
 	rlwinm	r12, r13, 14, 18, 28;	/* Compute pgdir/pmd offset */	\
@@ -329,15 +328,6 @@ set_ivor:
 	rlwimi	r12, r13, 23, 20, 28;	/* Compute pte address */	\
 	lwz	r11, 4(r12);		/* Get pte entry */
 #endif /* HUGEPAGE */
-#else /* !PTE_64BIT */
-#define FIND_PTE	\
-	rlwimi	r11, r13, 12, 20, 29;	/* Create L1 (pgdir/pmd) address */	\
-	lwz	r11, 0(r11);		/* Get L1 entry */			\
-	rlwinm.	r12, r11, 0, 0, 19;	/* Extract L2 (pte) base address */	\
-	beq	2f;			/* Bail if no table */			\
-	rlwimi	r12, r13, 22, 20, 29;	/* Compute PTE address */		\
-	lwz	r11, 0(r12);		/* Get Linux PTE */
-#endif
 
 /*
  * Interrupt vector entry code
@@ -473,21 +463,15 @@ END_BTB_FLUSH_SECTION
 4:
 	FIND_PTE
 
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT|_PAGE_BAP_SR
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED
-#endif
 	andc.	r13,r13,r11		/* Check permission */
 
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
 	subf	r13,r11,r12		/* create false data dep */
 	lwzx	r13,r11,r13		/* Get upper pte bits */
 #else
 	lwz	r13,0(r12)		/* Get upper pte bits */
-#endif
 #endif
 
 	bne	2f			/* Bail if permission/valid mismatch */
@@ -552,12 +536,8 @@ END_BTB_FLUSH_SECTION
 
 	FIND_PTE
 	/* Make up the required permissions for kernel code */
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_SX
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#endif
 	b	4f
 
 	/* Get the PGD for the current thread */
@@ -573,23 +553,17 @@ END_BTB_FLUSH_SECTION
 
 	FIND_PTE
 	/* Make up the required permissions for user code */
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_UX
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#endif
 
 4:
 	andc.	r13,r13,r11		/* Check permission */
 
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
 	subf	r13,r11,r12		/* create false data dep */
 	lwzx	r13,r11,r13		/* Get upper pte bits */
 #else
 	lwz	r13,0(r12)		/* Get upper pte bits */
-#endif
 #endif
 
 	bne	2f			/* Bail if permission mismatch */
@@ -683,7 +657,7 @@ interrupt_end:
  *	r10 - tsize encoding (if HUGETLB_PAGE) or available to use
  *	r11 - TLB (info from Linux PTE)
  *	r12 - available to use
- *	r13 - upper bits of PTE (if PTE_64BIT) or available to use
+ *	r13 - upper bits of PTE
  *	CR5 - results of addr >= PAGE_OFFSET
  *	MAS0, MAS1 - loaded with proper value when we get here
  *	MAS2, MAS3 - will need additional info from Linux PTE
@@ -751,7 +725,6 @@ finish_tlb_load:
 	 * here we (properly should) assume have the appropriate value.
 	 */
 finish_tlb_load_cont:
-#ifdef CONFIG_PTE_64BIT
 	rlwinm	r12, r11, 32-2, 26, 31	/* Move in perm bits */
 	andi.	r10, r11, _PAGE_DIRTY
 	bne	1f
@@ -764,26 +737,9 @@ BEGIN_MMU_FTR_SECTION
 	srwi	r10, r13, 12		/* grab RPN[12:31] */
 	mtspr	SPRN_MAS7, r10
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
-#else
-	li	r10, (_PAGE_EXEC | _PAGE_READ)
-	mr	r13, r11
-	rlwimi	r10, r11, 31, 29, 29	/* extract _PAGE_DIRTY into SW */
-	and	r12, r11, r10
-	mcrf	cr0, cr5		/* Test for user page */
-	slwi	r10, r12, 1
-	or	r10, r10, r12
-	rlwinm	r10, r10, 0, ~_PAGE_EXEC	/* Clear SX on user pages */
-	isellt	r12, r10, r12
-	rlwimi	r13, r12, 0, 20, 31	/* Get RPN from PTE, merge w/ perms */
-	mtspr	SPRN_MAS3, r13
-#endif
 
 	mfspr	r12, SPRN_MAS2
-#ifdef CONFIG_PTE_64BIT
 	rlwimi	r12, r11, 32-19, 27, 31	/* extract WIMGE from pte */
-#else
-	rlwimi	r12, r11, 26, 27, 31	/* extract WIMGE from pte */
-#endif
 #ifdef CONFIG_HUGETLB_PAGE
 	beq	6, 3f			/* don't mask if page isn't huge */
 	li	r13, 1
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index f399917c17bd..bac02c83bb3e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -276,7 +276,7 @@ config PPC_BOOK3S
 config PPC_E500
 	select FSL_EMB_PERFMON
 	bool
-	select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
+	select ARCH_SUPPORTS_HUGETLBFS
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
 	select PPC_KUEP
@@ -337,7 +337,7 @@ config BOOKE
 config PTE_64BIT
 	bool
 	depends on 44x || PPC_E500 || PPC_86xx
-	default y if PHYS_64BIT
+	default y if PPC_E500 || PHYS_64BIT
 
 config PHYS_64BIT
 	bool 'Large physical address support' if PPC_E500 || PPC_86xx

From 0ee95a1d458630272d0415d0ffa9424fcb606c90 Mon Sep 17 00:00:00 2001
From: "Christophe Leroy (CS GROUP)" <chleroy@kernel.org>
Date: Tue, 3 Feb 2026 08:30:41 +0100
Subject: [PATCH 0763/1303] powerpc/uaccess: Fix inline assembly for clang
 build on PPC32

Test robot reports the following error with clang-16.0.6:

   In file included from kernel/rseq.c:75:
   include/linux/rseq_entry.h:141:3: error: invalid operand for instruction
                   unsafe_get_user(offset, &ucs->post_commit_offset, efault);
                   ^
   include/linux/uaccess.h:608:2: note: expanded from macro 'unsafe_get_user'
           arch_unsafe_get_user(x, ptr, local_label);      \
           ^
   arch/powerpc/include/asm/uaccess.h:518:2: note: expanded from macro 'arch_unsafe_get_user'
           __get_user_size_goto(__gu_val, __gu_addr, sizeof(*(p)), e); \
           ^
   arch/powerpc/include/asm/uaccess.h:284:2: note: expanded from macro '__get_user_size_goto'
           __get_user_size_allowed(x, ptr, size, __gus_retval);    \
           ^
   arch/powerpc/include/asm/uaccess.h:275:10: note: expanded from macro '__get_user_size_allowed'
           case 8: __get_user_asm2(x, (u64 __user *)ptr, retval);  break;  \
                   ^
   arch/powerpc/include/asm/uaccess.h:258:4: note: expanded from macro '__get_user_asm2'
                   "       li %1+1,0\n"                    \
                    ^
   <inline asm>:7:5: note: instantiated into assembly here
           li 31+1,0
              ^
   1 error generated.

On PPC32, for 64 bits vars a pair of registers is used. Usually the
lower register in the pair is the high part and the higher register is
the low part. GCC uses r3/r4 ... r11/r12 ... r14/r15 ... r30/r31

In older kernel code inline assembly was using %1 and %1+1 to represent
64 bits values. However here it looks like clang uses r31 as high part,
allthough r32 doesn't exist hence the error.

Allthoug %1+1 should work, most places now use %L1 instead of %1+1, so
let's do the same here.

With that change, the build doesn't fail anymore and a disassembly shows
clang uses r17/r18 and r31/r14 pair when GCC would have used r16/r17 and
r30/r31:

	Disassembly of section .fixup:

	00000000 <.fixup>:
	   0:	38 a0 ff f2 	li      r5,-14
	   4:	3a 20 00 00 	li      r17,0
	   8:	3a 40 00 00 	li      r18,0
	   c:	48 00 00 00 	b       c <.fixup+0xc>
				c: R_PPC_REL24	.text+0xbc
	  10:	38 a0 ff f2 	li      r5,-14
	  14:	3b e0 00 00 	li      r31,0
	  18:	39 c0 00 00 	li      r14,0
	  1c:	48 00 00 00 	b       1c <.fixup+0x1c>
				1c: R_PPC_REL24	.text+0x144

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602021825.otcItxGi-lkp@intel.com/
Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()")
Signed-off-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Acked-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/8ca3a657a650e497a96bfe7acde2f637dadab344.1770103646.git.chleroy@kernel.org
---
 arch/powerpc/include/asm/uaccess.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index ba1d878c3f40..570b3d91e2e4 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -255,7 +255,7 @@ __gus_failed:								\
 		".section .fixup,\"ax\"\n"		\
 		"4:	li %0,%3\n"			\
 		"	li %1,0\n"			\
-		"	li %1+1,0\n"			\
+		"	li %L1,0\n"			\
 		"	b 3b\n"				\
 		".previous\n"				\
 		EX_TABLE(1b, 4b)			\

From 0706178339974d4332a782ba851cb6694bd210fe Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 28 Jan 2026 08:02:20 -0600
Subject: [PATCH 0764/1303] powerpc: dts: fsl: Drop unused .dtsi files

These files are not included by anything and therefore don't get built or
tested.

There's also no upstream driver for the interlaken-lac stuff.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260128140222.1627203-1-robh@kernel.org
---
 .../boot/dts/fsl/interlaken-lac-portals.dtsi  | 156 ------------------
 arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi |  45 -----
 .../boot/dts/fsl/pq3-mpic-message-B.dtsi      |  43 -----
 .../fsl/qoriq-fman3-0-10g-1-best-effort.dtsi  |  80 ---------
 4 files changed, 324 deletions(-)
 delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi

diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
deleted file mode 100644
index 9cffccf4e07e..000000000000
--- a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
+++ /dev/null
@@ -1,156 +0,0 @@
-/* T4240 Interlaken LAC Portal device tree stub with 24 portals.
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#address-cells = <0x1>;
-#size-cells = <0x1>;
-compatible = "fsl,interlaken-lac-portals";
-
-lportal0: lac-portal@0 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x0 0x1000>;
-};
-
-lportal1: lac-portal@1000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x1000 0x1000>;
-};
-
-lportal2: lac-portal@2000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x2000 0x1000>;
-};
-
-lportal3: lac-portal@3000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x3000 0x1000>;
-};
-
-lportal4: lac-portal@4000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x4000 0x1000>;
-};
-
-lportal5: lac-portal@5000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x5000 0x1000>;
-};
-
-lportal6: lac-portal@6000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x6000 0x1000>;
-};
-
-lportal7: lac-portal@7000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x7000 0x1000>;
-};
-
-lportal8: lac-portal@8000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x8000 0x1000>;
-};
-
-lportal9: lac-portal@9000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x9000 0x1000>;
-};
-
-lportal10: lac-portal@A000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xA000 0x1000>;
-};
-
-lportal11: lac-portal@B000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xB000 0x1000>;
-};
-
-lportal12: lac-portal@C000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xC000 0x1000>;
-};
-
-lportal13: lac-portal@D000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xD000 0x1000>;
-};
-
-lportal14: lac-portal@E000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xE000 0x1000>;
-};
-
-lportal15: lac-portal@F000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xF000 0x1000>;
-};
-
-lportal16: lac-portal@10000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x10000 0x1000>;
-};
-
-lportal17: lac-portal@11000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x11000 0x1000>;
-};
-
-lportal18: lac-portal@1200 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x12000 0x1000>;
-};
-
-lportal19: lac-portal@13000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x13000 0x1000>;
-};
-
-lportal20: lac-portal@14000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x14000 0x1000>;
-};
-
-lportal21: lac-portal@15000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x15000 0x1000>;
-};
-
-lportal22: lac-portal@16000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x16000 0x1000>;
-};
-
-lportal23: lac-portal@17000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x17000 0x1000>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
deleted file mode 100644
index e8208720ac0e..000000000000
--- a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * T4 Interlaken Look-aside Controller (LAC) device tree stub
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-lac: lac@229000 {
-	compatible = "fsl,interlaken-lac";
-	reg = <0x229000 0x1000>;
-	interrupts = <16 2 1 18>;
-};
-
-lac-hv@228000 {
-	compatible = "fsl,interlaken-lac-hv";
-	reg = <0x228000 0x1000>;
-	fsl,non-hv-node = <&lac>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi b/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
deleted file mode 100644
index 1cf0b77b1efe..000000000000
--- a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * PQ3 MPIC Message (Group B) device tree stub [ controller @ offset 0x42400 ]
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-message@42400 {
-	compatible = "fsl,mpic-v3.1-msgr";
-	reg = <0x42400 0x200>;
-	interrupts = <
-		0xb4 2 0 0
-		0xb5 2 0 0
-		0xb6 2 0 0
-		0xb7 2 0 0>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
deleted file mode 100644
index 71eb75e82c2e..000000000000
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * QorIQ FMan v3 1g port #1 device tree stub [ controller @ offset 0x400000 ]
- *
- * Copyright 2012 - 2015 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *	 notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *	 notice, this list of conditions and the following disclaimer in the
- *	 documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *	 names of its contributors may be used to endorse or promote products
- *	 derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-fman@400000 {
-	fman0_rx_0x09: port@89000 {
-		cell-index = <0x9>;
-		compatible = "fsl,fman-v3-port-rx";
-		reg = <0x89000 0x1000>;
-		fsl,fman-10g-port;
-		fsl,fman-best-effort-port;
-	};
-
-	fman0_tx_0x29: port@a9000 {
-		cell-index = <0x29>;
-		compatible = "fsl,fman-v3-port-tx";
-		reg = <0xa9000 0x1000>;
-		fsl,fman-10g-port;
-		fsl,fman-best-effort-port;
-	};
-
-	ethernet@e2000 {
-		cell-index = <1>;
-		compatible = "fsl,fman-memac";
-		reg = <0xe2000 0x1000>;
-		fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>;
-		ptp-timer = <&ptp_timer0>;
-		pcsphy-handle = <&pcsphy1>, <&qsgmiia_pcs1>;
-		pcs-handle-names = "sgmii", "qsgmii";
-	};
-
-	mdio@e1000 {
-		qsgmiia_pcs1: ethernet-pcs@1 {
-			compatible = "fsl,lynx-pcs";
-			reg = <1>;
-		};
-	};
-
-	mdio@e3000 {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
-		reg = <0xe3000 0x1000>;
-		fsl,erratum-a011043; /* must ignore read errors */
-
-		pcsphy1: ethernet-phy@0 {
-			reg = <0x0>;
-		};
-	};
-};

From 6fc5d63c6ff5fe5e5beea3e7fe2ca3058351ae99 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 29 Oct 2025 12:40:46 -0500
Subject: [PATCH 0765/1303] powerpc/prom_init: Fixup missing #size-cells on
 PowerMac media-bay nodes

Similar to other PowerMac mac-io devices, the media-bay node is missing the
"#size-cells" property.

Depends-on: commit 045b14ca5c36 ("of: WARN on deprecated #address-cells/#size-cells handling")
Reported-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20251029174047.1620073-1-robh@kernel.org
---
 arch/powerpc/kernel/prom_init.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 827c958677f8..f26e80cbc615 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2893,7 +2893,8 @@ static void __init fixup_device_tree_pmac(void)
 	for (node = 0; prom_next_node(&node); ) {
 		type[0] = '\0';
 		prom_getprop(node, "device_type", type, sizeof(type));
-		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s"))
+		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s") &&
+		    prom_strcmp(type, "media-bay"))
 			continue;
 
 		if (prom_getproplen(node, "#size-cells") != PROM_ERROR)

From 20197b967a6a29dab81495f25a988515bda84cfe Mon Sep 17 00:00:00 2001
From: Sourabh Jain <sourabhjain@linux.ibm.com>
Date: Wed, 24 Dec 2025 20:42:57 +0530
Subject: [PATCH 0766/1303] powerpc/kexec/core: use big-endian types for crash
 variables

Use explicit word-sized big-endian types for kexec and crash related
variables. This makes the endianness unambiguous and avoids type
mismatches that trigger sparse warnings.

The change addresses sparse warnings like below (seen on both 32-bit
and 64-bit builds):

CHECK   ../arch/powerpc/kexec/core.c
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] crashk_base
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] crashk_size
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned long long static [addressable] [toplevel] mem_limit
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] kernel_end
sparse:    got restricted __be32 [usertype]

No functional change intended.

Fixes: ea961a828fe7 ("powerpc: Fix endian issues in kexec and crash dump code")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202512221405.VHPKPjnp-lkp@intel.com/
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20251224151257.28672-1-sourabhjain@linux.ibm.com
---
 arch/powerpc/kexec/core.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 104c05520bf0..dc44f11be353 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -23,6 +23,7 @@
 #include <asm/firmware.h>
 
 #define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
+#define __be_word __PASTE(__be, BITS_PER_LONG)
 
 #ifdef CONFIG_CRASH_DUMP
 void machine_crash_shutdown(struct pt_regs *regs)
@@ -146,25 +147,25 @@ int __init overlaps_crashkernel(unsigned long start, unsigned long size)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static phys_addr_t crashk_base;
-static phys_addr_t crashk_size;
-static unsigned long long mem_limit;
+static __be_word crashk_base;
+static __be_word crashk_size;
+static __be_word mem_limit;
 
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
 	.name = "linux,crashkernel-size",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &crashk_size,
 };
 
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
-	.length = sizeof(unsigned long long),
+	.length = sizeof(__be_word),
 	.value = &mem_limit,
 };
 
@@ -193,11 +194,11 @@ static void __init export_crashk_values(struct device_node *node)
 }
 #endif /* CONFIG_CRASH_RESERVE */
 
-static phys_addr_t kernel_end;
+static __be_word kernel_end;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &kernel_end,
 };
 

From 04e707cb77c272cb0bb2e2e3c5c7f844d804a089 Mon Sep 17 00:00:00 2001
From: Sourabh Jain <sourabhjain@linux.ibm.com>
Date: Fri, 27 Feb 2026 22:48:01 +0530
Subject: [PATCH 0767/1303] powerpc/crash: adjust the elfcorehdr size

With crash hotplug support enabled, additional memory is allocated to
the elfcorehdr kexec segment to accommodate resources added during
memory hotplug events. However, the kdump FDT is not updated with the
same size, which can result in elfcorehdr corruption in the kdump
kernel.

Update elf_headers_sz (the kimage member representing the size of the
elfcorehdr kexec segment) to reflect the total memory allocated for the
elfcorehdr segment instead of the elfcorehdr buffer size at the time of
kdump load. This allows of_kexec_alloc_and_setup_fdt() to reserve the
full elfcorehdr memory in the kdump FDT and prevents elfcorehdr
corruption.

Fixes: 849599b702ef8 ("powerpc/crash: add crash memory hotplug support")
Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260227171801.2238847-1-sourabhjain@linux.ibm.com
---
 arch/powerpc/kexec/file_load_64.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index e7ef8b2a2554..5f6d50e4c3d4 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -450,6 +450,11 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 	kbuf->buffer = headers;
 	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf->bufsz = headers_sz;
+
+	/*
+	 * Account for extra space required to accommodate additional memory
+	 * ranges in elfcorehdr due to memory hotplug events.
+	 */
 	kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
 	kbuf->top_down = false;
 
@@ -460,7 +465,14 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 	}
 
 	image->elf_load_addr = kbuf->mem;
-	image->elf_headers_sz = headers_sz;
+
+	/*
+	 * If CONFIG_CRASH_HOTPLUG is enabled, the elfcorehdr kexec segment
+	 * memsz can be larger than bufsz. Always initialize elf_headers_sz
+	 * with memsz. This ensures the correct size is reserved for elfcorehdr
+	 * memory in the FDT prepared for kdump.
+	 */
+	image->elf_headers_sz = kbuf->memsz;
 	image->elf_headers = headers;
 out:
 	kfree(cmem);

From fbdfa8da05b6ae44114fc4f9b3e83e1736fd411c Mon Sep 17 00:00:00 2001
From: Naveen Anandhan <mr.navi8680@gmail.com>
Date: Sat, 28 Feb 2026 13:17:35 +0530
Subject: [PATCH 0768/1303] selftests: tc-testing: fix list_categories() crash
 on list type

list_categories() builds a set directly from the 'category'
field of each test case. Since 'category' is a list,
set(map(...)) attempts to insert lists into a set, which
raises:

  TypeError: unhashable type: 'list'

Flatten category lists and collect unique category names
using set.update() instead.

Signed-off-by: Naveen Anandhan <mr.navi8680@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc_helper.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index 0440d252c4c5..bc447ca57333 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -38,10 +38,14 @@ def list_test_cases(testlist):
 
 
 def list_categories(testlist):
-    """ Show all categories that are present in a test case file. """
-    categories = set(map(lambda x: x['category'], testlist))
+    """Show all unique categories present in the test cases."""
+    categories = set()
+    for t in testlist:
+        if 'category' in t:
+            categories.update(t['category'])
+
     print("Available categories:")
-    print(", ".join(str(s) for s in categories))
+    print(", ".join(sorted(categories)))
     print("")
 
 

From 5c3daa5301693d2e5364483a3405649a0fdaed98 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 2 Mar 2026 22:31:44 +0800
Subject: [PATCH 0769/1303] power: sequencing: pcie-m2: Fix device node
 reference leak in probe

In pwrseq_pcie_m2_probe(), ctx->of_node acquires an explicit reference
to the device node using of_node_get(), but there is no corresponding
of_node_put() in the driver's error handling paths or removal.

Since the ctx is tied to the lifecycle of the platform device, there
is no need to hold an additional reference to the device's own of_node.

Fixes: 52e7b5bd62ba ("power: sequencing: Add the Power Sequencing driver for the PCIe M.2 connectors")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260302-m2-v1-1-a6533e18aa69@gmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/power/sequencing/pwrseq-pcie-m2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c
index d31a7dd8b35c..dadb4aad9d5d 100644
--- a/drivers/power/sequencing/pwrseq-pcie-m2.c
+++ b/drivers/power/sequencing/pwrseq-pcie-m2.c
@@ -109,7 +109,7 @@ static int pwrseq_pcie_m2_probe(struct platform_device *pdev)
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->of_node = of_node_get(dev->of_node);
+	ctx->of_node = dev_of_node(dev);
 	ctx->pdata = device_get_match_data(dev);
 	if (!ctx->pdata)
 		return dev_err_probe(dev, -ENODEV,

From b3b1d3ae1d87bc9398fb715c945968bf4c75a09a Mon Sep 17 00:00:00 2001
From: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Date: Wed, 4 Mar 2026 08:22:59 +0100
Subject: [PATCH 0770/1303] ata: libata-core: Disable LPM on ST1000DM010-2EP102

According to a user report, the ST1000DM010-2EP102 has problems with LPM,
causing random system freezes. The drive belongs to the same BarraCuda
family as the ST2000DM008-2FR102 which has the same issue.

Cc: stable@vger.kernel.org
Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Reported-by: Filippo Baiamonte <filippo.ba03@bugzilla.kernel.org>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221163
Signed-off-by: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ccbf320524da..76b012f544ea 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4189,6 +4189,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 						ATA_QUIRK_FIRMWARE_WARN },
 
 	/* Seagate disks with LPM issues */
+	{ "ST1000DM010-2EP102",	NULL,		ATA_QUIRK_NOLPM },
 	{ "ST2000DM008-2FR102",	NULL,		ATA_QUIRK_NOLPM },
 
 	/* drives which fail FPDMA_AA activation (some may freeze afterwards)

From 6270b8ac2f41858952074b23c2d3d9aa2fe1bfa9 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 26 Feb 2026 07:46:46 +0900
Subject: [PATCH 0771/1303] xfs: remove scratch field from struct xfs_gc_bio

The scratch field in struct xfs_gc_bio is unused. Remove it.

Fixes: 102f444b57b3 ("xfs: rework zone GC buffer management")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_gc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 7efeecd2d85f..309f70098524 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -96,7 +96,6 @@ struct xfs_gc_bio {
 	 */
 	xfs_fsblock_t			old_startblock;
 	xfs_daddr_t			new_daddr;
-	struct xfs_zone_scratch		*scratch;
 
 	/* Are we writing to a sequential write required zone? */
 	bool				is_seq;
@@ -779,7 +778,6 @@ xfs_zone_gc_split_write(
 	ihold(VFS_I(chunk->ip));
 	split_chunk->ip = chunk->ip;
 	split_chunk->is_seq = chunk->is_seq;
-	split_chunk->scratch = chunk->scratch;
 	split_chunk->offset = chunk->offset;
 	split_chunk->len = split_len;
 	split_chunk->old_startblock = chunk->old_startblock;

From 0ca1a8331c0fa5e57844e003a5d667a15b1e002c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 2 Mar 2026 09:31:58 -0800
Subject: [PATCH 0772/1303] xfs: fix race between healthmon unmount and
 read_iter

xfs/1879 on one of my test VMs got stuck due to the xfs_io healthmon
subcommand sleeping in wait_event_interruptible at:

 xfs_healthmon_read_iter+0x558/0x5f8 [xfs]
 vfs_read+0x248/0x320
 ksys_read+0x78/0x120

Looking at xfs_healthmon_read_iter, in !O_NONBLOCK mode it will sleep
until the mount cookie == DETACHED_MOUNT_COOKIE, there are events
waiting to be formatted, or there are formatted events in the read
buffer that could be copied to userspace.

Poking into the running kernel, I see that there are zero events in the
list, the read buffer is empty, and the mount cookie is indeed in
DETACHED state.  IOWs, xfs_healthmon_has_eventdata should have returned
true, but instead we're asleep waiting for a wakeup.

I think what happened here is that xfs_healthmon_read_iter and
xfs_healthmon_unmount were racing with each other, and _read_iter lost
the race.  _unmount queued an unmount event, which woke up _read_iter.
It found, formatted, and copied the event out to userspace.  That
cleared out the pending event list and emptied the read buffer.  xfs_io
then called read() again, so _has_eventdata decided that we should sleep
on the empty event queue.

Next, _unmount called xfs_healthmon_detach, which set the mount cookie
to DETACHED.  Unfortunately, it didn't call wake_up_all on the hm, so
the wait_event_interruptible in the _read_iter thread remains asleep.
That's why the test stalled.

Fix this by moving the wake_up_all call to xfs_healthmon_detach.

Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_healthmon.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c
index 4a06d6632f65..26c325d34bd1 100644
--- a/fs/xfs/xfs_healthmon.c
+++ b/fs/xfs/xfs_healthmon.c
@@ -141,6 +141,16 @@ xfs_healthmon_detach(
 	hm->mount_cookie = DETACHED_MOUNT_COOKIE;
 	spin_unlock(&xfs_healthmon_lock);
 
+	/*
+	 * Wake up any readers that might remain.  This can happen if unmount
+	 * races with the healthmon fd owner entering ->read_iter, having
+	 * already emptied the event queue.
+	 *
+	 * In the ->release case there shouldn't be any readers because the
+	 * only users of the waiter are read and poll.
+	 */
+	wake_up_all(&hm->wait);
+
 	trace_xfs_healthmon_detach(hm);
 	xfs_healthmon_put(hm);
 }
@@ -1027,13 +1037,6 @@ xfs_healthmon_release(
 	 * process can create another health monitor file.
 	 */
 	xfs_healthmon_detach(hm);
-
-	/*
-	 * Wake up any readers that might be left.  There shouldn't be any
-	 * because the only users of the waiter are read and poll.
-	 */
-	wake_up_all(&hm->wait);
-
 	xfs_healthmon_put(hm);
 	return 0;
 }

From 61ded1083b264ff67ca8c2de822c66b6febaf9a8 Mon Sep 17 00:00:00 2001
From: Yujie Liu <yujie.liu@intel.com>
Date: Fri, 27 Feb 2026 16:24:52 +0800
Subject: [PATCH 0773/1303] drm/sched: Fix kernel-doc warning for
 drm_sched_job_done()

There is a kernel-doc warning for the scheduler:

Warning: drivers/gpu/drm/scheduler/sched_main.c:367 function parameter 'result' not described in 'drm_sched_job_done'

Fix the warning by describing the undocumented error code.

Fixes: 539f9ee4b52a ("drm/scheduler: properly forward fence errors")
Signed-off-by: Yujie Liu <yujie.liu@intel.com>
[phasta: Flesh out commit message]
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patch.msgid.link/20260227082452.1802922-1-yujie.liu@intel.com
---
 drivers/gpu/drm/scheduler/sched_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index e6ee35406165..2d5cb21a05b6 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -361,6 +361,7 @@ static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
 /**
  * drm_sched_job_done - complete a job
  * @s_job: pointer to the job which is done
+ * @result: 0 on success, -ERRNO on error
  *
  * Finish the job's fence and resubmit the work items.
  */

From aac9b27f7c1f2b2cf7f50a9ca633ecbbcaf22af9 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 3 Mar 2026 11:03:42 +0100
Subject: [PATCH 0774/1303] ata: libata: cancel pending work after clearing
 deferred_qc

Syzbot reported a WARN_ON() in ata_scsi_deferred_qc_work(), caused by
ap->ops->qc_defer() returning non-zero before issuing the deferred qc.

ata_scsi_schedule_deferred_qc() is called during each command completion.
This function will check if there is a deferred QC, and if
ap->ops->qc_defer() returns zero, meaning that it is possible to queue the
deferred qc at this time (without being deferred), then it will queue the
work which will issue the deferred qc.

Once the work get to run, which can potentially be a very long time after
the work was scheduled, there is a WARN_ON() if ap->ops->qc_defer() returns
non-zero.

While we hold the ap->lock both when assigning and clearing deferred_qc,
and the work itself holds the ap->lock, the code currently does not cancel
the work after clearing the deferred qc.

This means that the following scenario can happen:
1) One or several NCQ commands are queued.
2) A non-NCQ command is queued, gets stored in ap->deferred_qc.
3) Last NCQ command gets completed, work is queued to issue the deferred
   qc.
4) Timeout or error happens, ap->deferred_qc is cleared. The queued work is
   currently NOT canceled.
5) Port is reset.
6) One or several NCQ commands are queued.
7) A non-NCQ command is queued, gets stored in ap->deferred_qc.
8) Work is finally run. Yet at this time, there is still NCQ commands in
   flight.

The work in 8) really belongs to the non-NCQ command in 2), not to the
non-NCQ command in 7). The reason why the work is executed when it is not
supposed to, is because it was never canceled when ap->deferred_qc was
cleared in 4). Thus, ensure that we always cancel the work after clearing
ap->deferred_qc.

Another potential fix would have been to let ata_scsi_deferred_qc_work() do
nothing if ap->ops->qc_defer() returns non-zero. However, canceling the
work when clearing ap->deferred_qc seems slightly more logical, as we hold
the ap->lock when clearing ap->deferred_qc, so we know that the work cannot
be holding the lock. (The function could be waiting for the lock, but that
is okay since it will do nothing if ap->deferred_qc is not set.)

Reported-by: syzbot+bcaf842a1e8ead8dfb89@syzkaller.appspotmail.com
Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Fixes: eddb98ad9364 ("ata: libata-eh: correctly handle deferred qc timeouts")
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-eh.c   | 1 +
 drivers/ata/libata-scsi.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index b373cceb95d2..563432400f72 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -659,6 +659,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 			 */
 			WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE);
 			ap->deferred_qc = NULL;
+			cancel_work(&ap->deferred_qc_work);
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
 		} else if (i < ATA_MAX_QUEUE) {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c0dd75a0287c..ad798e5246b4 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1699,6 +1699,7 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap)
 
 	scmd = qc->scsicmd;
 	ap->deferred_qc = NULL;
+	cancel_work(&ap->deferred_qc_work);
 	ata_qc_free(qc);
 	scmd->result = (DID_SOFT_ERROR << 16);
 	scsi_done(scmd);

From fb1091febd668398aa84c161b8d9a1834321e021 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Mon, 2 Mar 2026 10:55:37 +0100
Subject: [PATCH 0775/1303] mm/slab: allow sheaf refill if blocking is not
 allowed

Ming Lei reported [1] a regression in the ublk null target benchmark due
to sheaves. The profile shows that the alloc_from_pcs() fastpath fails
and allocations fall back to ___slab_alloc(). It also shows the
allocations happen through mempool_alloc().

The strategy of mempool_alloc() is to call the underlying allocator
(here slab) without __GFP_DIRECT_RECLAIM first. This does not play well
with __pcs_replace_empty_main() checking for gfpflags_allow_blocking()
to decide if it should refill an empty sheaf or fallback to the
slowpath, so we end up falling back.

We could change the mempool strategy but there might be other paths
doing the same ting. So instead allow sheaf refill when blocking is not
allowed, changing the condition to gfpflags_allow_spinning(). The
original condition was unnecessarily restrictive.

Note this doesn't fully resolve the regression [1] as another component
of that are memoryless nodes, which is to be addressed separately.

Reported-by: Ming Lei <ming.lei@redhat.com>
Fixes: e47c897a2949 ("slab: add sheaves to most caches")
Link: https://lore.kernel.org/all/aZ0SbIqaIkwoW2mB@fedora/ [1]
Link: https://patch.msgid.link/20260302095536.34062-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index b1e9f16ba435..20cb4f3b636d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4567,7 +4567,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	struct slab_sheaf *empty = NULL;
 	struct slab_sheaf *full;
 	struct node_barn *barn;
-	bool can_alloc;
+	bool allow_spin;
 
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
@@ -4588,8 +4588,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 	}
 
-	full = barn_replace_empty_sheaf(barn, pcs->main,
-					gfpflags_allow_spinning(gfp));
+	allow_spin = gfpflags_allow_spinning(gfp);
+
+	full = barn_replace_empty_sheaf(barn, pcs->main, allow_spin);
 
 	if (full) {
 		stat(s, BARN_GET);
@@ -4599,9 +4600,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 
 	stat(s, BARN_GET_FAIL);
 
-	can_alloc = gfpflags_allow_blocking(gfp);
-
-	if (can_alloc) {
+	if (allow_spin) {
 		if (pcs->spare) {
 			empty = pcs->spare;
 			pcs->spare = NULL;
@@ -4611,8 +4610,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	local_unlock(&s->cpu_sheaves->lock);
+	pcs = NULL;
 
-	if (!can_alloc)
+	if (!allow_spin)
 		return NULL;
 
 	if (empty) {
@@ -4632,11 +4632,8 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	if (!full)
 		return NULL;
 
-	/*
-	 * we can reach here only when gfpflags_allow_blocking
-	 * so this must not be an irq
-	 */
-	local_lock(&s->cpu_sheaves->lock);
+	if (!local_trylock(&s->cpu_sheaves->lock))
+		goto barn_put;
 	pcs = this_cpu_ptr(s->cpu_sheaves);
 
 	/*
@@ -4667,6 +4664,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return pcs;
 	}
 
+barn_put:
 	barn_put_full_sheaf(barn, full);
 	stat(s, BARN_PUT);
 

From 6432f15c818cb30eec7c4ca378ecdebd9796f741 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Tue, 3 Mar 2026 22:57:22 +0900
Subject: [PATCH 0776/1303] mm/slab: change stride type from unsigned short to
 unsigned int

Commit 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
defined the type of slab->stride as unsigned short, because the author
initially planned to store stride within the lower 16 bits of the
page_type field, but later stored it in unused bits in the counters
field instead.

However, the idea of having only 2-byte stride turned out to be a
serious mistake. On systems with 64k pages, order-1 pages are 128k,
which is larger than USHRT_MAX. It triggers a debug warning because
s->size is 128k while stride, truncated to 2 bytes, becomes zero:

  ------------[ cut here ]------------
  Warning! stride (0) != s->size (131072)
  WARNING: mm/slub.c:2231 at alloc_slab_obj_exts_early.constprop.0+0x524/0x534, CPU#6: systemd-sysctl/307
  Modules linked in:
  CPU: 6 UID: 0 PID: 307 Comm: systemd-sysctl Not tainted 7.0.0-rc1+ #6 PREEMPTLAZY
  Hardware name: IBM,9009-22A POWER9 (architected) 0x4e0202 0xf000005 of:IBM,FW950.E0 (VL950_179) hv:phyp pSeries
  NIP:  c0000000008a9ac0 LR: c0000000008a9abc CTR: 0000000000000000
  REGS: c0000000141f7390 TRAP: 0700   Not tainted  (7.0.0-rc1+)
  MSR:  8000000000029033 <SF,EE,ME,IR,DR,RI,LE>  CR: 28004400  XER: 00000005
  CFAR: c000000000279318 IRQMASK: 0
  GPR00: c0000000008a9abc c0000000141f7630 c00000000252a300 c00000001427b200
  GPR04: 0000000000000004 0000000000000000 c000000000278fd0 0000000000000000
  GPR08: fffffffffffe0000 0000000000000000 0000000000000000 0000000022004400
  GPR12: c000000000f644b0 c000000017ff8f00 0000000000000000 0000000000000000
  GPR16: 0000000000000000 c0000000141f7aa0 0000000000000000 c0000000141f7a88
  GPR20: 0000000000000000 0000000000400cc0 ffffffffffffffff c00000001427b180
  GPR24: 0000000000000004 00000000000c0cc0 c000000004e89a20 c00000005de90011
  GPR28: 0000000000010010 c00000005df00000 c000000006017f80 c00c000000177a00
  NIP [c0000000008a9ac0] alloc_slab_obj_exts_early.constprop.0+0x524/0x534
  LR [c0000000008a9abc] alloc_slab_obj_exts_early.constprop.0+0x520/0x534
  Call Trace:
  [c0000000141f7630] [c0000000008a9abc] alloc_slab_obj_exts_early.constprop.0+0x520/0x534 (unreliable)
  [c0000000141f76c0] [c0000000008aafbc] allocate_slab+0x154/0x94c
  [c0000000141f7760] [c0000000008b41c0] refill_objects+0x124/0x16c
  [c0000000141f77c0] [c0000000008b4be0] __pcs_replace_empty_main+0x2b0/0x444
  [c0000000141f7810] [c0000000008b9600] __kvmalloc_node_noprof+0x840/0x914
  [c0000000141f7900] [c000000000a3dd40] seq_read_iter+0x60c/0xb00
  [c0000000141f7a10] [c000000000b36b24] proc_reg_read_iter+0x154/0x1fc
  [c0000000141f7a50] [c0000000009cee7c] vfs_read+0x39c/0x4e4
  [c0000000141f7b30] [c0000000009d0214] ksys_read+0x9c/0x180
  [c0000000141f7b90] [c00000000003a8d0] system_call_exception+0x1e0/0x4b0
  [c0000000141f7e50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec

This leads to slab_obj_ext() returning the first slabobj_ext or all
objects and confuses the reference counting of object cgroups [1] and
memory (un)charging for memory cgroups [2].

Fortunately, the counters field has 32 unused bits instead of 16
on 64-bit CPUs, which is wide enough to hold any value of s->size.
Change the type to unsigned int.

Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Closes: https://lore.kernel.org/lkml/ca241daa-e7e7-4604-a48d-de91ec9184a5@linux.ibm.com [1]
Closes: https://lore.kernel.org/all/ddff7c7d-c0c3-4780-808f-9a83268bbf0c@linux.ibm.com [2]
Fixes: 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260303135722.2680521-1-harry.yoo@oracle.com
Reviewed-by: Hao Li <hao.li@linux.dev>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slab.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/mm/slab.h b/mm/slab.h
index f6ef862b60ef..e9ab292acd22 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -59,7 +59,7 @@ struct freelist_counters {
 					 * to save memory. In case ->stride field is not available,
 					 * such optimizations are disabled.
 					 */
-					unsigned short stride;
+					unsigned int stride;
 #endif
 				};
 			};
@@ -559,20 +559,20 @@ static inline void put_slab_obj_exts(unsigned long obj_exts)
 }
 
 #ifdef CONFIG_64BIT
-static inline void slab_set_stride(struct slab *slab, unsigned short stride)
+static inline void slab_set_stride(struct slab *slab, unsigned int stride)
 {
 	slab->stride = stride;
 }
-static inline unsigned short slab_get_stride(struct slab *slab)
+static inline unsigned int slab_get_stride(struct slab *slab)
 {
 	return slab->stride;
 }
 #else
-static inline void slab_set_stride(struct slab *slab, unsigned short stride)
+static inline void slab_set_stride(struct slab *slab, unsigned int stride)
 {
 	VM_WARN_ON_ONCE(stride != sizeof(struct slabobj_ext));
 }
-static inline unsigned short slab_get_stride(struct slab *slab)
+static inline unsigned int slab_get_stride(struct slab *slab)
 {
 	return sizeof(struct slabobj_ext);
 }

From 0fb59eaca18f1254ecdce34354eec3cb1b3b5e10 Mon Sep 17 00:00:00 2001
From: Shawn Lin <shawn.lin@rock-chips.com>
Date: Wed, 25 Feb 2026 10:55:01 +0800
Subject: [PATCH 0777/1303] pmdomain: rockchip: Fix PD_VCODEC for RK3588

>From the RK3588 TRM Table 7-1 RK3588 Voltage Domain and Power Domain Summary,
PD_RKVDEC0/1 and PD_VENC0/1 rely on VD_VCODEC which require extra voltages to
be applied, otherwise it breaks RK3588-evb1-v10 board after vdec support landed[1].
The panic looks like below:

  rockchip-pm-domain fd8d8000.power-management:power-controller: failed to set domain 'rkvdec0' on, val=0
  rockchip-pm-domain fd8d8000.power-management:power-controller: failed to set domain 'rkvdec1' on, val=0
  ...
  Hardware name: Rockchip RK3588S EVB1 V10 Board (DT)
  Workqueue: pm genpd_power_off_work_fn
  Call trace:
  show_stack+0x18/0x24 (C)
  dump_stack_lvl+0x40/0x84
  dump_stack+0x18/0x24
  vpanic+0x1ec/0x4fc
  vpanic+0x0/0x4fc
  check_panic_on_warn+0x0/0x94
  arm64_serror_panic+0x6c/0x78
  do_serror+0xc4/0xcc
  el1h_64_error_handler+0x3c/0x5c
  el1h_64_error+0x6c/0x70
  regmap_mmio_read32le+0x18/0x24 (P)
  regmap_bus_reg_read+0xfc/0x130
  regmap_read+0x188/0x1ac
  regmap_read+0x54/0x78
  rockchip_pd_power+0xcc/0x5f0
  rockchip_pd_power_off+0x1c/0x4c
  genpd_power_off+0x84/0x120
  genpd_power_off+0x1b4/0x260
  genpd_power_off_work_fn+0x38/0x58
  process_scheduled_works+0x194/0x2c4
  worker_thread+0x2ac/0x3d8
  kthread+0x104/0x124
  ret_from_fork+0x10/0x20
  SMP: stopping secondary CPUs
  Kernel Offset: disabled
  CPU features: 0x3000000,000e0005,40230521,0400720b
  Memory Limit: none
  ---[ end Kernel panic - not syncing: Asynchronous SError Interrupt ]---

Chaoyi pointed out the PD_VCODEC is the parent of PD_RKVDEC0/1 and PD_VENC0/1, so checking
the PD_VCODEC is enough.

[1] https://lore.kernel.org/linux-rockchip/20251020212009.8852-2-detlev.casanova@collabora.com/

Fixes: db6df2e3fc16 ("pmdomain: rockchip: add regulator support")
Cc: stable@vger.kernel.org
Suggested-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Reviewed-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/rockchip/pm-domains.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c
index 997e93c12951..44d34840ede7 100644
--- a/drivers/pmdomain/rockchip/pm-domains.c
+++ b/drivers/pmdomain/rockchip/pm-domains.c
@@ -1311,7 +1311,7 @@ static const struct rockchip_domain_info rk3576_pm_domains[] = {
 static const struct rockchip_domain_info rk3588_pm_domains[] = {
 	[RK3588_PD_GPU]		= DOMAIN_RK3588("gpu",     0x0, BIT(0),  0,       0x0, 0,       BIT(1),  0x0, BIT(0),  BIT(0),  false, true),
 	[RK3588_PD_NPU]		= DOMAIN_RK3588("npu",     0x0, BIT(1),  BIT(1),  0x0, 0,       0,       0x0, 0,       0,       false, true),
-	[RK3588_PD_VCODEC]	= DOMAIN_RK3588("vcodec",  0x0, BIT(2),  BIT(2),  0x0, 0,       0,       0x0, 0,       0,       false, false),
+	[RK3588_PD_VCODEC]	= DOMAIN_RK3588("vcodec",  0x0, BIT(2),  BIT(2),  0x0, 0,       0,       0x0, 0,       0,       false, true),
 	[RK3588_PD_NPUTOP]	= DOMAIN_RK3588("nputop",  0x0, BIT(3),  0,       0x0, BIT(11), BIT(2),  0x0, BIT(1),  BIT(1),  false, false),
 	[RK3588_PD_NPU1]	= DOMAIN_RK3588("npu1",    0x0, BIT(4),  0,       0x0, BIT(12), BIT(3),  0x0, BIT(2),  BIT(2),  false, false),
 	[RK3588_PD_NPU2]	= DOMAIN_RK3588("npu2",    0x0, BIT(5),  0,       0x0, BIT(13), BIT(4),  0x0, BIT(3),  BIT(3),  false, false),

From a58d487fb1a52579d3c37544ea371da78ed70c45 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Wed, 4 Mar 2026 09:56:16 +0100
Subject: [PATCH 0778/1303] drm/ttm/tests: Fix build failure on PREEMPT_RT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a compile error in the kunit tests when CONFIG_PREEMPT_RT is
enabled, and the normal mutex is converted into a rtmutex.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602261547.3bM6yVAS-lkp@intel.com/
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://patch.msgid.link/20260304085616.1216961-1-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/ttm/tests/ttm_bo_test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
index d468f8322072..f3103307b5df 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
@@ -222,13 +222,13 @@ static void ttm_bo_reserve_interrupted(struct kunit *test)
 		KUNIT_FAIL(test, "Couldn't create ttm bo reserve task\n");
 
 	/* Take a lock so the threaded reserve has to wait */
-	mutex_lock(&bo->base.resv->lock.base);
+	dma_resv_lock(bo->base.resv, NULL);
 
 	wake_up_process(task);
 	msleep(20);
 	err = kthread_stop(task);
 
-	mutex_unlock(&bo->base.resv->lock.base);
+	dma_resv_unlock(bo->base.resv);
 
 	KUNIT_ASSERT_EQ(test, err, -ERESTARTSYS);
 }

From 3d1973a0c76a78a4728cff13648a188ed486cf44 Mon Sep 17 00:00:00 2001
From: Jan Stancek <jstancek@redhat.com>
Date: Wed, 25 Feb 2026 20:30:23 +0100
Subject: [PATCH 0779/1303] x86/boot: Handle relative CONFIG_EFI_SBAT_FILE file
 paths

CONFIG_EFI_SBAT_FILE can be a relative path. When compiling using a different
output directory (O=) the build currently fails because it can't find the
filename set in CONFIG_EFI_SBAT_FILE:

  arch/x86/boot/compressed/sbat.S: Assembler messages:
  arch/x86/boot/compressed/sbat.S:6: Error: file not found: kernel.sbat

Add $(srctree) as include dir for sbat.o.

  [ bp: Massage commit message. ]

Fixes: 61b57d35396a ("x86/efi: Implement support for embedding SBAT data for x86")
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/f4eda155b0cef91d4d316b4e92f5771cb0aa7187.1772047658.git.jstancek@redhat.com
---
 arch/x86/boot/compressed/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 68f9d7a1683b..b8b2b7bea1d3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -113,6 +113,7 @@ vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o
 
 ifdef CONFIG_EFI_SBAT
 $(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE)
+AFLAGS_sbat.o += -I $(srctree)
 endif
 
 $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE

From fbb143e4a6efa4a175e856fc898754b06cb13c4f Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 4 Mar 2026 07:19:55 +0000
Subject: [PATCH 0780/1303] ASoC: dt-bindings: renesas,rz-ssi: Document RZ/G3L
 SoC

Document RZ/G3L SSIF-2 bindings. The RZ/G3L SSIF-2 IP is identical to one
found on the RZ/G2L SoC.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20260304072000.6787-1-biju.das.jz@bp.renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
index e4cdbf2202b9..1394f78281fc 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
+++ b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
@@ -20,6 +20,7 @@ properties:
           - renesas,r9a07g044-ssi  # RZ/G2{L,LC}
           - renesas,r9a07g054-ssi  # RZ/V2L
           - renesas,r9a08g045-ssi  # RZ/G3S
+          - renesas,r9a08g046-ssi  # RZ/G3L
       - const: renesas,rz-ssi
 
   reg:

From 325291b20f8a6f14b9c82edbf5d12e4e71f6adaa Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Wed, 4 Mar 2026 14:32:55 +0800
Subject: [PATCH 0781/1303] ASoC: amd: yc: Add DMI quirk for ASUS EXPERTBOOK
 PM1503CDA

Add a DMI quirk for the ASUS EXPERTBOOK PM1503CDA fixing the
issue where the internal microphone was not detected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221070
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260304063255.139331-1-zhangheng@kylinos.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 7af4daeb4c6f..1324543b42d7 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -710,6 +710,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"),
+		}
+	},
 	{}
 };
 

From cfc69c2e6c699c96949f7b0455195b0bfb7dc715 Mon Sep 17 00:00:00 2001
From: Charles Haithcock <chaithco@redhat.com>
Date: Fri, 27 Feb 2026 18:41:15 -0700
Subject: [PATCH 0782/1303] i2c: i801: Revert "i2c: i801: replace acpi_lock
 with I2C bus lock"

This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1.

Under rare circumstances, multiple udev threads can collect i801 device
info on boot and walk i801_acpi_io_handler somewhat concurrently. The
first will note the area is reserved by acpi to prevent further touches.
This ultimately causes the area to be deregistered. The second will
enter i801_acpi_io_handler after the area is unregistered but before a
check can be made that the area is unregistered. i2c_lock_bus relies on
the now unregistered area containing lock_ops to lock the bus. The end
result is a kernel panic on boot with the following backtrace;

[   14.971872] ioatdma 0000:09:00.2: enabling device (0100 -> 0102)
[   14.971873] BUG: kernel NULL pointer dereference, address: 0000000000000000
[   14.971880] #PF: supervisor read access in kernel mode
[   14.971884] #PF: error_code(0x0000) - not-present page
[   14.971887] PGD 0 P4D 0
[   14.971894] Oops: 0000 [#1] PREEMPT SMP PTI
[   14.971900] CPU: 5 PID: 956 Comm: systemd-udevd Not tainted 5.14.0-611.5.1.el9_7.x86_64 #1
[   14.971905] Hardware name: XXXXXXXXXXXXXXXXXXXXXXX BIOS 1.20.10.SV91 01/30/2023
[   14.971908] RIP: 0010:i801_acpi_io_handler+0x2d/0xb0 [i2c_i801]
[   14.971929] Code: 00 00 49 8b 40 20 41 57 41 56 4d 8b b8 30 04 00 00 49 89 ce 41 55 41 89 d5 41 54 49 89 f4 be 02 00 00 00 55 4c 89 c5 53 89 fb <48> 8b 00 4c 89 c7 e8 18 61 54 e9 80 bd 80 04 00 00 00 75 09 4c 3b
[   14.971933] RSP: 0018:ffffbaa841483838 EFLAGS: 00010282
[   14.971938] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9685e01ba568
[   14.971941] RDX: 0000000000000008 RSI: 0000000000000002 RDI: 0000000000000000
[   14.971944] RBP: ffff9685ca22f028 R08: ffff9685ca22f028 R09: ffff9685ca22f028
[   14.971948] R10: 000000000000000b R11: 0000000000000580 R12: 0000000000000580
[   14.971951] R13: 0000000000000008 R14: ffff9685e01ba568 R15: ffff9685c222f000
[   14.971954] FS:  00007f8287c0ab40(0000) GS:ffff96a47f940000(0000) knlGS:0000000000000000
[   14.971959] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   14.971963] CR2: 0000000000000000 CR3: 0000000168090001 CR4: 00000000003706f0
[   14.971966] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   14.971968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   14.971972] Call Trace:
[   14.971977]  <TASK>
[   14.971981]  ? show_trace_log_lvl+0x1c4/0x2df
[   14.971994]  ? show_trace_log_lvl+0x1c4/0x2df
[   14.972003]  ? acpi_ev_address_space_dispatch+0x16e/0x3c0
[   14.972014]  ? __die_body.cold+0x8/0xd
[   14.972021]  ? page_fault_oops+0x132/0x170
[   14.972028]  ? exc_page_fault+0x61/0x150
[   14.972036]  ? asm_exc_page_fault+0x22/0x30
[   14.972045]  ? i801_acpi_io_handler+0x2d/0xb0 [i2c_i801]
[   14.972061]  acpi_ev_address_space_dispatch+0x16e/0x3c0
[   14.972069]  ? __pfx_i801_acpi_io_handler+0x10/0x10 [i2c_i801]
[   14.972085]  acpi_ex_access_region+0x5b/0xd0
[   14.972093]  acpi_ex_field_datum_io+0x73/0x2e0
[   14.972100]  acpi_ex_read_data_from_field+0x8e/0x230
[   14.972106]  acpi_ex_resolve_node_to_value+0x23d/0x310
[   14.972114]  acpi_ds_evaluate_name_path+0xad/0x110
[   14.972121]  acpi_ds_exec_end_op+0x321/0x510
[   14.972127]  acpi_ps_parse_loop+0xf7/0x680
[   14.972136]  acpi_ps_parse_aml+0x17a/0x3d0
[   14.972143]  acpi_ps_execute_method+0x137/0x270
[   14.972150]  acpi_ns_evaluate+0x1f4/0x2e0
[   14.972158]  acpi_evaluate_object+0x134/0x2f0
[   14.972164]  acpi_evaluate_integer+0x50/0xe0
[   14.972173]  ? vsnprintf+0x24b/0x570
[   14.972181]  acpi_ac_get_state.part.0+0x23/0x70
[   14.972189]  get_ac_property+0x4e/0x60
[   14.972195]  power_supply_show_property+0x90/0x1f0
[   14.972205]  add_prop_uevent+0x29/0x90
[   14.972213]  power_supply_uevent+0x109/0x1d0
[   14.972222]  dev_uevent+0x10e/0x2f0
[   14.972228]  uevent_show+0x8e/0x100
[   14.972236]  dev_attr_show+0x19/0x40
[   14.972246]  sysfs_kf_seq_show+0x9b/0x100
[   14.972253]  seq_read_iter+0x120/0x4b0
[   14.972262]  ? selinux_file_permission+0x106/0x150
[   14.972273]  vfs_read+0x24f/0x3a0
[   14.972284]  ksys_read+0x5f/0xe0
[   14.972291]  do_syscall_64+0x5f/0xe0
...

The kernel panic is mitigated by setting limiting the count of udev
children to 1. Revert to using the acpi_lock to continue protecting
marking the area as owned by firmware without relying on a lock in
a potentially unmapped region of memory.

Fixes: f707d6b9e7c1 ("i2c: i801: replace acpi_lock with I2C bus lock")
Signed-off-by: Charles Haithcock <chaithco@redhat.com>
[wsa: added Fixes-tag and updated comment stating the importance of the lock]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-i801.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 9e1789725edf..32a3cef02c7b 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -310,9 +310,10 @@ struct i801_priv {
 
 	/*
 	 * If set to true the host controller registers are reserved for
-	 * ACPI AML use.
+	 * ACPI AML use. Needs extra protection by acpi_lock.
 	 */
 	bool acpi_reserved;
+	struct mutex acpi_lock;
 };
 
 #define FEATURE_SMBUS_PEC	BIT(0)
@@ -894,8 +895,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 	int hwpec, ret;
 	struct i801_priv *priv = i2c_get_adapdata(adap);
 
-	if (priv->acpi_reserved)
+	mutex_lock(&priv->acpi_lock);
+	if (priv->acpi_reserved) {
+		mutex_unlock(&priv->acpi_lock);
 		return -EBUSY;
+	}
 
 	pm_runtime_get_sync(&priv->pci_dev->dev);
 
@@ -935,6 +939,7 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 	iowrite8(SMBHSTSTS_INUSE_STS | STATUS_FLAGS, SMBHSTSTS(priv));
 
 	pm_runtime_put_autosuspend(&priv->pci_dev->dev);
+	mutex_unlock(&priv->acpi_lock);
 	return ret;
 }
 
@@ -1465,7 +1470,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
 	 * further access from the driver itself. This device is now owned
 	 * by the system firmware.
 	 */
-	i2c_lock_bus(&priv->adapter, I2C_LOCK_SEGMENT);
+	mutex_lock(&priv->acpi_lock);
 
 	if (!priv->acpi_reserved && i801_acpi_is_smbus_ioport(priv, address)) {
 		priv->acpi_reserved = true;
@@ -1485,7 +1490,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
 	else
 		status = acpi_os_write_port(address, (u32)*value, bits);
 
-	i2c_unlock_bus(&priv->adapter, I2C_LOCK_SEGMENT);
+	mutex_unlock(&priv->acpi_lock);
 
 	return status;
 }
@@ -1545,6 +1550,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	priv->adapter.dev.parent = &dev->dev;
 	acpi_use_parent_companion(&priv->adapter.dev);
 	priv->adapter.retries = 3;
+	mutex_init(&priv->acpi_lock);
 
 	priv->pci_dev = dev;
 	priv->features = id->driver_data;

From 6932256d3a3764f3a5e06e2cb8603be45b6a9fef Mon Sep 17 00:00:00 2001
From: Gerd Rausch <gerd.rausch@oracle.com>
Date: Wed, 25 Feb 2026 15:37:49 -0800
Subject: [PATCH 0783/1303] time/jiffies: Fix sysctl file error on
 configurations where USER_HZ < HZ

Commit 2dc164a48e6fd ("sysctl: Create converter functions with two new
macros") incorrectly returns error to user space when jiffies sysctl
converter is used. The old overflow check got replaced with an
unconditional one:
     +    if (USER_HZ < HZ)
     +        return -EINVAL;
which will always be true on configurations with "USER_HZ < HZ".

Remove the check; it is no longer needed as clock_t_to_jiffies() returns
ULONG_MAX for the overflow case and proc_int_u2k_conv_uop() checks for
"> INT_MAX" after conversion

Fixes: 2dc164a48e6fd ("sysctl: Create converter functions with two new macros")
Reported-by: Colm Harrington <colm.harrington@oracle.com>
Signed-off-by: Gerd Rausch <gerd.rausch@oracle.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 kernel/time/jiffies.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a5c7d15fce72..9daf8c5d9687 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies);
 int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ)
-		return -EINVAL;
 	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
 				  do_proc_int_conv_userhz_jiffies);
 }

From debc1a492b2695d05973994fb0f796dbd9ceaae6 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 3 Mar 2026 15:34:20 -0800
Subject: [PATCH 0784/1303] iomap: don't mark folio uptodate if read IO has
 bytes pending

If a folio has ifs metadata attached to it and the folio is partially
read in through an async IO helper with the rest of it then being read
in through post-EOF zeroing or as inline data, and the helper
successfully finishes the read first, then post-EOF zeroing / reading
inline will mark the folio as uptodate in iomap_set_range_uptodate().

This is a problem because when the read completion path later calls
iomap_read_end(), it will call folio_end_read(), which sets the uptodate
bit using XOR semantics. Calling folio_end_read() on a folio that was
already marked uptodate clears the uptodate bit.

Fix this by not marking the folio as uptodate if the read IO has bytes
pending. The folio uptodate state will be set in the read completion
path through iomap_end_read() -> folio_end_read().

Reported-by: Wei Gao <wegao@suse.com>
Suggested-by: Sasha Levin <sashal@kernel.org>
Tested-by: Wei Gao <wegao@suse.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Cc: stable@vger.kernel.org # v6.19
Link: https://lore.kernel.org/linux-fsdevel/aYbmy8JdgXwsGaPP@autotest-wegao.qe.prg2.suse.org/
Fixes: b2f35ac4146d ("iomap: add caller-provided callbacks for read and readahead")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20260303233420.874231-2-joannelkoong@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index bc82083e420a..00f0efaf12b2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -80,18 +80,27 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off,
 {
 	struct iomap_folio_state *ifs = folio->private;
 	unsigned long flags;
-	bool uptodate = true;
+	bool mark_uptodate = true;
 
 	if (folio_test_uptodate(folio))
 		return;
 
 	if (ifs) {
 		spin_lock_irqsave(&ifs->state_lock, flags);
-		uptodate = ifs_set_range_uptodate(folio, ifs, off, len);
+		/*
+		 * If a read with bytes pending is in progress, we must not call
+		 * folio_mark_uptodate(). The read completion path
+		 * (iomap_read_end()) will call folio_end_read(), which uses XOR
+		 * semantics to set the uptodate bit. If we set it here, the XOR
+		 * in folio_end_read() will clear it, leaving the folio not
+		 * uptodate.
+		 */
+		mark_uptodate = ifs_set_range_uptodate(folio, ifs, off, len) &&
+				!ifs->read_bytes_pending;
 		spin_unlock_irqrestore(&ifs->state_lock, flags);
 	}
 
-	if (uptodate)
+	if (mark_uptodate)
 		folio_mark_uptodate(folio);
 }
 

From ace7dcc8181373a0338efa1686c5e36eb121dff2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 25 Feb 2026 09:42:20 +0200
Subject: [PATCH 0785/1303] drm/dp: Add definition for Panel Replay full-line
 granularity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP specification is saying value 0xff 0xff in PANEL REPLAY SELECTIVE UPDATE
X GRANULARITY CAPABILITY registers (0xb2 and 0xb3) means full-line
granularity. Add definition for this.

Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/20260225074221.1744330-1-jouni.hogander@intel.com
(cherry picked from commit b93311673263bb98a200ab1cb6304f969bdada5c)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 include/drm/display/drm_dp.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h
index e4eebabab975..8b15d3eeb716 100644
--- a/include/drm/display/drm_dp.h
+++ b/include/drm/display/drm_dp.h
@@ -571,6 +571,8 @@
 # define DP_PANEL_REPLAY_LINK_OFF_SUPPORTED_IN_PR_AFTER_ADAPTIVE_SYNC_SDP	(1 << 7)
 
 #define DP_PANEL_REPLAY_CAP_X_GRANULARITY		0xb2
+# define DP_PANEL_REPLAY_FULL_LINE_GRANULARITY		0xffff
+
 #define DP_PANEL_REPLAY_CAP_Y_GRANULARITY		0xb4
 
 /* Link Configuration */

From a99cac460ddeb3705cb54a8421339f351586b25d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 25 Feb 2026 09:42:21 +0200
Subject: [PATCH 0786/1303] drm/i915/psr: Fix for Panel Replay X granularity
 DPCD register handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP specification is saying value 0xff 0xff in PANEL REPLAY SELECTIVE UPDATE
X GRANULARITY CAPABILITY registers (0xb2 and 0xb3) means full-line
granularity. Take this into account when handling Panel Replay X
granularity informed by the panel.

Fixes: 1cc854647450 ("drm/i915/psr: Use SU granularity information available in intel_connector")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7284
Tested-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patch.msgid.link/20260225074221.1744330-2-jouni.hogander@intel.com
(cherry picked from commit f5c8f824a495e849492f09a43bd965a8f4d86cb2)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 62208ffc5101..4ce1173a2e91 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1307,9 +1307,14 @@ static bool psr2_granularity_check(struct intel_crtc_state *crtc_state,
 	u16 sink_y_granularity = crtc_state->has_panel_replay ?
 		connector->dp.panel_replay_caps.su_y_granularity :
 		connector->dp.psr_caps.su_y_granularity;
-	u16 sink_w_granularity =  crtc_state->has_panel_replay ?
-		connector->dp.panel_replay_caps.su_w_granularity :
-		connector->dp.psr_caps.su_w_granularity;
+	u16 sink_w_granularity;
+
+	if (crtc_state->has_panel_replay)
+		sink_w_granularity = connector->dp.panel_replay_caps.su_w_granularity ==
+			DP_PANEL_REPLAY_FULL_LINE_GRANULARITY ?
+			crtc_hdisplay : connector->dp.panel_replay_caps.su_w_granularity;
+	else
+		sink_w_granularity = connector->dp.psr_caps.su_w_granularity;
 
 	/* PSR2 HW only send full lines so we only need to validate the width */
 	if (crtc_hdisplay % sink_w_granularity)

From 531bb98a030cc1073bd7ed9a502c0a3a781e92ee Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 4 Mar 2026 12:37:43 +0000
Subject: [PATCH 0787/1303] io_uring/zcrx: use READ_ONCE with user shared RQEs

Refill queue entries are shared with the user space, use READ_ONCE when
reading them.

Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider");
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 19b287d21f4b..0461edebb042 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -927,11 +927,12 @@ static inline bool io_parse_rqe(struct io_uring_zcrx_rqe *rqe,
 				struct io_zcrx_ifq *ifq,
 				struct net_iov **ret_niov)
 {
+	__u64 off = READ_ONCE(rqe->off);
 	unsigned niov_idx, area_idx;
 	struct io_zcrx_area *area;
 
-	area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT;
-	niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift;
+	area_idx = off >> IORING_ZCRX_AREA_SHIFT;
+	niov_idx = (off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift;
 
 	if (unlikely(rqe->__pad || area_idx))
 		return false;

From d320f160aa5ff36cdf83c645cca52b615e866e32 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 2 Mar 2026 09:30:02 -0800
Subject: [PATCH 0788/1303] iomap: reject delalloc mappings during writeback

Filesystems should never provide a delayed allocation mapping to
writeback; they're supposed to allocate the space before replying.
This can lead to weird IO errors and crashes in the block layer if the
filesystem is being malicious, or if it hadn't set iomap->dev because
it's a delalloc mapping.

Fix this by failing writeback on delalloc mappings.  Currently no
filesystems actually misbehave in this manner, but we ought to be
stricter about things like that.

Cc: stable@vger.kernel.org # v5.5
Fixes: 598ecfbaa742ac ("iomap: lift the xfs writeback code to iomap")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/20260302173002.GL13829@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/ioend.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 4d1ef8a2cee9..60546fa14dfe 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -215,17 +215,18 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 	WARN_ON_ONCE(!folio->private && map_len < dirty_len);
 
 	switch (wpc->iomap.type) {
-	case IOMAP_INLINE:
-		WARN_ON_ONCE(1);
-		return -EIO;
+	case IOMAP_UNWRITTEN:
+		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
+		break;
+	case IOMAP_MAPPED:
+		break;
 	case IOMAP_HOLE:
 		return map_len;
 	default:
-		break;
+		WARN_ON_ONCE(1);
+		return -EIO;
 	}
 
-	if (wpc->iomap.type == IOMAP_UNWRITTEN)
-		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
 	if (wpc->iomap.flags & IOMAP_F_SHARED)
 		ioend_flags |= IOMAP_IOEND_SHARED;
 	if (folio_test_dropbehind(folio))

From a99d34e5ecb9a8f2212ee5a01140313bb115f9be Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Wed, 11 Feb 2026 11:41:59 +0100
Subject: [PATCH 0789/1303] Revert "drm/pagemap: Disable device-to-device
 migration"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With commit
a69d1ab971a6 ("mm: Fix a hmm_range_fault() livelock / starvation problem")
device-to-device migration is not functional again and the
disabling can be reverted.

Add the above commit as a Fixes: tag in order for the revert to not
take place unless that commit is present.

This reverts commit 10dd1eaa80a56d3cf6d7c36b5269c8fed617f001.

Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: b570f37a2ce4 ("mm: Fix a hmm_range_fault() livelock / starvation problem")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260211104159.114947-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 1a3c0049b3f56278c9caf2784c53f6ab435fd12c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Rodrigo updated Fixes tag]
---
 drivers/gpu/drm/drm_pagemap.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index bdc79140875c..862675ac5bb2 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -480,18 +480,8 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 		.start		= start,
 		.end		= end,
 		.pgmap_owner	= pagemap->owner,
-		/*
-		 * FIXME: MIGRATE_VMA_SELECT_DEVICE_PRIVATE intermittently
-		 * causes 'xe_exec_system_allocator --r *race*no*' to trigger aa
-		 * engine reset and a hard hang due to getting stuck on a folio
-		 * lock. This should work and needs to be root-caused. The only
-		 * downside of not selecting MIGRATE_VMA_SELECT_DEVICE_PRIVATE
-		 * is that device-to-device migrations won’t work; instead,
-		 * memory will bounce through system memory. This path should be
-		 * rare and only occur when the madvise attributes of memory are
-		 * changed or atomics are being used.
-		 */
-		.flags		= MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT,
+		.flags		= MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT |
+		MIGRATE_VMA_SELECT_DEVICE_PRIVATE,
 	};
 	unsigned long i, npages = npages_in_range(start, end);
 	unsigned long own_pages = 0, migrated_pages = 0;

From b3368ecca9538b88ddf982ea99064860fd5add97 Mon Sep 17 00:00:00 2001
From: Zhanjun Dong <zhanjun.dong@intel.com>
Date: Fri, 20 Feb 2026 17:53:08 -0500
Subject: [PATCH 0790/1303] drm/xe/gsc: Fix GSC proxy cleanup on early
 initialization failure

xe_gsc_proxy_remove undoes what is done in both xe_gsc_proxy_init and
xe_gsc_proxy_start; however, if we fail between those 2 calls, it is
possible that the HW forcewake access hasn't been initialized yet and so
we hit errors when the cleanup code tries to write GSC register. To
avoid that, split the cleanup in 2 functions so that the HW cleanup is
only called if the HW setup was completed successfully.

Since the HW cleanup (interrupt disabling) is now removed from
xe_gsc_proxy_remove, the cleanup on error paths in xe_gsc_proxy_start
must be updated to disable interrupts before returning.

Fixes: ff6cd29b690b ("drm/xe: Cleanup unwind of gt initialization")
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patch.msgid.link/20260220225308.101469-1-zhanjun.dong@intel.com
(cherry picked from commit 2b37c401b265c07b46408b5cb36a4b757c9b5060)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gsc_proxy.c | 43 +++++++++++++++++++++++++------
 drivers/gpu/drm/xe/xe_gsc_types.h |  2 ++
 2 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c
index 42438b21f235..707db650a2ae 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.c
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c
@@ -435,15 +435,11 @@ static int proxy_channel_alloc(struct xe_gsc *gsc)
 	return 0;
 }
 
-static void xe_gsc_proxy_remove(void *arg)
+static void xe_gsc_proxy_stop(struct xe_gsc *gsc)
 {
-	struct xe_gsc *gsc = arg;
 	struct xe_gt *gt = gsc_to_gt(gsc);
 	struct xe_device *xe = gt_to_xe(gt);
 
-	if (!gsc->proxy.component_added)
-		return;
-
 	/* disable HECI2 IRQs */
 	scoped_guard(xe_pm_runtime, xe) {
 		CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FW_GSC);
@@ -455,6 +451,30 @@ static void xe_gsc_proxy_remove(void *arg)
 	}
 
 	xe_gsc_wait_for_worker_completion(gsc);
+	gsc->proxy.started = false;
+}
+
+static void xe_gsc_proxy_remove(void *arg)
+{
+	struct xe_gsc *gsc = arg;
+	struct xe_gt *gt = gsc_to_gt(gsc);
+	struct xe_device *xe = gt_to_xe(gt);
+
+	if (!gsc->proxy.component_added)
+		return;
+
+	/*
+	 * GSC proxy start is an async process that can be ongoing during
+	 * Xe module load/unload. Using devm managed action to register
+	 * xe_gsc_proxy_stop could cause issues if Xe module unload has
+	 * already started when the action is registered, potentially leading
+	 * to the cleanup being called at the wrong time. Therefore, instead
+	 * of registering a separate devm action to undo what is done in
+	 * proxy start, we call it from here, but only if the start has
+	 * completed successfully (tracked with the 'started' flag).
+	 */
+	if (gsc->proxy.started)
+		xe_gsc_proxy_stop(gsc);
 
 	component_del(xe->drm.dev, &xe_gsc_proxy_component_ops);
 	gsc->proxy.component_added = false;
@@ -510,6 +530,7 @@ int xe_gsc_proxy_init(struct xe_gsc *gsc)
  */
 int xe_gsc_proxy_start(struct xe_gsc *gsc)
 {
+	struct xe_gt *gt = gsc_to_gt(gsc);
 	int err;
 
 	/* enable the proxy interrupt in the GSC shim layer */
@@ -521,12 +542,18 @@ int xe_gsc_proxy_start(struct xe_gsc *gsc)
 	 */
 	err = xe_gsc_proxy_request_handler(gsc);
 	if (err)
-		return err;
+		goto err_irq_disable;
 
 	if (!xe_gsc_proxy_init_done(gsc)) {
-		xe_gt_err(gsc_to_gt(gsc), "GSC FW reports proxy init not completed\n");
-		return -EIO;
+		xe_gt_err(gt, "GSC FW reports proxy init not completed\n");
+		err = -EIO;
+		goto err_irq_disable;
 	}
 
+	gsc->proxy.started = true;
 	return 0;
+
+err_irq_disable:
+	gsc_proxy_irq_toggle(gsc, false);
+	return err;
 }
diff --git a/drivers/gpu/drm/xe/xe_gsc_types.h b/drivers/gpu/drm/xe/xe_gsc_types.h
index 97c056656df0..5aaa2a75861f 100644
--- a/drivers/gpu/drm/xe/xe_gsc_types.h
+++ b/drivers/gpu/drm/xe/xe_gsc_types.h
@@ -58,6 +58,8 @@ struct xe_gsc {
 		struct mutex mutex;
 		/** @proxy.component_added: whether the component has been added */
 		bool component_added;
+		/** @proxy.started: whether the proxy has been started */
+		bool started;
 		/** @proxy.bo: object to store message to and from the GSC */
 		struct xe_bo *bo;
 		/** @proxy.to_gsc: map of the memory used to send messages to the GSC */

From 89865e6dc8487b627302bdced3f965cd0c406835 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 27 Feb 2026 08:43:41 -0800
Subject: [PATCH 0791/1303] drm/xe/xe2_hpg: Correct implementation of
 Wa_16025250150

Wa_16025250150 asks us to set five register fields of the register to
0x1 each.  However we were just OR'ing this into the existing register
value (which has a default of 0x4 for each nibble-sized field) resulting
in final field values of 0x5 instead of the desired 0x1.  Correct the
RTP programming (use FIELD_SET instead of SET) to ensure each field is
assigned to exactly the value we want.

Cc: Aradhya Bhatia <aradhya.bhatia@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Cc: stable@vger.kernel.org # v6.16+
Fixes: 7654d51f1fd8 ("drm/xe/xe2hpg: Add Wa_16025250150")
Reviewed-by: Ngai-Mint Kwan <ngai-mint.kwan@linux.intel.com>
Link: https://patch.msgid.link/20260227164341.3600098-2-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit d139209ef88e48af1f6731cd45440421c757b6b5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index c7b1bd79ab17..462c2fa712e0 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -241,12 +241,13 @@ static const struct xe_rtp_entry_sr gt_was[] = {
 
 	{ XE_RTP_NAME("16025250150"),
 	  XE_RTP_RULES(GRAPHICS_VERSION(2001)),
-	  XE_RTP_ACTIONS(SET(LSN_VC_REG2,
-			     LSN_LNI_WGT(1) |
-			     LSN_LNE_WGT(1) |
-			     LSN_DIM_X_WGT(1) |
-			     LSN_DIM_Y_WGT(1) |
-			     LSN_DIM_Z_WGT(1)))
+	  XE_RTP_ACTIONS(FIELD_SET(LSN_VC_REG2,
+				   LSN_LNI_WGT_MASK | LSN_LNE_WGT_MASK |
+				   LSN_DIM_X_WGT_MASK | LSN_DIM_Y_WGT_MASK |
+				   LSN_DIM_Z_WGT_MASK,
+				   LSN_LNI_WGT(1) | LSN_LNE_WGT(1) |
+				   LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) |
+				   LSN_DIM_Z_WGT(1)))
 	},
 
 	/* Xe2_HPM */

From 3091723785def05ebfe6a50866f87a044ae314ba Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Wed, 4 Feb 2026 17:28:11 +0000
Subject: [PATCH 0792/1303] drm/xe/reg_sr: Fix leak on xa_store failure

Free the newly allocated entry when xa_store() fails to avoid a memory
leak on the error path.

v2: use goto fail_free. (Bala)

Fixes: e5283bd4dfec ("drm/xe/reg_sr: Remove register pool")
Cc: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patch.msgid.link/20260204172810.1486719-2-shuicheng.lin@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 6bc6fec71ac45f52db609af4e62bdb96b9f5fadb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_reg_sr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c
index 2e5c78940b41..a07be161cfa2 100644
--- a/drivers/gpu/drm/xe/xe_reg_sr.c
+++ b/drivers/gpu/drm/xe/xe_reg_sr.c
@@ -98,10 +98,12 @@ int xe_reg_sr_add(struct xe_reg_sr *sr,
 	*pentry = *e;
 	ret = xa_err(xa_store(&sr->xa, idx, pentry, GFP_KERNEL));
 	if (ret)
-		goto fail;
+		goto fail_free;
 
 	return 0;
 
+fail_free:
+	kfree(pentry);
 fail:
 	xe_gt_err(gt,
 		  "discarding save-restore reg %04lx (clear: %08x, set: %08x, masked: %s, mcr: %s): ret=%d\n",

From 0cfe9c4838f1147713f6b5c02094cd4dc0c598fa Mon Sep 17 00:00:00 2001
From: Varun Gupta <varun.gupta@intel.com>
Date: Mon, 23 Feb 2026 23:21:45 +0530
Subject: [PATCH 0793/1303] drm/xe: Fix memory leak in xe_vm_madvise_ioctl

When check_bo_args_are_sane() validation fails, jump to the new
free_vmas cleanup label to properly free the allocated resources.
This ensures proper cleanup in this error path.

Fixes: 293032eec4ba ("drm/xe/bo: Update atomic_access attribute on madvise")
Cc: stable@vger.kernel.org # v6.18+
Reviewed-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Varun Gupta <varun.gupta@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260223175145.1532801-1-varun.gupta@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
(cherry picked from commit 29bd06faf727a4b76663e4be0f7d770e2d2a7965)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 95bf53cc29e3..bc39a9a9790c 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -453,7 +453,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 						    madvise_range.num_vmas,
 						    args->atomic.val)) {
 				err = -EINVAL;
-				goto madv_fini;
+				goto free_vmas;
 			}
 		}
 
@@ -490,6 +490,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 err_fini:
 	if (madvise_range.has_bo_vmas)
 		drm_exec_fini(&exec);
+free_vmas:
 	kfree(madvise_range.vmas);
 	madvise_range.vmas = NULL;
 madv_fini:

From 8da8df43124128e0478beadb58faa9cab56a3f13 Mon Sep 17 00:00:00 2001
From: Yang Xiuwei <yangxiuwei@kylinos.cn>
Date: Wed, 4 Mar 2026 12:51:19 +0800
Subject: [PATCH 0794/1303] block: use __bio_add_page in bio_copy_kern

Since the bio is allocated with the exact number of pages needed via
blk_rq_map_bio_alloc(), and the loop iterates exactly that many times,
bio_add_page() cannot fail due to insufficient space.  Switch to
__bio_add_page() and remove the dead error handling code.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Yang Xiuwei <yangxiuwei@kylinos.cn>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 4533094d9458..c6fa2238d578 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -398,8 +398,7 @@ static struct bio *bio_copy_kern(struct request *rq, void *data, unsigned int le
 		if (op_is_write(op))
 			memcpy(page_address(page), p, bytes);
 
-		if (bio_add_page(bio, page, bytes, 0) < bytes)
-			break;
+		__bio_add_page(bio, page, bytes, 0);
 
 		len -= bytes;
 		p += bytes;

From cfdf6456c0aca337ff05cb1eb6e6f453e1d9dea1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Feb 2026 09:08:14 -0300
Subject: [PATCH 0795/1303] tools headers: Sync uapi/linux/prctl.h with the
 kernel source

To pick up the changes in these csets:

  5ca243f6e3c30b97 ("prctl: add arch-agnostic prctl()s for indirect branch tracking")
  28621ec2d46c6adf ("rseq: Add prctl() to enable time slice extensions")

That don't introduced these new prctls:

  $ tools/perf/trace/beauty/prctl_option.sh > before.txt
  $ cp include/uapi/linux/prctl.h tools/perf/trace/beauty/include/uapi/linux/prctl.h
  $ tools/perf/trace/beauty/prctl_option.sh > after.txt
  $ diff -u before.txt after.txt
  --- before.txt	2026-02-27 09:07:16.435611457 -0300
  +++ after.txt	2026-02-27 09:07:28.189816531 -0300
  @@ -73,6 +73,10 @@
   	[76] = "LOCK_SHADOW_STACK_STATUS",
   	[77] = "TIMER_CREATE_RESTORE_IDS",
   	[78] = "FUTEX_HASH",
  +	[79] = "RSEQ_SLICE_EXTENSION",
  +	[80] = "GET_INDIR_BR_LP_STATUS",
  +	[81] = "SET_INDIR_BR_LP_STATUS",
  +	[82] = "LOCK_INDIR_BR_LP_STATUS",
   };
   static const char *prctl_set_mm_options[] = {
   	[1] = "START_CODE",
  $

That now will be used to decode the syscall option and also to compose
filters, for instance:

  [root@five ~]# perf trace -e syscalls:sys_enter_prctl --filter option==SET_NAME
       0.000 Isolated Servi/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23f13b7aee)
       0.032 DOM Worker/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23deb25670)
       7.920 :3474328/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fbb10)
       7.935 StreamT~s #374/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fb970)
       8.400 Isolated Servi/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24bab10)
       8.418 StreamT~s #374/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24ba970)
  ^C[root@five ~]#

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/prctl.h include/uapi/linux/prctl.h

Please see tools/include/uapi/README for further details.

Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../trace/beauty/include/uapi/linux/prctl.h   | 37 +++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 51c4e8c82b1e..55b0446fff9d 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -386,4 +386,41 @@ struct prctl_mm_map {
 # define PR_FUTEX_HASH_SET_SLOTS	1
 # define PR_FUTEX_HASH_GET_SLOTS	2
 
+/* RSEQ time slice extensions */
+#define PR_RSEQ_SLICE_EXTENSION			79
+# define PR_RSEQ_SLICE_EXTENSION_GET		1
+# define PR_RSEQ_SLICE_EXTENSION_SET		2
+/*
+ * Bits for RSEQ_SLICE_EXTENSION_GET/SET
+ * PR_RSEQ_SLICE_EXT_ENABLE:	Enable
+ */
+# define PR_RSEQ_SLICE_EXT_ENABLE		0x01
+
+/*
+ * Get the current indirect branch tracking configuration for the current
+ * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS.
+ */
+#define PR_GET_INDIR_BR_LP_STATUS      80
+
+/*
+ * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will
+ * enable cpu feature for user thread, to track all indirect branches and ensure
+ * they land on arch defined landing pad instruction.
+ * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction.
+ * arch64 - If enabled, an indirect branch must land on a BTI instruction.
+ * riscv - If enabled, an indirect branch must land on an lpad instruction.
+ * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect
+ * branches will no more be tracked by cpu to land on arch defined landing pad
+ * instruction.
+ */
+#define PR_SET_INDIR_BR_LP_STATUS      81
+# define PR_INDIR_BR_LP_ENABLE		   (1UL << 0)
+
+/*
+ * Prevent further changes to the specified indirect branch tracking
+ * configuration.  All bits may be locked via this call, including
+ * undefined bits.
+ */
+#define PR_LOCK_INDIR_BR_LP_STATUS      82
+
 #endif /* _LINUX_PRCTL_H */

From f079ff37324accb91c6247b59e249ebc22bf55f5 Mon Sep 17 00:00:00 2001
From: Changqing Li <changqing.li@windriver.com>
Date: Mon, 28 Jul 2025 17:31:53 +0800
Subject: [PATCH 0796/1303] tools build: Make in-target rule robust against too
 long argument error

The command length of in-target scales with the depth of the directory
times the number of objects in the Makefile.

When there are many objects, and O=[absolute_path] is set, and the
absolute_path is relatively long.

It is possible that this line "$(call if_changed,$(host)ld_multi)" will
report error: "make[4]: /bin/sh: Argument list too long"

For example, build perf tools with O=/long/output/path

Like built-in.a and *.mod rules in scripts/Makefile.build, add
$(objpredix)/ by the shell command instead of by Make's builtin
function.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Changqing Li <changqing.li@windriver.com>
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.build | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 60e65870eae1..ad69efdd4e85 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -70,11 +70,13 @@ quiet_cmd_gen = GEN     $@
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD      $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
-                     $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
+                     printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                     xargs $(LD) -r -o $@,rm -f $@; $(AR) rcs $@)
 
 quiet_cmd_host_ld_multi = HOSTLD  $@
       cmd_host_ld_multi = $(if $(strip $(obj-y)),\
-                          $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
+                          printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                          xargs $(HOSTLD) -r -o $@,rm -f $@; $(HOSTAR) rcs $@)
 
 rust_common_cmd = \
 	$(RUSTC) $(rust_flags) \

From b6712d91f8f5a289f642c208083a8f5c27b8ab90 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Tue, 3 Mar 2026 13:15:01 -0800
Subject: [PATCH 0797/1303] perf build: Prevent "argument list too long" error

Due to a recent change, building perf may result in a build error when
it is trying to "prune orphans".

The file list passed to "rm" may exceed what the shell can handle.

The build will then abort with an error like this:

    TEST    [...]/arm64/build/linux-custom/tools/perf/pmu-events/metric_test.log
  make[5]: /bin/sh: Argument list too long
  make[5]: *** [pmu-events/Build:217: prune_orphans] Error 127
  make[5]: *** Waiting for unfinished jobs....
  make[4]: *** [Makefile.perf:773: [...]/tools/perf/pmu-events/pmu-events-in.o] Error 2
  make[4]: *** Waiting for unfinished jobs....
  make[3]: *** [Makefile.perf:289: sub-make] Error 2

Processing the arguments via "xargs", instead of passing the list of
files directly to "rm" via the shell, prevents this issue.

Fixes: 36a1b0061a584430 ("perf build: Reduce pmu-events related copying and mkdirs")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/Build | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 63c65788d442..dc5f94862a3b 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -214,7 +214,8 @@ ifneq ($(strip $(ORPHAN_FILES)),)
 quiet_cmd_rm  = RM      $^
 
 prune_orphans: $(ORPHAN_FILES)
-	$(Q)$(call echo-cmd,rm)rm -f $^
+	# The list of files can be long. Use xargs to prevent issues.
+	$(Q)$(call echo-cmd,rm)echo "$^" | xargs rm -f
 
 JEVENTS_DEPS += prune_orphans
 endif

From 212dd8477653fe72c2a6a99143cd662f6430cf4f Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 27 Feb 2026 15:51:42 +0000
Subject: [PATCH 0798/1303] arm64: Silence sparse warnings caused by the type
 casting in (cmp)xchg

The arm64 xchg/cmpxchg() wrappers cast the arguments to (unsigned long)
prior to invoking the static inline functions implementing the
operation. Some restrictive type annotations (e.g. __bitwise) lead to
sparse warnings like below:

sparse warnings: (new ones prefixed by >>)
   fs/crypto/bio.c:67:17: sparse: sparse: cast from restricted blk_status_t
>> fs/crypto/bio.c:67:17: sparse: sparse: cast to restricted blk_status_t

Force the casting in the arm64 xchg/cmpxchg() wrappers to silence
sparse.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602230947.uNRsPyBn-lkp@intel.com/
Link: https://lore.kernel.org/r/202602230947.uNRsPyBn-lkp@intel.com/
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cmpxchg.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index d7a540736741..6cf3cd6873f5 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -91,8 +91,9 @@ __XCHG_GEN(_mb)
 #define __xchg_wrapper(sfx, ptr, x)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret = (__force __typeof__(*(ptr)))				\
+		__arch_xchg##sfx((__force unsigned long)(x), (ptr),	\
+				  sizeof(*(ptr)));			\
 	__ret;								\
 })
 
@@ -175,9 +176,10 @@ __CMPXCHG_GEN(_mb)
 #define __cmpxchg_wrapper(sfx, ptr, o, n)				\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__cmpxchg##sfx((ptr), (unsigned long)(o),		\
-				(unsigned long)(n), sizeof(*(ptr)));	\
+	__ret = (__force __typeof__(*(ptr)))				\
+		__cmpxchg##sfx((ptr), (__force unsigned long)(o),	\
+				(__force unsigned long)(n),		\
+				sizeof(*(ptr)));			\
 	__ret;								\
 })
 

From 82169dace41cbaa951341b0f80f4570be3b2dec0 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 18 Feb 2026 10:52:04 +0100
Subject: [PATCH 0799/1303] xenbus: add xenbus_device parameter to
 xenbus_read_driver_state()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to prepare checking the xenbus device status in
xenbus_read_driver_state(), add the pointer to struct xenbus_device
as a parameter.

Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: "Martin K. Petersen" <martin.petersen@oracle.com> # SCSI
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>	# drivers/pci/xen-pcifront.c
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260218095205.453657-2-jgross@suse.com>
---
 drivers/net/xen-netfront.c                 | 34 +++++++++++-----------
 drivers/pci/xen-pcifront.c                 |  8 ++---
 drivers/scsi/xen-scsifront.c               |  2 +-
 drivers/xen/xen-pciback/xenbus.c           | 10 +++----
 drivers/xen/xenbus/xenbus_client.c         |  4 ++-
 drivers/xen/xenbus/xenbus_probe.c          |  6 ++--
 drivers/xen/xenbus/xenbus_probe_frontend.c |  2 +-
 include/xen/xenbus.h                       |  3 +-
 8 files changed, 36 insertions(+), 33 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 7c2220366623..e2da977c9c50 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1646,7 +1646,7 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	/* avoid the race with XDP headroom adjustment */
 	wait_event(module_wq,
-		   xenbus_read_driver_state(np->xbdev->otherend) ==
+		   xenbus_read_driver_state(np->xbdev, np->xbdev->otherend) ==
 		   XenbusStateReconfigured);
 	np->netfront_xdp_enabled = true;
 
@@ -1764,9 +1764,9 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	do {
 		xenbus_switch_state(dev, XenbusStateInitialising);
 		err = wait_event_timeout(module_wq,
-				 xenbus_read_driver_state(dev->otherend) !=
+				 xenbus_read_driver_state(dev, dev->otherend) !=
 				 XenbusStateClosed &&
-				 xenbus_read_driver_state(dev->otherend) !=
+				 xenbus_read_driver_state(dev, dev->otherend) !=
 				 XenbusStateUnknown, XENNET_TIMEOUT);
 	} while (!err);
 
@@ -2627,31 +2627,31 @@ static void xennet_bus_close(struct xenbus_device *dev)
 {
 	int ret;
 
-	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+	if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed)
 		return;
 	do {
 		xenbus_switch_state(dev, XenbusStateClosing);
 		ret = wait_event_timeout(module_wq,
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosing ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosed ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateUnknown,
-				   XENNET_TIMEOUT);
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosing ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosed ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateUnknown,
+				XENNET_TIMEOUT);
 	} while (!ret);
 
-	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+	if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed)
 		return;
 
 	do {
 		xenbus_switch_state(dev, XenbusStateClosed);
 		ret = wait_event_timeout(module_wq,
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosed ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateUnknown,
-				   XENNET_TIMEOUT);
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosed ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateUnknown,
+				XENNET_TIMEOUT);
 	} while (!ret);
 }
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 11636634ae51..cd22bf984024 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -856,7 +856,7 @@ static void pcifront_try_connect(struct pcifront_device *pdev)
 	int err;
 
 	/* Only connect once */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitialised)
 		return;
 
@@ -876,7 +876,7 @@ static int pcifront_try_disconnect(struct pcifront_device *pdev)
 	enum xenbus_state prev_state;
 
 
-	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+	prev_state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename);
 
 	if (prev_state >= XenbusStateClosing)
 		goto out;
@@ -895,7 +895,7 @@ static int pcifront_try_disconnect(struct pcifront_device *pdev)
 
 static void pcifront_attach_devices(struct pcifront_device *pdev)
 {
-	if (xenbus_read_driver_state(pdev->xdev->nodename) ==
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) ==
 	    XenbusStateReconfiguring)
 		pcifront_connect(pdev);
 }
@@ -909,7 +909,7 @@ static int pcifront_detach_devices(struct pcifront_device *pdev)
 	struct pci_dev *pci_dev;
 	char str[64];
 
-	state = xenbus_read_driver_state(pdev->xdev->nodename);
+	state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename);
 	if (state == XenbusStateInitialised) {
 		dev_dbg(&pdev->xdev->dev, "Handle skipped connect.\n");
 		/* We missed Connected and need to initialize. */
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 924025305753..ef74d4da5ab0 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -1175,7 +1175,7 @@ static void scsifront_backend_changed(struct xenbus_device *dev,
 			return;
 		}
 
-		if (xenbus_read_driver_state(dev->nodename) ==
+		if (xenbus_read_driver_state(dev, dev->nodename) ==
 		    XenbusStateInitialised)
 			scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_ADD_LUN);
 
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index b11e401f1b1e..4bd1c7a8957e 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -149,12 +149,12 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev)
 
 	mutex_lock(&pdev->dev_lock);
 	/* Make sure we only do this setup once */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitialised)
 		goto out;
 
 	/* Wait for frontend to state that it has published the configuration */
-	if (xenbus_read_driver_state(pdev->xdev->otherend) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->otherend) !=
 	    XenbusStateInitialised)
 		goto out;
 
@@ -374,7 +374,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev,
 	dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n");
 
 	mutex_lock(&pdev->dev_lock);
-	if (xenbus_read_driver_state(pdev->xdev->nodename) != state)
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != state)
 		goto out;
 
 	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
@@ -572,7 +572,7 @@ static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev)
 	/* It's possible we could get the call to setup twice, so make sure
 	 * we're not already connected.
 	 */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitWait)
 		goto out;
 
@@ -662,7 +662,7 @@ static void xen_pcibk_be_watch(struct xenbus_watch *watch,
 	struct xen_pcibk_device *pdev =
 	    container_of(watch, struct xen_pcibk_device, be_watch);
 
-	switch (xenbus_read_driver_state(pdev->xdev->nodename)) {
+	switch (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename)) {
 	case XenbusStateInitWait:
 		xen_pcibk_setup_backend(pdev);
 		break;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 2dc874fb5506..e502435145ae 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -931,12 +931,14 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 
 /**
  * xenbus_read_driver_state - read state from a store path
+ * @dev: xenbus device pointer
  * @path: path for driver
  *
  * Returns: the state of the driver rooted at the given store path, or
  * XenbusStateUnknown if no state can be read.
  */
-enum xenbus_state xenbus_read_driver_state(const char *path)
+enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
+					   const char *path)
 {
 	enum xenbus_state result;
 	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 9f9011cd7447..2eed06ba5d38 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -191,7 +191,7 @@ void xenbus_otherend_changed(struct xenbus_watch *watch,
 		return;
 	}
 
-	state = xenbus_read_driver_state(dev->otherend);
+	state = xenbus_read_driver_state(dev, dev->otherend);
 
 	dev_dbg(&dev->dev, "state is %d, (%s), %s, %s\n",
 		state, xenbus_strstate(state), dev->otherend_watch.node, path);
@@ -364,7 +364,7 @@ void xenbus_dev_remove(struct device *_dev)
 	 * closed.
 	 */
 	if (!drv->allow_rebind ||
-	    xenbus_read_driver_state(dev->nodename) == XenbusStateClosing)
+	    xenbus_read_driver_state(dev, dev->nodename) == XenbusStateClosing)
 		xenbus_switch_state(dev, XenbusStateClosed);
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_remove);
@@ -514,7 +514,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 	size_t stringlen;
 	char *tmpstring;
 
-	enum xenbus_state state = xenbus_read_driver_state(nodename);
+	enum xenbus_state state = xenbus_read_driver_state(NULL, nodename);
 
 	if (state != XenbusStateInitialising) {
 		/* Device is not new, so ignore it.  This can happen if a
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index f04707d1f667..ca04609730df 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -253,7 +253,7 @@ static int print_device_status(struct device *dev, void *data)
 	} else if (xendev->state < XenbusStateConnected) {
 		enum xenbus_state rstate = XenbusStateUnknown;
 		if (xendev->otherend)
-			rstate = xenbus_read_driver_state(xendev->otherend);
+			rstate = xenbus_read_driver_state(xendev, xendev->otherend);
 		pr_warn("Timeout connecting to device: %s (local state %d, remote state %d)\n",
 			xendev->nodename, xendev->state, rstate);
 	}
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index c94caf852aea..15319da65b7f 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -228,7 +228,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr);
 int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port);
 int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port);
 
-enum xenbus_state xenbus_read_driver_state(const char *path);
+enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
+					   const char *path);
 
 __printf(3, 4)
 void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...);

From e2dcf9065536ab4a1b00828ff0d19f7d282dfecc Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 18 Feb 2026 10:52:05 +0100
Subject: [PATCH 0800/1303] xen/xenbus: better handle backend crash
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the backend domain crashes, coordinated device cleanup is not
possible (as it involves waiting for the backend state change). In that
case, toolstack forcefully removes frontend xenstore entries.
xenbus_dev_changed() handles this case, and triggers device cleanup.
It's possible that toolstack manages to connect new device in that
place, before xenbus_dev_changed() notices the old one is missing. If
that happens, new one won't be probed and will forever remain in
XenbusStateInitialising.

Fix this by checking the frontend's state in Xenstore. In case it has
been reset to XenbusStateInitialising by Xen tools, consider this
being the result of an unplug+plug operation.

It's important that cleanup on such unplug doesn't modify Xenstore
entries (especially the "state" key) as it belong to the new device
to be probed - changing it would derail establishing connection to the
new backend (most likely, closing the device before it was even
connected). Handle this case by setting new xenbus_device->vanished
flag to true, and check it before changing state entry.

And even if xenbus_dev_changed() correctly detects the device was
forcefully removed, the cleanup handling is still racy. Since this whole
handling doesn't happened in a single Xenstore transaction, it's possible
that toolstack might put a new device there already. Avoid re-creating
the state key (which in the case of loosing the race would actually
close newly attached device).

The problem does not apply to frontend domain crash, as this case
involves coordinated cleanup.

Problem originally reported at
https://lore.kernel.org/xen-devel/aOZvivyZ9YhVWDLN@mail-itl/T/#t,
including reproduction steps.

Based-on-patch-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260218095205.453657-3-jgross@suse.com>
---
 drivers/xen/xenbus/xenbus_client.c | 13 +++++++++--
 drivers/xen/xenbus/xenbus_probe.c  | 36 ++++++++++++++++++++++++++++++
 include/xen/xenbus.h               |  1 +
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index e502435145ae..19672b08a680 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -226,8 +226,9 @@ __xenbus_switch_state(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int current_state;
 	int err, abort;
+	bool vanished = false;
 
-	if (state == dev->state)
+	if (state == dev->state || dev->vanished)
 		return 0;
 
 again:
@@ -242,6 +243,10 @@ __xenbus_switch_state(struct xenbus_device *dev,
 	err = xenbus_scanf(xbt, dev->nodename, "state", "%d", &current_state);
 	if (err != 1)
 		goto abort;
+	if (current_state != dev->state && current_state == XenbusStateInitialising) {
+		vanished = true;
+		goto abort;
+	}
 
 	err = xenbus_printf(xbt, dev->nodename, "state", "%d", state);
 	if (err) {
@@ -256,7 +261,7 @@ __xenbus_switch_state(struct xenbus_device *dev,
 		if (err == -EAGAIN && !abort)
 			goto again;
 		xenbus_switch_fatal(dev, depth, err, "ending transaction");
-	} else
+	} else if (!vanished)
 		dev->state = state;
 
 	return 0;
@@ -941,6 +946,10 @@ enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
 					   const char *path)
 {
 	enum xenbus_state result;
+
+	if (dev && dev->vanished)
+		return XenbusStateUnknown;
+
 	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
 	if (err)
 		result = XenbusStateUnknown;
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 2eed06ba5d38..eb260eceb4d2 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -444,6 +444,9 @@ static void xenbus_cleanup_devices(const char *path, struct bus_type *bus)
 		info.dev = NULL;
 		bus_for_each_dev(bus, NULL, &info, cleanup_dev);
 		if (info.dev) {
+			dev_warn(&info.dev->dev,
+				 "device forcefully removed from xenstore\n");
+			info.dev->vanished = true;
 			device_unregister(&info.dev->dev);
 			put_device(&info.dev->dev);
 		}
@@ -659,6 +662,39 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 		return;
 
 	dev = xenbus_device_find(root, &bus->bus);
+	/*
+	 * Backend domain crash results in not coordinated frontend removal,
+	 * without going through XenbusStateClosing. If this is a new instance
+	 * of the same device Xen tools will have reset the state to
+	 * XenbusStateInitializing.
+	 * It might be that the backend crashed early during the init phase of
+	 * device setup, in which case the known state would have been
+	 * XenbusStateInitializing. So test the backend domid to match the
+	 * saved one. In case the new backend happens to have the same domid as
+	 * the old one, we can just carry on, as there is no inconsistency
+	 * resulting in this case.
+	 */
+	if (dev && !strcmp(bus->root, "device")) {
+		enum xenbus_state state = xenbus_read_driver_state(dev, dev->nodename);
+		unsigned int backend = xenbus_read_unsigned(root, "backend-id",
+							    dev->otherend_id);
+
+		if (state == XenbusStateInitialising &&
+		    (state != dev->state || backend != dev->otherend_id)) {
+			/*
+			 * State has been reset, assume the old one vanished
+			 * and new one needs to be probed.
+			 */
+			dev_warn(&dev->dev,
+				 "state reset occurred, reconnecting\n");
+			dev->vanished = true;
+		}
+		if (dev->vanished) {
+			device_unregister(&dev->dev);
+			put_device(&dev->dev);
+			dev = NULL;
+		}
+	}
 	if (!dev)
 		xenbus_probe_node(bus, type, root);
 	else
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 15319da65b7f..8ca15743af7f 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -80,6 +80,7 @@ struct xenbus_device {
 	const char *devicetype;
 	const char *nodename;
 	const char *otherend;
+	bool vanished;
 	int otherend_id;
 	struct xenbus_watch otherend_watch;
 	struct device dev;

From c25c4aa3f79a488cc270507935a29c07dc6bddfc Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 27 Feb 2026 18:53:06 +0000
Subject: [PATCH 0801/1303] arm64: mm: Add PTE_DIRTY back to PAGE_KERNEL* to
 fix kexec/hibernation

Commit 143937ca51cc ("arm64, mm: avoid always making PTE dirty in
pte_mkwrite()") changed pte_mkwrite_novma() to only clear PTE_RDONLY
when PTE_DIRTY is set. This was to allow writable-clean PTEs for swap
pages that haven't actually been written.

However, this broke kexec and hibernation for some platforms. Both go
through trans_pgd_create_copy() -> _copy_pte(), which calls
pte_mkwrite_novma() to make the temporary linear-map copy fully
writable. With the updated pte_mkwrite_novma(), read-only kernel pages
(without PTE_DIRTY) remain read-only in the temporary mapping.
While such behaviour is fine for user pages where hardware DBM or
trapping will make them writeable, subsequent in-kernel writes by the
kexec relocation code will fault.

Add PTE_DIRTY back to all _PAGE_KERNEL* protection definitions. This was
the case prior to 5.4, commit aa57157be69f ("arm64: Ensure
VM_WRITE|VM_SHARED ptes are clean by default"). With the kernel
linear-map PTEs always having PTE_DIRTY set, pte_mkwrite_novma()
correctly clears PTE_RDONLY.

Fixes: 143937ca51cc ("arm64, mm: avoid always making PTE dirty in pte_mkwrite()")
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: stable@vger.kernel.org
Reported-by: Jianpeng Chang <jianpeng.chang.cn@windriver.com>
Link: https://lore.kernel.org/r/20251204062722.3367201-1-jianpeng.chang.cn@windriver.com
Cc: Will Deacon <will@kernel.org>
Cc: Huang, Ying <ying.huang@linux.alibaba.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Huang Ying <ying.huang@linux.alibaba.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2b32639160de..f560e6420267 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -50,11 +50,11 @@
 
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
-#define _PAGE_KERNEL		(PROT_NORMAL)
-#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
-#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
-#define _PAGE_KERNEL_EXEC	(PROT_NORMAL & ~PTE_PXN)
-#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
+#define _PAGE_KERNEL		(PROT_NORMAL | PTE_DIRTY)
+#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC	((PROT_NORMAL & ~PTE_PXN) | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT | PTE_DIRTY)
 
 #define _PAGE_SHARED		(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define _PAGE_SHARED_EXEC	(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)

From 30f998c992c9d32a5c2774ec1b624339483db19d Mon Sep 17 00:00:00 2001
From: Dmitrii Dolgov <9erthalion6@gmail.com>
Date: Thu, 26 Feb 2026 17:59:59 +0100
Subject: [PATCH 0802/1303] tools build: Fix rust cross compilation

Currently no target is specified to compile rust code when needed, which
breaks cross compilation. E.g. for arm64:

      LD      /tmp/build/tests/workloads/perf-test-in.o
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    [...repeated...]
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a: error adding symbols: file in wrong format
    make[5]: *** [/perf/tools/build/Makefile.build:162: /tmp/build/tests/workloads/perf-test-in.o] Error 1
    make[4]: *** [/perf/tools/build/Makefile.build:156: workloads] Error 2
    make[3]: *** [/perf/tools/build/Makefile.build:156: tests] Error 2
    make[2]: *** [Makefile.perf:785: /tmp/build/perf-test-in.o] Error 2
    make[2]: *** Waiting for unfinished jobs....
    make[1]: *** [Makefile.perf:289: sub-make] Error 2
    make: *** [Makefile:76: all] Error 2

Detect required target and pass it via rust_flags to the compiler.

Note that CROSS_COMPILE might be different from what rust compiler
expects, since it may omit the target vendor value, e.g.
"aarch64-linux-gnu" instead of "aarch64-unknown-linux-gnu".

Thus explicitly map supported CROSS_COMPILE values to corresponding Rust
versions, as suggested by Miguel Ojeda.

Tested using arm64 cross-compilation example from [1].

Fixes: 2e05bb52a12d3cdb ("perf test workload: Add code_with_type test workload")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Levi Zim <i@kxxt.dev>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nicolas Schier <nsc@kernel.org>
Link: https://perfwiki.github.io/main/arm64-cross-compilation-dockerfile/ [1]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Build.include  |  9 +++++++++
 tools/perf/Makefile.config | 18 ++++++++++++++++++
 tools/perf/Makefile.perf   |  2 +-
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/tools/build/Build.include b/tools/build/Build.include
index e45b2eb0d24a..cd0baa7a168d 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -98,6 +98,15 @@ c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1))
 c_flags   = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2))
 cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
 
+###
+# Rust flags to be used on rule definition, includes:
+# - global $(RUST_FLAGS)
+# - per target Rust flags
+# - per object Rust flags
+rust_flags_1 = $(RUST_FLAGS) $(RUST_FLAGS_$(basetarget).o) $(RUST_FLAGS_$(obj))
+rust_flags_2 = $(filter-out $(RUST_FLAGS_REMOVE_$(basetarget).o), $(rust_flags_1))
+rust_flags   = $(filter-out $(RUST_FLAGS_REMOVE_$(obj)), $(rust_flags_2))
+
 ###
 ## HOSTCC C flags
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index a8dc72cfe48e..15fbba9f4ca8 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1163,6 +1163,24 @@ ifndef NO_RUST
     CFLAGS += -DHAVE_RUST_SUPPORT
     $(call detected,CONFIG_RUST_SUPPORT)
   endif
+
+  ifneq ($(CROSS_COMPILE),)
+    RUST_TARGET_FLAGS_arm	:= arm-unknown-linux-gnueabi
+    RUST_TARGET_FLAGS_arm64	:= aarch64-unknown-linux-gnu
+    RUST_TARGET_FLAGS_m68k	:= m68k-unknown-linux-gnu
+    RUST_TARGET_FLAGS_mips	:= mipsel-unknown-linux-gnu
+    RUST_TARGET_FLAGS_powerpc	:= powerpc64le-unknown-linux-gnu
+    RUST_TARGET_FLAGS_riscv	:= riscv64gc-unknown-linux-gnu
+    RUST_TARGET_FLAGS_s390	:= s390x-unknown-linux-gnu
+    RUST_TARGET_FLAGS_x86	:= x86_64-unknown-linux-gnu
+    RUST_TARGET_FLAGS_x86_64	:= x86_64-unknown-linux-gnu
+
+    ifeq ($(RUST_TARGET_FLAGS_$(ARCH)),)
+      $(error Unknown rust cross compilation architecture $(ARCH))
+    endif
+
+    RUST_FLAGS += --target=$(RUST_TARGET_FLAGS_$(ARCH))
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 11b63bafdb23..f7b936deeaa2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -274,7 +274,7 @@ ifeq ($(PYLINT),1)
   PYLINT := $(shell which pylint 2> /dev/null)
 endif
 
-export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
+export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK
 export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT
 
 include $(srctree)/tools/build/Makefile.include

From 6036165ab1851ee28cedea592ee0393b77bfd0c0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:41:12 -0300
Subject: [PATCH 0803/1303] perf beauty: Sync linux/mount.h copy with the
 kernel sources

To pick the changes from:

  9b8a0ba68246a61d ("mount: add OPEN_TREE_NAMESPACE")
  0e5032237ee55301 ("statmount: accept fd as a parameter")

That doesn't change anything in tools this time as nothing that is
harvested by the beauty scripts got changed:

  $ ls -1 tools/perf/trace/beauty/*mount*sh
  tools/perf/trace/beauty/fsmount.sh
  tools/perf/trace/beauty/mount_flags.sh
  tools/perf/trace/beauty/move_mount_flags.sh
  $

This addresses this perf build warning.

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/mount.h include/uapi/linux/mount.h

Please see tools/include/uapi/README for further details.

Cc: Christian Brauner <brauner@kernel.org>
Cc: Bhavik Sachdev <b.sachdev1904@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/mount.h | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index 5d3f8c9e3a62..d9d86598d100 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -61,7 +61,8 @@
 /*
  * open_tree() flags.
  */
-#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLONE		(1 << 0)	/* Clone the target tree and attach the clone */
+#define OPEN_TREE_NAMESPACE	(1 << 1)	/* Clone the target tree into a new mount namespace */
 #define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
 
 /*
@@ -197,7 +198,10 @@ struct statmount {
  */
 struct mnt_id_req {
 	__u32 size;
-	__u32 mnt_ns_fd;
+	union {
+		__u32 mnt_ns_fd;
+		__u32 mnt_fd;
+	};
 	__u64 mnt_id;
 	__u64 param;
 	__u64 mnt_ns_id;
@@ -232,4 +236,9 @@ struct mnt_id_req {
 #define LSMT_ROOT		0xffffffffffffffff	/* root mount */
 #define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
 
+/*
+ * @flag bits for statmount(2)
+ */
+#define STATMOUNT_BY_FD		0x00000001U	/* want mountinfo for given fd */
+
 #endif /* _UAPI_LINUX_MOUNT_H */

From e367679f167e46372cafca9cd903d60f84aa5e72 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:46:01 -0300
Subject: [PATCH 0804/1303] perf beauty: Sync UAPI linux/fs.h with kernel
 sources

To pick up changes from:

  0e6b7eae1fded85f ("fs: add FS_XFLAG_VERITY for fs-verity files")

These are used to beautify fs syscall arguments, albeit the changes in
this update are not affecting those beautifiers.

This addresses these tools/perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h

Please see tools/include/uapi/README.

Cc: Andrey Albershteyn <aalbersh@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/fs.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 66ca526cf786..70b2b661f42c 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -253,6 +253,7 @@ struct file_attr {
 #define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
 #define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
 #define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_VERITY		0x00020000	/* fs-verity enabled */
 #define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
 
 /* the read-only stuff doesn't really belong here, but any other place is

From 3abbb7cae8d8bffae3516d885cde9f13c6ceb833 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: [PATCH 0805/1303] perf beauty: Update the
 arch/x86/include/asm/irq_vectors.h copy with the kernel sources

To pick up the change in:

  a1fab3e69d9d0e9b ("x86/irq: Fix comment on IRQ vector layout")

That just adds one comment, so no changes in perf tooling, just silences
this build warning:

  diff -u tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h arch/x86/include/asm/irq_vectors.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
index 6e1d5b955aae..85253fc8e384 100644
--- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
+++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
@@ -77,6 +77,7 @@
  */
 #define IRQ_WORK_VECTOR			0xf6
 
+/* IRQ vector for PMIs when running a guest with a mediated PMU. */
 #define PERF_GUEST_MEDIATED_PMI_VECTOR	0xf5
 
 #define DEFERRED_ERROR_VECTOR		0xf4

From ecd5a2fd4c7495a1a923c754c47cdd500f5b30df Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: [PATCH 0806/1303] perf beauty: Update the linux/perf_event.h copy
 with the kernel sources

Update it as one comment got realigned, probably in a merge, so no
changes in perf tooling, just silences this build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 76e9d0664d0c..fd10aa8d697f 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1396,7 +1396,7 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L4			0x0004 /* L4 */
 #define PERF_MEM_LVLNUM_L2_MHB			0x0005 /* L2 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_MSC			0x0006 /* Memory-side Cache */
-#define PERF_MEM_LVLNUM_L0			0x0007   /* L0 */
+#define PERF_MEM_LVLNUM_L0			0x0007 /* L0 */
 #define PERF_MEM_LVLNUM_UNC			0x0008 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL			0x0009 /* CXL */
 #define PERF_MEM_LVLNUM_IO			0x000a /* I/O */

From c3320153769f05fd7fe9d840cb555dd3080ae424 Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Fri, 27 Feb 2026 19:19:28 -0500
Subject: [PATCH 0807/1303] nvme: fix memory allocation in nvme_pr_read_keys()

nvme_pr_read_keys() takes num_keys from userspace and uses it to
calculate the allocation size for rse via struct_size(). The upper
limit is PR_KEYS_MAX (64K).

A malicious or buggy userspace can pass a large num_keys value that
results in a 4MB allocation attempt at most, causing a warning in
the page allocator when the order exceeds MAX_PAGE_ORDER.

To fix this, use kvzalloc() instead of kzalloc().

This bug has the same reasoning and fix with the patch below:
https://lore.kernel.org/linux-block/20251212013510.3576091-1-kartikey406@gmail.com/

Warning log:
WARNING: mm/page_alloc.c:5216 at __alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216, CPU#1: syz-executor117/272
Modules linked in:
CPU: 1 UID: 0 PID: 272 Comm: syz-executor117 Not tainted 6.19.0 #1 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
RIP: 0010:__alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216
Code: ff 83 bd a8 fe ff ff 0a 0f 86 69 fb ff ff 0f b6 1d f9 f9 c4 04 80 fb 01 0f 87 3b 76 30 ff 83 e3 01 75 09 c6 05 e4 f9 c4 04 01 <0f> 0b 48 c7 85 70 fe ff ff 00 00 00 00 e9 8f fd ff ff 31 c0 e9 0d
RSP: 0018:ffffc90000fcf450 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff920001f9ea0
RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000040dc0
RBP: ffffc90000fcf648 R08: ffff88800b6c3380 R09: 0000000000000001
R10: ffffc90000fcf840 R11: ffff88807ffad280 R12: 0000000000000000
R13: 0000000000040dc0 R14: 0000000000000001 R15: ffffc90000fcf620
FS:  0000555565db33c0(0000) GS:ffff8880be26c000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000002000000c CR3: 0000000003b72000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 alloc_pages_mpol+0x236/0x4d0 mm/mempolicy.c:2486
 alloc_frozen_pages_noprof+0x149/0x180 mm/mempolicy.c:2557
 ___kmalloc_large_node+0x10c/0x140 mm/slub.c:5598
 __kmalloc_large_node_noprof+0x25/0xc0 mm/slub.c:5629
 __do_kmalloc_node mm/slub.c:5645 [inline]
 __kmalloc_noprof+0x483/0x6f0 mm/slub.c:5669
 kmalloc_noprof include/linux/slab.h:961 [inline]
 kzalloc_noprof include/linux/slab.h:1094 [inline]
 nvme_pr_read_keys+0x8f/0x4c0 drivers/nvme/host/pr.c:245
 blkdev_pr_read_keys block/ioctl.c:456 [inline]
 blkdev_common_ioctl+0x1b71/0x29b0 block/ioctl.c:730
 blkdev_ioctl+0x299/0x700 block/ioctl.c:786
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x1bf/0x220 fs/ioctl.c:583
 x64_sys_call+0x1280/0x21b0 mnt/fuzznvme_1/fuzznvme/linux-build/v6.19/./arch/x86/include/generated/asm/syscalls_64.h:17
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x71/0x330 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7fb893d3108d
Code: 28 c3 e8 46 1e 00 00 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffff61f2f38 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffff61f3138 RCX: 00007fb893d3108d
RDX: 0000000020000040 RSI: 00000000c01070ce RDI: 0000000000000003
RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffff61f3138
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
R13: 00007ffff61f3128 R14: 00007fb893dae530 R15: 0000000000000001
 </TASK>

Fixes: 5fd96a4e15de (nvme: Add pr_ops read_keys support)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index ad2ecc2f49a9..fe7dbe264815 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -242,7 +242,7 @@ static int nvme_pr_read_keys(struct block_device *bdev,
 	if (rse_len > U32_MAX)
 		return -EINVAL;
 
-	rse = kzalloc(rse_len, GFP_KERNEL);
+	rse = kvzalloc(rse_len, GFP_KERNEL);
 	if (!rse)
 		return -ENOMEM;
 
@@ -267,7 +267,7 @@ static int nvme_pr_read_keys(struct block_device *bdev,
 	}
 
 free_rse:
-	kfree(rse);
+	kvfree(rse);
 	return ret;
 }
 

From 916a9f385d81a65f7209614742208b8a923434bd Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: [PATCH 0808/1303] tools headers: Update the linux/gfp_types.h copy
 with the kernel sources

To pick up the changes in:

  f3ec502b6755a3bf ("mm/slab: mark alloc tags empty for sheaves allocated with __GFP_NO_OBJ_EXT")
  241b3a09639c317b ("mm: clarify GFP_ATOMIC/GFP_NOWAIT doc-comment")

That just adds some comments, so no changes in perf tooling, just silences
this build warning:

Warning: Kernel ABI header differences:
  diff -u tools/include/linux/gfp_types.h include/linux/gfp_types.h

Please see tools/include/uapi/README.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/gfp_types.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h
index 3de43b12209e..6c75df30a281 100644
--- a/tools/include/linux/gfp_types.h
+++ b/tools/include/linux/gfp_types.h
@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
@@ -309,8 +311,10 @@ enum {
  *
  * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
  * watermark is applied to allow access to "atomic reserves".
- * The current implementation doesn't support NMI and few other strict
- * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
+ * The current implementation doesn't support NMI, nor contexts that disable
+ * preemption under PREEMPT_RT. This includes raw_spin_lock() and plain
+ * preempt_disable() - see "Memory allocation" in
+ * Documentation/core-api/real-time/differences.rst for more info.
  *
  * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
  * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
@@ -321,6 +325,7 @@ enum {
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
  * reclaim, start physical IO or use any filesystem callback.  It is very
  * likely to fail to allocate memory, even for very small allocations.
+ * The same restrictions on calling contexts apply as for %GFP_ATOMIC.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.

From 9cd284105bb77b063b61523f62096e853b8b890b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:32:19 -0300
Subject: [PATCH 0809/1303] tools headers UAPI: Sync linux/kvm.h with the
 kernel sources

To pick the changes in:

  f7ab71f178d56447 ("KVM: s390: Add explicit padding to struct kvm_s390_keyop")
  0ee4ddc1647b8b3b ("KVM: s390: Storage key manipulation IOCTL")
  fa9893fadbc245e1 ("KVM: Introduce KVM_EXIT_SNP_REQ_CERTS for SNP certificate-fetching")
  f174a9ffcd48d78a ("KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots")

That just rebuilds perf, as these patches add just one new KVM ioctl,
but for S390, that is not being considered by tools/perf/trace/beauty/kvm_ioctl.sh
so far.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index dddb781b0507..65500f5db379 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -135,6 +135,12 @@ struct kvm_xen_exit {
 	} u;
 };
 
+struct kvm_exit_snp_req_certs {
+	__u64 gpa;
+	__u64 npages;
+	__u64 ret;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -180,6 +186,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_MEMORY_FAULT     39
 #define KVM_EXIT_TDX              40
 #define KVM_EXIT_ARM_SEA          41
+#define KVM_EXIT_ARM_LDST64B      42
+#define KVM_EXIT_SNP_REQ_CERTS    43
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -402,7 +410,7 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
-		/* KVM_EXIT_ARM_NISV */
+		/* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */
 		struct {
 			__u64 esr_iss;
 			__u64 fault_ipa;
@@ -482,6 +490,8 @@ struct kvm_run {
 			__u64 gva;
 			__u64 gpa;
 		} arm_sea;
+		/* KVM_EXIT_SNP_REQ_CERTS */
+		struct kvm_exit_snp_req_certs snp_req_certs;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -974,6 +984,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_GUEST_MEMFD_FLAGS 244
 #define KVM_CAP_ARM_SEA_TO_USER 245
 #define KVM_CAP_S390_USER_OPEREXEC 246
+#define KVM_CAP_S390_KEYOP 247
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1219,6 +1230,16 @@ struct kvm_vfio_spapr_tce {
 	__s32	tablefd;
 };
 
+#define KVM_S390_KEYOP_ISKE 0x01
+#define KVM_S390_KEYOP_RRBE 0x02
+#define KVM_S390_KEYOP_SSKE 0x03
+struct kvm_s390_keyop {
+	__u64 guest_addr;
+	__u8  key;
+	__u8  operation;
+	__u8  pad[6];
+};
+
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
@@ -1238,6 +1259,7 @@ struct kvm_vfio_spapr_tce {
 #define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
 #define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
 #define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
+#define KVM_S390_KEYOP           _IOWR(KVMIO, 0x53, struct kvm_s390_keyop)
 
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)

From 48084cc153a5b0fbf0aa98d47670d3be0b9f64d5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:40 +0100
Subject: [PATCH 0810/1303] x86/numa: Store extra copy of numa_nodes_parsed

The topology setup code needs to know the total number of physical
nodes enumerated in SRAT; however NUMA_EMU can cause the existing
numa_nodes_parsed bitmap to be fictitious. Therefore, keep a copy of
the bitmap specifically to retain the physical node count.

Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110059.889884023@infradead.org
---
 arch/x86/include/asm/numa.h | 6 ++++++
 arch/x86/mm/numa.c          | 8 ++++++++
 arch/x86/mm/srat.c          | 2 ++
 3 files changed, 16 insertions(+)

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 53ba39ce010c..a9063f332fa6 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -22,6 +22,7 @@ extern int numa_off;
  */
 extern s16 __apicid_to_node[MAX_LOCAL_APIC];
 extern nodemask_t numa_nodes_parsed __initdata;
+extern nodemask_t numa_phys_nodes_parsed __initdata;
 
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
@@ -48,6 +49,7 @@ extern void __init init_cpu_to_node(void);
 extern void numa_add_cpu(unsigned int cpu);
 extern void numa_remove_cpu(unsigned int cpu);
 extern void init_gi_nodes(void);
+extern int num_phys_nodes(void);
 #else	/* CONFIG_NUMA */
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
@@ -55,6 +57,10 @@ static inline void init_cpu_to_node(void)		{ }
 static inline void numa_add_cpu(unsigned int cpu)	{ }
 static inline void numa_remove_cpu(unsigned int cpu)	{ }
 static inline void init_gi_nodes(void)			{ }
+static inline int num_phys_nodes(void)
+{
+	return 1;
+}
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 7a97327140df..99d0a9332c14 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -48,6 +48,8 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
+nodemask_t numa_phys_nodes_parsed __initdata;
+
 int numa_cpu_node(int cpu)
 {
 	u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
@@ -57,6 +59,11 @@ int numa_cpu_node(int cpu)
 	return NUMA_NO_NODE;
 }
 
+int __init num_phys_nodes(void)
+{
+	return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES);
+}
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
@@ -210,6 +217,7 @@ static int __init dummy_numa_init(void)
 	       0LLU, PFN_PHYS(max_pfn) - 1);
 
 	node_set(0, numa_nodes_parsed);
+	node_set(0, numa_phys_nodes_parsed);
 	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
 
 	return 0;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 6f8e0f21c710..44ca66651756 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -57,6 +57,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 	}
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
 	pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node);
 }
 
@@ -97,6 +98,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
 	pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node);
 }
 

From ae6730ff42b3a13d94b405edeb5e40108b6d21b6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:41 +0100
Subject: [PATCH 0811/1303] x86/topo: Add topology_num_nodes_per_package()

Use the MADT and SRAT table data to compute __num_nodes_per_package.

Specifically, SRAT has already been parsed in x86_numa_init(), which is called
before acpi_boot_init() which parses MADT. So both are available in
topology_init_possible_cpus().

This number is useful to divinate the various Intel CoD/SNC and AMD NPS modes,
since the platforms are failing to provide this otherwise.

Doing it this way is independent of the number of online CPUs and
other such shenanigans.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.004091624@infradead.org
---
 arch/x86/include/asm/topology.h |  6 ++++++
 arch/x86/kernel/cpu/common.c    |  3 +++
 arch/x86/kernel/cpu/topology.c  | 13 +++++++++++--
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 1fadf0cf520c..0ba9bdb99871 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -155,6 +155,7 @@ extern unsigned int __max_logical_packages;
 extern unsigned int __max_threads_per_core;
 extern unsigned int __num_threads_per_package;
 extern unsigned int __num_cores_per_package;
+extern unsigned int __num_nodes_per_package;
 
 const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c);
 enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c);
@@ -179,6 +180,11 @@ static inline unsigned int topology_num_threads_per_package(void)
 	return __num_threads_per_package;
 }
 
+static inline unsigned int topology_num_nodes_per_package(void)
+{
+	return __num_nodes_per_package;
+}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level);
 #else
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1c3261cae40c..a8ff4376c286 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -95,6 +95,9 @@ EXPORT_SYMBOL(__max_dies_per_package);
 unsigned int __max_logical_packages __ro_after_init = 1;
 EXPORT_SYMBOL(__max_logical_packages);
 
+unsigned int __num_nodes_per_package __ro_after_init = 1;
+EXPORT_SYMBOL(__num_nodes_per_package);
+
 unsigned int __num_cores_per_package __ro_after_init = 1;
 EXPORT_SYMBOL(__num_cores_per_package);
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 23190a786d31..eafcb1fc185a 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -31,6 +31,7 @@
 #include <asm/mpspec.h>
 #include <asm/msr.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 
 #include "cpu.h"
 
@@ -492,11 +493,19 @@ void __init topology_init_possible_cpus(void)
 	set_nr_cpu_ids(allowed);
 
 	cnta = domain_weight(TOPO_PKG_DOMAIN);
-	cntb = domain_weight(TOPO_DIE_DOMAIN);
 	__max_logical_packages = cnta;
+
+	pr_info("Max. logical packages: %3u\n", __max_logical_packages);
+
+	cntb = num_phys_nodes();
+	__num_nodes_per_package = DIV_ROUND_UP(cntb, cnta);
+
+	pr_info("Max. logical nodes:    %3u\n", cntb);
+	pr_info("Num. nodes per package:%3u\n", __num_nodes_per_package);
+
+	cntb = domain_weight(TOPO_DIE_DOMAIN);
 	__max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta));
 
-	pr_info("Max. logical packages: %3u\n", cnta);
 	pr_info("Max. logical dies:     %3u\n", cntb);
 	pr_info("Max. dies per package: %3u\n", __max_dies_per_package);
 

From 717b64d58cff6fb97f97be07e382ed7641167a56 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:42 +0100
Subject: [PATCH 0812/1303] x86/topo: Replace x86_has_numa_in_package

.. with the brand spanking new topology_num_nodes_per_package().

Having the topology setup determine this value during MADT/SRAT parsing before
SMP bringup avoids having to detect this situation when building the SMP
topology masks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.123701837@infradead.org
---
 arch/x86/kernel/smpboot.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5cd6950ab672..db3e481cdbb2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -468,13 +468,6 @@ static int x86_cluster_flags(void)
 }
 #endif
 
-/*
- * Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
- * Sub-NUMA Clustering have this.
- */
-static bool x86_has_numa_in_package;
-
 static struct sched_domain_topology_level x86_topology[] = {
 	SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT),
 #ifdef CONFIG_SCHED_CLUSTER
@@ -496,7 +489,7 @@ static void __init build_sched_topology(void)
 	 * PKG domain since the NUMA domains will auto-magically create the
 	 * right spanning domains based on the SLIT.
 	 */
-	if (x86_has_numa_in_package) {
+	if (topology_num_nodes_per_package() > 1) {
 		unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2;
 
 		memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom]));
@@ -550,7 +543,7 @@ int arch_sched_node_distance(int from, int to)
 	case INTEL_GRANITERAPIDS_X:
 	case INTEL_ATOM_DARKMONT_X:
 
-		if (!x86_has_numa_in_package || topology_max_packages() == 1 ||
+		if (topology_max_packages() == 1 || topology_num_nodes_per_package() == 1 ||
 		    d < REMOTE_DISTANCE)
 			return d;
 
@@ -606,7 +599,7 @@ void set_cpu_sibling_map(int cpu)
 		o = &cpu_data(i);
 
 		if (match_pkg(c, o) && !topology_same_node(c, o))
-			x86_has_numa_in_package = true;
+			WARN_ON_ONCE(topology_num_nodes_per_package() == 1);
 
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(topology_sibling_cpumask, cpu, i);

From 528d89a4707e5bfd86e30823c45dbb66877df900 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:43 +0100
Subject: [PATCH 0813/1303] x86/topo: Fix SNC topology mess

Per 4d6dd05d07d0 ("sched/topology: Fix sched domain build error for GNR, CWF in
SNC-3 mode"), the original crazy SNC-3 SLIT table was:

node distances:
node     0    1    2    3    4    5
    0:   10   15   17   21   28   26
    1:   15   10   15   23   26   23
    2:   17   15   10   26   23   21
    3:   21   28   26   10   15   17
    4:   23   26   23   15   10   15
    5:   26   23   21   17   15   10

And per:

  https://lore.kernel.org/lkml/20250825075642.GQ3245006@noisy.programming.kicks-ass.net/

The suggestion was to average the off-trace clusters to restore sanity.

However, 4d6dd05d07d0 implements this under various assumptions:

 - anything GNR/CWF with numa_in_package;
 - there will never be more than 2 packages;
 - the off-trace cluster will have distance >20

And then HPE shows up with a machine that matches the
Vendor-Family-Model checks but looks like this:

Here's an 8 socket (2 chassis) HPE system with SNC enabled:

node   0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15
  0:  10  12  16  16  16  16  18  18  40  40  40  40  40  40  40  40
  1:  12  10  16  16  16  16  18  18  40  40  40  40  40  40  40  40
  2:  16  16  10  12  18  18  16  16  40  40  40  40  40  40  40  40
  3:  16  16  12  10  18  18  16  16  40  40  40  40  40  40  40  40
  4:  16  16  18  18  10  12  16  16  40  40  40  40  40  40  40  40
  5:  16  16  18  18  12  10  16  16  40  40  40  40  40  40  40  40
  6:  18  18  16  16  16  16  10  12  40  40  40  40  40  40  40  40
  7:  18  18  16  16  16  16  12  10  40  40  40  40  40  40  40  40
  8:  40  40  40  40  40  40  40  40  10  12  16  16  16  16  18  18
  9:  40  40  40  40  40  40  40  40  12  10  16  16  16  16  18  18
 10:  40  40  40  40  40  40  40  40  16  16  10  12  18  18  16  16
 11:  40  40  40  40  40  40  40  40  16  16  12  10  18  18  16  16
 12:  40  40  40  40  40  40  40  40  16  16  18  18  10  12  16  16
 13:  40  40  40  40  40  40  40  40  16  16  18  18  12  10  16  16
 14:  40  40  40  40  40  40  40  40  18  18  16  16  16  16  10  12
 15:  40  40  40  40  40  40  40  40  18  18  16  16  16  16  12  10

 10 = Same chassis and socket
 12 = Same chassis and socket (SNC)
 16 = Same chassis and adjacent socket
 18 = Same chassis and non-adjacent socket
 40 = Different chassis

Turns out, the 'max 2 packages' thing is only relevant to the SNC-3 parts, the
smaller parts do 8 sockets (like usual). The above SLIT table is sane, but
violates the previous assumptions and trips a WARN.

Now that the topology code has a sensible measure of nodes-per-package, we can
use that to divinate the SNC mode at hand, and only fix up SNC-3 topologies.

There is a 'healthy' amount of paranoia code validating the assumptions on the
SLIT table, a simple pr_err(FW_BUG) print on failure and a fallback to using
the regular table. Lets see how long this lasts :-)

Fixes: 4d6dd05d07d0 ("sched/topology: Fix sched domain build error for GNR, CWF in SNC-3 mode")
Reported-by: Kyle Meyer <kyle.meyer@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.238361290@infradead.org
---
 arch/x86/kernel/smpboot.c | 188 ++++++++++++++++++++++++++++----------
 1 file changed, 142 insertions(+), 46 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index db3e481cdbb2..294a8ea60298 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -506,33 +506,149 @@ static void __init build_sched_topology(void)
 }
 
 #ifdef CONFIG_NUMA
-static int sched_avg_remote_distance;
-static int avg_remote_numa_distance(void)
+/*
+ * Test if the on-trace cluster at (N,N) is symmetric.
+ * Uses upper triangle iteration to avoid obvious duplicates.
+ */
+static bool slit_cluster_symmetric(int N)
 {
-	int i, j;
-	int distance, nr_remote, total_distance;
+	int u = topology_num_nodes_per_package();
 
-	if (sched_avg_remote_distance > 0)
-		return sched_avg_remote_distance;
-
-	nr_remote = 0;
-	total_distance = 0;
-	for_each_node_state(i, N_CPU) {
-		for_each_node_state(j, N_CPU) {
-			distance = node_distance(i, j);
-
-			if (distance >= REMOTE_DISTANCE) {
-				nr_remote++;
-				total_distance += distance;
-			}
+	for (int k = 0; k < u; k++) {
+		for (int l = k; l < u; l++) {
+			if (node_distance(N + k, N + l) !=
+			    node_distance(N + l, N + k))
+				return false;
 		}
 	}
-	if (nr_remote)
-		sched_avg_remote_distance = total_distance / nr_remote;
-	else
-		sched_avg_remote_distance = REMOTE_DISTANCE;
 
-	return sched_avg_remote_distance;
+	return true;
+}
+
+/*
+ * Return the package-id of the cluster, or ~0 if indeterminate.
+ * Each node in the on-trace cluster should have the same package-id.
+ */
+static u32 slit_cluster_package(int N)
+{
+	int u = topology_num_nodes_per_package();
+	u32 pkg_id = ~0;
+
+	for (int n = 0; n < u; n++) {
+		const struct cpumask *cpus = cpumask_of_node(N + n);
+		int cpu;
+
+		for_each_cpu(cpu, cpus) {
+			u32 id = topology_logical_package_id(cpu);
+
+			if (pkg_id == ~0)
+				pkg_id = id;
+			if (pkg_id != id)
+				return ~0;
+		}
+	}
+
+	return pkg_id;
+}
+
+/*
+ * Validate the SLIT table is of the form expected for SNC, specifically:
+ *
+ *  - each on-trace cluster should be symmetric,
+ *  - each on-trace cluster should have a unique package-id.
+ *
+ * If you NUMA_EMU on top of SNC, you get to keep the pieces.
+ */
+static bool slit_validate(void)
+{
+	int u = topology_num_nodes_per_package();
+	u32 pkg_id, prev_pkg_id = ~0;
+
+	for (int pkg = 0; pkg < topology_max_packages(); pkg++) {
+		int n = pkg * u;
+
+		/*
+		 * Ensure the on-trace cluster is symmetric and each cluster
+		 * has a different package id.
+		 */
+		if (!slit_cluster_symmetric(n))
+			return false;
+		pkg_id = slit_cluster_package(n);
+		if (pkg_id == ~0)
+			return false;
+		if (pkg && pkg_id == prev_pkg_id)
+			return false;
+
+		prev_pkg_id = pkg_id;
+	}
+
+	return true;
+}
+
+/*
+ * Compute a sanitized SLIT table for SNC; notably SNC-3 can end up with
+ * asymmetric off-trace clusters, reflecting physical assymmetries. However
+ * this leads to 'unfortunate' sched_domain configurations.
+ *
+ * For example dual socket GNR with SNC-3:
+ *
+ * node distances:
+ * node     0    1    2    3    4    5
+ *     0:   10   15   17   21   28   26
+ *     1:   15   10   15   23   26   23
+ *     2:   17   15   10   26   23   21
+ *     3:   21   28   26   10   15   17
+ *     4:   23   26   23   15   10   15
+ *     5:   26   23   21   17   15   10
+ *
+ * Fix things up by averaging out the off-trace clusters; resulting in:
+ *
+ * node     0    1    2    3    4    5
+ *     0:   10   15   17   24   24   24
+ *     1:   15   10   15   24   24   24
+ *     2:   17   15   10   24   24   24
+ *     3:   24   24   24   10   15   17
+ *     4:   24   24   24   15   10   15
+ *     5:   24   24   24   17   15   10
+ */
+static int slit_cluster_distance(int i, int j)
+{
+	static int slit_valid = -1;
+	int u = topology_num_nodes_per_package();
+	long d = 0;
+	int x, y;
+
+	if (slit_valid < 0) {
+		slit_valid = slit_validate();
+		if (!slit_valid)
+			pr_err(FW_BUG "SLIT table doesn't have the expected form for SNC -- fixup disabled!\n");
+		else
+			pr_info("Fixing up SNC SLIT table.\n");
+	}
+
+	/*
+	 * Is this a unit cluster on the trace?
+	 */
+	if ((i / u) == (j / u) || !slit_valid)
+		return node_distance(i, j);
+
+	/*
+	 * Off-trace cluster.
+	 *
+	 * Notably average out the symmetric pair of off-trace clusters to
+	 * ensure the resulting SLIT table is symmetric.
+	 */
+	x = i - (i % u);
+	y = j - (j % u);
+
+	for (i = x; i < x + u; i++) {
+		for (j = y; j < y + u; j++) {
+			d += node_distance(i, j);
+			d += node_distance(j, i);
+		}
+	}
+
+	return d / (2*u*u);
 }
 
 int arch_sched_node_distance(int from, int to)
@@ -542,34 +658,14 @@ int arch_sched_node_distance(int from, int to)
 	switch (boot_cpu_data.x86_vfm) {
 	case INTEL_GRANITERAPIDS_X:
 	case INTEL_ATOM_DARKMONT_X:
-
-		if (topology_max_packages() == 1 || topology_num_nodes_per_package() == 1 ||
-		    d < REMOTE_DISTANCE)
+		if (topology_max_packages() == 1 ||
+		    topology_num_nodes_per_package() < 3)
 			return d;
 
 		/*
-		 * With SNC enabled, there could be too many levels of remote
-		 * NUMA node distances, creating NUMA domain levels
-		 * including local nodes and partial remote nodes.
-		 *
-		 * Trim finer distance tuning for NUMA nodes in remote package
-		 * for the purpose of building sched domains. Group NUMA nodes
-		 * in the remote package in the same sched group.
-		 * Simplify NUMA domains and avoid extra NUMA levels including
-		 * different remote NUMA nodes and local nodes.
-		 *
-		 * GNR and CWF don't expect systems with more than 2 packages
-		 * and more than 2 hops between packages. Single average remote
-		 * distance won't be appropriate if there are more than 2
-		 * packages as average distance to different remote packages
-		 * could be different.
+		 * Handle SNC-3 asymmetries.
 		 */
-		WARN_ONCE(topology_max_packages() > 2,
-			  "sched: Expect only up to 2 packages for GNR or CWF, "
-			  "but saw %d packages when building sched domains.",
-			  topology_max_packages());
-
-		d = avg_remote_numa_distance();
+		return slit_cluster_distance(from, to);
 	}
 	return d;
 }

From 59674fc9d0bfd96ce8a776680ee1cf22c28c9ac7 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Tue, 3 Mar 2026 11:55:44 +0100
Subject: [PATCH 0814/1303] x86/resctrl: Fix SNC detection

Now that the x86 topology code has a sensible nodes-per-package
measure, that does not depend on the online status of CPUs, use this
to divinate the SNC mode.

Note that when Cluster on Die (CoD) is configured on older systems this
will also show multiple NUMA nodes per package. Intel Resource Director
Technology is incomaptible with CoD. Print a warning and do not use the
fixup MSR_RMID_SNC_CONFIG.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Link: https://patch.msgid.link/aaCxbbgjL6OZ6VMd@agluck-desk3
Link: https://patch.msgid.link/20260303110100.367976706@infradead.org
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 36 ++++-----------------------
 1 file changed, 5 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index e6a154240b8d..9bd87bae4983 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -364,7 +364,7 @@ void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 		msr_clear_bit(MSR_RMID_SNC_CONFIG, 0);
 }
 
-/* CPU models that support MSR_RMID_SNC_CONFIG */
+/* CPU models that support SNC and MSR_RMID_SNC_CONFIG */
 static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
 	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0),
@@ -375,40 +375,14 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	{}
 };
 
-/*
- * There isn't a simple hardware bit that indicates whether a CPU is running
- * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the
- * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in
- * the same NUMA node as CPU0.
- * It is not possible to accurately determine SNC state if the system is
- * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
- * to L3 caches. It will be OK if system is booted with hyperthreading
- * disabled (since this doesn't affect the ratio).
- */
 static __init int snc_get_config(void)
 {
-	struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE);
-	const cpumask_t *node0_cpumask;
-	int cpus_per_node, cpus_per_l3;
-	int ret;
+	int ret = topology_num_nodes_per_package();
 
-	if (!x86_match_cpu(snc_cpu_ids) || !ci)
+	if (ret > 1 && !x86_match_cpu(snc_cpu_ids)) {
+		pr_warn("CoD enabled system? Resctrl not supported\n");
 		return 1;
-
-	cpus_read_lock();
-	if (num_online_cpus() != num_present_cpus())
-		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
-	cpus_read_unlock();
-
-	node0_cpumask = cpumask_of_node(cpu_to_node(0));
-
-	cpus_per_node = cpumask_weight(node0_cpumask);
-	cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map);
-
-	if (!cpus_per_node || !cpus_per_l3)
-		return 1;
-
-	ret = cpus_per_l3 / cpus_per_node;
+	}
 
 	/* sanity check: Only valid results are 1, 2, 3, 4, 6 */
 	switch (ret) {

From 4ebe2b8cda7e91a30c1cf1d297605682540d4ad9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:47:03 -0300
Subject: [PATCH 0815/1303] tools headers x86 cpufeatures: Sync with the kernel
 sources

To pick the changes from:

  f24ef0093dd8cf60 ("KVM: x86: Advertise MOVRS CPUID to userspace")
  f49ecf5e110ab0ed ("x86/cpufeature: Replace X86_FEATURE_SYSENTER32 with X86_FEATURE_SYSFAST32")
  db5e82496492b489 ("KVM: SVM: Virtualize and advertise support for ERAPS")

This causes these perf files to be rebuilt and brings some X86_FEATURE
that may be used by:

      CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
      CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Please see tools/include/uapi/README for further details.

Cc: Amit Shah <amit.shah@amd.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index c3b53beb1300..dbe104df339b 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -84,7 +84,7 @@
 #define X86_FEATURE_PEBS		( 3*32+12) /* "pebs" Precise-Event Based Sampling */
 #define X86_FEATURE_BTS			( 3*32+13) /* "bts" Branch Trace Store */
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* syscall in IA32 userspace */
-#define X86_FEATURE_SYSENTER32		( 3*32+15) /* sysenter in IA32 userspace */
+#define X86_FEATURE_SYSFAST32		( 3*32+15) /* sysenter/syscall in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* "rep_good" REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
 #define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* Clear CPU buffers using VERW */
@@ -326,6 +326,7 @@
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* "lam" Linear Address Masking */
+#define X86_FEATURE_MOVRS		(12*32+31) /* MOVRS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
@@ -472,6 +473,7 @@
 #define X86_FEATURE_GP_ON_USER_CPUID	(20*32+17) /* User CPUID faulting */
 
 #define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
+#define X86_FEATURE_ERAPS		(20*32+24) /* Enhanced Return Address Predictor Security */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */

From 1b3f004bac8e2c9e340ac237bd5b36b686ae63e8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:54:08 -0300
Subject: [PATCH 0816/1303] tools headers UAPI: Sync x86's asm/kvm.h with the
 kernel sources

To pick the changes in:

  6517dfbcc918f970 ("KVM: x86: Add x2APIC "features" to control EOI broadcast suppression")
  20c3c4108d58f87c ("KVM: SEV: Add KVM_SEV_SNP_ENABLE_REQ_CERTS command")

This silences these perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Khushit Shah <khushit.shah@nutanix.com>
Cc: Michael Roth <michael.roth@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 7ceff6583652..846a63215ce1 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -503,6 +503,7 @@ struct kvm_sync_regs {
 #define KVM_X86_GRP_SEV			1
 #  define KVM_X86_SEV_VMSA_FEATURES	0
 #  define KVM_X86_SNP_POLICY_BITS	1
+#  define KVM_X86_SEV_SNP_REQ_CERTS	2
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -743,6 +744,7 @@ enum sev_cmd_id {
 	KVM_SEV_SNP_LAUNCH_START = 100,
 	KVM_SEV_SNP_LAUNCH_UPDATE,
 	KVM_SEV_SNP_LAUNCH_FINISH,
+	KVM_SEV_SNP_ENABLE_REQ_CERTS,
 
 	KVM_SEV_NR_MAX,
 };
@@ -914,8 +916,10 @@ struct kvm_sev_snp_launch_finish {
 	__u64 pad1[4];
 };
 
-#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+#define KVM_X2APIC_API_USE_32BIT_IDS			_BITULL(0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK		_BITULL(1)
+#define KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST	_BITULL(2)
+#define KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST	_BITULL(3)
 
 struct kvm_hyperv_eventfd {
 	__u32 conn_id;

From d658686a1331db3bb108ca079d76deb3208ed949 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@redhat.com>
Date: Mon, 2 Mar 2026 16:45:40 +0100
Subject: [PATCH 0817/1303] sched/deadline: Fix missing ENQUEUE_REPLENISH
 during PI de-boosting

Running stress-ng --schedpolicy 0 on an RT kernel on a big machine
might lead to the following WARNINGs (edited).

 sched: DL de-boosted task PID 22725: REPLENISH flag missing

 WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8
 ... (running_bw underflow)
 Call trace:
  dequeue_task_dl+0x15c/0x1f8 (P)
  dequeue_task+0x80/0x168
  deactivate_task+0x24/0x50
  push_dl_task+0x264/0x2e0
  dl_task_timer+0x1b0/0x228
  __hrtimer_run_queues+0x188/0x378
  hrtimer_interrupt+0xfc/0x260
  ...

The problem is that when a SCHED_DEADLINE task (lock holder) is
changed to a lower priority class via sched_setscheduler(), it may
fail to properly inherit the parameters of potential DEADLINE donors
if it didn't already inherit them in the past (shorter deadline than
donor's at that time). This might lead to bandwidth accounting
corruption, as enqueue_task_dl() won't recognize the lock holder as
boosted.

The scenario occurs when:
1. A DEADLINE task (donor) blocks on a PI mutex held by another
   DEADLINE task (holder), but the holder doesn't inherit parameters
   (e.g., it already has a shorter deadline)
2. sched_setscheduler() changes the holder from DEADLINE to a lower
   class while still holding the mutex
3. The holder should now inherit DEADLINE parameters from the donor
   and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen

Fix the issue by introducing __setscheduler_dl_pi(), which detects when
a DEADLINE (proper or boosted) task gets setscheduled to a lower
priority class. In case, the function makes the task inherit DEADLINE
parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to
ensure proper bandwidth accounting during the next enqueue operation.

Fixes: 2279f540ea7d ("sched/deadline: Fix priority inheritance with multiple scheduling classes")
Reported-by: Bruno Goncalves <bgoncalv@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260302-upstream-fix-deadline-piboost-b4-v3-1-6ba32184a9e0@redhat.com
---
 kernel/sched/syscalls.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 6f10db3646e7..cadb0e9fe19b 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -284,6 +284,35 @@ static bool check_same_owner(struct task_struct *p)
 		uid_eq(cred->euid, pcred->uid));
 }
 
+#ifdef CONFIG_RT_MUTEXES
+static inline void __setscheduler_dl_pi(int newprio, int policy,
+			      struct task_struct *p,
+			      struct sched_change_ctx *scope)
+{
+	/*
+	 * In case a DEADLINE task (either proper or boosted) gets
+	 * setscheduled to a lower priority class, check if it neeeds to
+	 * inherit parameters from a potential pi_task. In that case make
+	 * sure replenishment happens with the next enqueue.
+	 */
+
+	if (dl_prio(newprio) && !dl_policy(policy)) {
+		struct task_struct *pi_task = rt_mutex_get_top_task(p);
+
+		if (pi_task) {
+			p->dl.pi_se = pi_task->dl.pi_se;
+			scope->flags |= ENQUEUE_REPLENISH;
+		}
+	}
+}
+#else /* !CONFIG_RT_MUTEXES */
+static inline void __setscheduler_dl_pi(int newprio, int policy,
+			      struct task_struct *p,
+			      struct sched_change_ctx *scope)
+{
+}
+#endif /* !CONFIG_RT_MUTEXES */
+
 #ifdef CONFIG_UCLAMP_TASK
 
 static int uclamp_validate(struct task_struct *p,
@@ -655,6 +684,7 @@ int __sched_setscheduler(struct task_struct *p,
 			__setscheduler_params(p, attr);
 			p->sched_class = next_class;
 			p->prio = newprio;
+			__setscheduler_dl_pi(newprio, policy, p, scope);
 		}
 		__setscheduler_uclamp(p, attr);
 

From b5ef09a77d0b5213268300eedd8a7d28b4e92d47 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Thu, 26 Feb 2026 17:03:07 -0800
Subject: [PATCH 0818/1303] x86/entry/vdso32: Work around libgcc unwinder bug

The unwinder code in libgcc has a long standing bug which causes it to
fail to pick up the signal frame CFI flag. This is a generic bug
across all platforms.

It affects the __kernel_sigreturn and __kernel_rt_sigreturn vdso entry
points on i386. The x86-64 kernel doesn't provide a sigreturn stub,
and so there is no kernel-provided code that is affected on x86-64.

libgcc does have a legacy fallback path which happens to work as long
as the bytes immediately before each of the sigreturn functions fall
outside any function. This patch adds a nop before the ALIGN to each
of the sigreturn stubs to ensure that this is, indeed, the case.

The rest of the patch is just a comment which documents the invariants
that need to be maintained for this legacy path to work correctly.

This is a manifest bug: in the current vdso, __kernel_vsyscall is a
multiple of 16 bytes long and thus __kernel_sigreturn does not have
any padding in front of it.

Closes: https://lore.kernel.org/lkml/f3412cc3e8f66d1853cc9d572c0f2fab076872b1.camel@xry111.site
Fixes: 884961618ee5 ("x86/entry/vdso32: Remove open-coded DWARF in sigreturn.S")
Reported-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050
Link: https://patch.msgid.link/20260227010308.310342-1-hpa@zytor.com
---
 arch/x86/entry/vdso/vdso32/sigreturn.S | 30 ++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index b433353bc8e3..b33fcc501ba3 100644
--- a/arch/x86/entry/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
@@ -35,9 +35,38 @@
 #endif
 .endm
 
+/*
+ * WARNING:
+ *
+ * A bug in the libgcc unwinder as of at least gcc 15.2 (2026) means that
+ * the unwinder fails to recognize the signal frame flag.
+ *
+ * There is a hacky legacy fallback path in libgcc which ends up
+ * getting invoked instead. It happens to work as long as BOTH of the
+ * following conditions are true:
+ *
+ * 1. There is at least one byte before the each of the sigreturn
+ *    functions which falls outside any function. This is enforced by
+ *    an explicit nop instruction before the ALIGN.
+ * 2. The code sequences between the entry point up to and including
+ *    the int $0x80 below need to match EXACTLY. Do not change them
+ *    in any way. The exact byte sequences are:
+ *
+ *    __kernel_sigreturn:
+ *        0:   58                      pop    %eax
+ *        1:   b8 77 00 00 00          mov    $0x77,%eax
+ *        6:   cd 80                   int    $0x80
+ *
+ *    __kernel_rt_sigreturn:
+ *        0:   b8 ad 00 00 00          mov    $0xad,%eax
+ *        5:   cd 80                   int    $0x80
+ *
+ * For details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050
+ */
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
 	ALIGN
 __kernel_sigreturn:
 	STARTPROC_SIGNAL_FRAME IA32_SIGFRAME_sigcontext
@@ -52,6 +81,7 @@ SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL)
 
 	.globl __kernel_rt_sigreturn
 	.type __kernel_rt_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
 	ALIGN
 __kernel_rt_sigreturn:
 	STARTPROC_SIGNAL_FRAME IA32_RT_SIGFRAME_sigcontext

From 340cea84f691c5206561bb2e0147158fe02070be Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 4 Mar 2026 18:15:53 +0530
Subject: [PATCH 0819/1303] cifs: open files should not hold ref on superblock

Today whenever we deal with a file, in addition to holding
a reference on the dentry, we also get a reference on the
superblock. This happens in two cases:
1. when a new cinode is allocated
2. when an oplock break is being processed

The reasoning for holding the superblock ref was to make sure
that when umount happens, if there are users of inodes and
dentries, it does not try to clean them up and wait for the
last ref to superblock to be dropped by last of such users.

But the side effect of doing that is that umount silently drops
a ref on the superblock and we could have deferred closes and
lease breaks still holding these refs.

Ideally, we should ensure that all of these users of inodes and
dentries are cleaned up at the time of umount, which is what this
code is doing.

This code change allows these code paths to use a ref on the
dentry (and hence the inode). That way, umount is
ensured to clean up SMB client resources when it's the last
ref on the superblock (For ex: when same objects are shared).

The code change also moves the call to close all the files in
deferred close list to the umount code path. It also waits for
oplock_break workers to be flushed before calling
kill_anon_super (which eventually frees up those objects).

Fixes: 24261fc23db9 ("cifs: delay super block destruction until all cifsFileInfo objects are gone")
Fixes: 705c79101ccf ("smb: client: fix use-after-free in cifs_oplock_break")
Cc: <stable@vger.kernel.org>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c    |  7 +++++--
 fs/smb/client/cifsproto.h |  1 +
 fs/smb/client/file.c      | 11 ----------
 fs/smb/client/misc.c      | 42 +++++++++++++++++++++++++++++++++++++++
 fs/smb/client/trace.h     |  2 ++
 5 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 427558404aa5..b6e3db993cc6 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -332,10 +332,14 @@ static void cifs_kill_sb(struct super_block *sb)
 
 	/*
 	 * We need to release all dentries for the cached directories
-	 * before we kill the sb.
+	 * and close all deferred file handles before we kill the sb.
 	 */
 	if (cifs_sb->root) {
 		close_all_cached_dirs(cifs_sb);
+		cifs_close_all_deferred_files_sb(cifs_sb);
+
+		/* Wait for all pending oplock breaks to complete */
+		flush_workqueue(cifsoplockd_wq);
 
 		/* finally release root dentry */
 		dput(cifs_sb->root);
@@ -868,7 +872,6 @@ static void cifs_umount_begin(struct super_block *sb)
 	spin_unlock(&tcon->tc_lock);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	cifs_close_all_deferred_files(tcon);
 	/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
 	/* cancel_notify_requests(tcon); */
 	if (tcon->ses && tcon->ses->server) {
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 96d6b5325aa3..800a7e418c32 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -261,6 +261,7 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode);
 
 void cifs_close_all_deferred_files(struct cifs_tcon *tcon);
 
+void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb);
 void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon,
 					   struct dentry *dentry);
 
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index f3ddcdf406c8..cffcf82c1b69 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -711,8 +711,6 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	mutex_init(&cfile->fh_mutex);
 	spin_lock_init(&cfile->file_info_lock);
 
-	cifs_sb_active(inode->i_sb);
-
 	/*
 	 * If the server returned a read oplock and we have mandatory brlocks,
 	 * set oplock level to None.
@@ -767,7 +765,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
 	struct inode *inode = d_inode(cifs_file->dentry);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsLockInfo *li, *tmp;
-	struct super_block *sb = inode->i_sb;
 
 	/*
 	 * Delete any outstanding lock records. We'll lose them when the file
@@ -785,7 +782,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
 
 	cifs_put_tlink(cifs_file->tlink);
 	dput(cifs_file->dentry);
-	cifs_sb_deactive(sb);
 	kfree(cifs_file->symlink_target);
 	kfree(cifs_file);
 }
@@ -3163,12 +3159,6 @@ void cifs_oplock_break(struct work_struct *work)
 	__u64 persistent_fid, volatile_fid;
 	__u16 net_fid;
 
-	/*
-	 * Hold a reference to the superblock to prevent it and its inodes from
-	 * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put()
-	 * may release the last reference to the sb and trigger inode eviction.
-	 */
-	cifs_sb_active(sb);
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
 			TASK_UNINTERRUPTIBLE);
 
@@ -3253,7 +3243,6 @@ void cifs_oplock_break(struct work_struct *work)
 	cifs_put_tlink(tlink);
 out:
 	cifs_done_oplock_break(cinode);
-	cifs_sb_deactive(sb);
 }
 
 static int cifs_swap_activate(struct swap_info_struct *sis,
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index bc24c92b8b95..2aff1cab6c31 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -28,6 +28,11 @@
 #include "fs_context.h"
 #include "cached_dir.h"
 
+struct tcon_list {
+	struct list_head entry;
+	struct cifs_tcon *tcon;
+};
+
 /* The xid serves as a useful identifier for each incoming vfs request,
    in a similar way to the mid which is useful to track each sent smb,
    and CurrentXid can also provide a running counter (although it
@@ -554,6 +559,43 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon)
 	}
 }
 
+void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb)
+{
+	struct rb_root *root = &cifs_sb->tlink_tree;
+	struct rb_node *node;
+	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
+	struct tcon_list *tmp_list, *q;
+	LIST_HEAD(tcon_head);
+
+	spin_lock(&cifs_sb->tlink_tree_lock);
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		tlink = rb_entry(node, struct tcon_link, tl_rbnode);
+		tcon = tlink_tcon(tlink);
+		if (IS_ERR(tcon))
+			continue;
+		tmp_list = kmalloc_obj(struct tcon_list, GFP_ATOMIC);
+		if (tmp_list == NULL)
+			break;
+		tmp_list->tcon = tcon;
+		/* Take a reference on tcon to prevent it from being freed */
+		spin_lock(&tcon->tc_lock);
+		++tcon->tc_count;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_get_close_defer_files);
+		spin_unlock(&tcon->tc_lock);
+		list_add_tail(&tmp_list->entry, &tcon_head);
+	}
+	spin_unlock(&cifs_sb->tlink_tree_lock);
+
+	list_for_each_entry_safe(tmp_list, q, &tcon_head, entry) {
+		cifs_close_all_deferred_files(tmp_list->tcon);
+		list_del(&tmp_list->entry);
+		cifs_put_tcon(tmp_list->tcon, netfs_trace_tcon_ref_put_close_defer_files);
+		kfree(tmp_list);
+	}
+}
+
 void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon,
 					   struct dentry *dentry)
 {
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 9228f95cae2b..acfbb63086ea 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -176,6 +176,7 @@
 	EM(netfs_trace_tcon_ref_get_cached_laundromat,	"GET Ch-Lau") \
 	EM(netfs_trace_tcon_ref_get_cached_lease_break,	"GET Ch-Lea") \
 	EM(netfs_trace_tcon_ref_get_cancelled_close,	"GET Cn-Cls") \
+	EM(netfs_trace_tcon_ref_get_close_defer_files,	"GET Cl-Def") \
 	EM(netfs_trace_tcon_ref_get_dfs_refer,		"GET DfsRef") \
 	EM(netfs_trace_tcon_ref_get_find,		"GET Find  ") \
 	EM(netfs_trace_tcon_ref_get_find_sess_tcon,	"GET FndSes") \
@@ -187,6 +188,7 @@
 	EM(netfs_trace_tcon_ref_put_cancelled_close,	"PUT Cn-Cls") \
 	EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \
 	EM(netfs_trace_tcon_ref_put_cancelled_mid,	"PUT Cn-Mid") \
+	EM(netfs_trace_tcon_ref_put_close_defer_files,	"PUT Cl-Def") \
 	EM(netfs_trace_tcon_ref_put_mnt_ctx,		"PUT MntCtx") \
 	EM(netfs_trace_tcon_ref_put_dfs_refer,		"PUT DfsRfr") \
 	EM(netfs_trace_tcon_ref_put_reconnect_server,	"PUT Reconn") \

From 0100e495cdf0436bd4ed2dc034d385b44cb5993c Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Sat, 21 Feb 2026 10:38:47 +0800
Subject: [PATCH 0820/1303] arm64: make runtime const not usable by modules

Similar as commit 284922f4c563 ("x86: uaccess: don't use runtime-const
rewriting in modules") does, make arm64's runtime const not usable by
modules too, to "make sure this doesn't get forgotten the next time
somebody wants to do runtime constant optimizations". The reason is
well explained in the above commit: "The runtime-const infrastructure
was never designed to handle the modular case, because the constant
fixup is only done at boot time for core kernel code."

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/runtime-const.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/runtime-const.h b/arch/arm64/include/asm/runtime-const.h
index be5915669d23..c3dbd3ae68f6 100644
--- a/arch/arm64/include/asm/runtime-const.h
+++ b/arch/arm64/include/asm/runtime-const.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef MODULE
+  #error "Cannot use runtime-const infrastructure from modules"
+#endif
+
 #include <asm/cacheflush.h>
 
 /* Sigh. You can still run arm64 in BE mode */

From 7a8464555d2e5f038758bb19e72ab4710b79e9cd Mon Sep 17 00:00:00 2001
From: zhidao su <soolaugust@gmail.com>
Date: Wed, 4 Mar 2026 13:37:30 +0800
Subject: [PATCH 0821/1303] sched_ext: Use WRITE_ONCE() for the write side of
 dsq->seq update

bpf_iter_scx_dsq_new() reads dsq->seq via READ_ONCE() without holding
any lock, making dsq->seq a lock-free concurrently accessed variable.
However, dispatch_enqueue(), the sole writer of dsq->seq, uses a plain
increment without the matching WRITE_ONCE() on the write side:

    dsq->seq++;
    ^^^^^^^^^^^
    plain write -- KCSAN data race

The KCSAN documentation requires that if one accessor uses READ_ONCE()
or WRITE_ONCE() on a variable to annotate lock-free access, all other
accesses must also use the appropriate accessor. A plain write leaves
the pair incomplete and will trigger KCSAN warnings.

Fix by using WRITE_ONCE() for the write side of the update:

    WRITE_ONCE(dsq->seq, dsq->seq + 1);

This is consistent with bpf_iter_scx_dsq_new() and makes the
concurrent access annotation complete and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 1594987d637b..c56de568ed94 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	}
 
 	/* seq records the order tasks are queued, used by BPF DSQ iterator */
-	dsq->seq++;
+	WRITE_ONCE(dsq->seq, dsq->seq + 1);
 	p->scx.dsq_seq = dsq->seq;
 
 	dsq_mod_nr(dsq, 1);

From 50d7b4332f27762d24641970fc34bb68a2621926 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 23 Feb 2026 18:39:28 +0100
Subject: [PATCH 0822/1303] mm: memfd_luo: always make all folios uptodate

Patch series "mm: memfd_luo: fixes for folio flag preservation".

This series contains a couple fixes for flag preservation for memfd live
update.

The first patch fixes memfd preservation when fallocate() was used to
pre-allocate some pages.  For these memfds, all the writes to fallocated
pages touched after preserve were lost.

The second patch fixes dirty flag tracking.  If the dirty flag is not
tracked correctly, the next kernel might incorrectly reclaim some folios
under memory pressure, losing user data.  This is a theoretical bug that I
observed when reading the code, and haven't been able to reproduce it.


This patch (of 2):

When a folio is added to a shmem file via fallocate, it is not zeroed on
allocation.  This is done as a performance optimization since it is
possible the folio will never end up being used at all.  When the folio is
used, shmem checks for the uptodate flag, and if absent, zeroes the folio
(and sets the flag) before returning to user.

With LUO, the flags of each folio are saved at preserve time.  It is
possible to have a memfd with some folios fallocated but not uptodate.
For those, the uptodate flag doesn't get saved.  The folios might later
end up being used and become uptodate.  They would get passed to the next
kernel via KHO correctly since they did get preserved.  But they won't
have the MEMFD_LUO_FOLIO_UPTODATE flag.

This means that when the memfd is retrieved, the folios will be added to
the shmem file without the uptodate flag.  They will be zeroed before
first use, losing the data in those folios.

Since we take a big performance hit in allocating, zeroing, and pinning
all folios at prepare time anyway, take some more and zero all
non-uptodate ones too.

Later when there is a stronger need to make prepare faster, this can be
optimized.

To avoid racing with another uptodate operation, take the folio lock.

Link: https://lkml.kernel.org/r/20260223173931.2221759-2-pratyush@kernel.org
Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memfd_luo.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index e485b828d173..1c9510289312 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -152,10 +152,31 @@ static int memfd_luo_preserve_folios(struct file *file,
 		if (err)
 			goto err_unpreserve;
 
+		folio_lock(folio);
+
 		if (folio_test_dirty(folio))
 			flags |= MEMFD_LUO_FOLIO_DIRTY;
-		if (folio_test_uptodate(folio))
-			flags |= MEMFD_LUO_FOLIO_UPTODATE;
+
+		/*
+		 * If the folio is not uptodate, it was fallocated but never
+		 * used. Saving this flag at prepare() doesn't work since it
+		 * might change later when someone uses the folio.
+		 *
+		 * Since we have taken the performance penalty of allocating,
+		 * zeroing, and pinning all the folios in the holes, take a bit
+		 * more and zero all non-uptodate folios too.
+		 *
+		 * NOTE: For someone looking to improve preserve performance,
+		 * this is a good place to look.
+		 */
+		if (!folio_test_uptodate(folio)) {
+			folio_zero_range(folio, 0, folio_size(folio));
+			flush_dcache_folio(folio);
+			folio_mark_uptodate(folio);
+		}
+		flags |= MEMFD_LUO_FOLIO_UPTODATE;
+
+		folio_unlock(folio);
 
 		pfolio->pfn = folio_pfn(folio);
 		pfolio->flags = flags;

From 7e04bf1f33151a30e06a65b74b5f2c19fc2be128 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 23 Feb 2026 18:39:29 +0100
Subject: [PATCH 0823/1303] mm: memfd_luo: always dirty all folios

A dirty folio is one which has been written to.  A clean folio is its
opposite.  Since a clean folio has no user data, it can be freed under
memory pressure.

memfd preservation with LUO saves the flag at preserve().  This is
problematic.  The folio might get dirtied later.  Saving it at freeze()
also doesn't work, since the dirty bit from PTE is normally synced at
unmap and there might still be mappings of the file at freeze().

To see why this is a problem, say a folio is clean at preserve, but gets
dirtied later.  The serialized state of the folio will mark it as clean.
After retrieve, the next kernel will see the folio as clean and might try
to reclaim it under memory pressure.  This will result in losing user
data.

Mark all folios of the file as dirty, and always set the
MEMFD_LUO_FOLIO_DIRTY flag.  This comes with the side effect of making all
clean folios un-reclaimable.  This is a cost that has to be paid for
participants of live update.  It is not expected to be a common use case
to preserve a lot of clean folios anyway.

Since the value of pfolio->flags is a constant now, drop the flags
variable and set it directly.

Link: https://lkml.kernel.org/r/20260223173931.2221759-3-pratyush@kernel.org
Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memfd_luo.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index 1c9510289312..b8edb9f981d7 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -146,7 +146,6 @@ static int memfd_luo_preserve_folios(struct file *file,
 	for (i = 0; i < nr_folios; i++) {
 		struct memfd_luo_folio_ser *pfolio = &folios_ser[i];
 		struct folio *folio = folios[i];
-		unsigned int flags = 0;
 
 		err = kho_preserve_folio(folio);
 		if (err)
@@ -154,8 +153,26 @@ static int memfd_luo_preserve_folios(struct file *file,
 
 		folio_lock(folio);
 
-		if (folio_test_dirty(folio))
-			flags |= MEMFD_LUO_FOLIO_DIRTY;
+		/*
+		 * A dirty folio is one which has been written to. A clean folio
+		 * is its opposite. Since a clean folio does not carry user
+		 * data, it can be freed by page reclaim under memory pressure.
+		 *
+		 * Saving the dirty flag at prepare() time doesn't work since it
+		 * can change later. Saving it at freeze() also won't work
+		 * because the dirty bit is normally synced at unmap and there
+		 * might still be a mapping of the file at freeze().
+		 *
+		 * To see why this is a problem, say a folio is clean at
+		 * preserve, but gets dirtied later. The pfolio flags will mark
+		 * it as clean. After retrieve, the next kernel might try to
+		 * reclaim this folio under memory pressure, losing user data.
+		 *
+		 * Unconditionally mark it dirty to avoid this problem. This
+		 * comes at the cost of making clean folios un-reclaimable after
+		 * live update.
+		 */
+		folio_mark_dirty(folio);
 
 		/*
 		 * If the folio is not uptodate, it was fallocated but never
@@ -174,12 +191,11 @@ static int memfd_luo_preserve_folios(struct file *file,
 			flush_dcache_folio(folio);
 			folio_mark_uptodate(folio);
 		}
-		flags |= MEMFD_LUO_FOLIO_UPTODATE;
 
 		folio_unlock(folio);
 
 		pfolio->pfn = folio_pfn(folio);
-		pfolio->flags = flags;
+		pfolio->flags = MEMFD_LUO_FOLIO_DIRTY | MEMFD_LUO_FOLIO_UPTODATE;
 		pfolio->index = folio->index;
 	}
 

From d210fdcac9c0d1380eab448aebc93f602c1cd4e6 Mon Sep 17 00:00:00 2001
From: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Date: Mon, 23 Feb 2026 17:10:59 -0800
Subject: [PATCH 0824/1303] mm/damon/core: clear walk_control on inactive
 context in damos_walk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

damos_walk() sets ctx->walk_control to the caller-provided control
structure before checking whether the context is running.  If the context
is inactive (damon_is_running() returns false), the function returns
-EINVAL without clearing ctx->walk_control.  This leaves a dangling
pointer to a stack-allocated structure that will be freed when the caller
returns.

This is structurally identical to the bug fixed in commit f9132fbc2e83
("mm/damon/core: remove call_control in inactive contexts") for
damon_call(), which had the same pattern of linking a control object and
returning an error without unlinking it.

The dangling walk_control pointer can cause:
1. Use-after-free if the context is later started and kdamond
   dereferences ctx->walk_control (e.g., in damos_walk_cancel()
   which writes to control->canceled and calls complete())
2. Permanent -EBUSY from subsequent damos_walk() calls, since the
   stale pointer is non-NULL

Nonetheless, the real user impact is quite restrictive.  The
use-after-free is impossible because there is no damos_walk() callers who
starts the context later.  The permanent -EBUSY can actually confuse
users, as DAMON is not running.  But the symptom is kept only while the
context is turned off.  Turning it on again will make DAMON internally
uses a newly generated damon_ctx object that doesn't have the invalid
damos_walk_control pointer, so everything will work fine again.

Fix this by clearing ctx->walk_control under walk_control_lock before
returning -EINVAL, mirroring the fix pattern from f9132fbc2e83.

Link: https://lkml.kernel.org/r/20260224011102.56033-1-sj@kernel.org
Fixes: bf0eaba0ff9c ("mm/damon/core: implement damos_walk()")
Reported-by: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Closes: https://lore.kernel.org/CPUPR80MB8171025468965E583EF2490F956CA@CPUPR80MB8171.lamprd80.prod.outlook.com
Signed-off-by: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Signed-off-by: SeongJae Park <sj@kernel.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index adfc52fee9dc..c1d1091d307e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1562,8 +1562,13 @@ int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control)
 	}
 	ctx->walk_control = control;
 	mutex_unlock(&ctx->walk_control_lock);
-	if (!damon_is_running(ctx))
+	if (!damon_is_running(ctx)) {
+		mutex_lock(&ctx->walk_control_lock);
+		if (ctx->walk_control == control)
+			ctx->walk_control = NULL;
+		mutex_unlock(&ctx->walk_control_lock);
 		return -EINVAL;
+	}
 	wait_for_completion(&control->completion);
 	if (control->canceled)
 		return -ECANCELED;

From f4355d6bb39fc8e53d772fa0654c8441b214e349 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Tue, 24 Feb 2026 22:12:31 -0500
Subject: [PATCH 0825/1303] mm/cma: move put_page_testzero() out of VM_WARN_ON
 in cma_release()

When CONFIG_DEBUG_VM is not set, VM_WARN_ON is a NOP.  Putting any
statement with side effect inside it is incorrect.  Collect all
!put_page_testzero() results and check the sum using WARN instead after
the loop.  It restores the same check in free_contig_range() before commit
e0c1326779cc ("mm: page_alloc: add alloc_contig_frozen_{range,pages}()"),
the commit prior to the Fixes one.

Link: https://lkml.kernel.org/r/20260225031231.2352011-1-ziy@nvidia.com
Fixes: 9bda131c6093 ("mm: cma: add cma_alloc_frozen{_compound}()")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Ron Economos <re@w6rz.net>
Closes: https://lore.kernel.org/all/1b17c38f-30d3-4bb4-a7e1-e74b19ada885@w6rz.net/
Suggested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Debugged-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Tested-by: Ron Economos <re@w6rz.net>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/cma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/cma.c b/mm/cma.c
index 94b5da468a7d..15cc0ae76c8e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -1013,6 +1013,7 @@ bool cma_release(struct cma *cma, const struct page *pages,
 		 unsigned long count)
 {
 	struct cma_memrange *cmr;
+	unsigned long ret = 0;
 	unsigned long i, pfn;
 
 	cmr = find_cma_memrange(cma, pages, count);
@@ -1021,7 +1022,9 @@ bool cma_release(struct cma *cma, const struct page *pages,
 
 	pfn = page_to_pfn(pages);
 	for (i = 0; i < count; i++, pfn++)
-		VM_WARN_ON(!put_page_testzero(pfn_to_page(pfn)));
+		ret += !put_page_testzero(pfn_to_page(pfn));
+
+	WARN(ret, "%lu pages are still in use!\n", ret);
 
 	__cma_release_frozen(cma, cmr, pages, count);
 

From 2d28ed588f8d7d0d41b0a4fad7f0d05e4bbf1797 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Tue, 24 Feb 2026 16:24:34 -0800
Subject: [PATCH 0826/1303] Revert "ptdesc: remove references to folios from
 __pagetable_ctor() and pagetable_dtor()"

This change swapped out mod_node_page_state for lruvec_stat_add_folio.
But, these two APIs are not interchangeable: the lruvec version also
increments memcg stats, in addition to "global" pgdat stats.

So after this change, the "pagetables" memcg stat in memory.stat always
yields "0", which is a userspace visible regression.

I tried to look for a refactor where we add a variant of
lruvec_stat_mod_folio which takes a pgdat and a memcg instead of a folio,
to try to adhere to the spirit of the original patch.  But at the end of
the day this just means we have to call folio_memcg(ptdesc_folio(ptdesc))
anyway, which doesn't really accomplish much.

This regression is visible in master as well as 6.18 stable, so CC stable
too.

Link: https://lkml.kernel.org/r/20260225002434.2953895-1-axelrasmussen@google.com
Fixes: f0c92726e89f ("ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()")
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5be3d8a8f806..abb4963c1f06 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
 #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
-static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
-{
-	return compound_nr(ptdesc_page(ptdesc));
-}
-
 static inline void __pagetable_ctor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
-	__SetPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
+	__folio_set_pgtable(folio);
+	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
 	ptlock_free(ptdesc);
-	__ClearPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
+	__folio_clear_pgtable(folio);
+	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor_free(struct ptdesc *ptdesc)

From 5548dd7fa84510f7bbce67c35cc3b388c86aeddf Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Thu, 26 Feb 2026 01:31:11 +0200
Subject: [PATCH 0827/1303] tools/testing: fix testing/vma and
 testing/radix-tree build

Build of VMA and radix-tree tests is unhappy after the conversion of
kzalloc() to kzalloc_obj() in lib/idr.c:

  cc -I../shared -I. -I../../include -I../../arch/x86/include -I../../../lib -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined  -DNUM_VMA_FLAG_BITS=128 -DNUM_MM_FLAG_BITS=128   -c -o idr.o idr.c
  idr.c: In function `ida_alloc_range':
  idr.c:420:34: error: implicit declaration of function `kzalloc_obj'; did you mean `kzalloc_node'? [-Wimplicit-function-declaration]
    420 |                         bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                  ^~~~~~~~~~~
        |                                  kzalloc_node
  idr.c:420:32: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    420 |                         bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                ^
  idr.c:447:40: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    447 |                                 bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                        ^
  idr.c:468:15: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    468 |         alloc = kzalloc_obj(*bitmap, gfp);
        |               ^
  make: *** [<builtin>: idr.o] Error 1

Import necessary macros from include/linux to tools/include/linux to fix
the compilation.

Link: https://lkml.kernel.org/r/20260225233111.2760752-1-rppt@kernel.org
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/linux/gfp.h      |  4 ++++
 tools/include/linux/overflow.h | 19 +++++++++++++++++++
 tools/include/linux/slab.h     |  9 +++++++++
 3 files changed, 32 insertions(+)

diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h
index 6a10ff5f5be9..9e957b57b694 100644
--- a/tools/include/linux/gfp.h
+++ b/tools/include/linux/gfp.h
@@ -5,6 +5,10 @@
 #include <linux/types.h>
 #include <linux/gfp_types.h>
 
+/* Helper macro to avoid gfp flags if they are the default one */
+#define __default_gfp(a,...) a
+#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL)
+
 static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 {
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
index dcb0c1bf6866..3427d7880326 100644
--- a/tools/include/linux/overflow.h
+++ b/tools/include/linux/overflow.h
@@ -68,6 +68,25 @@
 	__builtin_mul_overflow(__a, __b, __d);	\
 })
 
+/**
+ * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX
+ * @factor1: first factor
+ * @factor2: second factor
+ *
+ * Returns: calculate @factor1 * @factor2, both promoted to size_t,
+ * with any overflow causing the return value to be SIZE_MAX. The
+ * lvalue must be size_t to avoid implicit type conversion.
+ */
+static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(factor1, factor2, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
 /**
  * array_size() - Calculate size of 2-dimensional array.
  *
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
index 94937a699402..6d8e9413d5a4 100644
--- a/tools/include/linux/slab.h
+++ b/tools/include/linux/slab.h
@@ -202,4 +202,13 @@ static inline unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf)
 	return sheaf->size;
 }
 
+#define __alloc_objs(KMALLOC, GFP, TYPE, COUNT)				\
+({									\
+	const size_t __obj_size = size_mul(sizeof(TYPE), COUNT);	\
+	(TYPE *)KMALLOC(__obj_size, GFP);				\
+})
+
+#define kzalloc_obj(P, ...) \
+	__alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1)
+
 #endif		/* _TOOLS_SLAB_H */

From ba4c3698e6963eacd8e7c86c13343631bfeabe55 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Thu, 26 Feb 2026 11:54:21 +0900
Subject: [PATCH 0828/1303] zram: rename writeback_compressed device attr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename writeback_compressed attr to compressed_writeback to avoid possible
confusion and have more natural naming.  writeback_compressed may look
like an alternative version of writeback while in fact
writeback_compressed only sets a writeback property.  Make this
distinction more clear with a new compressed_writeback name.

This updates a feature which is new in 7.0-rcX.

Link: https://lkml.kernel.org/r/20260226025429.1042083-1-senozhatsky@chromium.org
Fixes: 4c1d61389e8e ("zram: introduce writeback_compressed device attribute")
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Suggested-by: Minchan Kim <minchan@kernel.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-block-zram  |  4 ++--
 Documentation/admin-guide/blockdev/zram.rst |  6 +++---
 drivers/block/zram/zram_drv.c               | 24 ++++++++++-----------
 drivers/block/zram/zram_drv.h               |  2 +-
 4 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index e538d4850d61..64c03010e951 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -151,11 +151,11 @@ Description:
 		The algorithm_params file is write-only and is used to setup
 		compression algorithm parameters.
 
-What:		/sys/block/zram<id>/writeback_compressed
+What:		/sys/block/zram<id>/compressed_writeback
 Date:		Decemeber 2025
 Contact:	Richard Chang <richardycc@google.com>
 Description:
-		The writeback_compressed device atrribute toggles compressed
+		The compressed_writeback device atrribute toggles compressed
 		writeback feature.
 
 What:		/sys/block/zram<id>/writeback_batch_size
diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst
index 94bb7f2245ee..451fa00d3004 100644
--- a/Documentation/admin-guide/blockdev/zram.rst
+++ b/Documentation/admin-guide/blockdev/zram.rst
@@ -216,7 +216,7 @@ writeback_limit   	WO	specifies the maximum amount of write IO zram
 writeback_limit_enable  RW	show and set writeback_limit feature
 writeback_batch_size	RW	show and set maximum number of in-flight
 				writeback operations
-writeback_compressed	RW	show and set compressed writeback feature
+compressed_writeback	RW	show and set compressed writeback feature
 comp_algorithm    	RW	show and change the compression algorithm
 algorithm_params	WO	setup compression algorithm parameters
 compact           	WO	trigger memory compaction
@@ -439,11 +439,11 @@ budget in next setting is user's job.
 By default zram stores written back pages in decompressed (raw) form, which
 means that writeback operation involves decompression of the page before
 writing it to the backing device.  This behavior can be changed by enabling
-`writeback_compressed` feature, which causes zram to write compressed pages
+`compressed_writeback` feature, which causes zram to write compressed pages
 to the backing device, thus avoiding decompression overhead.  To enable
 this feature, execute::
 
-	$ echo yes > /sys/block/zramX/writeback_compressed
+	$ echo yes > /sys/block/zramX/compressed_writeback
 
 Note that this feature should be configured before the `zramX` device is
 initialized.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index bca33403fc8b..a324ede6206d 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -549,7 +549,7 @@ static ssize_t bd_stat_show(struct device *dev, struct device_attribute *attr,
 	return ret;
 }
 
-static ssize_t writeback_compressed_store(struct device *dev,
+static ssize_t compressed_writeback_store(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t len)
 {
@@ -564,12 +564,12 @@ static ssize_t writeback_compressed_store(struct device *dev,
 		return -EBUSY;
 	}
 
-	zram->wb_compressed = val;
+	zram->compressed_wb = val;
 
 	return len;
 }
 
-static ssize_t writeback_compressed_show(struct device *dev,
+static ssize_t compressed_writeback_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
@@ -577,7 +577,7 @@ static ssize_t writeback_compressed_show(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 
 	guard(rwsem_read)(&zram->dev_lock);
-	val = zram->wb_compressed;
+	val = zram->compressed_wb;
 
 	return sysfs_emit(buf, "%d\n", val);
 }
@@ -946,7 +946,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 		goto out;
 	}
 
-	if (zram->wb_compressed) {
+	if (zram->compressed_wb) {
 		/*
 		 * ZRAM_WB slots get freed, we need to preserve data required
 		 * for read decompression.
@@ -960,7 +960,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 	set_slot_flag(zram, index, ZRAM_WB);
 	set_slot_handle(zram, index, req->blk_idx);
 
-	if (zram->wb_compressed) {
+	if (zram->compressed_wb) {
 		if (huge)
 			set_slot_flag(zram, index, ZRAM_HUGE);
 		set_slot_size(zram, index, size);
@@ -1100,7 +1100,7 @@ static int zram_writeback_slots(struct zram *zram,
 		 */
 		if (!test_slot_flag(zram, index, ZRAM_PP_SLOT))
 			goto next;
-		if (zram->wb_compressed)
+		if (zram->compressed_wb)
 			err = read_from_zspool_raw(zram, req->page, index);
 		else
 			err = read_from_zspool(zram, req->page, index);
@@ -1429,7 +1429,7 @@ static void zram_async_read_endio(struct bio *bio)
 	 *
 	 * Keep the existing behavior for now.
 	 */
-	if (zram->wb_compressed == false) {
+	if (zram->compressed_wb == false) {
 		/* No decompression needed, complete the parent IO */
 		bio_endio(req->parent);
 		bio_put(bio);
@@ -1508,7 +1508,7 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page, u32 index,
 	flush_work(&req.work);
 	destroy_work_on_stack(&req.work);
 
-	if (req.error || zram->wb_compressed == false)
+	if (req.error || zram->compressed_wb == false)
 		return req.error;
 
 	return decompress_bdev_page(zram, page, index);
@@ -3007,7 +3007,7 @@ static DEVICE_ATTR_WO(writeback);
 static DEVICE_ATTR_RW(writeback_limit);
 static DEVICE_ATTR_RW(writeback_limit_enable);
 static DEVICE_ATTR_RW(writeback_batch_size);
-static DEVICE_ATTR_RW(writeback_compressed);
+static DEVICE_ATTR_RW(compressed_writeback);
 #endif
 #ifdef CONFIG_ZRAM_MULTI_COMP
 static DEVICE_ATTR_RW(recomp_algorithm);
@@ -3031,7 +3031,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_writeback_limit.attr,
 	&dev_attr_writeback_limit_enable.attr,
 	&dev_attr_writeback_batch_size.attr,
-	&dev_attr_writeback_compressed.attr,
+	&dev_attr_compressed_writeback.attr,
 #endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,
@@ -3091,7 +3091,7 @@ static int zram_add(void)
 	init_rwsem(&zram->dev_lock);
 #ifdef CONFIG_ZRAM_WRITEBACK
 	zram->wb_batch_size = 32;
-	zram->wb_compressed = false;
+	zram->compressed_wb = false;
 #endif
 
 	/* gendisk structure */
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 515a72d9c06f..f0de8f8218f5 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -133,7 +133,7 @@ struct zram {
 #ifdef CONFIG_ZRAM_WRITEBACK
 	struct file *backing_dev;
 	bool wb_limit_enable;
-	bool wb_compressed;
+	bool compressed_wb;
 	u32 wb_batch_size;
 	u64 bd_wb_limit;
 	struct block_device *bdev;

From a1e59fc6ee4ed8988ea4aeb9224e75d03175be9c Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Thu, 26 Feb 2026 17:56:30 +0530
Subject: [PATCH 0829/1303] mm/hugetlb.c: use __pa() instead of virt_to_phys()
 in early bootmem alloc code

Architecture like powerpc, checks for pfn_valid() in their virt_to_phys()
implementation (when CONFIG_DEBUG_VIRTUAL is enabled) [1].  Commit
d49004c5f0c1 "arch, mm: consolidate initialization of nodes, zones and
memory map" changed the order of initialization between
hugetlb_bootmem_alloc() and free_area_init().  This means, pfn_valid() can
now return false in alloc_bootmem() path, since sparse_init() is not yet
done.

Since, alloc_bootmem() uses memblock_alloc(.., MEMBLOCK_ALLOC_ACCESSIBLE),
this means these allocations are always going to happen below high_memory,
where __pa() should return valid physical addresses.  Hence this patch
converts the two callers of virt_to_phys() in alloc_bootmem() path to
__pa() to avoid this bootup warning:

 ------------[ cut here ]------------
 WARNING: arch/powerpc/include/asm/io.h:879 at virt_to_phys+0x44/0x1b8, CPU#0: swapper/0
 Modules linked in:
 <...>
 NIP [c000000000601584] virt_to_phys+0x44/0x1b8
 LR [c000000004075de4] alloc_bootmem+0x144/0x1a8
 Call Trace:
 [c000000004d1fb50] [c000000004075dd4] alloc_bootmem+0x134/0x1a8
 [c000000004d1fba0] [c000000004075fac] __alloc_bootmem_huge_page+0x164/0x230
 [c000000004d1fbe0] [c000000004030bc4] alloc_bootmem_huge_page+0x44/0x138
 [c000000004d1fc10] [c000000004076e48] hugetlb_hstate_alloc_pages+0x350/0x5ac
 [c000000004d1fd30] [c0000000040782f0] hugetlb_bootmem_alloc+0x15c/0x19c
 [c000000004d1fd70] [c00000000406d7b4] mm_core_init_early+0x7c/0xdf4
 [c000000004d1ff30] [c000000004011d84] start_kernel+0xac/0xc58
 [c000000004d1ffe0] [c00000000000e99c] start_here_common+0x1c/0x20

[1]: https://lore.kernel.org/linuxppc-dev/87tsv5h544.ritesh.list@gmail.com/

Link: https://lkml.kernel.org/r/b4a7d2c6c4c1dd81dddc904fc21f01303290a4b8.1772107852.git.riteshh@linux.ibm.com
Fixes: d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones and memory map")
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0beb6e22bc26..327eaa4074d3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3101,7 +3101,7 @@ static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact)
 			 * extract the actual node first.
 			 */
 			if (m)
-				listnode = early_pfn_to_nid(PHYS_PFN(virt_to_phys(m)));
+				listnode = early_pfn_to_nid(PHYS_PFN(__pa(m)));
 		}
 
 		if (m) {
@@ -3160,7 +3160,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 	 * The head struct page is used to get folio information by the HugeTLB
 	 * subsystem like zone id and node id.
 	 */
-	memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE),
+	memblock_reserved_mark_noinit(__pa((void *)m + PAGE_SIZE),
 		huge_page_size(h) - PAGE_SIZE);
 
 	return 1;

From dccd5ee2625d50239510bcd73ed78559005e00a3 Mon Sep 17 00:00:00 2001
From: Hao Li <hao.li@linux.dev>
Date: Thu, 26 Feb 2026 19:51:37 +0800
Subject: [PATCH 0830/1303] memcg: fix slab accounting in refill_obj_stock()
 trylock path

In the trylock path of refill_obj_stock(), mod_objcg_mlstate() should use
the real alloc/free bytes (i.e., nr_acct) for accounting, rather than
nr_bytes.

The user-visible impact is that the NR_SLAB_RECLAIMABLE_B and
NR_SLAB_UNRECLAIMABLE_B stats can end up being incorrect.

For example, if a user allocates a 6144-byte object, then before this
fix efill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=2048), even
though it should account for 6144 bytes (i.e., nr_acct).

When the user later frees the same object with kfree(),
refill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=6144).  This
ends up adding 6144 to the stats, but it should be applying -6144
(i.e., nr_acct) since the object is being freed.

Link: https://lkml.kernel.org/r/20260226115145.62903-1-hao.li@linux.dev
Fixes: 200577f69f29 ("memcg: objcg stock trylock without irq disabling")
Signed-off-by: Hao Li <hao.li@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a52da3a5e4fd..772bac21d155 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3086,7 +3086,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 
 	if (!local_trylock(&obj_stock.lock)) {
 		if (pgdat)
-			mod_objcg_mlstate(objcg, pgdat, idx, nr_bytes);
+			mod_objcg_mlstate(objcg, pgdat, idx, nr_acct);
 		nr_pages = nr_bytes >> PAGE_SHIFT;
 		nr_bytes = nr_bytes & (PAGE_SIZE - 1);
 		atomic_add(nr_bytes, &objcg->nr_charged_bytes);

From 06de173b138513087896f9cf090f30b35846518d Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Sun, 1 Mar 2026 10:09:02 +0800
Subject: [PATCH 0831/1303] MAINTAINERS: add RELAY entry

RELAYFS was originally developed by Tom Zanussi and Karim Yaghmour in
2005[1].  Jens Axboe converted it from filesystem into a generic API in
2006[2] and made it widely known through the notable I/O tracing tool
blktrace.  In the decade, there remain a few users scatterred across
different subsystems, like recently added wifi commit[3] that is an
example to show how to communicate between users and kernel.  Last year
I've already done some maintenance and added/corrected some diagnostic
counters.

At Tencent, we internally maintain RELAY as one of most crucial components
of network observibility platform which was shared a bit at LPC 2025[4][5]
and hopefully will be published in the paper this year.  RELAY has proven
highly efficient due to its inherent design essence.  This design becomes
the indispensable way to build a 7x24 platform monitoring various hot
paths even without any selectively sampling (yes, sampling is commonly
used to avoid the overall performance degradation).  One of the
recommended usages is to use its zerocopy function relay_reserve() to
transfer data in a raw format that can be recognized and parsed by the
corresponding application to userspace without introducing heavy locks and
complicated logic that appears in other types of approaches, like printk.
More details can be discovered by reading through the Documentation :)

Credits are given to the all the contributors and reviewers for
RELAY/RELAYFS in the past and future! Many thanks!

[1]: commit e82894f84dbb ("[PATCH] relayfs")
[2]: commit b86ff981a825 ("[PATCH] relay: migrate from relayfs to a generic relay API")
[3]: commit c1bf6959dd81 ("wifi: ath11k: Register relayfs entries for CFR dump")
[4]: https://lpc.events/event/19/contributions/2055/
[5]: https://lpc.events/event/19/contributions/2010/

Link: https://lkml.kernel.org/r/20260301020902.56476-1-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Jens Axboe <axboe@kernel.dk>
Cc: Andriy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Tom Zanussi <zanussi@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e4572a36afd2..0ecf11bab619 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22284,6 +22284,16 @@ L:	linux-wireless@vger.kernel.org
 S:	Orphan
 F:	drivers/net/wireless/rsi/
 
+RELAY
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Jens Axboe <axboe@kernel.dk>
+M:	Jason Xing <kernelxing@tencent.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	Documentation/filesystems/relay.rst
+F:	include/linux/relay.h
+F:	kernel/relay.c
+
 REGISTER MAP ABSTRACTION
 M:	Mark Brown <broonie@kernel.org>
 L:	linux-kernel@vger.kernel.org

From 431b04f0084d244569e81ca4216a40644b23b0c5 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Mon, 2 Mar 2026 11:13:46 +0100
Subject: [PATCH 0832/1303] MAINTAINERS: add co-maintainer and reviewer for
 SLAB ALLOCATOR

Promote Harry Yoo from reviewer to maintainer.  Harry's been involved in
slab development for multiple years now and doing a great job.

Add Hao Li as a new reviewer.  Hao has been doing very useful reviews for
a while now, so make it official and ensure the Cc's.

Link: https://lkml.kernel.org/r/20260302101345.36713-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: Hao Li <hao.li@linux.dev>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0ecf11bab619..e510fbc6f882 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24361,11 +24361,12 @@ F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
 M:	Vlastimil Babka <vbabka@kernel.org>
+M:	Harry Yoo <harry.yoo@oracle.com>
 M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Hao Li <hao.li@linux.dev>
 R:	Christoph Lameter <cl@gentwo.org>
 R:	David Rientjes <rientjes@google.com>
 R:	Roman Gushchin <roman.gushchin@linux.dev>
-R:	Harry Yoo <harry.yoo@oracle.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git

From 577a1f495fd78d8fb61b67ac3d3b595b01f6fcb0 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 2 Mar 2026 15:31:59 -0500
Subject: [PATCH 0833/1303] mm/huge_memory: fix a folio_split() race condition
 with folio_try_get()

During a pagecache folio split, the values in the related xarray should
not be changed from the original folio at xarray split time until all
after-split folios are well formed and stored in the xarray.  Current use
of xas_try_split() in __split_unmapped_folio() lets some after-split
folios show up at wrong indices in the xarray.  When these misplaced
after-split folios are unfrozen, before correct folios are stored via
__xa_store(), and grabbed by folio_try_get(), they are returned to
userspace at wrong file indices, causing data corruption.  More detailed
explanation is at the bottom.

The reproducer is at: https://github.com/dfinity/thp-madv-remove-test
It
1. creates a memfd,
2. forks,
3. in the child process, maps the file with large folios (via shmem code
   path) and reads the mapped file continuously with 16 threads,
4. in the parent process, uses madvise(MADV_REMOVE) to punch poles in the
   large folio.

Data corruption can be observed without the fix.  Basically, data from a
wrong page->index is returned.

Fix it by using the original folio in xas_try_split() calls, so that
folio_try_get() can get the right after-split folios after the original
folio is unfrozen.

Uniform split, split_huge_page*(), is not affected, since it uses
xas_split_alloc() and xas_split() only once and stores the original folio
in the xarray.  Change xas_split() used in uniform split branch to use the
original folio to avoid confusion.

Fixes below points to the commit introduces the code, but folio_split() is
used in a later commit 7460b470a131f ("mm/truncate: use folio_split() in
truncate operation").

More details:

For example, a folio f is split non-uniformly into f, f2, f3, f4 like
below:
+----------------+---------+----+----+
|       f        |    f2   | f3 | f4 |
+----------------+---------+----+----+
but the xarray would look like below after __split_unmapped_folio() is
done:
+----------------+---------+----+----+
|       f        |    f2   | f3 | f3 |
+----------------+---------+----+----+

After __split_unmapped_folio(), the code changes the xarray and unfreezes
after-split folios:

1. unfreezes f2, __xa_store(f2)
2. unfreezes f3, __xa_store(f3)
3. unfreezes f4, __xa_store(f4), which overwrites the second f3 to f4.
4. unfreezes f.

Meanwhile, a parallel filemap_get_entry() can read the second f3 from the
xarray and use folio_try_get() on it at step 2 when f3 is unfrozen. Then,
f3 is wrongly returned to user.

After the fix, the xarray looks like below after __split_unmapped_folio():
+----------------+---------+----+----+
|       f        |    f    | f  | f  |
+----------------+---------+----+----+
so that the race window no longer exists.

[ziy@nvidia.com: move comment, per David]
  Link: https://lkml.kernel.org/r/5C9FA053-A4C6-4615-BE05-74E47A6462B3@nvidia.com
Link: https://lkml.kernel.org/r/20260302203159.3208341-1-ziy@nvidia.com
Fixes: 00527733d0dc ("mm/huge_memory: add two new (not yet used) functions for folio_split()")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Bas van Dijk <bas@dfinity.org>
Closes: https://lore.kernel.org/all/CAKNNEtw5_kZomhkugedKMPOG-sxs5Q5OLumWJdiWXv+C9Yct0w@mail.gmail.com/
Tested-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8e2746ea74ad..912c248a3f7e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3631,6 +3631,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 	const bool is_anon = folio_test_anon(folio);
 	int old_order = folio_order(folio);
 	int start_order = split_type == SPLIT_TYPE_UNIFORM ? new_order : old_order - 1;
+	struct folio *old_folio = folio;
 	int split_order;
 
 	/*
@@ -3651,12 +3652,16 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 			 * uniform split has xas_split_alloc() called before
 			 * irq is disabled to allocate enough memory, whereas
 			 * non-uniform split can handle ENOMEM.
+			 * Use the to-be-split folio, so that a parallel
+			 * folio_try_get() waits on it until xarray is updated
+			 * with after-split folios and the original one is
+			 * unfrozen.
 			 */
-			if (split_type == SPLIT_TYPE_UNIFORM)
-				xas_split(xas, folio, old_order);
-			else {
+			if (split_type == SPLIT_TYPE_UNIFORM) {
+				xas_split(xas, old_folio, old_order);
+			} else {
 				xas_set_order(xas, folio->index, split_order);
-				xas_try_split(xas, folio, old_order);
+				xas_try_split(xas, old_folio, old_order);
 				if (xas_error(xas))
 					return xas_error(xas);
 			}

From 7392f8e4ea632622b2cd2086675ba022db238b3a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:52:29 -0800
Subject: [PATCH 0834/1303] uaccess: correct kernel-doc parameter format

Use the correct kernel-doc function parameter format to avoid kernel-doc
warnings:

Warning: include/linux/uaccess.h:814 function parameter 'uptr' not
 described in 'scoped_user_rw_access_size'
Warning: include/linux/uaccess.h:826 function parameter 'uptr' not
 described in 'scoped_user_rw_access'

Link: https://lkml.kernel.org/r/20260302005229.3471955-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/uaccess.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1f3804245c06..001cfef21b61 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -806,7 +806,7 @@ for (bool done = false; !done; done = true)						\
 
 /**
  * scoped_user_rw_access_size - Start a scoped user read/write access with given size
- * @uptr	Pointer to the user space address to read from and write to
+ * @uptr:	Pointer to the user space address to read from and write to
  * @size:	Size of the access starting from @uptr
  * @elbl:	Error label to goto when the access region is rejected
  *
@@ -817,7 +817,7 @@ for (bool done = false; !done; done = true)						\
 
 /**
  * scoped_user_rw_access - Start a scoped user read/write access
- * @uptr	Pointer to the user space address to read from and write to
+ * @uptr:	Pointer to the user space address to read from and write to
  * @elbl:	Error label to goto when the access region is rejected
  *
  * The size of the access starting from @uptr is determined via sizeof(*@uptr)).

From 599b4e290c8766b19378d85d4310c6ec8f90ade4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:52:22 -0800
Subject: [PATCH 0835/1303] mm/mmu_notifier: clean up mmu_notifier.h kernel-doc

Eliminate kernel-doc warnings in mmu_notifier.h:
- add a missing struct short description
- use the correct format for function parameters
- add missing function return comment sections

Warning: include/linux/mmu_notifier.h:236 missing initial short
 description on line: * struct mmu_interval_notifier_ops
Warning: include/linux/mmu_notifier.h:325 function parameter 'interval_sub'
 not described in 'mmu_interval_set_seq'
Warning: include/linux/mmu_notifier.h:325 function parameter 'cur_seq'
 not described in 'mmu_interval_set_seq'
Warning: include/linux/mmu_notifier.h:346 function parameter 'interval_sub'
 not described in 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:346 function parameter 'seq' not
 described in 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:346 No description found for return
 value of 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:370 function parameter 'interval_sub'
 not described in 'mmu_interval_check_retry'
Warning: include/linux/mmu_notifier.h:370 function parameter 'seq' not
 described in 'mmu_interval_check_retry'
Warning: include/linux/mmu_notifier.h:370 No description found for return
 value of 'mmu_interval_check_retry'

Link: https://lkml.kernel.org/r/20260302005222.3470783-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmu_notifier.h | 31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 07a2bbaf86e9..8450e18a87c2 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -234,7 +234,7 @@ struct mmu_notifier {
 };
 
 /**
- * struct mmu_interval_notifier_ops
+ * struct mmu_interval_notifier_ops - callback for range notification
  * @invalidate: Upon return the caller must stop using any SPTEs within this
  *              range. This function can sleep. Return false only if sleeping
  *              was required but mmu_notifier_range_blockable(range) is false.
@@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub);
 
 /**
  * mmu_interval_set_seq - Save the invalidation sequence
- * @interval_sub - The subscription passed to invalidate
- * @cur_seq - The cur_seq passed to the invalidate() callback
+ * @interval_sub: The subscription passed to invalidate
+ * @cur_seq: The cur_seq passed to the invalidate() callback
  *
  * This must be called unconditionally from the invalidate callback of a
  * struct mmu_interval_notifier_ops under the same lock that is used to call
@@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_read_retry - End a read side critical section against a VA range
- * interval_sub: The subscription
- * seq: The return of the paired mmu_interval_read_begin()
+ * @interval_sub: The subscription
+ * @seq: The return of the paired mmu_interval_read_begin()
  *
  * This MUST be called under a user provided lock that is also held
  * unconditionally by op->invalidate() when it calls mmu_interval_set_seq().
@@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
  * Each call should be paired with a single mmu_interval_read_begin() and
  * should be used to conclude the read side.
  *
- * Returns true if an invalidation collided with this critical section, and
+ * Returns: true if an invalidation collided with this critical section, and
  * the caller should retry.
  */
 static inline bool
@@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_check_retry - Test if a collision has occurred
- * interval_sub: The subscription
- * seq: The return of the matching mmu_interval_read_begin()
+ * @interval_sub: The subscription
+ * @seq: The return of the matching mmu_interval_read_begin()
  *
  * This can be used in the critical section between mmu_interval_read_begin()
- * and mmu_interval_read_retry().  A return of true indicates an invalidation
- * has collided with this critical region and a future
- * mmu_interval_read_retry() will return true.
- *
- * False is not reliable and only suggests a collision may not have
- * occurred. It can be called many times and does not have to hold the user
- * provided lock.
+ * and mmu_interval_read_retry().
  *
  * This call can be used as part of loops and other expensive operations to
  * expedite a retry.
+ * It can be called many times and does not have to hold the user
+ * provided lock.
+ *
+ * Returns: true indicates an invalidation has collided with this critical
+ * region and a future mmu_interval_read_retry() will return true.
+ * False is not reliable and only suggests a collision may not have
+ * occurred.
  */
 static inline bool
 mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub,

From b12bbe35c7c1e431f2fa01fe9291daa52fb7ab43 Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Date: Tue, 3 Mar 2026 19:50:25 +0000
Subject: [PATCH 0836/1303] MAINTAINERS, mailmap: update email address for
 Lorenzo Stoakes

I want to experiment with a new email setup, and using the @kernel.org
address is the easiest way to have flexibility on this.

Link: https://lkml.kernel.org/r/20260303195025.1170895-1-ljs@kernel.org
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    |  3 ++-
 MAINTAINERS | 20 ++++++++++----------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/.mailmap b/.mailmap
index c124a1306d26..fd062abdb133 100644
--- a/.mailmap
+++ b/.mailmap
@@ -491,7 +491,8 @@ Lior David <quic_liord@quicinc.com> <liord@codeaurora.org>
 Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@linaro.org>
 Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@intel.com>
 Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
-Lorenzo Stoakes <lorenzo.stoakes@oracle.com> <lstoakes@gmail.com>
+Lorenzo Stoakes <ljs@kernel.org> <lstoakes@gmail.com>
+Lorenzo Stoakes <ljs@kernel.org> <lorenzo.stoakes@oracle.com>
 Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
 Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
 Lucas De Marchi <demarchi@kernel.org> <lucas.demarchi@intel.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index e510fbc6f882..a3b4e75ad1ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16654,7 +16654,7 @@ F:	mm/balloon.c
 MEMORY MANAGEMENT - CORE
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
@@ -16784,7 +16784,7 @@ F:	mm/workingset.c
 MEMORY MANAGEMENT - MISC
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
@@ -16875,7 +16875,7 @@ R:	David Hildenbrand <david@kernel.org>
 R:	Michal Hocko <mhocko@kernel.org>
 R:	Qi Zheng <zhengqi.arch@bytedance.com>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/vmscan.c
@@ -16884,7 +16884,7 @@ F:	mm/workingset.c
 MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
@@ -16929,7 +16929,7 @@ F:	mm/swapfile.c
 MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Zi Yan <ziy@nvidia.com>
 R:	Baolin Wang <baolin.wang@linux.alibaba.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
@@ -16969,7 +16969,7 @@ F:	tools/testing/selftests/mm/uffd-*.[ch]
 
 MEMORY MANAGEMENT - RUST
 M:	Alice Ryhl <aliceryhl@google.com>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 L:	linux-mm@kvack.org
 L:	rust-for-linux@vger.kernel.org
@@ -16985,7 +16985,7 @@ F:	rust/kernel/page.rs
 MEMORY MAPPING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 R:	Pedro Falcato <pfalcato@suse.de>
@@ -17015,7 +17015,7 @@ MEMORY MAPPING - LOCKING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Suren Baghdasaryan <surenb@google.com>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
 L:	linux-mm@kvack.org
@@ -17030,7 +17030,7 @@ F:	mm/mmap_lock.c
 MEMORY MAPPING - MADVISE (MEMORY ADVICE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
@@ -23183,7 +23183,7 @@ K:	\b(?i:rust)\b
 
 RUST [ALLOC]
 M:	Danilo Krummrich <dakr@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Uladzislau Rezki <urezki@gmail.com>

From 68785c5e79e0fc1eacf63026fbba32be3867f410 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Wed, 25 Feb 2026 22:51:06 -0500
Subject: [PATCH 0837/1303] drm/amd/pm: remove invalid
 gpu_metrics.energy_accumulator on smu v13.0.x

v1:
The metrics->EnergyAccumulator field has been deprecated on newer pmfw.

v2:
add smu 13.0.0/13.0.7/13.0.10 support.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8de9edb35976fa56565dc8fbb5d1310e8e10187c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 8 +++++++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 3 ++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index e030f1e186cb..b32c053950c9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2034,6 +2034,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 			smu, SMU_DRIVER_TABLE_GPU_METRICS);
 	SmuMetricsExternal_t metrics_ext;
 	SmuMetrics_t *metrics = &metrics_ext.SmuMetrics;
+	uint32_t mp1_ver = amdgpu_ip_version(smu->adev, MP1_HWIP, 0);
 	int ret = 0;
 
 	ret = smu_cmn_get_metrics_table(smu,
@@ -2058,7 +2059,12 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+
+	if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) ||
+	    (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800))
+		gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	else
+		gpu_metrics->energy_accumulator = UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index af0482c9caa7..f08cfa510a8a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2065,7 +2065,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ?
+		metrics->EnergyAccumulator : UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;

From 2c1030f2e84885cc58bffef6af67d5b9d2e7098f Mon Sep 17 00:00:00 2001
From: Alysa Liu <Alysa.Liu@amd.com>
Date: Thu, 5 Feb 2026 11:21:45 -0500
Subject: [PATCH 0838/1303] drm/amdgpu: Fix use-after-free race in VM acquire

Replace non-atomic vm->process_info assignment with cmpxchg()
to prevent race when parent/child processes sharing a drm_file
both try to acquire the same VM after fork().

Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c7c573275ec20db05be769288a3e3bb2250ec618)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 06c1913d5a3f..29b400cdd6d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1439,7 +1439,10 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 		*process_info = info;
 	}
 
-	vm->process_info = *process_info;
+	if (cmpxchg(&vm->process_info, NULL, *process_info) != NULL) {
+		ret = -EINVAL;
+		goto already_acquired;
+	}
 
 	/* Validate page directory and attach eviction fence */
 	ret = amdgpu_bo_reserve(vm->root.bo, true);
@@ -1479,6 +1482,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 	amdgpu_bo_unreserve(vm->root.bo);
 reserve_pd_fail:
 	vm->process_info = NULL;
+already_acquired:
 	if (info) {
 		dma_fence_put(&info->eviction_fence->base);
 		*process_info = NULL;

From a145bbff6f53ab80757a15eba5ad2ba8e3bdc9dc Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Wed, 25 Feb 2026 13:57:01 +0530
Subject: [PATCH 0839/1303] drm/amdgpu/psp: Use Indirect access address for GFX
 to PSP mailbox

The reason the RAP is not granting access to 0x58200 is that
a dedicated RSMU slot would have to be spent for this address range,
and MPASP is close to running out of RSMU slots.

This will help to fix PSP TOC load failure during secureboot.
GFX Driver Need to use indirect access for SMN address regs.

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9b822e26eea3899003aa8a89d5e2c4408e066e20)
---
 drivers/gpu/drm/amd/amdgpu/psp_v15_0.c        | 20 +++++++++----------
 .../include/asic_reg/mp/mp_15_0_0_offset.h    | 18 +++++++++++++++++
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
index 723ddae17644..73a709773e85 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
@@ -69,12 +69,12 @@ static int psp_v15_0_0_ring_stop(struct psp_context *psp,
 				   0x80000000, 0x80000000, false);
 	} else {
 		/* Write the ring destroy command*/
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64,
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64,
 			     GFX_CTRL_CMD_ID_DESTROY_RINGS);
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 		/* Wait for response flag (bit 31) */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 	}
 
@@ -116,7 +116,7 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 	} else {
 		/* Wait for sOS ready for ring creation */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 		if (ret) {
 			DRM_ERROR("Failed to wait for trust OS ready for ring creation\n");
@@ -125,23 +125,23 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 		/* Write low address of the ring to C2PMSG_69 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_69, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_69, psp_ring_reg);
 		/* Write high address of the ring to C2PMSG_70 */
 		psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_70, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_70, psp_ring_reg);
 		/* Write size of ring to C2PMSG_71 */
 		psp_ring_reg = ring->ring_size;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_71, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_71, psp_ring_reg);
 		/* Write the ring initialization command to C2PMSG_64 */
 		psp_ring_reg = ring_type;
 		psp_ring_reg = psp_ring_reg << 16;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, psp_ring_reg);
 
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 
 		/* Wait for response flag (bit 31) in C2PMSG_64 */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x8000FFFF, false);
 	}
 
@@ -174,7 +174,7 @@ static uint32_t psp_v15_0_0_ring_get_wptr(struct psp_context *psp)
 	if (amdgpu_sriov_vf(adev))
 		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102);
 	else
-		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67);
+		data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67);
 
 	return data;
 }
@@ -188,7 +188,7 @@ static void psp_v15_0_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
 		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_101,
 			     GFX_CTRL_CMD_ID_CONSUME_CMD);
 	} else
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67, value);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value);
 }
 
 static const struct psp_funcs psp_v15_0_0_funcs = {
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
index 0e4c195297a4..fe97943b9b97 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
@@ -82,6 +82,24 @@
 #define regMPASP_SMN_IH_SW_INT_CTRL                                                                     0x0142
 #define regMPASP_SMN_IH_SW_INT_CTRL_BASE_IDX                                                            0
 
+// addressBlock: mp_SmuMpASPPub_PcruDec
+// base address: 0x3800000
+#define regMPASP_PCRU1_MPASP_C2PMSG_64                                                   0x4280
+#define regMPASP_PCRU1_MPASP_C2PMSG_64_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_65                                                   0x4281
+#define regMPASP_PCRU1_MPASP_C2PMSG_65_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_66                                                   0x4282
+#define regMPASP_PCRU1_MPASP_C2PMSG_66_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_67                                                   0x4283
+#define regMPASP_PCRU1_MPASP_C2PMSG_67_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_68                                                   0x4284
+#define regMPASP_PCRU1_MPASP_C2PMSG_68_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_69                                                   0x4285
+#define regMPASP_PCRU1_MPASP_C2PMSG_69_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_70                                                   0x4286
+#define regMPASP_PCRU1_MPASP_C2PMSG_70_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_71                                                   0x4287
+#define regMPASP_PCRU1_MPASP_C2PMSG_71_BASE_IDX                                          3
 
 // addressBlock: mp_SmuMp1_SmnDec
 // base address: 0x0

From 048c1c4e51715ffddd4189745c07f530f34fbe37 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:32 +0000
Subject: [PATCH 0840/1303] drm/amdgpu/userq: Consolidate wait ioctl exit path

If we gate the fence destruction with a check telling us whether there are
valid pointers in there we can eliminate the need for dual, basically
identical, exit paths.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bea29bb0dd29012949cd44fdb122465a9fd5cf91)
---
 .../gpu/drm/amd/amdgpu/amdgpu_userq_fence.c   | 28 ++++---------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 7e9cf1868cc9..77969a6017a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -983,32 +983,14 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			r = -EFAULT;
 			goto free_fences;
 		}
-
-		kfree(fences);
-		kfree(fence_info);
 	}
 
-	drm_exec_fini(&exec);
-	for (i = 0; i < num_read_bo_handles; i++)
-		drm_gem_object_put(gobj_read[i]);
-	kfree(gobj_read);
-
-	for (i = 0; i < num_write_bo_handles; i++)
-		drm_gem_object_put(gobj_write[i]);
-	kfree(gobj_write);
-
-	kfree(timeline_points);
-	kfree(timeline_handles);
-	kfree(syncobj_handles);
-	kfree(bo_handles_write);
-	kfree(bo_handles_read);
-
-	return 0;
-
 free_fences:
-	while (num_fences-- > 0)
-		dma_fence_put(fences[num_fences]);
-	kfree(fences);
+	if (fences) {
+		while (num_fences-- > 0)
+			dma_fence_put(fences[num_fences]);
+		kfree(fences);
+	}
 free_fence_info:
 	kfree(fence_info);
 exec_fini:

From 65b5c326ce4103620c977b8dcb1699bdac4da143 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Mon, 2 Mar 2026 18:50:46 +0530
Subject: [PATCH 0841/1303] drm/amdgpu/userq: refcount userqueues to avoid any
 race conditions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To avoid race condition and avoid UAF cases, implement kref
based queues and protect the below operations using xa lock
a. Getting a queue from xarray
b. Increment/Decrement it's refcount

Every time some one want to access a queue, always get via
amdgpu_userq_get to make sure we have locks in place and get
the object if active.

A userqueue is destroyed on the last refcount is dropped which
typically would be via IOCTL or during fini.

v2: Add the missing drop in one the condition in the signal ioclt [Alex]

v3: remove the queue from the xarray first in the free queue ioctl path
    [Christian]

- Pass queue to the amdgpu_userq_put directly.
- make amdgpu_userq_put xa_lock free since we are doing put for each get
  only and final put is done via destroy and we remove the queue from xa
  with lock.
- use userq_put in fini too so cleanup is done fully.

v4: Use xa_erase directly rather than doing load and erase in free
    ioctl. Also remove some of the error logs which could be exploited
    by the user to flood the logs [Christian]

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4952189b284d4d847f92636bb42dd747747129c0)
Cc: <stable@vger.kernel.org> # 048c1c4e5171: drm/amdgpu/userq: Consolidate wait ioctl exit path
Cc: <stable@vger.kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c     | 116 ++++++++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h     |   4 +
 .../gpu/drm/amd/amdgpu/amdgpu_userq_fence.c   |  14 ++-
 3 files changed, 95 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 9d67b770bcc2..7c450350847d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -446,8 +446,7 @@ static int amdgpu_userq_wait_for_last_fence(struct amdgpu_usermode_queue *queue)
 	return ret;
 }
 
-static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
-				 int queue_id)
+static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue)
 {
 	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
@@ -461,7 +460,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	uq_funcs->mqd_destroy(queue);
 	amdgpu_userq_fence_driver_free(queue);
 	/* Use interrupt-safe locking since IRQ handlers may access these XArrays */
-	xa_erase_irq(&uq_mgr->userq_xa, (unsigned long)queue_id);
 	xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index);
 	queue->userq_mgr = NULL;
 	list_del(&queue->userq_va_list);
@@ -470,12 +468,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	up_read(&adev->reset_domain->sem);
 }
 
-static struct amdgpu_usermode_queue *
-amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid)
-{
-	return xa_load(&uq_mgr->userq_xa, qid);
-}
-
 void
 amdgpu_userq_ensure_ev_fence(struct amdgpu_userq_mgr *uq_mgr,
 			     struct amdgpu_eviction_fence_mgr *evf_mgr)
@@ -625,22 +617,13 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 }
 
 static int
-amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
+amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue)
 {
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_userq_mgr *uq_mgr = &fpriv->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
-	struct amdgpu_usermode_queue *queue;
 	int r = 0;
 
 	cancel_delayed_work_sync(&uq_mgr->resume_work);
 	mutex_lock(&uq_mgr->userq_mutex);
-	queue = amdgpu_userq_find(uq_mgr, queue_id);
-	if (!queue) {
-		drm_dbg_driver(adev_to_drm(uq_mgr->adev), "Invalid queue id to destroy\n");
-		mutex_unlock(&uq_mgr->userq_mutex);
-		return -EINVAL;
-	}
 	amdgpu_userq_wait_for_last_fence(queue);
 	/* Cancel any pending hang detection work and cleanup */
 	if (queue->hang_detect_fence) {
@@ -672,7 +655,7 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 		drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n");
 		queue->state = AMDGPU_USERQ_STATE_HUNG;
 	}
-	amdgpu_userq_cleanup(queue, queue_id);
+	amdgpu_userq_cleanup(queue);
 	mutex_unlock(&uq_mgr->userq_mutex);
 
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -680,6 +663,37 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 	return r;
 }
 
+static void amdgpu_userq_kref_destroy(struct kref *kref)
+{
+	int r;
+	struct amdgpu_usermode_queue *queue =
+		container_of(kref, struct amdgpu_usermode_queue, refcount);
+	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
+
+	r = amdgpu_userq_destroy(uq_mgr, queue);
+	if (r)
+		drm_file_err(uq_mgr->file, "Failed to destroy usermode queue %d\n", r);
+}
+
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid)
+{
+	struct amdgpu_usermode_queue *queue;
+
+	xa_lock(&uq_mgr->userq_xa);
+	queue = xa_load(&uq_mgr->userq_xa, qid);
+	if (queue)
+		kref_get(&queue->refcount);
+	xa_unlock(&uq_mgr->userq_xa);
+
+	return queue;
+}
+
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue)
+{
+	if (queue)
+		kref_put(&queue->refcount, amdgpu_userq_kref_destroy);
+}
+
 static int amdgpu_userq_priority_permit(struct drm_file *filp,
 					int priority)
 {
@@ -834,6 +848,9 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		goto unlock;
 	}
 
+	/* drop this refcount during queue destroy */
+	kref_init(&queue->refcount);
+
 	/* Wait for mode-1 reset to complete */
 	down_read(&adev->reset_domain->sem);
 	r = xa_err(xa_store_irq(&adev->userq_doorbell_xa, index, queue, GFP_KERNEL));
@@ -985,7 +1002,9 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp)
 {
 	union drm_amdgpu_userq *args = data;
-	int r;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_usermode_queue *queue;
+	int r = 0;
 
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
@@ -1000,11 +1019,16 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 			drm_file_err(filp, "Failed to create usermode queue\n");
 		break;
 
-	case AMDGPU_USERQ_OP_FREE:
-		r = amdgpu_userq_destroy(filp, args->in.queue_id);
-		if (r)
-			drm_file_err(filp, "Failed to destroy usermode queue\n");
+	case AMDGPU_USERQ_OP_FREE: {
+		xa_lock(&fpriv->userq_mgr.userq_xa);
+		queue = __xa_erase(&fpriv->userq_mgr.userq_xa, args->in.queue_id);
+		xa_unlock(&fpriv->userq_mgr.userq_xa);
+		if (!queue)
+			return -ENOENT;
+
+		amdgpu_userq_put(queue);
 		break;
+	}
 
 	default:
 		drm_dbg_driver(dev, "Invalid user queue op specified: %d\n", args->in.op);
@@ -1023,16 +1047,23 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 
 	/* Resume all the queues for this process */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		if (!amdgpu_userq_buffer_vas_mapped(queue)) {
 			drm_file_err(uq_mgr->file,
 				     "trying restore queue without va mapping\n");
 			queue->state = AMDGPU_USERQ_STATE_INVALID_VA;
+			amdgpu_userq_put(queue);
 			continue;
 		}
 
 		r = amdgpu_userq_restore_helper(queue);
 		if (r)
 			ret = r;
+
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1266,9 +1297,13 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 	amdgpu_userq_detect_and_reset_queues(uq_mgr);
 	/* Try to unmap all the queues in this process ctx */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
 		r = amdgpu_userq_preempt_helper(queue);
 		if (r)
 			ret = r;
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1301,16 +1336,24 @@ amdgpu_userq_wait_for_signal(struct amdgpu_userq_mgr *uq_mgr)
 	int ret;
 
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		struct dma_fence *f = queue->last_fence;
 
-		if (!f || dma_fence_is_signaled(f))
+		if (!f || dma_fence_is_signaled(f)) {
+			amdgpu_userq_put(queue);
 			continue;
+		}
 		ret = dma_fence_wait_timeout(f, true, msecs_to_jiffies(100));
 		if (ret <= 0) {
 			drm_file_err(uq_mgr->file, "Timed out waiting for fence=%llu:%llu\n",
 				     f->context, f->seqno);
+			amdgpu_userq_put(queue);
 			return -ETIMEDOUT;
 		}
+		amdgpu_userq_put(queue);
 	}
 
 	return 0;
@@ -1361,20 +1404,23 @@ int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *f
 void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	unsigned long queue_id;
+	unsigned long queue_id = 0;
 
-	cancel_delayed_work_sync(&userq_mgr->resume_work);
+	for (;;) {
+		xa_lock(&userq_mgr->userq_xa);
+		queue = xa_find(&userq_mgr->userq_xa, &queue_id, ULONG_MAX,
+				XA_PRESENT);
+		if (queue)
+			__xa_erase(&userq_mgr->userq_xa, queue_id);
+		xa_unlock(&userq_mgr->userq_xa);
 
-	mutex_lock(&userq_mgr->userq_mutex);
-	amdgpu_userq_detect_and_reset_queues(userq_mgr);
-	xa_for_each(&userq_mgr->userq_xa, queue_id, queue) {
-		amdgpu_userq_wait_for_last_fence(queue);
-		amdgpu_userq_unmap_helper(queue);
-		amdgpu_userq_cleanup(queue, queue_id);
+		if (!queue)
+			break;
+
+		amdgpu_userq_put(queue);
 	}
 
 	xa_destroy(&userq_mgr->userq_xa);
-	mutex_unlock(&userq_mgr->userq_mutex);
 	mutex_destroy(&userq_mgr->userq_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index 5845d8959034..736c1d38297c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -74,6 +74,7 @@ struct amdgpu_usermode_queue {
 	struct dentry		*debugfs_queue;
 	struct delayed_work hang_detect_work;
 	struct dma_fence *hang_detect_fence;
+	struct kref		refcount;
 
 	struct list_head	userq_va_list;
 };
@@ -112,6 +113,9 @@ struct amdgpu_db_info {
 	struct amdgpu_userq_obj	*db_obj;
 };
 
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid);
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue);
+
 int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 
 int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *file_priv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 77969a6017a4..5239b06b9ab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -466,7 +466,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_signal *args = data;
 	struct drm_gem_object **gobj_write = NULL;
 	struct drm_gem_object **gobj_read = NULL;
-	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_usermode_queue *queue = NULL;
 	struct amdgpu_userq_fence *userq_fence;
 	struct drm_syncobj **syncobj = NULL;
 	u32 *bo_handles_write, num_write_bo_handles;
@@ -553,7 +553,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	}
 
 	/* Retrieve the user queue */
-	queue = xa_load(&userq_mgr->userq_xa, args->queue_id);
+	queue = amdgpu_userq_get(userq_mgr, args->queue_id);
 	if (!queue) {
 		r = -ENOENT;
 		goto put_gobj_write;
@@ -648,6 +648,9 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 free_syncobj_handles:
 	kfree(syncobj_handles);
 
+	if (queue)
+		amdgpu_userq_put(queue);
+
 	return r;
 }
 
@@ -660,7 +663,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_wait *wait_info = data;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_userq_mgr *userq_mgr = &fpriv->userq_mgr;
-	struct amdgpu_usermode_queue *waitq;
+	struct amdgpu_usermode_queue *waitq = NULL;
 	struct drm_gem_object **gobj_write;
 	struct drm_gem_object **gobj_read;
 	struct dma_fence **fences = NULL;
@@ -926,7 +929,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 		 */
 		num_fences = dma_fence_dedup_array(fences, num_fences);
 
-		waitq = xa_load(&userq_mgr->userq_xa, wait_info->waitq_id);
+		waitq = amdgpu_userq_get(userq_mgr, wait_info->waitq_id);
 		if (!waitq) {
 			r = -EINVAL;
 			goto free_fences;
@@ -1014,5 +1017,8 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 free_bo_handles_read:
 	kfree(bo_handles_read);
 
+	if (waitq)
+		amdgpu_userq_put(waitq);
+
 	return r;
 }

From e48a869957a70cc39b4090cd27c36a86f8db9b92 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Wed, 25 Feb 2026 09:51:35 +0100
Subject: [PATCH 0842/1303] timekeeping: Fix timex status validation for
 auxiliary clocks

The timekeeping_validate_timex() function validates the timex status
of an auxiliary system clock even when the status is not to be changed,
which causes unexpected errors for applications that make read-only
clock_adjtime() calls, or set some other timex fields, but without
clearing the status field.

Do the AUX-specific status validation only when the modes field contains
ADJ_STATUS, i.e. the application is actually trying to change the
status. This makes the AUX-specific clock_adjtime() behavior consistent
with CLOCK_REALTIME.

Fixes: 4eca49d0b621 ("timekeeping: Prepare do_adtimex() for auxiliary clocks")
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260225085231.276751-1-mlichvar@redhat.com
---
 kernel/time/timekeeping.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 91fa2003351c..c07e562ee4c1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2653,7 +2653,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux
 
 	if (aux_clock) {
 		/* Auxiliary clocks are similar to TAI and do not have leap seconds */
-		if (txc->status & (STA_INS | STA_DEL))
+		if (txc->modes & ADJ_STATUS &&
+		    txc->status & (STA_INS | STA_DEL))
 			return -EINVAL;
 
 		/* No TAI offset setting */
@@ -2661,7 +2662,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux
 			return -EINVAL;
 
 		/* No PPS support either */
-		if (txc->status & (STA_PPSFREQ | STA_PPSTIME))
+		if (txc->modes & ADJ_STATUS &&
+		    txc->status & (STA_PPSFREQ | STA_PPSTIME))
 			return -EINVAL;
 	}
 

From da994db94e60f9a9411108ddf4d1836147ad4c9c Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Date: Fri, 20 Feb 2026 15:11:48 -0600
Subject: [PATCH 0843/1303] remoteproc: sysmon: Correct subsys_name_len type in
 QMI request

The QMI message encoder has up until recently read a single byte (as
elem_size == 1), but with the introduction of big endian support it's
become apparent that this field is expected to be a full u32 -
regardless of the size of the length in the encoded message (which is
what elem_size specifies).

The result is that the encoder now reads past the length byte and
rejects the unreasonably large length formed when including the
following 3 bytes from the subsys_name array.

Fix this by changing to the expected type.

Fixes: 1fb82ee806d1 ("remoteproc: qcom: Introduce sysmon")
Signed-off-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Reviewed-by: Chris Lew <christopher.lew@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260220-qmi-encode-invalid-length-v2-1-5674be35ab29@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_sysmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c
index cf10e8ecfb8f..3ceec1fd6d99 100644
--- a/drivers/remoteproc/qcom_sysmon.c
+++ b/drivers/remoteproc/qcom_sysmon.c
@@ -203,7 +203,7 @@ static const struct qmi_elem_info ssctl_shutdown_resp_ei[] = {
 };
 
 struct ssctl_subsys_event_req {
-	u8 subsys_name_len;
+	u32 subsys_name_len;
 	char subsys_name[SSCTL_SUBSYS_NAME_LENGTH];
 	u32 event;
 	u8 evt_driven_valid;

From f82859c84a9862e242c904e72fb0625fef9b24e7 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 4 Mar 2026 11:50:12 -0800
Subject: [PATCH 0844/1303] accel/amdxdna: Fix major version check on NPU1
 platform

Add the missing major number in npu1_fw_feature_table.

Without the major version specified, the firmware feature check fails,
preventing new firmware commands from being enabled on the NPU1
platform.

With the correct major version populated, the driver properly detects
firmware support and enables the new command.

Fixes: f1eac46fe5f7 ("accel/amdxdna: Update firmware version check for latest firmware")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260304195012.3616908-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/npu1_regs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c
index 6e3d3ca69c04..1320e924e548 100644
--- a/drivers/accel/amdxdna/npu1_regs.c
+++ b/drivers/accel/amdxdna/npu1_regs.c
@@ -67,7 +67,7 @@ const struct dpm_clk_freq npu1_dpm_clk_table[] = {
 
 static const struct aie2_fw_feature_tbl npu1_fw_feature_table[] = {
 	{ .major = 5, .min_minor = 7 },
-	{ .features = BIT_U64(AIE2_NPU_COMMAND), .min_minor = 8 },
+	{ .features = BIT_U64(AIE2_NPU_COMMAND), .major = 5, .min_minor = 8 },
 	{ 0 }
 };
 

From 8f3c6f08ababad2e3bdd239728cf66a9949446b4 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 24 Feb 2026 13:17:50 +1000
Subject: [PATCH 0845/1303] nouveau/dpcd: return EBUSY for aux xfer if the
 device is asleep

If we have runtime suspended, and userspace wants to use /dev/drm_dp_*
then just tell it the device is busy instead of crashing in the GSP
code.

WARNING: CPU: 2 PID: 565741 at drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c:164 r535_gsp_msgq_wait+0x9a/0xb0 [nouveau]
CPU: 2 UID: 0 PID: 565741 Comm: fwupd Not tainted 6.18.10-200.fc43.x86_64 #1 PREEMPT(lazy)
Hardware name: LENOVO 20QTS0PQ00/20QTS0PQ00, BIOS N2OET65W (1.52 ) 08/05/2024
RIP: 0010:r535_gsp_msgq_wait+0x9a/0xb0 [nouveau]

This is a simple fix to get backported. We should probably engineer a
proper power domain solution to wake up devices and keep them awake
while fw updates are happening.

Cc: stable@vger.kernel.org
Fixes: 8894f4919bc4 ("drm/nouveau: register a drm_dp_aux channel for each dp connector")
Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patch.msgid.link/20260224031750.791621-1-airlied@gmail.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nouveau_connector.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 00d4530aea71..cc239492c7f0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1230,6 +1230,9 @@ nouveau_connector_aux_xfer(struct drm_dp_aux *obj, struct drm_dp_aux_msg *msg)
 	u8 size = msg->size;
 	int ret;
 
+	if (pm_runtime_suspended(nv_connector->base.dev->dev))
+		return -EBUSY;
+
 	nv_encoder = find_encoder(&nv_connector->base, DCB_OUTPUT_DP);
 	if (!nv_encoder)
 		return -ENODEV;

From 170a4b21f49b3dcff3115b4c90758f0a0d77375a Mon Sep 17 00:00:00 2001
From: Olivier Sobrie <olivier@sobrie.be>
Date: Wed, 4 Mar 2026 22:20:39 +0100
Subject: [PATCH 0846/1303] hwmon: (max6639) fix inverted polarity

According to MAX6639 documentation:

  D1: PWM Output Polarity. PWM output is low at
  100% duty cycle when this bit is set to zero. PWM
  output is high at 100% duty cycle when this bit is set
  to 1.

Up to commit 0f33272b60ed ("hwmon: (max6639) : Update hwmon init using
info structure"), the polarity was set to high (0x2) when no platform
data was set. After the patch, the polarity register wasn't set anymore
if no platform data was specified. Nowadays, since commit 7506ebcd662b
("hwmon: (max6639) : Configure based on DT property"), it is always set
to low which doesn't match with the comment above and change the
behavior compared to versions prior 0f33272b60ed.

Fixes: 0f33272b60ed ("hwmon: (max6639) : Update hwmon init using info structure")
Signed-off-by: Olivier Sobrie <olivier@sobrie.be>
Link: https://lore.kernel.org/r/20260304212039.570274-1-olivier@sobrie.be
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/max6639.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c
index a0a1dbbda887..9a3c515efe2e 100644
--- a/drivers/hwmon/max6639.c
+++ b/drivers/hwmon/max6639.c
@@ -607,7 +607,7 @@ static int max6639_init_client(struct i2c_client *client,
 			return err;
 
 		/* Fans PWM polarity high by default */
-		err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x00);
+		err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x02);
 		if (err)
 			return err;
 

From 6944e6d8a6d4c1e654de1da112da8fef1b30e623 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Thu, 5 Mar 2026 03:57:57 +0800
Subject: [PATCH 0847/1303] sched_ext/selftests: Fix format specifier and
 buffer length in file_write_long()

Use %ld (not %lu) for signed long, and pass the actual string length
returned by sprintf() to write_text() instead of sizeof(buf).

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/util.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c
index e47769c91918..2111329ed289 100644
--- a/tools/testing/selftests/sched_ext/util.c
+++ b/tools/testing/selftests/sched_ext/util.c
@@ -60,11 +60,11 @@ int file_write_long(const char *path, long val)
 	char buf[64];
 	int ret;
 
-	ret = sprintf(buf, "%lu", val);
+	ret = sprintf(buf, "%ld", val);
 	if (ret < 0)
 		return ret;
 
-	if (write_text(path, buf, sizeof(buf)) <= 0)
+	if (write_text(path, buf, ret) <= 0)
 		return -1;
 
 	return 0;

From 126fe7ef12ffe42fdc600fe22df733e96fa418ec Mon Sep 17 00:00:00 2001
From: Joe Damato <joe@dama.to>
Date: Mon, 2 Mar 2026 18:42:01 -0800
Subject: [PATCH 0848/1303] mailmap: Add entry for Joe Damato

My Fastly email address is no longer used. Add a mailmap entry to
reflect that.

Signed-off-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303024202.2526604-1-joe@dama.to
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..a02e9aa9aed4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -396,6 +396,7 @@ Jiri Slaby <jirislaby@kernel.org> <xslaby@fi.muni.cz>
 Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com>
 Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com>
 Jishnu Prakash <quic_jprakash@quicinc.com> <jprakash@codeaurora.org>
+Joe Damato <joe@dama.to> <jdamato@fastly.com>
 Joel Granados <joel.granados@kernel.org> <j.granados@samsung.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
 Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>

From 18b43bec5437914e3b51bb08dc6c6e7b0a2df4d1 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 3 Mar 2026 11:37:20 +0800
Subject: [PATCH 0849/1303] mailmap: reflect my gmail as default

Use my gmail instead so that I can easily handle those emails
that CC me.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://patch.msgid.link/20260303033720.84108-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index a02e9aa9aed4..7fefbcc82d1a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -348,6 +348,7 @@ Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
+Jason Xing <kerneljasonxing@gmail.com>  <kernelxing@tencent.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>

From 25dd70a03b1f5f3aa71e1a5091ecd9cd2a13ee43 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Wed, 4 Mar 2026 15:51:17 -0800
Subject: [PATCH 0850/1303] hwmon: (pmbus/q54sj108a2) fix stack overflow in
 debugfs read

The q54sj108a2_debugfs_read function suffers from a stack buffer overflow
due to incorrect arguments passed to bin2hex(). The function currently
passes 'data' as the destination and 'data_char' as the source.

Because bin2hex() converts each input byte into two hex characters, a
32-byte block read results in 64 bytes of output. Since 'data' is only
34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end
of the buffer onto the stack.

Additionally, the arguments were swapped: it was reading from the
zero-initialized 'data_char' and writing to 'data', resulting in
all-zero output regardless of the actual I2C read.

Fix this by:
1. Expanding 'data_char' to 66 bytes to safely hold the hex output.
2. Correcting the bin2hex() argument order and using the actual read count.
3. Using a pointer to select the correct output buffer for the final
   simple_read_from_buffer call.

Fixes: d014538aa385 ("hwmon: (pmbus) Driver for Delta power supplies Q54SJ108A2")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260304235116.1045-1-sanman.p211993@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/q54sj108a2.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/hwmon/pmbus/q54sj108a2.c b/drivers/hwmon/pmbus/q54sj108a2.c
index fc030ca34480..d5d60a9af8c5 100644
--- a/drivers/hwmon/pmbus/q54sj108a2.c
+++ b/drivers/hwmon/pmbus/q54sj108a2.c
@@ -79,7 +79,8 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf,
 	int idx = *idxp;
 	struct q54sj108a2_data *psu = to_psu(idxp, idx);
 	char data[I2C_SMBUS_BLOCK_MAX + 2] = { 0 };
-	char data_char[I2C_SMBUS_BLOCK_MAX + 2] = { 0 };
+	char data_char[I2C_SMBUS_BLOCK_MAX * 2 + 2] = { 0 };
+	char *out = data;
 	char *res;
 
 	switch (idx) {
@@ -150,27 +151,27 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf,
 		if (rc < 0)
 			return rc;
 
-		res = bin2hex(data, data_char, 32);
-		rc = res - data;
-
+		res = bin2hex(data_char, data, rc);
+		rc = res - data_char;
+		out = data_char;
 		break;
 	case Q54SJ108A2_DEBUGFS_FLASH_KEY:
 		rc = i2c_smbus_read_block_data(psu->client, PMBUS_FLASH_KEY_WRITE, data);
 		if (rc < 0)
 			return rc;
 
-		res = bin2hex(data, data_char, 4);
-		rc = res - data;
-
+		res = bin2hex(data_char, data, rc);
+		rc = res - data_char;
+		out = data_char;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	data[rc] = '\n';
+	out[rc] = '\n';
 	rc += 2;
 
-	return simple_read_from_buffer(buf, count, ppos, data, rc);
+	return simple_read_from_buffer(buf, count, ppos, out, rc);
 }
 
 static ssize_t q54sj108a2_debugfs_write(struct file *file, const char __user *buf,

From 7f083faf59d14c04e01ec05a7507f036c965acf8 Mon Sep 17 00:00:00 2001
From: Koichiro Den <den@valinux.co.jp>
Date: Sat, 28 Feb 2026 23:53:07 +0900
Subject: [PATCH 0851/1303] net: sched: avoid qdisc_reset_all_tx_gt() vs
 dequeue race for lockless qdiscs

When shrinking the number of real tx queues,
netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush
qdiscs for queues which will no longer be used.

qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with
qdisc_lock(). However, for lockless qdiscs, the dequeue path is
serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so
qdisc_reset() can run concurrently with __qdisc_run() and free skbs
while they are still being dequeued, leading to UAF.

This can easily be reproduced on e.g. virtio-net by imposing heavy
traffic while frequently changing the number of queue pairs:

  iperf3 -ub0 -c $peer -t 0 &
  while :; do
    ethtool -L eth0 combined 1
    ethtool -L eth0 combined 2
  done

With KASAN enabled, this leads to reports like:

  BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760
  ...
  Call Trace:
   <TASK>
   ...
   __qdisc_run+0x133f/0x1760
   __dev_queue_xmit+0x248f/0x3550
   ip_finish_output2+0xa42/0x2110
   ip_output+0x1a7/0x410
   ip_send_skb+0x2e6/0x480
   udp_send_skb+0xb0a/0x1590
   udp_sendmsg+0x13c9/0x1fc0
   ...
   </TASK>

  Allocated by task 1270 on cpu 5 at 44.558414s:
   ...
   alloc_skb_with_frags+0x84/0x7c0
   sock_alloc_send_pskb+0x69a/0x830
   __ip_append_data+0x1b86/0x48c0
   ip_make_skb+0x1e8/0x2b0
   udp_sendmsg+0x13a6/0x1fc0
   ...

  Freed by task 1306 on cpu 3 at 44.558445s:
   ...
   kmem_cache_free+0x117/0x5e0
   pfifo_fast_reset+0x14d/0x580
   qdisc_reset+0x9e/0x5f0
   netif_set_real_num_tx_queues+0x303/0x840
   virtnet_set_channels+0x1bf/0x260 [virtio_net]
   ethnl_set_channels+0x684/0xae0
   ethnl_default_set_doit+0x31a/0x890
   ...

Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by
taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the
serialization model already used by dev_reset_queue().

Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state
reflects an empty queue, avoiding needless re-scheduling.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Link: https://patch.msgid.link/20260228145307.3955532-1-den@valinux.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sch_generic.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c3a7268b567e..d5d55cb21686 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb)
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
 	struct Qdisc *qdisc;
+	bool nolock;
 
 	for (; i < dev->num_tx_queues; i++) {
 		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		if (qdisc) {
+			nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+			if (nolock)
+				spin_lock_bh(&qdisc->seqlock);
 			spin_lock_bh(qdisc_lock(qdisc));
 			qdisc_reset(qdisc);
 			spin_unlock_bh(qdisc_lock(qdisc));
+			if (nolock) {
+				clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+				clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
+				spin_unlock_bh(&qdisc->seqlock);
+			}
 		}
 	}
 }

From 165573e41f2f66ef98940cf65f838b2cb575d9d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Mar 2026 20:55:27 +0000
Subject: [PATCH 0852/1303] tcp: secure_seq: add back ports to TS offset

This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets")

tcp_tw_recycle went away in 2017.

Zhouyan Deng reported off-path TCP source port leakage via
SYN cookie side-channel that can be fixed in multiple ways.

One of them is to bring back TCP ports in TS offset randomization.

As a bonus, we perform a single siphash() computation
to provide both an ISN and a TS offset.

Fixes: 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets")
Reported-by: Zhouyan Deng <dengzhouyan_nwpu@163.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260302205527.1982836-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/secure_seq.h | 45 ++++++++++++++++++----
 include/net/tcp.h        |  6 ++-
 net/core/secure_seq.c    | 80 +++++++++++++++-------------------------
 net/ipv4/syncookies.c    | 11 ++++--
 net/ipv4/tcp_input.c     |  8 +++-
 net/ipv4/tcp_ipv4.c      | 37 +++++++++----------
 net/ipv6/syncookies.c    | 11 ++++--
 net/ipv6/tcp_ipv6.c      | 37 +++++++++----------
 8 files changed, 127 insertions(+), 108 deletions(-)

diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index cddebafb9f77..6f996229167b 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -5,16 +5,47 @@
 #include <linux/types.h>
 
 struct net;
+extern struct net init_net;
+
+union tcp_seq_and_ts_off {
+	struct {
+		u32 seq;
+		u32 ts_off;
+	};
+	u64 hash64;
+};
 
 u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
-		   __be16 sport, __be16 dport);
-u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr);
-u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
-		     __be16 sport, __be16 dport);
-u32 secure_tcpv6_ts_off(const struct net *net,
-			const __be32 *saddr, const __be32 *daddr);
+union tcp_seq_and_ts_off
+secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr,
+			  __be16 sport, __be16 dport);
 
+static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+				 __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr,
+				       sport, dport);
+
+	return ts.seq;
+}
+
+union tcp_seq_and_ts_off
+secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr,
+			    const __be32 *daddr,
+			    __be16 sport, __be16 dport);
+
+static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+				   __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr,
+					 sport, dport);
+
+	return ts.seq;
+}
 #endif /* _NET_SECURE_SEQ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eb8bf63fdafc..978eea2d5df0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -43,6 +43,7 @@
 #include <net/dst.h>
 #include <net/mptcp.h>
 #include <net/xfrm.h>
+#include <net/secure_seq.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
@@ -2464,8 +2465,9 @@ struct tcp_request_sock_ops {
 				       struct flowi *fl,
 				       struct request_sock *req,
 				       u32 tw_isn);
-	u32 (*init_seq)(const struct sk_buff *skb);
-	u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb);
+	union tcp_seq_and_ts_off (*init_seq_and_ts_off)(
+					const struct net *net,
+					const struct sk_buff *skb);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 9a3965680451..6a6f2cda5aae 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -20,7 +20,6 @@
 #include <net/tcp.h>
 
 static siphash_aligned_key_t net_secret;
-static siphash_aligned_key_t ts_secret;
 
 #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ)
 
@@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void)
 {
 	net_get_random_once(&net_secret, sizeof(net_secret));
 }
-
-static __always_inline void ts_secret_init(void)
-{
-	net_get_random_once(&ts_secret, sizeof(ts_secret));
-}
 #endif
 
 #ifdef CONFIG_INET
@@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq)
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-u32 secure_tcpv6_ts_off(const struct net *net,
-			const __be32 *saddr, const __be32 *daddr)
-{
-	const struct {
-		struct in6_addr saddr;
-		struct in6_addr daddr;
-	} __aligned(SIPHASH_ALIGNMENT) combined = {
-		.saddr = *(struct in6_addr *)saddr,
-		.daddr = *(struct in6_addr *)daddr,
-	};
-
-	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
-		return 0;
-
-	ts_secret_init();
-	return siphash(&combined, offsetofend(typeof(combined), daddr),
-		       &ts_secret);
-}
-EXPORT_IPV6_MOD(secure_tcpv6_ts_off);
-
-u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
-		     __be16 sport, __be16 dport)
+union tcp_seq_and_ts_off
+secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr,
+			    const __be32 *daddr, __be16 sport, __be16 dport)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
 		.sport = sport,
 		.dport = dport
 	};
-	u32 hash;
+	union tcp_seq_and_ts_off st;
 
 	net_secret_init();
-	hash = siphash(&combined, offsetofend(typeof(combined), dport),
-		       &net_secret);
-	return seq_scale(hash);
+
+	st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport),
+			    &net_secret);
+
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
+		st.ts_off = 0;
+
+	st.seq = seq_scale(st.seq);
+	return st;
 }
-EXPORT_SYMBOL(secure_tcpv6_seq);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off);
 
 u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr)
-{
-	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
-		return 0;
-
-	ts_secret_init();
-	return siphash_2u32((__force u32)saddr, (__force u32)daddr,
-			    &ts_secret);
-}
-
 /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
-		   __be16 sport, __be16 dport)
+union tcp_seq_and_ts_off
+secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr,
+			  __be16 sport, __be16 dport)
 {
-	u32 hash;
+	u32 ports = (__force u32)sport << 16 | (__force u32)dport;
+	union tcp_seq_and_ts_off st;
 
 	net_secret_init();
-	hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
-			    (__force u32)sport << 16 | (__force u32)dport,
-			    &net_secret);
-	return seq_scale(hash);
+
+	st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr,
+				 ports, &net_secret);
+
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
+		st.ts_off = 0;
+
+	st.seq = seq_scale(st.seq);
+	return st;
 }
-EXPORT_SYMBOL_GPL(secure_tcp_seq);
+EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off);
 
 u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 061751aabc8e..fc3affd9c801 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
 	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcp_ts_off(net,
-					  ip_hdr(skb)->daddr,
-					  ip_hdr(skb)->saddr);
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcp_seq_and_ts_off(net,
+					       ip_hdr(skb)->daddr,
+					       ip_hdr(skb)->saddr,
+					       tcp_hdr(skb)->dest,
+					       tcp_hdr(skb)->source);
+		tsoff = st.ts_off;
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7b03f2460751..cba89733d121 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7646,6 +7646,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sock *fastopen_sk = NULL;
+	union tcp_seq_and_ts_off st;
 	struct request_sock *req;
 	bool want_cookie = false;
 	struct dst_entry *dst;
@@ -7715,9 +7716,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (!dst)
 		goto drop_and_free;
 
+	if (tmp_opt.tstamp_ok || (!want_cookie && !isn))
+		st = af_ops->init_seq_and_ts_off(net, skb);
+
 	if (tmp_opt.tstamp_ok) {
 		tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
-		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
+		tcp_rsk(req)->ts_off = st.ts_off;
 	}
 	if (!want_cookie && !isn) {
 		int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
@@ -7739,7 +7743,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_release;
 		}
 
-		isn = af_ops->init_seq(skb);
+		isn = st.seq;
 	}
 
 	tcp_ecn_create_request(req, skb, sk, dst);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 910c25cb24e1..c7b2463c2e25 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -105,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
 
 static DEFINE_MUTEX(tcp_exit_batch_mutex);
 
-static u32 tcp_v4_init_seq(const struct sk_buff *skb)
+static union tcp_seq_and_ts_off
+tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)
 {
-	return secure_tcp_seq(ip_hdr(skb)->daddr,
-			      ip_hdr(skb)->saddr,
-			      tcp_hdr(skb)->dest,
-			      tcp_hdr(skb)->source);
-}
-
-static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
-{
-	return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr);
+	return secure_tcp_seq_and_ts_off(net,
+					 ip_hdr(skb)->daddr,
+					 ip_hdr(skb)->saddr,
+					 tcp_hdr(skb)->dest,
+					 tcp_hdr(skb)->source);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -327,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len
 	rt = NULL;
 
 	if (likely(!tp->repair)) {
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcp_seq_and_ts_off(net,
+					       inet->inet_saddr,
+					       inet->inet_daddr,
+					       inet->inet_sport,
+					       usin->sin_port);
 		if (!tp->write_seq)
-			WRITE_ONCE(tp->write_seq,
-				   secure_tcp_seq(inet->inet_saddr,
-						  inet->inet_daddr,
-						  inet->inet_sport,
-						  usin->sin_port));
-		WRITE_ONCE(tp->tsoffset,
-			   secure_tcp_ts_off(net, inet->inet_saddr,
-					     inet->inet_daddr));
+			WRITE_ONCE(tp->write_seq, st.seq);
+		WRITE_ONCE(tp->tsoffset, st.ts_off);
 	}
 
 	atomic_set(&inet->inet_id, get_random_u16());
@@ -1677,8 +1675,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
 	.route_req	=	tcp_v4_route_req,
-	.init_seq	=	tcp_v4_init_seq,
-	.init_ts_off	=	tcp_v4_init_ts_off,
+	.init_seq_and_ts_off	=	tcp_v4_init_seq_and_ts_off,
 	.send_synack	=	tcp_v4_send_synack,
 };
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7e007f013ec8..4f6f0d751d6c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
 	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcpv6_ts_off(net,
-					    ipv6_hdr(skb)->daddr.s6_addr32,
-					    ipv6_hdr(skb)->saddr.s6_addr32);
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcpv6_seq_and_ts_off(net,
+						 ipv6_hdr(skb)->daddr.s6_addr32,
+						 ipv6_hdr(skb)->saddr.s6_addr32,
+						 tcp_hdr(skb)->dest,
+						 tcp_hdr(skb)->source);
+		tsoff = st.ts_off;
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5195a46b951e..bb09d5ccf599 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -105,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static u32 tcp_v6_init_seq(const struct sk_buff *skb)
+static union tcp_seq_and_ts_off
+tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)
 {
-	return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
-				ipv6_hdr(skb)->saddr.s6_addr32,
-				tcp_hdr(skb)->dest,
-				tcp_hdr(skb)->source);
-}
-
-static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
-{
-	return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32,
-				   ipv6_hdr(skb)->saddr.s6_addr32);
+	return secure_tcpv6_seq_and_ts_off(net,
+					   ipv6_hdr(skb)->daddr.s6_addr32,
+					   ipv6_hdr(skb)->saddr.s6_addr32,
+					   tcp_hdr(skb)->dest,
+					   tcp_hdr(skb)->source);
 }
 
 static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
@@ -320,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
 	sk_set_txhash(sk);
 
 	if (likely(!tp->repair)) {
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcpv6_seq_and_ts_off(net,
+						 np->saddr.s6_addr32,
+						 sk->sk_v6_daddr.s6_addr32,
+						 inet->inet_sport,
+						 inet->inet_dport);
 		if (!tp->write_seq)
-			WRITE_ONCE(tp->write_seq,
-				   secure_tcpv6_seq(np->saddr.s6_addr32,
-						    sk->sk_v6_daddr.s6_addr32,
-						    inet->inet_sport,
-						    inet->inet_dport));
-		tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32,
-						   sk->sk_v6_daddr.s6_addr32);
+			WRITE_ONCE(tp->write_seq, st.seq);
+		tp->tsoffset = st.ts_off;
 	}
 
 	if (tcp_fastopen_defer_connect(sk, &err))
@@ -817,8 +815,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
 	.route_req	=	tcp_v6_route_req,
-	.init_seq	=	tcp_v6_init_seq,
-	.init_ts_off	=	tcp_v6_init_ts_off,
+	.init_seq_and_ts_off	= tcp_v6_init_seq_and_ts_off,
 	.send_synack	=	tcp_v6_send_synack,
 };
 

From f7d92f11bd33a6eb49c7c812255ef4ab13681f0f Mon Sep 17 00:00:00 2001
From: Ian Ray <ian.ray@gehealthcare.com>
Date: Mon, 2 Mar 2026 18:32:37 +0200
Subject: [PATCH 0853/1303] net: nfc: nci: Fix zero-length proprietary
 notifications

NCI NFC controllers may have proprietary OIDs with zero-length payload.
One example is: drivers/nfc/nxp-nci/core.c, NXP_NCI_RF_TXLDO_ERROR_NTF.

Allow a zero length payload in proprietary notifications *only*.

Before:

-- >8 --
kernel: nci: nci_recv_frame: len 3
-- >8 --

After:

-- >8 --
kernel: nci: nci_recv_frame: len 3
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x23, plen=0
kernel: nci: nci_ntf_packet: unknown ntf opcode 0x123
kernel: nfc nfc0: NFC: RF transmitter couldn't start. Bad power and/or configuration?
-- >8 --

After fixing the hardware:

-- >8 --
kernel: nci: nci_recv_frame: len 27
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x5, plen=24
kernel: nci: nci_rf_intf_activated_ntf_packet: rf_discovery_id 1
-- >8 --

Fixes: d24b03535e5e ("nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet")
Signed-off-by: Ian Ray <ian.ray@gehealthcare.com>
Link: https://patch.msgid.link/20260302163238.140576-1-ian.ray@gehealthcare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6e9b76e2cc56..e95eef85971f 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1482,10 +1482,20 @@ static bool nci_valid_size(struct sk_buff *skb)
 	unsigned int hdr_size = NCI_CTRL_HDR_SIZE;
 
 	if (skb->len < hdr_size ||
-	    !nci_plen(skb->data) ||
 	    skb->len < hdr_size + nci_plen(skb->data)) {
 		return false;
 	}
+
+	if (!nci_plen(skb->data)) {
+		/* Allow zero length in proprietary notifications (0x20 - 0x3F). */
+		if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 &&
+		    nci_mt(skb->data) == NCI_MT_NTF_PKT)
+			return true;
+
+		/* Disallow zero length otherwise. */
+		return false;
+	}
+
 	return true;
 }
 

From a4c2b8be2e5329e7fac6e8f64ddcb8958155cfcb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2026 01:56:40 +0000
Subject: [PATCH 0854/1303] net_sched: sch_fq: clear q->band_pkt_count[] in
 fq_reset()

When/if a NIC resets, queues are deactivated by dev_deactivate_many(),
then reactivated when the reset operation completes.

fq_reset() removes all the skbs from various queues.

If we do not clear q->band_pkt_count[], these counters keep growing
and can eventually reach sch->limit, preventing new packets to be queued.

Many thanks to Praveen for discovering the root cause.

Fixes: 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling")
Diagnosed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260304015640.961780-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_fq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 80235e85f844..05084c9af48e 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -827,6 +827,7 @@ static void fq_reset(struct Qdisc *sch)
 	for (idx = 0; idx < FQ_BANDS; idx++) {
 		q->band_flows[idx].new_flows.first = NULL;
 		q->band_flows[idx].old_flows.first = NULL;
+		q->band_pkt_count[idx] = 0;
 	}
 	q->delayed		= RB_ROOT;
 	q->flows		= 0;

From 40bf00ec2ee271df5ba67593991760adf8b5d0ed Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 2 Mar 2026 16:32:56 -0800
Subject: [PATCH 0855/1303] net: devmem: use READ_ONCE/WRITE_ONCE on
 binding->dev

binding->dev is protected on the write-side in
mp_dmabuf_devmem_uninstall() against concurrent writes, but due to the
concurrent bare reads in net_devmem_get_binding() and
validate_xmit_unreadable_skb() it should be wrapped in a
READ_ONCE/WRITE_ONCE pair to make sure no compiler optimizations play
with the underlying register in unforeseen ways.

Doesn't present a critical bug because the known compiler optimizations
don't result in bad behavior. There is no tearing on u64, and load
omissions/invented loads would only break if additional binding->dev
references were inlined together (they aren't right now).

This just more strictly follows the linux memory model (i.e.,
"Lock-Protected Writes With Lockless Reads" in
tools/memory-model/Documentation/access-marking.txt).

Fixes: bd61848900bf ("net: devmem: Implement TX path")
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260302-devmem-membar-fix-v2-1-5b33c9cbc28b@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c    | 2 +-
 net/core/devmem.c | 6 ++++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4af4cf2d63a4..20610a192ec7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
 	if (shinfo->nr_frags > 0) {
 		niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0]));
 		if (net_is_devmem_iov(niov) &&
-		    net_devmem_iov_binding(niov)->dev != dev)
+		    READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev)
 			goto out_free;
 	}
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 8c9aad776bf4..69d79aee07ef 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
 	 * net_device.
 	 */
 	dst_dev = dst_dev_rcu(dst);
-	if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) {
+	if (unlikely(!dst_dev) ||
+	    unlikely(dst_dev != READ_ONCE(binding->dev))) {
 		err = -ENODEV;
 		goto out_unlock;
 	}
@@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv,
 			xa_erase(&binding->bound_rxqs, xa_idx);
 			if (xa_empty(&binding->bound_rxqs)) {
 				mutex_lock(&binding->lock);
-				binding->dev = NULL;
+				ASSERT_EXCLUSIVE_WRITER(binding->dev);
+				WRITE_ONCE(binding->dev, NULL);
 				mutex_unlock(&binding->lock);
 			}
 			break;

From 7bd4b0c4779f978a6528c9b7937d2ca18e936e2c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:41 -0800
Subject: [PATCH 0856/1303] nfc: nci: free skb on nci_transceive early error
 paths

nci_transceive() takes ownership of the skb passed by the caller,
but the -EPROTO, -EINVAL, and -EBUSY error paths return without
freeing it.

Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes
the nci/nci_dev selftest hits the error path occasionally in NIPA,
and kmemleak detects leaks:

unreferenced object 0xff11000015ce6a40 (size 640):
  comm "nci_dev", pid 3954, jiffies 4295441246
  hex dump (first 32 bytes):
    6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b  kkkk.......kkkkk
    6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
  backtrace (crc 7c40cc2a):
    kmem_cache_alloc_node_noprof+0x492/0x630
    __alloc_skb+0x11e/0x5f0
    alloc_skb_with_frags+0xc6/0x8f0
    sock_alloc_send_pskb+0x326/0x3f0
    nfc_alloc_send_skb+0x94/0x1d0
    rawsock_sendmsg+0x162/0x4c0
    do_syscall_64+0x117/0xfc0

Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e95eef85971f..e859b834c0f1 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1035,18 +1035,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	struct nci_conn_info *conn_info;
 
 	conn_info = ndev->rf_conn_info;
-	if (!conn_info)
+	if (!conn_info) {
+		kfree_skb(skb);
 		return -EPROTO;
+	}
 
 	pr_debug("target_idx %d, len %d\n", target->idx, skb->len);
 
 	if (!ndev->target_active_prot) {
 		pr_err("unable to exchange data, no active target\n");
+		kfree_skb(skb);
 		return -EINVAL;
 	}
 
-	if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+	if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) {
+		kfree_skb(skb);
 		return -EBUSY;
+	}
 
 	/* store cb and context to be used on receiving data */
 	conn_info->data_exchange_cb = cb;

From d42449d2c17cdf06d1f63268557450bd3f051e9a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:42 -0800
Subject: [PATCH 0857/1303] nfc: digital: free skb on digital_in_send error
 paths

digital_in_send() takes ownership of the skb passed by the caller
(nfc_data_exchange), make sure it's freed on all error paths.

Found looking around the real driver for similar bugs to the one
just fixed in nci.

Fixes: 2c66daecc409 ("NFC Digital: Add NFC-A technology support")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/digital_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index 3670bb33732e..7cb1e6aaae90 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	int rc;
 
 	data_exch = kzalloc_obj(*data_exch);
-	if (!data_exch)
+	if (!data_exch) {
+		kfree_skb(skb);
 		return -ENOMEM;
+	}
 
 	data_exch->cb = cb;
 	data_exch->cb_context = cb_context;
@@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 				 data_exch);
 
 exit:
-	if (rc)
+	if (rc) {
+		kfree_skb(skb);
 		kfree(data_exch);
+	}
 
 	return rc;
 }

From 66083581945bd5b8e99fe49b5aeb83d03f62d053 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:43 -0800
Subject: [PATCH 0858/1303] nfc: nci: complete pending data exchange on device
 close

In nci_close_device(), complete any pending data exchange before
closing. The data exchange callback (e.g.
rawsock_data_exchange_complete) holds a socket reference.

NIPA occasionally hits this leak:

unreferenced object 0xff1100000f435000 (size 2048):
  comm "nci_dev", pid 3954, jiffies 4295441245
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00  '..@............
  backtrace (crc ec2b3c5):
    __kmalloc_noprof+0x4db/0x730
    sk_prot_alloc.isra.0+0xe4/0x1d0
    sk_alloc+0x36/0x760
    rawsock_create+0xd1/0x540
    nfc_sock_create+0x11f/0x280
    __sock_create+0x22d/0x630
    __sys_socket+0x115/0x1d0
    __x64_sys_socket+0x72/0xd0
    do_syscall_64+0x117/0xfc0
    entry_SYSCALL_64_after_hwframe+0x4b/0x53

Fixes: 38f04c6b1b68 ("NFC: protect nci_data_exchange transactions")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e859b834c0f1..43d871525dbc 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev)
 		flush_workqueue(ndev->cmd_wq);
 		timer_delete_sync(&ndev->cmd_timer);
 		timer_delete_sync(&ndev->data_timer);
+		if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+			nci_data_exchange_complete(ndev, NULL,
+						   ndev->cur_conn_id,
+						   -ENODEV);
 		mutex_unlock(&ndev->req_lock);
 		return 0;
 	}
@@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev)
 	flush_workqueue(ndev->cmd_wq);
 
 	timer_delete_sync(&ndev->cmd_timer);
+	timer_delete_sync(&ndev->data_timer);
+
+	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+		nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id,
+					   -ENODEV);
 
 	/* Clear flags except NCI_UNREG */
 	ndev->flags &= BIT(NCI_UNREG);

From 0efdc02f4f6d52f8ca5d5889560f325a836ce0a8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:44 -0800
Subject: [PATCH 0859/1303] nfc: nci: clear NCI_DATA_EXCHANGE before calling
 completion callback

Move clear_bit(NCI_DATA_EXCHANGE) before invoking the data exchange
callback in nci_data_exchange_complete().

The callback (e.g. rawsock_data_exchange_complete) may immediately
schedule another data exchange via schedule_work(tx_work).  On a
multi-CPU system, tx_work can run and reach nci_transceive() before
the current nci_data_exchange_complete() clears the flag, causing
test_and_set_bit(NCI_DATA_EXCHANGE) to return -EBUSY and the new
transfer to fail.

This causes intermittent flakes in nci/nci_dev in NIPA:

  # #  RUN           NCI.NCI1_0.t4t_tag_read ...
  # # t4t_tag_read: Test terminated by timeout
  # #          FAIL  NCI.NCI1_0.t4t_tag_read
  # not ok 3 NCI.NCI1_0.t4t_tag_read

Fixes: 38f04c6b1b68 ("NFC: protect nci_data_exchange transactions")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/data.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 78f4131af3cf..5f98c73db5af 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
 	if (!conn_info) {
 		kfree_skb(skb);
-		goto exit;
+		clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
+		return;
 	}
 
 	cb = conn_info->data_exchange_cb;
@@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	timer_delete_sync(&ndev->data_timer);
 	clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 
+	/* Mark the exchange as done before calling the callback.
+	 * The callback (e.g. rawsock_data_exchange_complete) may
+	 * want to immediately queue another data exchange.
+	 */
+	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
+
 	if (cb) {
 		/* forward skb to nfc core */
 		cb(cb_context, skb, err);
@@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 		/* no waiting callback, free skb */
 		kfree_skb(skb);
 	}
-
-exit:
-	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
 }
 
 /* ----------------- NCI TX Data ----------------- */

From d793458c45df2aed498d7f74145eab7ee22d25aa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:45 -0800
Subject: [PATCH 0860/1303] nfc: rawsock: cancel tx_work before socket teardown

In rawsock_release(), cancel any pending tx_work and purge the write
queue before orphaning the socket.  rawsock_tx_work runs on the system
workqueue and calls nfc_data_exchange which dereferences the NCI
device.  Without synchronization, tx_work can race with socket and
device teardown when a process is killed (e.g. by SIGKILL), leading
to use-after-free or leaked references.

Set SEND_SHUTDOWN first so that if tx_work is already running it will
see the flag and skip transmitting, then use cancel_work_sync to wait
for any in-progress execution to finish, and finally purge any
remaining queued skbs.

Fixes: 23b7869c0fd0 ("NFC: add the NFC socket raw protocol")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/rawsock.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index b049022399ae..f7d7a599fade 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock)
 	if (sock->type == SOCK_RAW)
 		nfc_sock_unlink(&raw_sk_list, sk);
 
+	if (sk->sk_state == TCP_ESTABLISHED) {
+		/* Prevent rawsock_tx_work from starting new transmits and
+		 * wait for any in-progress work to finish.  This must happen
+		 * before the socket is orphaned to avoid a race where
+		 * rawsock_tx_work runs after the NCI device has been freed.
+		 */
+		sk->sk_shutdown |= SEND_SHUTDOWN;
+		cancel_work_sync(&nfc_rawsock(sk)->tx_work);
+		rawsock_write_queue_purge(sk);
+	}
+
 	sock_orphan(sk);
 	sock_put(sk);
 

From 8c09412e584d9bcc0e71d758ec1008d1c8d1a326 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 3 Mar 2026 11:56:02 +0100
Subject: [PATCH 0861/1303] selftests: mptcp: more stable simult_flows tests

By default, the netem qdisc can keep up to 1000 packets under its belly
to deal with the configured rate and delay. The simult flows test-case
simulates very low speed links, to avoid problems due to slow CPUs and
the TCP stack tend to transmit at a slightly higher rate than the
(virtual) link constraints.

All the above causes a relatively large amount of packets being enqueued
in the netem qdiscs - the longer the transfer, the longer the queue -
producing increasingly high TCP RTT samples and consequently increasingly
larger receive buffer size due to DRS.

When the receive buffer size becomes considerably larger than the needed
size, the tests results can flake, i.e. because minimal inaccuracy in the
pacing rate can lead to a single subflow usage towards the end of the
connection for a considerable amount of data.

Address the issue explicitly setting netem limits suitable for the
configured link speeds and unflake all the affected tests.

Fixes: 1a418cb8e888 ("mptcp: simult flow self-tests")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-1-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 806aaa7d2d61..d11a8b949aab 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -237,10 +237,13 @@ run_test()
 	for dev in ns2eth1 ns2eth2; do
 		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
 	done
-	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
-	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# keep the queued pkts number low, or the RTT estimator will see
+	# increasing latency over time.
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50
 
 	# time is measured in ms, account for transfer size, aggregated link speed
 	# and header overhead (10%)

From fb8d0bccb221080630efcd9660c9f9349e53cc9e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:03 +0100
Subject: [PATCH 0862/1303] mptcp: pm: avoid sending RM_ADDR over same subflow

RM_ADDR are sent over an active subflow, the first one in the subflows
list. There is then a high chance the initial subflow is picked. With
the in-kernel PM, when an endpoint is removed, a RM_ADDR is sent, then
linked subflows are closed. This is done for each active MPTCP
connection.

MPTCP endpoints are likely removed because the attached network is no
longer available or usable. In this case, it is better to avoid sending
this RM_ADDR over the subflow that is going to be removed, but prefer
sending it over another active and non stale subflow, if any.

This modification avoids situations where the other end is not notified
when a subflow is no longer usable: typically when the endpoint linked
to the initial subflow is removed, especially on the server side.

Fixes: 8dd5efb1f91b ("mptcp: send ack for rm_addr")
Cc: stable@vger.kernel.org
Reported-by: Frank Lorenz <lorenz-frank@web.de>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/612
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-2-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c | 55 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 7298836469b3..57a456690406 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 }
 
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
+			       const struct mptcp_rm_list *rm_list)
 {
-	struct mptcp_subflow_context *subflow, *alt = NULL;
+	u8 i, id = subflow_get_local_id(subflow);
+
+	for (i = 0; i < rm_list->nr; i++) {
+		if (rm_list->ids[i] == id)
+			return true;
+	}
+
+	return false;
+}
+
+static void
+mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
+				  const struct mptcp_rm_list *rm_list)
+{
+	struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
+		if (!__mptcp_subflow_active(subflow))
+			continue;
 
-			if (!alt)
-				alt = subflow;
+		if (unlikely(subflow->stale)) {
+			if (!stale)
+				stale = subflow;
+		} else if (unlikely(rm_list &&
+				    subflow_in_rm_list(subflow, rm_list))) {
+			if (!same_id)
+				same_id = subflow;
+		} else {
+			goto send_ack;
 		}
 	}
 
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
+	if (same_id)
+		subflow = same_id;
+	else if (stale)
+		subflow = stale;
+	else
+		return;
+
+send_ack:
+	mptcp_pm_send_ack(msk, subflow, false, false);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	mptcp_pm_addr_send_ack_avoid_list(msk, NULL);
 }
 
 int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack_avoid_list(msk, rm_list);
 	return 0;
 }
 

From 560edd99b5f58b2d4bbe3c8e51e1eed68d887b0e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:04 +0100
Subject: [PATCH 0863/1303] selftests: mptcp: join: check RM_ADDR not sent over
 same subflow

This validates the previous commit: RM_ADDR were sent over the first
found active subflow which could be the same as the one being removed.
It is more likely to loose this notification.

For this check, RM_ADDR are explicitly dropped when trying to send them
over the initial subflow, when removing the endpoint attached to it. If
it is dropped, the test will complain because some RM_ADDR have not been
received.

Note that only the RM_ADDR are dropped, to allow the linked subflow to
be quickly and cleanly closed. To only drop those RM_ADDR, a cBPF byte
code is used. If the IPTables commands fail, that's OK, the tests will
continue to pass, but not validate this part. This can be ignored:
another subtest fully depends on such command, and will be marked as
skipped.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 8dd5efb1f91b ("mptcp: send ack for rm_addr")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-3-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index dc1f200aaa81..058ad5a13d24 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
 			       6 0 0 65535,
 			       6 0 0 0"
 
+# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption
+# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c &&
+#				  (ip[66] & 0xf0) == 0x40'"
+CBPF_MPTCP_SUBOPTION_RM_ADDR="13,
+			      48 0 0 0,
+			      84 0 0 240,
+			      21 0 9 64,
+			      48 0 0 32,
+			      84 0 0 240,
+			      21 0 6 192,
+			      48 0 0 53,
+			      21 0 4 12,
+			      48 0 0 66,
+			      84 0 0 240,
+			      21 0 1 64,
+			      6 0 0 65535,
+			      6 0 0 0"
+
 init_partial()
 {
 	capout=$(mktemp)
@@ -4217,6 +4235,14 @@ endpoint_tests()
 		chk_subflow_nr "after no reject" 3
 		chk_mptcp_info subflows 2 subflows 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		local i
 		for i in $(seq 3); do
 			pm_nl_del_endpoint $ns2 1 10.0.1.2
@@ -4229,6 +4255,7 @@ endpoint_tests()
 			chk_subflow_nr "after re-add id 0 ($i)" 3
 			chk_mptcp_info subflows 3 subflows 3
 		done
+		[ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1
 
 		mptcp_lib_kill_group_wait $tests_pid
 
@@ -4288,11 +4315,20 @@ endpoint_tests()
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		pm_nl_del_endpoint $ns1 42 10.0.1.1
 		sleep 0.5
 		chk_subflow_nr "after delete ID 0" 2
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
+		[ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1
 
 		pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
 		wait_mpj 4

From 579a752464a64cb5f9139102f0e6b90a1f595ceb Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:05 +0100
Subject: [PATCH 0864/1303] mptcp: pm: in-kernel: always mark signal+subflow
 endp as used

Syzkaller managed to find a combination of actions that was generating
this warning:

  msk->pm.local_addr_used == 0
  WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961
  Modules linked in:
  CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full)
  Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014
  RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline]
  RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline]
  RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210
  Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a
  RSP: 0018:ffffc90001663880 EFLAGS: 00010293
  RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff
  R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640
  R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650
  FS:  00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115
   genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
   genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210
   netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550
   genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
   netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
   netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344
   netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894
   sock_sendmsg_nosec net/socket.c:727 [inline]
   __sock_sendmsg+0xc9/0xf0 net/socket.c:742
   ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592
   ___sys_sendmsg+0x2de/0x320 net/socket.c:2646
   __sys_sendmsg net/socket.c:2678 [inline]
   __do_sys_sendmsg net/socket.c:2683 [inline]
   __se_sys_sendmsg net/socket.c:2681 [inline]
   __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f66346f826d
  Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d
  RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007
  RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8
  R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770
   </TASK>

The actions that caused that seem to be:

 - Set the MPTCP subflows limit to 0
 - Create an MPTCP endpoint with both the 'signal' and 'subflow' flags
 - Create a new MPTCP connection from a different address: an ADD_ADDR
   linked to the MPTCP endpoint will be sent ('signal' flag), but no
   subflows is initiated ('subflow' flag)
 - Remove the MPTCP endpoint

In this case, msk->pm.local_addr_used has been kept to 0 -- because no
subflows have been created -- but the corresponding bit in
msk->pm.id_avail_bitmap has been cleared when the ADD_ADDR has been
sent. This later causes a splat when removing the MPTCP endpoint because
msk->pm.local_addr_used has been kept to 0.

Now, if an endpoint has both the signal and subflow flags, but it is not
possible to create subflows because of the limits or the c-flag case,
then the local endpoint counter is still incremented: the endpoint is
used at the end. This avoids issues later when removing the endpoint and
calling __mark_subflow_endp_available(), which expects
msk->pm.local_addr_used to have been previously incremented if the
endpoint was marked as used according to msk->pm.id_avail_bitmap.

Note that signal_and_subflow variable is reset to false when the limits
and the c-flag case allows subflows creation. Also, local_addr_used is
only incremented for non ID0 subflows.

Fixes: 85df533a787b ("mptcp: pm: do not ignore 'subflow' if 'signal' flag is also set")
Cc: stable@vger.kernel.org
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/613
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-4-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_kernel.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index b5316a6c7d1b..b2b9df43960e 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -418,6 +418,15 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	}
 
 exit:
+	/* If an endpoint has both the signal and subflow flags, but it is not
+	 * possible to create subflows -- the 'while' loop body above never
+	 * executed --  then still mark the endp as used, which is somehow the
+	 * case. This avoids issues later when removing the endpoint and calling
+	 * __mark_subflow_endp_available(), which expects the increment here.
+	 */
+	if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id)
+		msk->pm.local_addr_used++;
+
 	mptcp_pm_nl_check_work_pending(msk);
 }
 

From 1777f349ff41b62dfe27454b69c27b0bc99ffca5 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:06 +0100
Subject: [PATCH 0865/1303] selftests: mptcp: join: check removing
 signal+subflow endp

This validates the previous commit: endpoints with both the signal and
subflow flags should always be marked as used even if it was not
possible to create new subflows due to the MPTCP PM limits.

For this test, an extra endpoint is created with both the signal and the
subflow flags, and limits are set not to create extra subflows. In this
case, an ADD_ADDR is sent, but no subflows are created. Still, the local
endpoint is marked as used, and no warning is fired when removing the
endpoint, after having sent a RM_ADDR.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 85df533a787b ("mptcp: pm: do not ignore 'subflow' if 'signal' flag is also set")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-5-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 058ad5a13d24..a3144d7298a5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -2626,6 +2626,19 @@ remove_tests()
 		chk_rst_nr 0 0
 	fi
 
+	# signal+subflow with limits, remove
+	if reset "remove signal+subflow with limits"; then
+		pm_nl_set_limits $ns1 0 0
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow
+		pm_nl_set_limits $ns2 0 0
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 0 0 0
+		chk_add_nr 1 1
+		chk_rm_nr 1 0 invert
+		chk_rst_nr 0 0
+	fi
+
 	# addresses remove
 	if reset "remove addresses"; then
 		pm_nl_set_limits $ns1 3 3

From 35dfedce442c4060cfe5b98368bc9643fb995716 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:25 +0000
Subject: [PATCH 0866/1303] net: stmmac: Fix error handling in VLAN add and
 delete paths

stmmac_vlan_rx_add_vid() updates active_vlans and the VLAN hash
register before writing the HW filter entry. If the filter write
fails, it leaves a stale VID in active_vlans and the hash register.

stmmac_vlan_rx_kill_vid() has the reverse problem: it clears
active_vlans before removing the HW filter. On failure, the VID is
gone from active_vlans but still present in the HW filter table.

To fix this, reorder the operations to update the hash table first,
then attempt the HW filter operation. If the HW filter fails, roll
back both the active_vlans bitmap and the hash table by calling
stmmac_vlan_update() again.

Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-2-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c  | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e00aa42a1961..b6a127316ab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6794,9 +6794,13 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 
 	if (priv->hw->num_vlan) {
 		ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
-		if (ret)
+		if (ret) {
+			clear_bit(vid, priv->active_vlans);
+			stmmac_vlan_update(priv, is_double);
 			goto err_pm_put;
+		}
 	}
+
 err_pm_put:
 	pm_runtime_put(priv->device);
 
@@ -6820,15 +6824,21 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		is_double = true;
 
 	clear_bit(vid, priv->active_vlans);
+	ret = stmmac_vlan_update(priv, is_double);
+	if (ret) {
+		set_bit(vid, priv->active_vlans);
+		goto del_vlan_error;
+	}
 
 	if (priv->hw->num_vlan) {
 		ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
-		if (ret)
+		if (ret) {
+			set_bit(vid, priv->active_vlans);
+			stmmac_vlan_update(priv, is_double);
 			goto del_vlan_error;
+		}
 	}
 
-	ret = stmmac_vlan_update(priv, is_double);
-
 del_vlan_error:
 	pm_runtime_put(priv->device);
 

From e38200e361cbe331806dc454c76c11c7cd95e1b9 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:26 +0000
Subject: [PATCH 0867/1303] net: stmmac: Improve double VLAN handling

The double VLAN bits (EDVLP, ESVL, DOVLTC) are handled inconsistently
between the two vlan_update_hash() implementations:

- dwxgmac2_update_vlan_hash() explicitly clears the double VLAN bits when
is_double is false, meaning that adding a 802.1Q VLAN will disable
double VLAN mode:

  $ ip link add link eth0 name eth0.200 type vlan id 200 protocol 802.1ad
  $ ip link add link eth0 name eth0.100 type vlan id 100
  # Double VLAN bits no longer set

- vlan_update_hash() sets these bits and only clears them when the last
VLAN has been removed, so double VLAN mode remains enabled even after all
802.1AD VLANs are removed.

Address both issues by tracking the number of active 802.1AD VLANs in
priv->num_double_vlans. Pass this count to stmmac_vlan_update() so both
implementations correctly set the double VLAN bits when any 802.1AD
VLAN is active, and clear them only when none remain.

Also update vlan_update_hash() to explicitly clear the double VLAN bits
when is_double is false, matching the dwxgmac2 behavior.

Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-3-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h     |  1 +
 .../net/ethernet/stmicro/stmmac/stmmac_main.c    | 16 ++++++++++++----
 .../net/ethernet/stmicro/stmmac/stmmac_vlan.c    |  8 ++++++++
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 51c96a738151..33667a26708c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -323,6 +323,7 @@ struct stmmac_priv {
 	void __iomem *ptpaddr;
 	void __iomem *estaddr;
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	unsigned int num_double_vlans;
 	int sfty_irq;
 	int sfty_ce_irq;
 	int sfty_ue_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b6a127316ab5..01d181c2c68e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6775,6 +6775,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int num_double_vlans;
 	bool is_double = false;
 	int ret;
 
@@ -6786,7 +6787,8 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 		is_double = true;
 
 	set_bit(vid, priv->active_vlans);
-	ret = stmmac_vlan_update(priv, is_double);
+	num_double_vlans = priv->num_double_vlans + is_double;
+	ret = stmmac_vlan_update(priv, num_double_vlans);
 	if (ret) {
 		clear_bit(vid, priv->active_vlans);
 		goto err_pm_put;
@@ -6796,11 +6798,13 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 		ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
 		if (ret) {
 			clear_bit(vid, priv->active_vlans);
-			stmmac_vlan_update(priv, is_double);
+			stmmac_vlan_update(priv, priv->num_double_vlans);
 			goto err_pm_put;
 		}
 	}
 
+	priv->num_double_vlans = num_double_vlans;
+
 err_pm_put:
 	pm_runtime_put(priv->device);
 
@@ -6813,6 +6817,7 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int num_double_vlans;
 	bool is_double = false;
 	int ret;
 
@@ -6824,7 +6829,8 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		is_double = true;
 
 	clear_bit(vid, priv->active_vlans);
-	ret = stmmac_vlan_update(priv, is_double);
+	num_double_vlans = priv->num_double_vlans - is_double;
+	ret = stmmac_vlan_update(priv, num_double_vlans);
 	if (ret) {
 		set_bit(vid, priv->active_vlans);
 		goto del_vlan_error;
@@ -6834,11 +6840,13 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
 		if (ret) {
 			set_bit(vid, priv->active_vlans);
-			stmmac_vlan_update(priv, is_double);
+			stmmac_vlan_update(priv, priv->num_double_vlans);
 			goto del_vlan_error;
 		}
 	}
 
+	priv->num_double_vlans = num_double_vlans;
+
 del_vlan_error:
 	pm_runtime_put(priv->device);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index b18404dd5a8b..de1a70e1c86e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -183,6 +183,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
 			value |= VLAN_EDVLP;
 			value |= VLAN_ESVL;
 			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
 		}
 
 		writel(value, ioaddr + VLAN_TAG);
@@ -193,6 +197,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
 			value |= VLAN_EDVLP;
 			value |= VLAN_ESVL;
 			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
 		}
 
 		writel(value | perfect_match, ioaddr + VLAN_TAG);

From bd7ad51253a76fb35886d01cfe9a37f0e4ed6709 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:27 +0000
Subject: [PATCH 0868/1303] net: stmmac: Fix VLAN HW state restore

When the network interface is opened or resumed, a DMA reset is performed,
which resets all hardware state, including VLAN state. Currently, only
the resume path is restoring the VLAN state via
stmmac_restore_hw_vlan_rx_fltr(), but that is incomplete: the VLAN hash
table and the VLAN_TAG control bits are not restored.

Therefore, add stmmac_vlan_restore(), which restores the full VLAN
state by updating both the HW filter entries and the hash table, and
call it from both the open and resume paths.

The VLAN restore is moved outside of phylink_rx_clk_stop_block/unblock
in the resume path because receive clock stop is already disabled when
stmmac supports VLAN.

Also, remove the hash readback code in vlan_restore_hw_rx_fltr() that
attempts to restore VTHM by reading VLAN_HASH_TABLE, as it always reads
zero after DMA reset, making it dead code.

Fixes: 3cd1cfcba26e ("net: stmmac: Implement VLAN Hash Filtering in XGMAC")
Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-4-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 24 +++++++++++++++++--
 .../net/ethernet/stmicro/stmmac/stmmac_vlan.c | 10 --------
 2 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 01d181c2c68e..6d4ce35e990f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -156,6 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue);
 static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue);
 static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 					  u32 rxmode, u32 chan);
+static int stmmac_vlan_restore(struct stmmac_priv *priv);
 
 #ifdef CONFIG_DEBUG_FS
 static const struct net_device_ops stmmac_netdev_ops;
@@ -4107,6 +4108,8 @@ static int __stmmac_open(struct net_device *dev,
 
 	phylink_start(priv->phylink);
 
+	stmmac_vlan_restore(priv);
+
 	ret = stmmac_request_irq(dev);
 	if (ret)
 		goto irq_error;
@@ -6853,6 +6856,23 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 	return ret;
 }
 
+static int stmmac_vlan_restore(struct stmmac_priv *priv)
+{
+	int ret;
+
+	if (!(priv->dev->features & NETIF_F_VLAN_FEATURES))
+		return 0;
+
+	if (priv->hw->num_vlan)
+		stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw);
+
+	ret = stmmac_vlan_update(priv, priv->num_double_vlans);
+	if (ret)
+		netdev_err(priv->dev, "Failed to restore VLANs\n");
+
+	return ret;
+}
+
 static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -8277,10 +8297,10 @@ int stmmac_resume(struct device *dev)
 	stmmac_init_coalesce(priv);
 	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_rx_mode(ndev);
-
-	stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw);
 	phylink_rx_clk_stop_unblock(priv->phylink);
 
+	stmmac_vlan_restore(priv);
+
 	stmmac_enable_all_queues(priv);
 	stmmac_enable_all_dma_irq(priv);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index de1a70e1c86e..fcc34867405e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -139,9 +139,6 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 				    struct mac_device_info *hw)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-	u32 hash;
 	u32 val;
 	int i;
 
@@ -158,13 +155,6 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 			vlan_write_filter(dev, hw, i, val);
 		}
 	}
-
-	hash = readl(ioaddr + VLAN_HASH_TABLE);
-	if (hash & VLAN_VLHT) {
-		value = readl(ioaddr + VLAN_TAG);
-		value |= VLAN_VTHM;
-		writel(value, ioaddr + VLAN_TAG);
-	}
 }
 
 static void vlan_update_hash(struct mac_device_info *hw, u32 hash,

From 2cd70e3968f505996d5fefdf7ca684f0f4575734 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:28 +0000
Subject: [PATCH 0869/1303] net: stmmac: Defer VLAN HW configuration when
 interface is down

VLAN register accesses on the MAC side require the PHY RX clock to be
active. When the network interface is down, the PHY is suspended and
the RX clock is unavailable, causing VLAN operations to fail with
timeouts.

The VLAN core automatically removes VID 0 after the interface goes down
and re-adds it when it comes back up, so these timeouts happen during
normal interface down/up:

    # ip link set end1 down
    renesas-gbeth 15c40000.ethernet end1: Timeout accessing MAC_VLAN_Tag_Filter
    renesas-gbeth 15c40000.ethernet end1: failed to kill vid 0081/0

Adding VLANs while the interface is down also fails:

    # ip link add link end1 name end1.10 type vlan id 10
    renesas-gbeth 15c40000.ethernet end1: Timeout accessing MAC_VLAN_Tag_Filter
    RTNETLINK answers: Device or resource busy

To fix this, check if the interface is up before accessing VLAN registers.
The software state is always kept up to date regardless of interface state.

When the interface is brought up, stmmac_vlan_restore() is called
to write the VLAN state to hardware.

Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-5-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |  3 ++
 .../net/ethernet/stmicro/stmmac/stmmac_vlan.c | 42 ++++++++++---------
 2 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6d4ce35e990f..6827c99bde8c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6769,6 +6769,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 		hash = 0;
 	}
 
+	if (!netif_running(priv->dev))
+		return 0;
+
 	return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index fcc34867405e..e24efe3bfedb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -76,7 +76,9 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev,
 		}
 
 		hw->vlan_filter[0] = vid;
-		vlan_write_single(dev, vid);
+
+		if (netif_running(dev))
+			vlan_write_single(dev, vid);
 
 		return 0;
 	}
@@ -97,12 +99,15 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev,
 		return -EPERM;
 	}
 
-	ret = vlan_write_filter(dev, hw, index, val);
+	if (netif_running(dev)) {
+		ret = vlan_write_filter(dev, hw, index, val);
+		if (ret)
+			return ret;
+	}
 
-	if (!ret)
-		hw->vlan_filter[index] = val;
+	hw->vlan_filter[index] = val;
 
-	return ret;
+	return 0;
 }
 
 static int vlan_del_hw_rx_fltr(struct net_device *dev,
@@ -115,7 +120,9 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 	if (hw->num_vlan == 1) {
 		if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) {
 			hw->vlan_filter[0] = 0;
-			vlan_write_single(dev, 0);
+
+			if (netif_running(dev))
+				vlan_write_single(dev, 0);
 		}
 		return 0;
 	}
@@ -124,22 +131,23 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 	for (i = 0; i < hw->num_vlan; i++) {
 		if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) &&
 		    ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) {
-			ret = vlan_write_filter(dev, hw, i, 0);
 
-			if (!ret)
-				hw->vlan_filter[i] = 0;
-			else
-				return ret;
+			if (netif_running(dev)) {
+				ret = vlan_write_filter(dev, hw, i, 0);
+				if (ret)
+					return ret;
+			}
+
+			hw->vlan_filter[i] = 0;
 		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 				    struct mac_device_info *hw)
 {
-	u32 val;
 	int i;
 
 	/* Single Rx VLAN Filter */
@@ -149,12 +157,8 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 	}
 
 	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) {
-			val = hw->vlan_filter[i];
-			vlan_write_filter(dev, hw, i, val);
-		}
-	}
+	for (i = 0; i < hw->num_vlan; i++)
+		vlan_write_filter(dev, hw, i, hw->vlan_filter[i]);
 }
 
 static void vlan_update_hash(struct mac_device_info *hw, u32 hash,

From 91d7e9df42598af28ca440b95b16a4e51a408771 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Date: Wed, 4 Mar 2026 20:27:52 -0300
Subject: [PATCH 0870/1303] drm/ttm: Fix bo resource use-after-free
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When allocating a lot of buffers and putting the TTM under memory pressure,
during swapout, it might crash the system with the stack trace below.

It turns out that ttm_bo_swapout_cb might replace bo->resource when it
moves it to system cached.

When commit c06da4b3573a ("drm/ttm: Tidy usage of local variables a little
bit") used a local variable for bo->resource, it used the freed resource
later in the function, leading to a UAF.

Move back to using bo->resource in all cases in that function instead of a
local variable.

[  604.814275] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  604.814284] #PF: supervisor read access in kernel mode
[  604.814288] #PF: error_code(0x0000) - not-present page
[  604.814291] PGD 0 P4D 0
[  604.814296] Oops: Oops: 0000 [#1] SMP NOPTI
[  604.814303] CPU: 2 UID: 0 PID: 4408 Comm: vulkan Tainted: G        W           7.0.0-rc2-00001-gc50a051e6aca #21 PREEMPT(full)  aef6eb0c02036a7c8a5e62e0c84a30c2be90688d
[  604.814309] Tainted: [W]=WARN
[  604.814311] Hardware name: Valve Jupiter/Jupiter, BIOS F7A0133 08/05/2024
[  604.814314] RIP: 0010:ttm_resource_move_to_lru_tail+0x100/0x160 [ttm]
[  604.814329] Code: 5b 5d e9 83 b4 1b cb 48 63 d2 48 c1 e0 04 48 8b 4e 40 48 8d 7e 40 48 8b ac d3 d8 00 00 00 48 89 c3 48 8d 54 05 68 48 8b 46 48 <48> 3b 38 0f 85 b3 3b 00 00 48 3b 79 08 0f 85 a9 3b 00 00 48 89 41
[  604.814332] RSP: 0018:ffffcfe54e3d7578 EFLAGS: 00010256
[  604.814336] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8cf09eced300
[  604.814339] RDX: 0000000000000068 RSI: ffff8cf1d4c1fc00 RDI: ffff8cf1d4c1fc40
[  604.814341] RBP: 0000000000000000 R08: ffff8cf09eced300 R09: 0000000000000000
[  604.814344] R10: 0000000000000000 R11: 0000000000000016 R12: ffff8cf1d4c1fc00
[  604.814346] R13: 0000000000000400 R14: ffff8cf096289c00 R15: ffff8cf084c8f688
[  604.814349] FS:  00007f00531b7780(0000) GS:ffff8cf4217a0000(0000) knlGS:0000000000000000
[  604.814352] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  604.814355] CR2: 0000000000000000 CR3: 000000018e3df000 CR4: 0000000000350ef0
[  604.814358] Call Trace:
[  604.814362]  <TASK>
[  604.814368]  ttm_bo_swapout_cb+0x24c/0x280 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814380]  ttm_lru_walk_for_evict+0xac/0x1d0 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814394]  ttm_bo_swapout+0x5b/0x80 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814405]  ttm_global_swapout+0x63/0x100 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814415]  ttm_tt_populate+0x82/0x130 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814424]  ttm_bo_populate+0x37/0xa0 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814433]  ttm_bo_handle_move_mem+0x157/0x170 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814443]  ttm_bo_validate+0xd9/0x180 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814453]  ttm_bo_init_reserved+0xa0/0x1b0 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.814461]  ? srso_return_thunk+0x5/0x5f
[  604.814469]  amdgpu_bo_create+0x1f5/0x500 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.814855]  ? __pfx_amdgpu_bo_user_destroy+0x10/0x10 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.815182]  amdgpu_bo_create_user+0x3d/0x70 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.815504]  amdgpu_gem_create_ioctl+0x16c/0x3b0 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.815830]  ? __pfx_amdgpu_bo_user_destroy+0x10/0x10 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.816155]  ? __pfx_amdgpu_gem_create_ioctl+0x10/0x10 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.816478]  drm_ioctl_kernel+0xae/0x100
[  604.816486]  drm_ioctl+0x283/0x510
[  604.816491]  ? __pfx_amdgpu_gem_create_ioctl+0x10/0x10 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.816819]  amdgpu_drm_ioctl+0x4a/0x80 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.817135]  __x64_sys_ioctl+0x96/0xe0
[  604.817142]  do_syscall_64+0x11b/0x7e0
[  604.817148]  ? srso_return_thunk+0x5/0x5f
[  604.817152]  ? srso_return_thunk+0x5/0x5f
[  604.817156]  ? walk_system_ram_range+0xb0/0x110
[  604.817161]  ? srso_return_thunk+0x5/0x5f
[  604.817165]  ? __pte_offset_map+0x1b/0xb0
[  604.817170]  ? srso_return_thunk+0x5/0x5f
[  604.817174]  ? pte_offset_map_lock+0x87/0xf0
[  604.817179]  ? srso_return_thunk+0x5/0x5f
[  604.817183]  ? insert_pfn+0x9f/0x1f0
[  604.817188]  ? srso_return_thunk+0x5/0x5f
[  604.817192]  ? vmf_insert_pfn_prot+0x97/0x190
[  604.817197]  ? srso_return_thunk+0x5/0x5f
[  604.817201]  ? ttm_bo_vm_fault_reserved+0x1a6/0x3f0 [ttm a469cf7fcb6737fdcf3fb5cdbcc8b1ca41f3e302]
[  604.817213]  ? srso_return_thunk+0x5/0x5f
[  604.817217]  ? amdgpu_gem_fault+0xe2/0x100 [amdgpu 361516226706227f4403914dbfdd3f90996136ca]
[  604.817542]  ? srso_return_thunk+0x5/0x5f
[  604.817546]  ? __do_fault+0x33/0x180
[  604.817550]  ? srso_return_thunk+0x5/0x5f
[  604.817554]  ? do_fault+0x178/0x610
[  604.817559]  ? srso_return_thunk+0x5/0x5f
[  604.817562]  ? __handle_mm_fault+0x9be/0x1120
[  604.817567]  ? srso_return_thunk+0x5/0x5f
[  604.817574]  ? srso_return_thunk+0x5/0x5f
[  604.817578]  ? count_memcg_events+0xc4/0x160
[  604.817583]  ? srso_return_thunk+0x5/0x5f
[  604.817587]  ? handle_mm_fault+0x1d7/0x2e0
[  604.817593]  ? srso_return_thunk+0x5/0x5f
[  604.817596]  ? do_user_addr_fault+0x173/0x660
[  604.817602]  ? srso_return_thunk+0x5/0x5f
[  604.817607]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  604.817612] RIP: 0033:0x7f00532cef4d
[  604.817617] Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
[  604.817620] RSP: 002b:00007ffd69ab0650 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[  604.817624] RAX: ffffffffffffffda RBX: 00007ffd69ab07d0 RCX: 00007f00532cef4d
[  604.817627] RDX: 00007ffd69ab0700 RSI: 00000000c0206440 RDI: 0000000000000005
[  604.817629] RBP: 00007ffd69ab06a0 R08: 00007f00533a0ac0 R09: 0000000000000000
[  604.817632] R10: 00007ffd69ab07c0 R11: 0000000000000246 R12: 00007ffd69ab0700
[  604.817634] R13: 00000000c0206440 R14: 0000000000000005 R15: 0000000000000243
[  604.817642]  </TASK>

Cc: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Christian König <christian.koenig@amd.com>
Fixes: c06da4b3573a ("drm/ttm: Tidy usage of local variables a little bit")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20260304-ttm_bo_res_uaf-v1-1-43f20125b67f@igalia.com
---
 drivers/gpu/drm/ttm/ttm_bo.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index acb9197db879..0765d69423d2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1107,8 +1107,7 @@ struct ttm_bo_swapout_walk {
 static s64
 ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo)
 {
-	struct ttm_resource *res = bo->resource;
-	struct ttm_place place = { .mem_type = res->mem_type };
+	struct ttm_place place = { .mem_type = bo->resource->mem_type };
 	struct ttm_bo_swapout_walk *swapout_walk =
 		container_of(walk, typeof(*swapout_walk), walk);
 	struct ttm_operation_ctx *ctx = walk->arg.ctx;
@@ -1148,7 +1147,7 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo)
 	/*
 	 * Move to system cached
 	 */
-	if (res->mem_type != TTM_PL_SYSTEM) {
+	if (bo->resource->mem_type != TTM_PL_SYSTEM) {
 		struct ttm_resource *evict_mem;
 		struct ttm_place hop;
 
@@ -1180,15 +1179,15 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo)
 
 	if (ttm_tt_is_populated(tt)) {
 		spin_lock(&bdev->lru_lock);
-		ttm_resource_del_bulk_move(res, bo);
+		ttm_resource_del_bulk_move(bo->resource, bo);
 		spin_unlock(&bdev->lru_lock);
 
 		ret = ttm_tt_swapout(bdev, tt, swapout_walk->gfp_flags);
 
 		spin_lock(&bdev->lru_lock);
 		if (ret)
-			ttm_resource_add_bulk_move(res, bo);
-		ttm_resource_move_to_lru_tail(res);
+			ttm_resource_add_bulk_move(bo->resource, bo);
+		ttm_resource_move_to_lru_tail(bo->resource);
 		spin_unlock(&bdev->lru_lock);
 	}
 

From 281cb17787d4284a7790b9cbd80fded826ca7739 Mon Sep 17 00:00:00 2001
From: hongao <hongao@uniontech.com>
Date: Wed, 4 Mar 2026 19:29:14 +0800
Subject: [PATCH 0871/1303] xfs: Remove redundant NULL check after __GFP_NOFAIL

kzalloc() is called with __GFP_NOFAIL, so a NULL return is not expected.
Drop the redundant !map check in xfs_dabuf_map().
Also switch the nirecs-sized allocation to kcalloc().

Signed-off-by: hongao <hongao@uniontech.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_da_btree.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 766631f0562e..09d4c17b3e7b 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2716,12 +2716,8 @@ xfs_dabuf_map(
 	 * larger one that needs to be free by the caller.
 	 */
 	if (nirecs > 1) {
-		map = kzalloc(nirecs * sizeof(struct xfs_buf_map),
-				GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
-		if (!map) {
-			error = -ENOMEM;
-			goto out_free_irecs;
-		}
+		map = kcalloc(nirecs, sizeof(struct xfs_buf_map),
+			      GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
 		*mapp = map;
 	}
 

From ce8ee8583ed83122405eabaa8fb351be4d9dc65c Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 5 Mar 2026 11:15:50 +0800
Subject: [PATCH 0872/1303] block: use trylock to avoid lockdep circular
 dependency in sysfs

Use trylock instead of blocking lock acquisition for update_nr_hwq_lock
in queue_requests_store() and elv_iosched_store() to avoid circular lock
dependency with kernfs active reference during concurrent disk deletion:

  update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
  kn->active -> update_nr_hwq_lock (via sysfs write path)

Return -EBUSY when the lock is not immediately available.

Reported-and-tested-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs-em-4acsHabMdT=jJhXkCzjnprD-aQH1OgrZo4nTnmMw@mail.gmail.com/
Fixes: 626ff4f8ebcb ("blk-mq: convert to serialize updating nr_requests with update_nr_hwq_lock")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-sysfs.c |  8 +++++++-
 block/elevator.c  | 12 +++++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f3b1968c80ce..55a1bbfef7d4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -78,8 +78,14 @@ queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 	/*
 	 * Serialize updating nr_requests with concurrent queue_requests_store()
 	 * and switching elevator.
+	 *
+	 * Use trylock to avoid circular lock dependency with kernfs active
+	 * reference during concurrent disk deletion:
+	 *   update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
+	 *   kn->active -> update_nr_hwq_lock (via this sysfs write path)
 	 */
-	down_write(&set->update_nr_hwq_lock);
+	if (!down_write_trylock(&set->update_nr_hwq_lock))
+		return -EBUSY;
 
 	if (nr == q->nr_requests)
 		goto unlock;
diff --git a/block/elevator.c b/block/elevator.c
index ebe2a1fcf011..3bcd37c2aa34 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -807,7 +807,16 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	elv_iosched_load_module(ctx.name);
 	ctx.type = elevator_find_get(ctx.name);
 
-	down_read(&set->update_nr_hwq_lock);
+	/*
+	 * Use trylock to avoid circular lock dependency with kernfs active
+	 * reference during concurrent disk deletion:
+	 *   update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
+	 *   kn->active -> update_nr_hwq_lock (via this sysfs write path)
+	 */
+	if (!down_read_trylock(&set->update_nr_hwq_lock)) {
+		ret = -EBUSY;
+		goto out;
+	}
 	if (!blk_queue_no_elv_switch(q)) {
 		ret = elevator_change(q, &ctx);
 		if (!ret)
@@ -817,6 +826,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	}
 	up_read(&set->update_nr_hwq_lock);
 
+out:
 	if (ctx.type)
 		elevator_put(ctx.type);
 	return ret;

From b824c3e16c1904bf80df489e293d1e3cbf98896d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 2 Mar 2026 17:26:31 +0100
Subject: [PATCH 0873/1303] net: Provide a PREEMPT_RT specific check for
 netdev_queue::_xmit_lock

After acquiring netdev_queue::_xmit_lock the number of the CPU owning
the lock is recorded in netdev_queue::xmit_lock_owner. This works as
long as the BH context is not preemptible.

On PREEMPT_RT the softirq context is preemptible and without the
softirq-lock it is possible to have multiple user in __dev_queue_xmit()
submitting a skb on the same CPU. This is fine in general but this means
also that the current CPU is recorded as netdev_queue::xmit_lock_owner.
This in turn leads to the recursion alert and the skb is dropped.

Instead checking the for CPU number, that owns the lock, PREEMPT_RT can
check if the lockowner matches the current task.

Add netif_tx_owned() which returns true if the current context owns the
lock by comparing the provided CPU number with the recorded number. This
resembles the current check by negating the condition (the current check
returns true if the lock is not owned).
On PREEMPT_RT use rt_mutex_owner() to return the lock owner and compare
the current task against it.
Use the new helper in __dev_queue_xmit() and netif_local_xmit_active()
which provides a similar check.
Update comments regarding pairing READ_ONCE().

Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/all/20260216134333.412332-1-spasswolf@web.de
Fixes: 3253cb49cbad4 ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20260302162631.uGUyIqDT@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 27 ++++++++++++++++++++++-----
 net/core/dev.c            |  5 +----
 net/core/netpoll.c        |  2 +-
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d4e6e00bb90a..67e25f6d15a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
@@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
@@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 	bool ok = spin_trylock(&txq->_xmit_lock);
 
 	if (likely(ok)) {
-		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		/* Pairs with READ_ONCE() in netif_tx_owned() */
 		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 	}
 	return ok;
@@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
@@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev)
 	local_bh_enable();
 }
 
+#ifndef CONFIG_PREEMPT_RT
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	/* Other cpus might concurrently change txq->xmit_lock_owner
+	 * to -1 or to their cpu id, but not to our id.
+	 */
+	return READ_ONCE(txq->xmit_lock_owner) == cpu;
+}
+
+#else
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	return rt_mutex_owner(&txq->_xmit_lock.lock) == current;
+}
+
+#endif
+
 static inline void netif_addr_lock(struct net_device *dev)
 {
 	unsigned char nest_level = 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index 20610a192ec7..14a83f2035b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4818,10 +4818,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	if (dev->flags & IFF_UP) {
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
-		/* Other cpus might concurrently change txq->xmit_lock_owner
-		 * to -1 or to their cpu id, but not to our id.
-		 */
-		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
+		if (!netif_tx_owned(txq, cpu)) {
 			bool is_list = false;
 
 			if (dev_xmit_recursion())
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a8558a52884f..cd74beffd209 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev)
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
 
-		if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id())
+		if (netif_tx_owned(txq, smp_processor_id()))
 			return 1;
 	}
 

From def602e498a4f951da95c95b1b8ce8ae68aa733a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 2 Mar 2026 23:12:37 +0100
Subject: [PATCH 0874/1303] netfilter: nf_tables: unconditionally bump
 set->nelems before insertion

In case that the set is full, a new element gets published then removed
without waiting for the RCU grace period, while RCU reader can be
walking over it already.

To address this issue, add the element transaction even if set is full,
but toggle the set_full flag to report -ENFILE so the abort path safely
unwinds the set to its previous state.

As for element updates, decrement set->nelems to restore it.

A simpler fix is to call synchronize_rcu() in the error path.
However, with a large batch adding elements to already maxed-out set,
this could cause noticeable slowdown of such batches.

Fixes: 35d0ac9070ef ("netfilter: nf_tables: fix set->nelems counting with no NLM_F_EXCL")
Reported-by: Inseo An <y0un9sa@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fd7f7e4e2a43..df67932d3e09 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7170,6 +7170,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_data_desc desc;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
+	bool set_full = false;
 	u64 expiration;
 	u64 timeout;
 	int err, i;
@@ -7461,10 +7462,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (err < 0)
 		goto err_elem_free;
 
+	if (!(flags & NFT_SET_ELEM_CATCHALL)) {
+		unsigned int max = nft_set_maxsize(set), nelems;
+
+		nelems = atomic_inc_return(&set->nelems);
+		if (nelems > max)
+			set_full = true;
+	}
+
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
 	if (trans == NULL) {
 		err = -ENOMEM;
-		goto err_elem_free;
+		goto err_set_size;
 	}
 
 	ext->genmask = nft_genmask_cur(ctx->net);
@@ -7516,7 +7525,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 
 						ue->priv = elem_priv;
 						nft_trans_commit_list_add_elem(ctx->net, trans);
-						goto err_elem_free;
+						goto err_set_size;
 					}
 				}
 			}
@@ -7534,23 +7543,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err_element_clash;
 	}
 
-	if (!(flags & NFT_SET_ELEM_CATCHALL)) {
-		unsigned int max = nft_set_maxsize(set);
-
-		if (!atomic_add_unless(&set->nelems, 1, max)) {
-			err = -ENFILE;
-			goto err_set_full;
-		}
-	}
-
 	nft_trans_container_elem(trans)->elems[0].priv = elem.priv;
 	nft_trans_commit_list_add_elem(ctx->net, trans);
-	return 0;
 
-err_set_full:
-	nft_setelem_remove(ctx->net, set, elem.priv);
+	return set_full ? -ENFILE : 0;
+
 err_element_clash:
 	kfree(trans);
+err_set_size:
+	if (!(flags & NFT_SET_ELEM_CATCHALL))
+		atomic_dec(&set->nelems);
 err_elem_free:
 	nf_tables_set_elem_destroy(ctx, set, elem.priv);
 err_parse_data:

From fb7fb4016300ac622c964069e286dc83166a5d52 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 2 Mar 2026 23:28:15 +0100
Subject: [PATCH 0875/1303] netfilter: nf_tables: clone set on flush only

Syzbot with fault injection triggered a failing memory allocation with
GFP_KERNEL which results in a WARN splat:

iter.err
WARNING: net/netfilter/nf_tables_api.c:845 at nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845, CPU#0: syz.0.17/5992
Modules linked in:
CPU: 0 UID: 0 PID: 5992 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
RIP: 0010:nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845
Code: 8b 05 86 5a 4e 09 48 3b 84 24 a0 00 00 00 75 62 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc e8 63 6d fa f7 90 <0f> 0b 90 43
+80 7c 35 00 00 0f 85 23 fe ff ff e9 26 fe ff ff 89 d9
RSP: 0018:ffffc900045af780 EFLAGS: 00010293
RAX: ffffffff89ca45bd RBX: 00000000fffffff4 RCX: ffff888028111e40
RDX: 0000000000000000 RSI: 00000000fffffff4 RDI: 0000000000000000
RBP: ffffc900045af870 R08: 0000000000400dc0 R09: 00000000ffffffff
R10: dffffc0000000000 R11: fffffbfff1d141db R12: ffffc900045af7e0
R13: 1ffff920008b5f24 R14: dffffc0000000000 R15: ffffc900045af920
FS:  000055557a6a5500(0000) GS:ffff888125496000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fb5ea271fc0 CR3: 000000003269e000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 __nft_release_table+0xceb/0x11f0 net/netfilter/nf_tables_api.c:12115
 nft_rcv_nl_event+0xc25/0xdb0 net/netfilter/nf_tables_api.c:12187
 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
 blocking_notifier_call_chain+0x6a/0x90 kernel/notifier.c:380
 netlink_release+0x123b/0x1ad0 net/netlink/af_netlink.c:761
 __sock_release net/socket.c:662 [inline]
 sock_close+0xc3/0x240 net/socket.c:1455

Restrict set clone to the flush set command in the preparation phase.
Add NFT_ITER_UPDATE_CLONE and use it for this purpose, update the rbtree
and pipapo backends to only clone the set when this iteration type is
used.

As for the existing NFT_ITER_UPDATE type, update the pipapo backend to
use the existing set clone if available, otherwise use the existing set
representation. After this update, there is no need to clone a set that
is being deleted, this includes bound anonymous set.

An alternative approach to NFT_ITER_UPDATE_CLONE is to add a .clone
interface and call it from the flush set path.

Reported-by: syzbot+4924a0edc148e8b4b342@syzkaller.appspotmail.com
Fixes: 3f1d886cc7c3 ("netfilter: nft_set_pipapo: move cloning of match info to insert/removal path")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 10 +++++++++-
 net/netfilter/nft_set_hash.c      |  1 +
 net/netfilter/nft_set_pipapo.c    | 11 +++++++++--
 net/netfilter/nft_set_rbtree.c    |  8 +++++---
 5 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 426534a711b0..ea6f29ad7888 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
  * @NFT_ITER_UNSPEC: unspecified, to catch errors
  * @NFT_ITER_READ: read-only iteration over set elements
  * @NFT_ITER_UPDATE: iteration under mutex to update set element state
+ * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element
  */
 enum nft_iter_type {
 	NFT_ITER_UNSPEC,
 	NFT_ITER_READ,
 	NFT_ITER_UPDATE,
+	NFT_ITER_UPDATE_CLONE,
 };
 
 struct nft_set;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index df67932d3e09..058f7004cb2b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 	}
 }
 
+/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation
+ * phase, the set clone might already exist from a previous command, or it might
+ * be a set that is going away and does not require a clone. The netns and
+ * netlink release paths also need to work on the live set.
+ */
 static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	struct nft_set_iter iter = {
@@ -7903,9 +7908,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx,
 
 static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask)
 {
+	/* The set backend might need to clone the set, do it now from the
+	 * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type.
+	 */
 	struct nft_set_iter iter = {
 		.genmask	= genmask,
-		.type		= NFT_ITER_UPDATE,
+		.type		= NFT_ITER_UPDATE_CLONE,
 		.fn		= nft_setelem_flush,
 	};
 
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 739b992bde59..b0e571c8e3f3 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 {
 	switch (iter->type) {
 	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		/* only relevant for netlink dumps which use READ type */
 		WARN_ON_ONCE(iter->skip != 0);
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 7ef4b44471d3..c091898df710 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2144,13 +2144,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 	const struct nft_pipapo_match *m;
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		m = pipapo_maybe_clone(set);
 		if (!m) {
 			iter->err = -ENOMEM;
 			return;
 		}
-
+		nft_pipapo_do_walk(ctx, set, m, iter);
+		break;
+	case NFT_ITER_UPDATE:
+		if (priv->clone)
+			m = priv->clone;
+		else
+			m = rcu_dereference_protected(priv->match,
+						      nft_pipapo_transaction_mutex_held(set));
 		nft_pipapo_do_walk(ctx, set, m, iter);
 		break;
 	case NFT_ITER_READ:
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 3f02e4478216..ee3d4f5b9ff7 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_rbtree *priv = nft_set_priv(set);
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
-		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
-
+	case NFT_ITER_UPDATE_CLONE:
 		if (nft_array_may_resize(set) < 0) {
 			iter->err = -ENOMEM;
 			break;
 		}
+		fallthrough;
+	case NFT_ITER_UPDATE:
+		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
+
 		nft_rbtree_do_walk(ctx, set, iter);
 		break;
 	case NFT_ITER_READ:

From 9df95785d3d8302f7c066050117b04cd3c2048c2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 3 Mar 2026 16:31:32 +0100
Subject: [PATCH 0876/1303] netfilter: nft_set_pipapo: split gc into unlink and
 reclaim phase

Yiming Qian reports Use-after-free in the pipapo set type:
  Under a large number of expired elements, commit-time GC can run for a very
  long time in a non-preemptible context, triggering soft lockup warnings and
  RCU stall reports (local denial of service).

We must split GC in an unlink and a reclaim phase.

We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.

call_rcu() does not protect us: dump operations or element lookups starting
after call_rcu has fired can still observe the free'd element, unless the
commit phase has made enough progress to swap the clone and live pointers
before any new reader has picked up the old version.

This a similar approach as done recently for the rbtree backend in commit
35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").

Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  5 +++
 net/netfilter/nf_tables_api.c     |  5 ---
 net/netfilter/nft_set_pipapo.c    | 51 ++++++++++++++++++++++++++-----
 net/netfilter/nft_set_pipapo.h    |  2 ++
 4 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ea6f29ad7888..e2d2bfc1f989 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1863,6 +1863,11 @@ struct nft_trans_gc {
 	struct rcu_head		rcu;
 };
 
+static inline int nft_trans_gc_space(const struct nft_trans_gc *trans)
+{
+	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
+}
+
 static inline void nft_ctx_update(struct nft_ctx *ctx,
 				  const struct nft_trans *trans)
 {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 058f7004cb2b..1862bd7fe804 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -10493,11 +10493,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans)
 	schedule_work(&trans_gc_work);
 }
 
-static int nft_trans_gc_space(struct nft_trans_gc *trans)
-{
-	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
-}
-
 struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc,
 					      unsigned int gc_seq, gfp_t gfp)
 {
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index c091898df710..a34632ae6048 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1680,11 +1680,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set,
 }
 
 /**
- * pipapo_gc() - Drop expired entries from set, destroy start and end elements
+ * pipapo_gc_scan() - Drop expired entries from set and link them to gc list
  * @set:	nftables API set representation
  * @m:		Matching data
  */
-static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
+static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct net *net = read_pnet(&set->net);
@@ -1697,6 +1697,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 	if (!gc)
 		return;
 
+	list_add(&gc->list, &priv->gc_head);
+
 	while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
 		union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
 		const struct nft_pipapo_field *f;
@@ -1724,9 +1726,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		 * NFT_SET_ELEM_DEAD_BIT.
 		 */
 		if (__nft_set_elem_expired(&e->ext, tstamp)) {
-			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
-			if (!gc)
-				return;
+			if (!nft_trans_gc_space(gc)) {
+				gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
+				if (!gc)
+					return;
+
+				list_add(&gc->list, &priv->gc_head);
+			}
 
 			nft_pipapo_gc_deactivate(net, set, e);
 			pipapo_drop(m, rulemap);
@@ -1740,10 +1746,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		}
 	}
 
-	gc = nft_trans_gc_catchall_sync(gc);
+	priv->last_gc = jiffies;
+}
+
+/**
+ * pipapo_gc_queue() - Free expired elements
+ * @set:	nftables API set representation
+ */
+static void pipapo_gc_queue(struct nft_set *set)
+{
+	struct nft_pipapo *priv = nft_set_priv(set);
+	struct nft_trans_gc *gc, *next;
+
+	/* always do a catchall cycle: */
+	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (gc) {
+		gc = nft_trans_gc_catchall_sync(gc);
+		if (gc)
+			nft_trans_gc_queue_sync_done(gc);
+	}
+
+	/* always purge queued gc elements. */
+	list_for_each_entry_safe(gc, next, &priv->gc_head, list) {
+		list_del(&gc->list);
 		nft_trans_gc_queue_sync_done(gc);
-		priv->last_gc = jiffies;
 	}
 }
 
@@ -1797,6 +1823,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu)
  *
  * We also need to create a new working copy for subsequent insertions and
  * deletions.
+ *
+ * After the live copy has been replaced by the clone, we can safely queue
+ * expired elements that have been collected by pipapo_gc_scan() for
+ * memory reclaim.
  */
 static void nft_pipapo_commit(struct nft_set *set)
 {
@@ -1807,7 +1837,7 @@ static void nft_pipapo_commit(struct nft_set *set)
 		return;
 
 	if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set)))
-		pipapo_gc(set, priv->clone);
+		pipapo_gc_scan(set, priv->clone);
 
 	old = rcu_replace_pointer(priv->match, priv->clone,
 				  nft_pipapo_transaction_mutex_held(set));
@@ -1815,6 +1845,8 @@ static void nft_pipapo_commit(struct nft_set *set)
 
 	if (old)
 		call_rcu(&old->rcu, pipapo_reclaim_match);
+
+	pipapo_gc_queue(set);
 }
 
 static void nft_pipapo_abort(const struct nft_set *set)
@@ -2279,6 +2311,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 		f->mt = NULL;
 	}
 
+	INIT_LIST_HEAD(&priv->gc_head);
 	rcu_assign_pointer(priv->match, m);
 
 	return 0;
@@ -2328,6 +2361,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_match *m;
 
+	WARN_ON_ONCE(!list_empty(&priv->gc_head));
+
 	m = rcu_dereference_protected(priv->match, true);
 
 	if (priv->clone) {
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index eaab422aa56a..9aee9a9eaeb7 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -156,12 +156,14 @@ struct nft_pipapo_match {
  * @clone:	Copy where pending insertions and deletions are kept
  * @width:	Total bytes to be matched for one packet, including padding
  * @last_gc:	Timestamp of last garbage collection run, jiffies
+ * @gc_head:	list of nft_trans_gc to queue up for mem reclaim
  */
 struct nft_pipapo {
 	struct nft_pipapo_match __rcu *match;
 	struct nft_pipapo_match *clone;
 	int width;
 	unsigned long last_gc;
+	struct list_head gc_head;
 };
 
 struct nft_pipapo_elem;

From 3d543d9515928e4754a741c338dbcdf68ac47e39 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 12:18:10 +0100
Subject: [PATCH 0877/1303] ALSA: us122l: drop redundant interface references

Driver core holds a reference to the USB interface and its parent USB
device while the interface is bound to a driver and there is no need to
take additional references unless the structures are needed after
disconnect.

Similarly, USB core holds a reference to all interfaces in the active
configuration so there is no need for a driver to take a reference to a
sibling interface only to release it at disconnect either.

Drop the redundant references to reduce cargo culting, make it easier to
spot drivers where extra references are needed, and reduce the risk of
memory leaks when drivers fail to release them.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260305111810.18688-1-johan@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/us122l.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index 011ea96e9779..f00b53346abd 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -520,8 +520,6 @@ static int us122l_usb_probe(struct usb_interface *intf,
 		return err;
 	}
 
-	usb_get_intf(usb_ifnum_to_if(device, 0));
-	usb_get_dev(device);
 	*cardp = card;
 	return 0;
 }
@@ -542,11 +540,9 @@ static int snd_us122l_probe(struct usb_interface *intf,
 	if (intf->cur_altsetting->desc.bInterfaceNumber != 1)
 		return 0;
 
-	err = us122l_usb_probe(usb_get_intf(intf), id, &card);
-	if (err < 0) {
-		usb_put_intf(intf);
+	err = us122l_usb_probe(intf, id, &card);
+	if (err < 0)
 		return err;
-	}
 
 	usb_set_intfdata(intf, card);
 	return 0;
@@ -574,10 +570,6 @@ static void snd_us122l_disconnect(struct usb_interface *intf)
 		snd_usbmidi_disconnect(p);
 	}
 
-	usb_put_intf(usb_ifnum_to_if(us122l->dev, 0));
-	usb_put_intf(usb_ifnum_to_if(us122l->dev, 1));
-	usb_put_dev(us122l->dev);
-
 	snd_card_free_when_closed(card);
 }
 

From ee8ade4d9678a456bb5ea675c270738b250eda68 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Thu, 5 Mar 2026 12:37:34 +0100
Subject: [PATCH 0878/1303] Revert "drm/syncobj: Fix handle <-> fd ioctls with
 dirty stack"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 2e3649e237237258a08d75afef96648dd2b379f7.

The problem occurs when userspace is compiled against new headers
with new members, but don't correctly initialise those new members.

This is not a kernel problem, and should be fixed in userspace by
correctly zero'ing all members.

Cc: Rob Clark <robdclark@chromium.org>
Cc: Julian Orth <ju.orth@gmail.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Michel Dänzer <michel.daenzer@mailbox.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Julian Orth <ju.orth@gmail.com>
Link: https://patch.msgid.link/20260305113734.1309238-1-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/drm_syncobj.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 49eccb43ce63..250734dee928 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -875,7 +875,7 @@ drm_syncobj_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 		return drm_syncobj_export_sync_file(file_private, args->handle,
 						    point, &args->fd);
 
-	if (point)
+	if (args->point)
 		return -EINVAL;
 
 	return drm_syncobj_handle_to_fd(file_private, args->handle,
@@ -909,7 +909,7 @@ drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 							  args->handle,
 							  point);
 
-	if (point)
+	if (args->point)
 		return -EINVAL;
 
 	return drm_syncobj_fd_to_handle(file_private, args->fd,

From 0abc73c8a40fd64ac1739c90bb4f42c418d27a5e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 3 Mar 2026 18:56:39 +0100
Subject: [PATCH 0879/1303] net: ethernet: mtk_eth_soc: Reset prog ptr to
 old_prog in case of error in mtk_xdp_setup()

Reset eBPF program pointer to old_prog and do not decrease its ref-count
if mtk_open routine in mtk_xdp_setup() fails.

Fixes: 7c26c20da5d42 ("net: ethernet: mtk_eth_soc: add basic XDP support")
Suggested-by: Paolo Valerio <pvalerio@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260303-mtk-xdp-prog-ptr-fix-v2-1-97b6dbbe240f@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index e5e2ffa9c542..ddc321a02fda 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -3748,12 +3748,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 		mtk_stop(dev);
 
 	old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held());
+
+	if (netif_running(dev) && need_update) {
+		int err;
+
+		err = mtk_open(dev);
+		if (err) {
+			rcu_assign_pointer(eth->prog, old_prog);
+
+			return err;
+		}
+	}
+
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (netif_running(dev) && need_update)
-		return mtk_open(dev);
-
 	return 0;
 }
 

From f26b098d937488e8f5c617d465760a10bfcc7f13 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Thu, 5 Mar 2026 10:31:17 +0100
Subject: [PATCH 0880/1303] ftrace: Add MAINTAINERS entries for all ftrace
 headers

There is currently no entry for ftrace_irq.h and ftrace_regs.h. Add a
generic entry for all *ftrace* headers to include them and prevent
overlooking future ftrace headers.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://patch.msgid.link/20260305093117.853700-1-jmarchan@redhat.com
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 61bf550fd37c..b8d1ad952827 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10484,7 +10484,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/ftrace*
 F:	arch/*/*/*/*ftrace*
 F:	arch/*/*/*ftrace*
-F:	include/*/ftrace.h
+F:	include/*/*ftrace*
 F:	kernel/trace/fgraph.c
 F:	kernel/trace/ftrace*
 F:	samples/ftrace

From ac6769c8f948dff33265c50e524aebf9aa6f1be0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 28 Feb 2026 16:45:59 +0000
Subject: [PATCH 0881/1303] KVM: arm64: Eagerly init vgic dist/redist on vgic
 creation

If vgic_allocate_private_irqs_locked() fails for any odd reason,
we exit kvm_vgic_create() early, leaving dist->rd_regions uninitialised.

kvm_vgic_dist_destroy() then comes along and walks into the weeds
trying to free the RDs. Got to love this stuff.

Solve it by moving all the static initialisation early, and make
sure that if we fail halfway, we're in a reasonable shape to
perform the rest of the teardown. While at it, reset the vgic model
on failure, just in case...

Reported-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com
Tested-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com
Fixes: b3aa9283c0c50 ("KVM: arm64: vgic: Hoist SGI/PPI alloc from vgic_init() to kvm_create_vgic()")
Link: https://lore.kernel.org/r/69a2d58c.050a0220.3a55be.003b.GAE@google.com
Link: https://patch.msgid.link/20260228164559.936268-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
---
 arch/arm64/kvm/vgic/vgic-init.c | 34 ++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 9b3091ad868c..e9b8b5fc480c 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -143,23 +143,6 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	kvm->arch.vgic.in_kernel = true;
 	kvm->arch.vgic.vgic_model = type;
 	kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		ret = vgic_allocate_private_irqs_locked(vcpu, type);
-		if (ret)
-			break;
-	}
-
-	if (ret) {
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-			kfree(vgic_cpu->private_irqs);
-			vgic_cpu->private_irqs = NULL;
-		}
-
-		goto out_unlock;
-	}
-
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 
 	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
@@ -176,6 +159,23 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
 	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
 
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = vgic_allocate_private_irqs_locked(vcpu, type);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+			kfree(vgic_cpu->private_irqs);
+			vgic_cpu->private_irqs = NULL;
+		}
+
+		kvm->arch.vgic.vgic_model = 0;
+		goto out_unlock;
+	}
+
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
 		kvm->arch.vgic.nassgicap = system_supports_direct_sgis();
 

From 8531d5a83d8eb8affb5c0249b466c28d94192603 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 5 Mar 2026 13:27:51 +0000
Subject: [PATCH 0882/1303] KVM: arm64: pkvm: Fallback to level-3 mapping on
 host stage-2 fault

If, for any odd reason, we cannot converge to mapping size that is
completely contained in a memblock region, we fail to install a S2
mapping and go back to the faulting instruction. Rince, repeat.

This happens when faulting in regions that are smaller than a page
or that do not have PAGE_SIZE-aligned boundaries (as witnessed on
an O6 board that refuses to boot in protected mode).

In this situation, fallback to using a PAGE_SIZE mapping anyway --
it isn't like we can go any lower.

Fixes: e728e705802fe ("KVM: arm64: Adjust range correctly during host stage-2 faults")
Link: https://lore.kernel.org/r/86wlzr77cn.wl-maz@kernel.org
Cc: stable@vger.kernel.org
Cc: Quentin Perret <qperret@google.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://patch.msgid.link/20260305132751.2928138-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 38f66a56a766..d815265bd374 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -518,7 +518,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		granule = kvm_granule_size(level);
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
-		if (!range_included(&cur, range))
+		if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL)
 			continue;
 		*range = cur;
 		return 0;

From 6be2681514261324c8ee8a1c6f76cefdf700220f Mon Sep 17 00:00:00 2001
From: Sun Jian <sun.jian.kdev@gmail.com>
Date: Wed, 25 Feb 2026 19:14:50 +0800
Subject: [PATCH 0883/1303] selftests/harness: order TEST_F and XFAIL_ADD
 constructors

TEST_F() allocates and registers its struct __test_metadata via mmap()
inside its constructor, and only then assigns the
_##fixture_##test##_object pointer.

XFAIL_ADD() runs in a constructor too and reads
_##fixture_##test##_object to initialize xfail->test. If XFAIL_ADD runs
first, xfail->test can be NULL and the expected failure will be reported
as FAIL.

Use constructor priorities to ensure TEST_F registration runs before
XFAIL_ADD, without adding extra state or runtime lookups.

Fixes: 2709473c9386 ("selftests: kselftest_harness: support using xfail")
Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Link: https://patch.msgid.link/20260225111451.347923-1-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/kselftest_harness.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 16a119a4656c..4afaef01c22e 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)
 		memset(s, c, n);
 }
 
+#define KSELFTEST_PRIO_TEST_F  20000
+#define KSELFTEST_PRIO_XFAIL   20001
+
 #define TEST_TIMEOUT_DEFAULT 30
 
 /* Utilities exposed to the test definitions */
@@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)
 			fixture_name##_teardown(_metadata, self, variant); \
 	} \
 	static struct __test_metadata *_##fixture_name##_##test_name##_object; \
-	static void __attribute__((constructor)) \
+	static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \
 			_register_##fixture_name##_##test_name(void) \
 	{ \
 		struct __test_metadata *object = mmap(NULL, sizeof(*object), \
@@ -880,7 +883,7 @@ struct __test_xfail {
 		.fixture = &_##fixture_name##_fixture_object, \
 		.variant = &_##fixture_name##_##variant_name##_object, \
 	}; \
-	static void __attribute__((constructor)) \
+	static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \
 		_register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \
 	{ \
 		_##fixture_name##_##variant_name##_##test_name##_xfail.test = \

From c952291593e54415a7bb74c4a7187a7c7c7e8651 Mon Sep 17 00:00:00 2001
From: Sun Jian <sun.jian.kdev@gmail.com>
Date: Wed, 25 Feb 2026 19:14:51 +0800
Subject: [PATCH 0884/1303] selftests: net: tun: don't abort XFAIL cases

The tun UDP tunnel GSO fixture contains XFAIL-marked variants intended to
exercise failure paths (e.g. EMSGSIZE / "Message too long").
Using ASSERT_EQ() in these tests aborts the subtest, which prevents the
harness from classifying them as XFAIL and can make the overall net: tun
test fail.

Switch the relevant ASSERT_EQ() checks to EXPECT_EQ() so the subtests
continue running and the failures are correctly reported and accounted
as XFAIL where applicable.

Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Link: https://patch.msgid.link/20260225111451.347923-2-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tun.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
index 8a5cd5cb5472..cf106a49b55e 100644
--- a/tools/testing/selftests/net/tun.c
+++ b/tools/testing/selftests/net/tun.c
@@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet)
 	ASSERT_EQ(ret, off);
 
 	ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss);
-	ASSERT_EQ(ret, variant->data_size);
-	ASSERT_EQ(r_num_mss, variant->r_num_mss);
+	EXPECT_EQ(ret, variant->data_size);
+	EXPECT_EQ(r_num_mss, variant->r_num_mss);
 }
 
 TEST_F(tun_vnet_udptnl, recv_gso_packet)
@@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet)
 	int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4;
 
 	ret = send_gso_packet_into_tunnel(self, variant);
-	ASSERT_EQ(ret, variant->data_size);
+	EXPECT_EQ(ret, variant->data_size);
 
 	memset(&vnet_hdr, 0, sizeof(vnet_hdr));
 	ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr);
-	ASSERT_EQ(ret, variant->data_size);
+	EXPECT_EQ(ret, variant->data_size);
 
 	if (!variant->no_gso) {
-		ASSERT_EQ(vh->gso_size, variant->gso_size);
+		EXPECT_EQ(vh->gso_size, variant->gso_size);
 		gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ?
 				    (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) :
 				    (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6);
-		ASSERT_EQ(vh->gso_type, gso_type);
+		EXPECT_EQ(vh->gso_type, gso_type);
 	}
 }
 

From f9b5bf12eb65e1e708a883a1e24712e81ed2f340 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:01 -0800
Subject: [PATCH 0885/1303] MAINTAINERS: remove Johan Hedberg from Bluetooth
 subsystem

We have not seen emails or tags from Johan in over 5 years,
and there is no recent mailing list activity.
Marcel Holtmann hasn't provided any tags in the Bluetooth
subsystem in over 5 years, but he is active on the Bluetooth
mailing list, providing informal review.
Luiz Augusto von Dentz is very active, handling essentially
all commits and reviews (12% coverage, but Luiz is the sole
active committer).

Subsystem BLUETOOTH SUBSYSTEM
  Changes 50 / 411 (12%)
  Last activity: 2026-02-23
  Marcel Holtmann <marcel@holtmann.org>:
  Johan Hedberg <johan.hedberg@gmail.com>:
  Luiz Augusto von Dentz <luiz.dentz@gmail.com>:
    Author 138d7eca445e 2026-02-23 00:00:00 164
    Committer 138d7eca445e 2026-02-23 00:00:00 361
    Tags 138d7eca445e 2026-02-23 00:00:00 362
  Top reviewers:
    [15]: pmenzel@molgen.mpg.de
    [8]: keescook@chromium.org
    [5]: willemb@google.com
    [4]: horms@kernel.org
    [3]: kuniyu@amazon.com
    [3]: luiz.von.dentz@intel.com
  INACTIVE MAINTAINER Johan Hedberg <johan.hedberg@gmail.com>

Acked-by: Marcel Holtmann <marcel@holtmann.org>
Link: https://patch.msgid.link/20260303215339.2333548-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index bee85351120e..4eb755b0a0d1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4615,7 +4615,6 @@ F:	drivers/bluetooth/
 
 BLUETOOTH SUBSYSTEM
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Johan Hedberg <johan.hedberg@gmail.com>
 M:	Luiz Augusto von Dentz <luiz.dentz@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 S:	Supported

From 80f8a19fe7cf5b1b5d541c7aaa37aa9d7653bda5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:02 -0800
Subject: [PATCH 0886/1303] MAINTAINERS: remove Manish Chopra from QLogic
 QL4xxx (now orphan)

We have not seen tags from Manish for the QL4xxx driver in over 5 years,
and there is no mailing list activity since Oct 2023. There has been
no maintainer activity in this subsystem at all.

Since there is no other maintainer for this driver it becomes an Orphan.

Subsystem QLOGIC QL4xxx ETHERNET DRIVER
  Changes 40 / 74 (54%)
  (No activity)
  Top reviewers:
    [30]: horms@kernel.org
    [2]: jiri@nvidia.com
    [2]: shannon.nelson@amd.com
    [1]: saeedm@nvidia.com
    [1]: aleksandr.loktionov@intel.com
    [1]: kory.maincent@bootlin.com
  INACTIVE MAINTAINER Manish Chopra <manishc@marvell.com>

Link: https://patch.msgid.link/20260303215339.2333548-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4eb755b0a0d1..a83af9a89141 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21451,9 +21451,8 @@ S:	Supported
 F:	drivers/scsi/qedi/
 
 QLOGIC QL4xxx ETHERNET DRIVER
-M:	Manish Chopra <manishc@marvell.com>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/net/ethernet/qlogic/qed/
 F:	drivers/net/ethernet/qlogic/qede/
 F:	include/linux/qed/

From e07f796a86b2f0fda976268a08c321579022fcbc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:03 -0800
Subject: [PATCH 0887/1303] MAINTAINERS: remove Jerin Jacob from Marvell
 OcteonTX2

We have not seen tags from Jerin for OcteonTX2 in over 5 years.
Recent lore activity is in DPDK (non-kernel), not Linux.
Sunil, Linu, Geetha, hariprasad, and Subbaraya are active,
though the review coverage isn't great (38%).

Subsystem MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
  Changes 53 / 138 (38%)
  Last activity: 2026-02-18
  Sunil Goutham <sgoutham@marvell.com>:
    Author fc1b2901e0fe 2024-03-08 00:00:00 1
    Tags 70f8986ecef1 2025-06-16 00:00:00 9
  Linu Cherian <lcherian@marvell.com>:
    Author a861e5809f3e 2025-10-30 00:00:00 7
    Tags a861e5809f3e 2025-10-30 00:00:00 7
  Geetha sowjanya <gakula@marvell.com>:
    Author 70e9a5760abf 2026-01-29 00:00:00 16
    Tags 70e9a5760abf 2026-01-29 00:00:00 20
  Jerin Jacob <jerinj@marvell.com>:
  hariprasad <hkelam@marvell.com>:
    Author 45be47bf5d7d 2026-02-18 00:00:00 22
    Tags 45be47bf5d7d 2026-02-18 00:00:00 25
  Subbaraya Sundeep <sbhatta@marvell.com>:
    Author 47a1208776d7 2025-10-30 00:00:00 20
    Tags 47a1208776d7 2025-10-30 00:00:00 30
  Top reviewers:
    [36]: horms@kernel.org
    [4]: jacob.e.keller@intel.com
    [4]: kalesh-anakkur.purayil@broadcom.com
    [3]: vadim.fedorenko@linux.dev
    [2]: shaojijie@huawei.com
    [2]: jiri@nvidia.com
  INACTIVE MAINTAINER Jerin Jacob <jerinj@marvell.com>

Link: https://patch.msgid.link/20260303215339.2333548-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a83af9a89141..de0f5a38b525 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15469,7 +15469,6 @@ MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
 M:	Linu Cherian <lcherian@marvell.com>
 M:	Geetha sowjanya <gakula@marvell.com>
-M:	Jerin Jacob <jerinj@marvell.com>
 M:	hariprasad <hkelam@marvell.com>
 M:	Subbaraya Sundeep <sbhatta@marvell.com>
 L:	netdev@vger.kernel.org

From 77f72ef58fb849cbe39fd69a20f9ae5076cd442b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:05 -0800
Subject: [PATCH 0888/1303] MAINTAINERS: remove Sean Wang from MediaTek
 Ethernet and switch

We have not seen tags from Sean in over 5 years,
with only one mailing list post since 2024.
Felix and Lorenzo are active for the Ethernet driver,
and Chester, Daniel and DENG Qingfang are active for
the switch driver.

Subsystem MEDIATEK ETHERNET DRIVER
  Changes 55 / 113 (48%)
  Last activity: 2025-10-12
  Felix Fietkau <nbd@nbd.name>:
    Author d4736737110f 2025-09-02 00:00:00 3
    Tags d4736737110f 2025-09-02 00:00:00 4
  Sean Wang <sean.wang@mediatek.com>:
  Lorenzo Bianconi <lorenzo@kernel.org>:
    Author 96326447d466 2025-08-13 00:00:00 35
    Tags 3abc0e55ea1f 2025-10-12 00:00:00 40
  Top reviewers:
    [26]: horms@kernel.org
    [5]: andrew@lunn.ch
    [4]: jacob.e.keller@intel.com
    [3]: shannon.nelson@amd.com
    [3]: michal.swiatkowski@linux.intel.com
  INACTIVE MAINTAINER Sean Wang <sean.wang@mediatek.com>

Subsystem MEDIATEK SWITCH DRIVER
  Changes 26 / 70 (37%)
  Last activity: 2025-12-01
  Chester A. Unal <chester.a.unal@arinc9.com>:
    Tags 585943b7ad30 2025-12-01 00:00:00 7
  Daniel Golle <daniel@makrotopia.org>:
    Author 497041d76301 2025-04-23 00:00:00 2
    Tags 3b87e60d2131 2025-12-01 00:00:00 14
  DENG Qingfang <dqfext@gmail.com>:
  Sean Wang <sean.wang@mediatek.com>:
  Top reviewers:
    [4]: andrew@lunn.ch
    [4]: florian.fainelli@broadcom.com
    [4]: arinc.unal@arinc9.com
    [2]: olteanv@gmail.com
  INACTIVE MAINTAINER Sean Wang <sean.wang@mediatek.com>

Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20260303215339.2333548-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index de0f5a38b525..706fb325bc67 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16157,7 +16157,6 @@ F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@nbd.name>
-M:	Sean Wang <sean.wang@mediatek.com>
 M:	Lorenzo Bianconi <lorenzo@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -16351,7 +16350,6 @@ MEDIATEK SWITCH DRIVER
 M:	Chester A. Unal <chester.a.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
 M:	DENG Qingfang <dqfext@gmail.com>
-M:	Sean Wang <sean.wang@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530-mdio.c

From 593cdf14523bfb837b947012cdc6545a53ea67b5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:06 -0800
Subject: [PATCH 0889/1303] MAINTAINERS: remove DENG Qingfang from MediaTek
 switch

We have not seen tags from DENG Qingfang for the MediaTek
switch driver in over 5 years. He is active upstream with
PPP/PPPoE patches in net-next. Chester and Daniel are active.

Subsystem MEDIATEK SWITCH DRIVER
  Changes 26 / 70 (37%)
  Last activity: 2025-12-01
  Chester A. Unal <chester.a.unal@arinc9.com>:
    Tags 585943b7ad30 2025-12-01 00:00:00 7
  Daniel Golle <daniel@makrotopia.org>:
    Author 497041d76301 2025-04-23 00:00:00 2
    Tags 3b87e60d2131 2025-12-01 00:00:00 14
  DENG Qingfang <dqfext@gmail.com>:
  Sean Wang <sean.wang@mediatek.com>:
  Top reviewers:
    [4]: andrew@lunn.ch
    [4]: florian.fainelli@broadcom.com
    [4]: arinc.unal@arinc9.com
    [2]: olteanv@gmail.com
  INACTIVE MAINTAINER DENG Qingfang <dqfext@gmail.com>

Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20260303215339.2333548-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 706fb325bc67..49bf6c8da74c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16349,7 +16349,6 @@ F:	include/soc/mediatek/smi.h
 MEDIATEK SWITCH DRIVER
 M:	Chester A. Unal <chester.a.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
-M:	DENG Qingfang <dqfext@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530-mdio.c

From 34f49454b25cd2e532f137174ef59b778f1a09f5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:07 -0800
Subject: [PATCH 0890/1303] MAINTAINERS: replace Clark Wang with Frank Li for
 Freescale FEC

We have not seen tags from Clark for FEC in over 5 years.
He has some limited recent activity on the mailing list in other
NXP subsystems (stmmac, phy). Wei Fang and Shenwei Wang are active,
with decent review coverage (61%).

Frank Li has been reviewing code actively more recenty, let's
make it official.

Subsystem FREESCALE IMX / MXC FEC DRIVER
  Changes 57 / 92 (61%)
  Last activity: 2026-02-10
  Wei Fang <wei.fang@nxp.com>:
    Author 25eb3058eb70 2026-02-10 00:00:00 33
    Tags 25eb3058eb70 2026-02-10 00:00:00 61
  Shenwei Wang <shenwei.wang@nxp.com>:
    Author d466c16026e9 2025-09-14 00:00:00 6
    Tags d466c16026e9 2025-09-14 00:00:00 6
  Clark Wang <xiaoning.wang@nxp.com>:
  Top reviewers:
    [23]: Frank.Li@nxp.com
    [17]: andrew@lunn.ch
    [4]: csokas.bence@prolan.hu
    [3]: horms@kernel.org
    [2]: maxime.chevallier@bootlin.com
  INACTIVE MAINTAINER Clark Wang <xiaoning.wang@nxp.com>

Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260303215339.2333548-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 49bf6c8da74c..b21c87332d14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10167,8 +10167,8 @@ F:	drivers/i2c/busses/i2c-cpm.c
 
 FREESCALE IMX / MXC FEC DRIVER
 M:	Wei Fang <wei.fang@nxp.com>
+R:	Frank Li <frank.li@nxp.com>
 R:	Shenwei Wang <shenwei.wang@nxp.com>
-R:	Clark Wang <xiaoning.wang@nxp.com>
 L:	imx@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained

From 60da2d2752ac4513fc3a91a0558dfd8176d2313f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:08 -0800
Subject: [PATCH 0891/1303] MAINTAINERS: remove Jonathan Lemon from OpenCompute
 PTP

We have not seen emails or tags from Jonathan in over 5 years,
and there is no recent mailing list activity.
Vadim Fedorenko is active.

Subsystem OPENCOMPUTE PTP CLOCK DRIVER
  Changes 49 / 130 (37%)
  Last activity: 2025-11-25
  Jonathan Lemon <jonathan.lemon@gmail.com>:
  Vadim Fedorenko <vadim.fedorenko@linux.dev>:
    Author d3ca2ef0c915 2025-09-19 00:00:00 5
    Tags 648282e2d1e5 2025-11-25 00:00:00 20
  Top reviewers:
    [7]: horms@kernel.org
    [4]: jiri@nvidia.com
    [3]: richardcochran@gmail.com
    [2]: aleksandr.loktionov@intel.com
  INACTIVE MAINTAINER Jonathan Lemon <jonathan.lemon@gmail.com>

Add Jonathan to CREDITS as the initial author of ptp_ocp.

Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20260303215339.2333548-9-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index d74c8b2b7ed3..fb9b4dc193a0 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2415,6 +2415,10 @@ S: Am Muehlenweg 38
 S: D53424 Remagen
 S: Germany
 
+N: Jonathan Lemon
+E: jonathan.lemon@gmail.com
+D: OpenCompute PTP clock driver (ptp_ocp)
+
 N: Colin Leroy
 E: colin@colino.net
 W: http://www.geekounet.org/
diff --git a/MAINTAINERS b/MAINTAINERS
index b21c87332d14..d63fe814b750 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19803,7 +19803,6 @@ F:	arch/*/boot/dts/
 F:	include/dt-bindings/
 
 OPENCOMPUTE PTP CLOCK DRIVER
-M:	Jonathan Lemon <jonathan.lemon@gmail.com>
 M:	Vadim Fedorenko <vadim.fedorenko@linux.dev>
 L:	netdev@vger.kernel.org
 S:	Maintained

From 9ede3e910f088fb3ffec0ed821f0b03951000d23 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:09 -0800
Subject: [PATCH 0892/1303] MAINTAINERS: replace Taras Chornyi with Elad
 Nachman for Marvell Prestera

We have not seen emails or tags from Taras in over 5 years,
and there is no recent mailing list activity.
Elad Nachman has been providing reviews in the last couple
of years and is the top reviewer for this subsystem.

Subsystem MARVELL PRESTERA ETHERNET SWITCH DRIVER
  Changes 39 / 157 (24%)
  (No activity)
  Top reviewers:
    [8]: enachman@marvell.com
    [6]: horms@kernel.org
    [4]: idosch@nvidia.com
    [3]: andrew@lunn.ch
    [3]: jacob.e.keller@intel.com
    [3]: jiri@nvidia.com
  INACTIVE MAINTAINER Taras Chornyi <taras.chornyi@plvision.eu>

Link: https://patch.msgid.link/20260303215339.2333548-10-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d63fe814b750..497822aac6aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15483,7 +15483,7 @@ S:	Supported
 F:	drivers/perf/marvell_pem_pmu.c
 
 MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M:	Taras Chornyi <taras.chornyi@plvision.eu>
+M:	Elad Nachman <enachman@marvell.com>
 S:	Supported
 W:	https://github.com/Marvell-switching/switchdev-prestera
 F:	drivers/net/ethernet/marvell/prestera/

From 4d37e68c46d15beb4af782b19d7f1b382316776c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:10 -0800
Subject: [PATCH 0893/1303] MAINTAINERS: remove Claudiu Manoil and Alexandre
 Belloni from Ocelot switch

We have not seen tags from Claudiu for the Ocelot switch driver
in over 5 years. He is active upstream in other NXP subsystems
(ENETC, gianfar), with 46 emails on lore since 2024.
We have not seen tags from Alexandre for the Ocelot switch driver
in over 5 years. He is very active upstream in other subsystems
(RTC, I3C, Atmel/Microchip SoC), with over 1,200 emails on lore
since 2024.
Vladimir Oltean is active.

Subsystem OCELOT ETHERNET SWITCH DRIVER
  Changes 180 / 494 (36%)
  Last activity: 2026-02-12
  Vladimir Oltean <vladimir.oltean@nxp.com>:
    Author c22ba07c827f 2026-02-10 00:00:00 33
    Tags 026f6513c588 2026-02-12 00:00:00 39
  Claudiu Manoil <claudiu.manoil@nxp.com>:
  Alexandre Belloni <alexandre.belloni@bootlin.com>:
  Top reviewers:
    [49]: f.fainelli@gmail.com
    [19]: horms@kernel.org
    [10]: richardcochran@gmail.com
    [9]: jacob.e.keller@intel.com
    [8]: colin.foster@in-advantage.com
  INACTIVE MAINTAINER Claudiu Manoil <claudiu.manoil@nxp.com>

Acked-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://patch.msgid.link/20260303215339.2333548-11-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 497822aac6aa..d050d756beec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19216,8 +19216,6 @@ F:	tools/objtool/
 
 OCELOT ETHERNET SWITCH DRIVER
 M:	Vladimir Oltean <vladimir.oltean@nxp.com>
-M:	Claudiu Manoil <claudiu.manoil@nxp.com>
-M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
 M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Supported

From ed6579002548f3d9c00380e2aeaa8305d3ed8fc5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:11 -0800
Subject: [PATCH 0894/1303] MAINTAINERS: remove Thomas Falcon from IBM ibmvnic

We have not seen emails or tags from Thomas's IBM address
(tlfalcon@linux.ibm.com) in over 5 years. Looks like Thomas
is active in perf tooling at Intel (thomas.falcon@intel.com).

Subsystem IBM Power SRIOV Virtual NIC Device Driver
  Changes 49 / 134 (36%)
  Last activity: 2025-08-26
  Haren Myneni <haren@linux.ibm.com>:
    Tags 3c14917953a5 2025-08-26 00:00:00 2
  Rick Lindsley <ricklind@linux.ibm.com>:
  Nick Child <nnac123@linux.ibm.com>:
    Author d93a6caab5d7 2025-03-25 00:00:00 14
    Tags d93a6caab5d7 2025-03-25 00:00:00 16
  Thomas Falcon <tlfalcon@linux.ibm.com>:
  Top reviewers:
    [22]: drt@linux.ibm.com
    [13]: horms@kernel.org
    [9]: ricklind@linux.vnet.ibm.com
    [3]: davemarq@linux.ibm.com
  INACTIVE MAINTAINER Thomas Falcon <tlfalcon@linux.ibm.com>

Move Thomas to CREDITS as the initial author of ibmvnic.

Acked-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://patch.msgid.link/20260303215339.2333548-12-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index fb9b4dc193a0..9091bac3d2da 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1242,6 +1242,10 @@ N: Veaceslav Falico
 E: vfalico@gmail.com
 D: Co-maintainer and co-author of the network bonding driver.
 
+N: Thomas Falcon
+E: tlfalcon@linux.ibm.com
+D: Initial author of the IBM ibmvnic network driver
+
 N: János Farkas
 E: chexum@shadow.banki.hu
 D: romfs, various (mostly networking) fixes
diff --git a/MAINTAINERS b/MAINTAINERS
index d050d756beec..3fcb17815e00 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12212,7 +12212,6 @@ IBM Power SRIOV Virtual NIC Device Driver
 M:	Haren Myneni <haren@linux.ibm.com>
 M:	Rick Lindsley <ricklind@linux.ibm.com>
 R:	Nick Child <nnac123@linux.ibm.com>
-R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/ibm/ibmvnic.*

From 4c2264ecdf39ddbdb62e37b156015aacf05d0dcb Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:13 +0800
Subject: [PATCH 0895/1303] KVM: arm64: nv: Check S2 limits based on
 implemented PA size

check_base_s2_limits() checks the validity of SL0 and inputsize against
ia_size (inputsize again!) but the pseudocode from DDI0487 G.a
AArch64.TranslationTableWalk() says that we should check against the
implemented PA size.

We would otherwise fail to walk S2 with a valid configuration. E.g.,
granule size = 4KB, inputsize = 40 bits, initial lookup level = 0 (no
concatenation) on a system with 48 bits PA range supported is allowed by
architecture.

Fix it by obtaining PA size by kvm_get_pa_bits(). Note that
kvm_get_pa_bits() returns the fixed limit now and should eventually reflect
the per VM PARange (one day!). Given that the configured PARange should not
be greater that kvm_ipa_limit, it at least fixes the problem described
above.

While at it, inject a level 0 translation fault to guest if
check_base_s2_limits() fails, as per the pseudocode.

Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic")
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-2-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 12c9f6e8dfda..9da28814b646 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -152,31 +152,31 @@ static int get_ia_size(struct s2_walk_info *wi)
 	return 64 - wi->t0sz;
 }
 
-static int check_base_s2_limits(struct s2_walk_info *wi,
+static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi,
 				int level, int input_size, int stride)
 {
-	int start_size, ia_size;
+	int start_size, pa_max;
 
-	ia_size = get_ia_size(wi);
+	pa_max = kvm_get_pa_bits(vcpu->kvm);
 
 	/* Check translation limits */
 	switch (BIT(wi->pgshift)) {
 	case SZ_64K:
-		if (level == 0 || (level == 1 && ia_size <= 42))
+		if (level == 0 || (level == 1 && pa_max <= 42))
 			return -EFAULT;
 		break;
 	case SZ_16K:
-		if (level == 0 || (level == 1 && ia_size <= 40))
+		if (level == 0 || (level == 1 && pa_max <= 40))
 			return -EFAULT;
 		break;
 	case SZ_4K:
-		if (level < 0 || (level == 0 && ia_size <= 42))
+		if (level < 0 || (level == 0 && pa_max <= 42))
 			return -EFAULT;
 		break;
 	}
 
 	/* Check input size limits */
-	if (input_size > ia_size)
+	if (input_size > pa_max)
 		return -EFAULT;
 
 	/* Check number of entries in starting level table */
@@ -269,9 +269,11 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 	if (input_size > 48 || input_size < 25)
 		return -EFAULT;
 
-	ret = check_base_s2_limits(wi, level, input_size, stride);
-	if (WARN_ON(ret))
+	ret = check_base_s2_limits(vcpu, wi, level, input_size, stride);
+	if (WARN_ON(ret)) {
+		out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT);
 		return ret;
+	}
 
 	base_lower_bound = 3 + input_size - ((3 - level) * stride +
 			   wi->pgshift);

From 99a339377f3c1bdf6edd5614d36893ab1806f9e6 Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:14 +0800
Subject: [PATCH 0896/1303] KVM: arm64: nv: Report addrsz fault at level 0 with
 a bad VTTBR.BADDR

As per R_BFHQH,

" When an Address size fault is generated, the reported fault code
  indicates one of the following:

  If the fault was generated due to the TTBR_ELx used in the translation
  having nonzero address bits above the OA size, then a fault at level 0. "

Fix the reported Address size fault level as being 0 if the base address is
wrongly programmed by L1.

Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic")
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-3-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9da28814b646..91e4f3cb580a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -280,7 +280,8 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 	base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
 
 	if (check_output_size(wi, base_addr)) {
-		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		/* R_BFHQH */
+		out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ);
 		return 1;
 	}
 

From eb54fa1025f8b520f0e83a807d76e35e4587c5ff Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:15 +0800
Subject: [PATCH 0897/1303] KVM: arm64: nv: Inject a SEA if failed to read the
 descriptor

Failure to read the descriptor (because it is outside of a memslot) should
result in a SEA being injected in the guest.

Suggested-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/86ms1m9lp3.wl-maz@kernel.org
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-4-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 91e4f3cb580a..2c43097248b2 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -296,8 +296,10 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 
 		paddr = base_addr | index;
 		ret = read_guest_s2_desc(vcpu, paddr, &desc, wi);
-		if (ret < 0)
+		if (ret < 0) {
+			out->esr = ESR_ELx_FSC_SEA_TTW(level);
 			return ret;
+		}
 
 		new_desc = desc;
 

From b92b0075ee1870f78f59ab1f7da7dbfdd718ad7a Mon Sep 17 00:00:00 2001
From: Pedro Falcato <pfalcato@suse.de>
Date: Thu, 5 Mar 2026 14:53:12 +0000
Subject: [PATCH 0898/1303] ata: libata-core: Add BRIDGE_OK quirk for QEMU
 drives

Currently, whenever you boot with a QEMU drive over an AHCI interface,
you get:
[    1.632121] ata1.00: applying bridge limits

This happens due to the kernel not believing the given drive is SATA,
since word 93 of IDENTIFY (ATA_ID_HW_CONFIG) is non-zero. The result is
a pretty severe limit in max_hw_sectors_kb, which limits our IO sizes.

QEMU has set word 93 erroneously for SATA drives but does not, in any
way, emulate any of these real hardware details. There is no PATA
drive and no SATA cable.

As such, add a BRIDGE_OK quirk for QEMU HARDDISK. Special care is taken
to limit this quirk to "2.5+", to allow for fixed future versions.

This results in the max_hw_sectors being limited solely by the
controller interface's limits. Which, for AHCI controllers, takes it
from 128KB to 32767KB.

Cc: stable@vger.kernel.org
Signed-off-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 76b012f544ea..6c4e567b6582 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4232,6 +4232,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	/* Devices that do not need bridging limits applied */
 	{ "MTRON MSP-SATA*",		NULL,	ATA_QUIRK_BRIDGE_OK },
 	{ "BUFFALO HD-QSU2/R5",		NULL,	ATA_QUIRK_BRIDGE_OK },
+	{ "QEMU HARDDISK",		"2.5+",	ATA_QUIRK_BRIDGE_OK },
 
 	/* Devices which aren't very happy with higher link speeds */
 	{ "WD My Book",			NULL,	ATA_QUIRK_1_5_GBPS },

From e5e890630533bdc15b26a34bb8e7ef539bdf1322 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Wed, 4 Mar 2026 13:03:56 +0100
Subject: [PATCH 0899/1303] net: bridge: fix nd_tbl NULL dereference when IPv6
 is disabled

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. Then, if neigh_suppress is enabled and an ICMPv6
Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will
dereference ipv6_stub->nd_tbl which is NULL, passing it to
neigh_lookup(). This causes a kernel NULL pointer dereference.

 BUG: kernel NULL pointer dereference, address: 0000000000000268
 Oops: 0000 [#1] PREEMPT SMP NOPTI
 [...]
 RIP: 0010:neigh_lookup+0x16/0xe0
 [...]
 Call Trace:
  <IRQ>
  ? neigh_lookup+0x16/0xe0
  br_do_suppress_nd+0x160/0x290 [bridge]
  br_handle_frame_finish+0x500/0x620 [bridge]
  br_handle_frame+0x353/0x440 [bridge]
  __netif_receive_skb_core.constprop.0+0x298/0x1110
  __netif_receive_skb_one_core+0x3d/0xa0
  process_backlog+0xa0/0x140
  __napi_poll+0x2c/0x170
  net_rx_action+0x2c4/0x3a0
  handle_softirqs+0xd0/0x270
  do_softirq+0x3f/0x60

Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in
the callers. This is in essence disabling NS/NA suppression when IPv6 is
disabled.

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Reported-by: Guruprasad C P <gurucp2005@gmail.com>
Closes: https://lore.kernel.org/netdev/CAHXs0ORzd62QOG-Fttqa2Cx_A_VFp=utE2H2VTX5nqfgs7LDxQ@mail.gmail.com/
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260304120357.9778-1-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_device.c | 2 +-
 net/bridge/br_input.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ee01122f466f..f7502e62dd35 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	     eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) &&
 	    br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
 		br_do_proxy_suppress_arp(skb, br, vid, NULL);
-	} else if (IS_ENABLED(CONFIG_IPV6) &&
+	} else if (ipv6_mod_enabled() &&
 		   skb->protocol == htons(ETH_P_IPV6) &&
 		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 1405f1061a54..2cbae0f9ae1f 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	    (skb->protocol == htons(ETH_P_ARP) ||
 	     skb->protocol == htons(ETH_P_RARP))) {
 		br_do_proxy_suppress_arp(skb, br, vid, p);
-	} else if (IS_ENABLED(CONFIG_IPV6) &&
+	} else if (ipv6_mod_enabled() &&
 		   skb->protocol == htons(ETH_P_IPV6) &&
 		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +

From 168ff39e4758897d2eee4756977d036d52884c7e Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Wed, 4 Mar 2026 13:03:57 +0100
Subject: [PATCH 0900/1303] net: vxlan: fix nd_tbl NULL dereference when IPv6
 is disabled

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. If an IPv6 packet is injected into the interface,
route_shortcircuit() is called and a NULL pointer dereference happens on
neigh_lookup().

 BUG: kernel NULL pointer dereference, address: 0000000000000380
 Oops: Oops: 0000 [#1] SMP NOPTI
 [...]
 RIP: 0010:neigh_lookup+0x20/0x270
 [...]
 Call Trace:
  <TASK>
  vxlan_xmit+0x638/0x1ef0 [vxlan]
  dev_hard_start_xmit+0x9e/0x2e0
  __dev_queue_xmit+0xbee/0x14e0
  packet_sendmsg+0x116f/0x1930
  __sys_sendto+0x1f5/0x200
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x12f/0x1590
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fix this by adding an early check on route_shortcircuit() when protocol
is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because
VXLAN can be built-in even when IPv6 is built as a module.

Fixes: e15a00aafa4b ("vxlan: add ipv6 route short circuit support")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Link: https://patch.msgid.link/20260304120357.9778-2-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 05558b6afecd..17c941aac32d 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2130,6 +2130,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	{
 		struct ipv6hdr *pip6;
 
+		/* check if nd_tbl is not initiliazed due to
+		 * ipv6.disable=1 set during boot
+		 */
+		if (!ipv6_stub->nd_tbl)
+			return false;
 		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 			return false;
 		pip6 = ipv6_hdr(skb);

From 21ec92774d1536f71bdc90b0e3d052eff99cf093 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 4 Mar 2026 19:38:13 +0800
Subject: [PATCH 0901/1303] net: ipv6: fix panic when IPv4 route references
 loopback IPv6 nexthop

When a standalone IPv6 nexthop object is created with a loopback device
(e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies
it as a reject route. This is because nexthop objects have no destination
prefix (fc_dst=::), causing fib6_is_reject() to match any loopback
nexthop. The reject path skips fib_nh_common_init(), leaving
nhc_pcpu_rth_output unallocated. If an IPv4 route later references this
nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and
panics.

Simplify the check in fib6_nh_init() to only match explicit reject
routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback
promotion heuristic in fib6_is_reject() is handled separately by
ip6_route_info_create_nh(). After this change, the three cases behave
as follows:

1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"):
   RTF_REJECT is set, enters reject path, skips fib_nh_common_init().
   No behavior change.

2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"):
   RTF_REJECT is not set, takes normal path, fib_nh_common_init() is
   called. ip6_route_info_create_nh() still promotes it to reject
   afterward. nhc_pcpu_rth_output is allocated but unused, which is
   harmless.

3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"):
   RTF_REJECT is not set, takes normal path, fib_nh_common_init() is
   called. nhc_pcpu_rth_output is properly allocated, fixing the crash
   when IPv4 routes reference this nexthop.

Suggested-by: Ido Schimmel <idosch@nvidia.com>
Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects")
Reported-by: syzbot+334190e097a98a1b81bb@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698f8482.a70a0220.2c38d7.00ca.GAE@google.com/T/
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260304113817.294966-2-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7db0c837196c..08cd86f49bf9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3583,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker;
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
-	int addr_type;
 	int err;
 
 	fib6_nh->fib_nh_family = AF_INET6;
@@ -3625,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 
 	fib6_nh->fib_nh_weight = 1;
 
-	/* We cannot add true routes via loopback here,
-	 * they would result in kernel looping; promote them to reject routes
+	/* Reset the nexthop device to the loopback device in case of reject
+	 * routes.
 	 */
-	addr_type = ipv6_addr_type(&cfg->fc_dst);
-	if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) {
+	if (cfg->fc_flags & RTF_REJECT) {
 		/* hold loopback dev/idev if we haven't done so. */
 		if (dev != net->loopback_dev) {
 			if (dev) {

From 46c1ef0cfcea50aaf0b52316fdab94bf4b45795b Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 4 Mar 2026 19:38:14 +0800
Subject: [PATCH 0902/1303] selftests: net: add test for IPv4 route with
 loopback IPv6 nexthop

Add a regression test for a kernel panic that occurs when an IPv4 route
references an IPv6 nexthop object created on the loopback device.

The test creates an IPv6 nexthop on lo, binds an IPv4 route to it, then
triggers a route lookup via ping to verify the kernel does not crash.

  ./fib_nexthops.sh
  Tests passed: 249
  Tests failed:   0

Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260304113817.294966-3-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_nexthops.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 21026b667667..6eb7f95e70e1 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal()
 
 	run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1"
 	log_test $? 2 "IPv4 route with invalid IPv6 gateway"
+
+	# Test IPv4 route with loopback IPv6 nexthop
+	# Regression test: loopback IPv6 nexthop was misclassified as reject
+	# route, skipping nhc_pcpu_rth_output allocation, causing panic when
+	# an IPv4 route references it and triggers __mkroute_output().
+	run_cmd "$IP -6 nexthop add id 20 dev lo"
+	run_cmd "$IP ro add 172.20.20.0/24 nhid 20"
+	run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1"
+	log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)"
+	run_cmd "$IP ro del 172.20.20.0/24"
+	run_cmd "$IP nexthop del id 20"
 }
 
 ipv4_fcnal_runtime()

From e2cedd400c3ec0302ffca2490e8751772906ac23 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Wed, 4 Mar 2026 09:06:02 -0500
Subject: [PATCH 0903/1303] net/sched: act_ife: Fix metalist update behavior

Whenever an ife action replace changes the metalist, instead of
replacing the old data on the metalist, the current ife code is appending
the new metadata. Aside from being innapropriate behavior, this may lead
to an unbounded addition of metadata to the metalist which might cause an
out of bounds error when running the encode op:

[  138.423369][    C1] ==================================================================
[  138.424317][    C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.424906][    C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255
[  138.425778][    C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full)
[  138.425795][    C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  138.425800][    C1] Call Trace:
[  138.425804][    C1]  <IRQ>
[  138.425808][    C1]  dump_stack_lvl (lib/dump_stack.c:122)
[  138.425828][    C1]  print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
[  138.425839][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425844][    C1]  ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1))
[  138.425853][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425859][    C1]  kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597)
[  138.425868][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425878][    C1]  kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1))
[  138.425884][    C1]  __asan_memset (mm/kasan/shadow.c:84 (discriminator 2))
[  138.425889][    C1]  ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425893][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:171)
[  138.425898][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425903][    C1]  ife_encode_meta_u16 (net/sched/act_ife.c:57)
[  138.425910][    C1]  ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114)
[  138.425916][    C1]  ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3))
[  138.425921][    C1]  ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45)
[  138.425927][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425931][    C1]  tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879)

To solve this issue, fix the replace behavior by adding the metalist to
the ife rcu data structure.

Fixes: aa9fd9a325d51 ("sched: act: ife: update parameters via rcu handling")
Reported-by: Ruitong Liu <cnitlrt@gmail.com>
Tested-by: Ruitong Liu <cnitlrt@gmail.com>
Co-developed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260304140603.76500-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tc_act/tc_ife.h |  4 +-
 net/sched/act_ife.c         | 93 ++++++++++++++++++-------------------
 2 files changed, 45 insertions(+), 52 deletions(-)

diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index c7f24a2da1ca..24d4d5a62b3c 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -13,15 +13,13 @@ struct tcf_ife_params {
 	u8 eth_src[ETH_ALEN];
 	u16 eth_type;
 	u16 flags;
-
+	struct list_head metalist;
 	struct rcu_head rcu;
 };
 
 struct tcf_ife_info {
 	struct tc_action common;
 	struct tcf_ife_params __rcu *params;
-	/* list of metaids allowed */
-	struct list_head metalist;
 };
 #define to_ife(a) ((struct tcf_ife_info *)a)
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 79df81d12894..d5e8a91bb4eb 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held)
 /* called when adding new meta information
 */
 static int __add_metainfo(const struct tcf_meta_ops *ops,
-			  struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			  int len, bool atomic, bool exists)
+			  struct tcf_ife_params *p, u32 metaid, void *metaval,
+			  int len, bool atomic)
 {
 	struct tcf_meta_info *mi = NULL;
 	int ret = 0;
@@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops,
 		}
 	}
 
-	if (exists)
-		spin_lock_bh(&ife->tcf_lock);
-	list_add_tail(&mi->metalist, &ife->metalist);
-	if (exists)
-		spin_unlock_bh(&ife->tcf_lock);
+	list_add_tail(&mi->metalist, &p->metalist);
 
 	return ret;
 }
 
 static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops,
-				    struct tcf_ife_info *ife, u32 metaid,
-				    bool exists)
+				    struct tcf_ife_params *p, u32 metaid)
 {
 	int ret;
 
 	if (!try_module_get(ops->owner))
 		return -ENOENT;
-	ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists);
+	ret = __add_metainfo(ops, p, metaid, NULL, 0, true);
 	if (ret)
 		module_put(ops->owner);
 	return ret;
 }
 
-static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool exists)
+static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval,
+			int len)
 {
 	const struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret;
 
 	if (!ops)
 		return -ENOENT;
-	ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists);
+	ret = __add_metainfo(ops, p, metaid, metaval, len, false);
 	if (ret)
 		/*put back what find_ife_oplist took */
 		module_put(ops->owner);
 	return ret;
 }
 
-static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
+static int use_all_metadata(struct tcf_ife_params *p)
 {
 	struct tcf_meta_ops *o;
 	int rc = 0;
@@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists);
+		rc = add_metainfo_and_get_ops(o, p, o->metaid);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 		return -EINVAL;
 }
 
-static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
+static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p)
 {
 	struct tcf_meta_info *e;
 	struct nlattr *nest;
@@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
 	int total_encoded = 0;
 
 	/*can only happen on decode */
-	if (list_empty(&ife->metalist))
+	if (list_empty(&p->metalist))
 		return 0;
 
 	nest = nla_nest_start_noflag(skb, TCA_IFE_METALST);
 	if (!nest)
 		goto out_nlmsg_trim;
 
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry(e, &p->metalist, metalist) {
 		if (!e->ops->get(skb, e))
 			total_encoded += 1;
 	}
@@ -403,13 +398,11 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
 	return -1;
 }
 
-/* under ife->tcf_lock */
-static void _tcf_ife_cleanup(struct tc_action *a)
+static void __tcf_ife_cleanup(struct tcf_ife_params *p)
 {
-	struct tcf_ife_info *ife = to_ife(a);
 	struct tcf_meta_info *e, *n;
 
-	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
+	list_for_each_entry_safe(e, n, &p->metalist, metalist) {
 		list_del(&e->metalist);
 		if (e->metaval) {
 			if (e->ops->release)
@@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 	}
 }
 
+static void tcf_ife_cleanup_params(struct rcu_head *head)
+{
+	struct tcf_ife_params *p = container_of(head, struct tcf_ife_params,
+						rcu);
+
+	__tcf_ife_cleanup(p);
+	kfree(p);
+}
+
 static void tcf_ife_cleanup(struct tc_action *a)
 {
 	struct tcf_ife_info *ife = to_ife(a);
 	struct tcf_ife_params *p;
 
-	spin_lock_bh(&ife->tcf_lock);
-	_tcf_ife_cleanup(a);
-	spin_unlock_bh(&ife->tcf_lock);
-
 	p = rcu_dereference_protected(ife->params, 1);
 	if (p)
-		kfree_rcu(p, rcu);
+		call_rcu(&p->rcu, tcf_ife_cleanup_params);
 }
 
 static int load_metalist(struct nlattr **tb, bool rtnl_held)
@@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held)
 	return 0;
 }
 
-static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
-			     bool exists, bool rtnl_held)
+static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb)
 {
 	int len = 0;
 	int rc = 0;
@@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = add_metainfo(ife, i, val, len, exists);
+			rc = add_metainfo(p, i, val, len);
 			if (rc)
 				return rc;
 		}
@@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	p = kzalloc_obj(*p);
 	if (!p)
 		return -ENOMEM;
+	INIT_LIST_HEAD(&p->metalist);
 
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
@@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	ife = to_ife(*a);
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&ife->metalist);
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
@@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_IFE_METALST]) {
-		err = populate_metalist(ife, tb2, exists,
-					!(flags & TCA_ACT_FLAGS_NO_RTNL));
+		err = populate_metalist(p, tb2);
 		if (err)
 			goto metadata_parse_err;
 	} else {
@@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		 * as we can. You better have at least one else we are
 		 * going to bail out
 		 */
-		err = use_all_metadata(ife, exists);
+		err = use_all_metadata(p);
 		if (err)
 			goto metadata_parse_err;
 	}
@@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 	if (p)
-		kfree_rcu(p, rcu);
+		call_rcu(&p->rcu, tcf_ife_cleanup_params);
 
 	return ret;
 metadata_parse_err:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 release_idr:
+	__tcf_ife_cleanup(p);
 	kfree(p);
 	tcf_idr_release(*a, bind);
 	return err;
@@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type))
 		goto nla_put_failure;
 
-	if (dump_metalist(skb, ife)) {
+	if (dump_metalist(skb, p)) {
 		/*ignore failure to dump metalist */
 		pr_info("Failed to dump metalist\n");
 	}
@@ -693,13 +689,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	return -1;
 }
 
-static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
+static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p,
 			      u16 metaid, u16 mlen, void *mdata)
 {
 	struct tcf_meta_info *e;
 
 	/* XXX: use hash to speed up */
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (metaid == e->metaid) {
 			if (e->ops) {
 				/* We check for decode presence already */
@@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 {
 	struct tcf_ife_info *ife = to_ife(a);
 	int action = ife->tcf_action;
+	struct tcf_ife_params *p;
 	u8 *ifehdr_end;
 	u8 *tlv_data;
 	u16 metalen;
 
+	p = rcu_dereference_bh(ife->params);
+
 	bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
 	tcf_lastuse_update(&ife->tcf_tm);
 
@@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 			return TC_ACT_SHOT;
 		}
 
-		if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
+		if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) {
 			/* abuse overlimits to count when we receive metadata
 			 * but dont have an ops for it
 			 */
@@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 /*XXX: check if we can do this at install time instead of current
  * send data path
 **/
-static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife)
+static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p)
 {
-	struct tcf_meta_info *e, *n;
+	struct tcf_meta_info *e;
 	int tot_run_sz = 0, run_sz = 0;
 
-	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (e->ops->check_presence) {
 			run_sz = e->ops->check_presence(skb, e);
 			tot_run_sz += run_sz;
@@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 	   OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
 	   where ORIGDATA = original ethernet header ...
 	 */
-	u16 metalen = ife_get_sz(skb, ife);
+	u16 metalen = ife_get_sz(skb, p);
 	int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
 	unsigned int skboff = 0;
 	int new_len = skb->len + hdrm;
@@ -833,25 +832,21 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 	if (!ife_meta)
 		goto drop;
 
-	spin_lock(&ife->tcf_lock);
-
 	/* XXX: we dont have a clever way of telling encode to
 	 * not repeat some of the computations that are done by
 	 * ops->presence_check...
 	 */
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (e->ops->encode) {
 			err = e->ops->encode(skb, (void *)(ife_meta + skboff),
 					     e);
 		}
 		if (err < 0) {
 			/* too corrupt to keep around if overwritten */
-			spin_unlock(&ife->tcf_lock);
 			goto drop;
 		}
 		skboff += err;
 	}
-	spin_unlock(&ife->tcf_lock);
 	oethh = (struct ethhdr *)skb->data;
 
 	if (!is_zero_ether_addr(p->eth_src))

From 5d1271ff4c131cd4a601dabdfdcdc1fe1252493f Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 4 Mar 2026 09:06:03 -0500
Subject: [PATCH 0904/1303] selftests/tc-testing: Add tests exercising act_ife
 metalist replace behaviour

Add 2 test cases to exercise fix in act_ife's internal metalist
behaviour.

- Update decode ife action into encode with tcindex metadata
- Update decode ife action into encode with multiple metadata

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260304140603.76500-2-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/actions/ife.json      | 99 +++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index f587a32e44c4..808aef4afe22 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -1279,5 +1279,104 @@
         "teardown": [
             "$TC actions flush action ife"
         ]
+    },
+    {
+        "id": "f2a0",
+        "name": "Update decode ife action with encode metadata",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife decode index 10"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j actions get action ife index 10",
+        "matchJSON": [
+            {
+                "total acts": 0
+            },
+            {
+                "actions": [
+                    {
+                        "order": 1,
+                        "kind": "ife",
+                        "mode": "encode",
+                        "control_action": {
+                            "type": "pipe"
+                        },
+                        "type": "0xed3e",
+                        "tcindex": 1,
+                        "index": 10,
+                        "ref": 1,
+                        "bind": 0,
+                        "not_in_hw": true
+                    }
+                ]
+            }
+        ],
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    },
+    {
+        "id": "d352",
+        "name": "Update decode ife action into encode with multiple metadata",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife decode index 10"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j actions get action ife index 10",
+        "matchJSON": [
+            {
+                "total acts": 0
+            },
+            {
+                "actions": [
+                    {
+                        "order": 1,
+                        "kind": "ife",
+                        "mode": "encode",
+                        "control_action": {
+                            "type": "pipe"
+                        },
+                        "type": "0xed3e",
+                        "tcindex": 1,
+                        "mark": 22,
+                        "index": 10,
+                        "ref": 1,
+                        "bind": 0,
+                        "not_in_hw": true
+                    }
+                ]
+            }
+        ],
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
     }
 ]

From 88b6b7f7b216108a09887b074395fa7b751880b1 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:42 +0100
Subject: [PATCH 0905/1303] xdp: use modulo operation to calculate XDP frag
 tailroom

The current formula for calculating XDP tailroom in mbuf packets works only
if each frag has its own page (if rxq->frag_size is PAGE_SIZE), this
defeats the purpose of the parameter overall and without any indication
leads to negative calculated tailroom on at least half of frags, if shared
pages are used.

There are not many drivers that set rxq->frag_size. Among them:
* i40e and enetc always split page uniformly between frags, use shared
  pages
* ice uses page_pool frags via libeth, those are power-of-2 and uniformly
  distributed across page
* idpf has variable frag_size with XDP on, so current API is not applicable
* mlx5, mtk and mvneta use PAGE_SIZE or 0 as frag_size for page_pool

As for AF_XDP ZC, only ice, i40e and idpf declare frag_size for it. Modulo
operation yields good results for aligned chunks, they are all power-of-2,
between 2K and PAGE_SIZE. Formula without modulo fails when chunk_size is
2K. Buffers in unaligned mode are not distributed uniformly, so modulo
operation would not work.

To accommodate unaligned buffers, we could define frag_size as
data + tailroom, and hence do not subtract offset when calculating
tailroom, but this would necessitate more changes in the drivers.

Define rxq->frag_size as an even portion of a page that fully belongs to a
single frag. When calculating tailroom, locate the data start within such
portion by performing a modulo operation on page offset.

Fixes: bf25146a5595 ("bpf: add frags support to the bpf_xdp_adjust_tail() API")
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-2-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 0d5d5a17acb2..d6fafb3633b0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4155,7 +4155,8 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
 		return -EOPNOTSUPP;
 
-	tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag);
+	tailroom = rxq->frag_size - skb_frag_size(frag) -
+		   skb_frag_off(frag) % rxq->frag_size;
 	if (unlikely(offset > tailroom))
 		return -EINVAL;
 

From 16394d80539937d348dd3b9ea32415c54e67a81b Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:43 +0100
Subject: [PATCH 0906/1303] xsk: introduce helper to determine rxq->frag_size

rxq->frag_size is basically a step between consecutive strictly aligned
frames. In ZC mode, chunk size fits exactly, but if chunks are unaligned,
there is no safe way to determine accessible space to grow tailroom.

Report frag_size to be zero, if chunks are unaligned, chunk_size otherwise.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-3-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index aefc368449d5..6b9ebae2dc95 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool);
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
@@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return 0;
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return 0;
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {

From 02852b47c706772af795d3e28fca99fc9b923b2c Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:44 +0100
Subject: [PATCH 0907/1303] ice: fix rxq info registering in mbuf packets

XDP RxQ info contains frag_size, which depends on the MTU. This makes the
old way of registering RxQ info before calculating new buffer sizes
invalid. Currently, it leads to frag_size being outdated, making it
sometimes impossible to grow tailroom in a mbuf packet. E.g. fragments are
actually 3K+, but frag size is still as if MTU was 1500.

Always register new XDP RxQ info after reconfiguring memory pools.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-4-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c    | 26 ++++++--------------
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  1 +
 drivers/net/ethernet/intel/ice/ice_txrx.c    |  4 ++-
 drivers/net/ethernet/intel/ice/ice_xsk.c     |  3 +++
 4 files changed, 14 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index d85b0a4baa37..165ef8afa8b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -666,23 +666,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 
 	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
 	    ring->vsi->type == ICE_VSI_LB) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-						 ring->q_index,
-						 ring->q_vector->napi.napi_id,
-						 ring->rx_buf_len);
-			if (err)
-				return err;
-		}
-
 		ice_rx_xsk_pool(ring);
 		err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool);
 		if (err)
 			return err;
 
 		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg(&ring->xdp_rxq);
-
 			rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
@@ -705,14 +694,13 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			if (err)
 				return err;
 
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-							 ring->q_index,
-							 ring->q_vector->napi.napi_id,
-							 ring->rx_buf_len);
-				if (err)
-					goto err_destroy_fq;
-			}
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				goto err_destroy_fq;
+
 			xdp_rxq_info_attach_page_pool(&ring->xdp_rxq,
 						      ring->pp);
 		}
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index b9be10b58856..301947d53ede 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3342,6 +3342,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
 		rx_rings[i].desc = NULL;
 		rx_rings[i].xdp_buf = NULL;
+		rx_rings[i].xdp_rxq = (struct xdp_rxq_info){ };
 
 		/* this is to allow wr32 to have something to write to
 		 * during early allocation of Rx buffers
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index a5bbce68f76c..a2cd4cf37734 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -560,7 +560,9 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 			i = 0;
 	}
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
+	if ((rx_ring->vsi->type == ICE_VSI_PF ||
+	     rx_ring->vsi->type == ICE_VSI_SF ||
+	     rx_ring->vsi->type == ICE_VSI_LB) &&
 	    xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) {
 		xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq);
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index c673094663a3..0643017541c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -899,6 +899,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	u16 ntc = rx_ring->next_to_clean;
 	u16 ntu = rx_ring->next_to_use;
 
+	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+
 	while (ntc != ntu) {
 		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 

From e142dc4ef0f451b7ef99d09aaa84e9389af629d7 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:45 +0100
Subject: [PATCH 0908/1303] ice: change XDP RxQ frag_size from DMA write length
 to xdp.frame_sz

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buff size instead
of DMA write size. Different assumptions in ice driver configuration lead
to negative tailroom.

This allows to trigger kernel panic, when using
XDP_ADJUST_TAIL_GROW_MULTI_BUFF xskxceiver test and changing packet size to
6912 and the requested offset to a huge value, e.g.
XSK_UMEM__MAX_FRAME_SIZE * 100.

Due to other quirks of the ZC configuration in ice, panic is not observed
in ZC mode, but tailroom growing still fails when it should not.

Use fill queue buffer truesize instead of DMA write size in XDP RxQ info.
Fix ZC mode too by using the new helper.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-5-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 165ef8afa8b0..1667f686ff75 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -661,7 +661,6 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 {
 	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	u32 num_bufs = ICE_DESC_UNUSED(ring);
-	u32 rx_buf_len;
 	int err;
 
 	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
@@ -672,12 +671,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return err;
 
 		if (ring->xsk_pool) {
-			rx_buf_len =
-				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			u32 frag_size =
+				xsk_pool_get_rx_frag_step(ring->xsk_pool);
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
 						 ring->q_vector->napi.napi_id,
-						 rx_buf_len);
+						 frag_size);
 			if (err)
 				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -697,7 +696,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
 						 ring->q_vector->napi.napi_id,
-						 ring->rx_buf_len);
+						 ring->truesize);
 			if (err)
 				goto err_destroy_fq;
 

From 8f497dc8a61429cc004720aa8e713743355d80cf Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:46 +0100
Subject: [PATCH 0909/1303] i40e: fix registering XDP RxQ info

Current way of handling XDP RxQ info in i40e has a problem, where frag_size
is not updated when xsk_buff_pool is detached or when MTU is changed, this
leads to growing tail always failing for multi-buffer packets.

Couple XDP RxQ info registering with buffer allocations and unregistering
with cleaning the ring.

Fixes: a045d2f2d03d ("i40e: set xdp_rxq_info::frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-6-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 34 ++++++++++++---------
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  5 +--
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7b9e147d7365..781ec5aa814b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3583,18 +3583,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (ring->vsi->type != I40E_VSI_MAIN)
 		goto skip;
 
-	if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->queue_index,
-					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
-		if (err)
-			return err;
-	}
-
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
-		xdp_rxq_info_unreg(&ring->xdp_rxq);
 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
@@ -3606,17 +3596,23 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
 		if (err)
-			return err;
+			goto unreg_xdp;
 		dev_info(&vsi->back->pdev->dev,
 			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_PAGE_SHARED,
 						 NULL);
 		if (err)
-			return err;
+			goto unreg_xdp;
 	}
 
 skip:
@@ -3654,7 +3650,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		dev_info(&vsi->back->pdev->dev,
 			 "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
 			 ring->queue_index, pf_q, err);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto unreg_xdp;
 	}
 
 	/* set the context in the HMC */
@@ -3663,7 +3660,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		dev_info(&vsi->back->pdev->dev,
 			 "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
 			 ring->queue_index, pf_q, err);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto unreg_xdp;
 	}
 
 	/* configure Rx buffer alignment */
@@ -3671,7 +3669,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		if (I40E_2K_TOO_SMALL_WITH_PADDING) {
 			dev_info(&vsi->back->pdev->dev,
 				 "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto unreg_xdp;
 		}
 		clear_ring_build_skb_enabled(ring);
 	} else {
@@ -3701,6 +3700,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	}
 
 	return 0;
+unreg_xdp:
+	if (ring->vsi->type == I40E_VSI_MAIN)
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
+
+	return err;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 34db7d8866b0..894f2d06d39d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1470,6 +1470,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 	if (!rx_ring->rx_bi)
 		return;
 
+	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+
 	if (rx_ring->xsk_pool) {
 		i40e_xsk_clean_rx_ring(rx_ring);
 		goto skip_free;
@@ -1527,8 +1530,6 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 {
 	i40e_clean_rx_ring(rx_ring);
-	if (rx_ring->vsi->type == I40E_VSI_MAIN)
-		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	rx_ring->xdp_prog = NULL;
 	kfree(rx_ring->rx_bi);
 	rx_ring->rx_bi = NULL;

From c69d22c6c46a1d792ba8af3d8d6356fdc0e6f538 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:47 +0100
Subject: [PATCH 0910/1303] i40e: use xdp.frame_sz as XDP RxQ info frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead
of DMA write size. Different assumptions in i40e driver configuration lead
to negative tailroom.

Set frag_size to the same value as frame_sz in shared pages mode, use new
helper to set frag_size when AF_XDP ZC is active.

Fixes: a045d2f2d03d ("i40e: set xdp_rxq_info::frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-7-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 781ec5aa814b..926d001b2150 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3569,6 +3569,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	u16 pf_q = vsi->base_queue + ring->queue_index;
 	struct i40e_hw *hw = &vsi->back->hw;
 	struct i40e_hmc_obj_rxq rx_ctx;
+	u32 xdp_frame_sz;
 	int err = 0;
 	bool ok;
 
@@ -3578,6 +3579,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
 	ring->rx_buf_len = vsi->rx_buf_len;
+	xdp_frame_sz = i40e_rx_pg_size(ring) / 2;
 
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
 	if (ring->vsi->type != I40E_VSI_MAIN)
@@ -3585,11 +3587,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
+		xdp_frame_sz = xsk_pool_get_rx_frag_step(ring->xsk_pool);
 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3605,7 +3608,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3616,7 +3619,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	}
 
 skip:
-	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+	xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
 				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));

From 75d9228982f23d68066ca0b7d87014c3eb8ddc85 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:48 +0100
Subject: [PATCH 0911/1303] libeth, idpf: use truesize as XDP RxQ info
 frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead
of DMA write size. Different assumptions in idpf driver configuration lead
to negative tailroom.

To make it worse, buffer sizes are not actually uniform in idpf when
splitq is enabled, as there are several buffer queues, so rxq->rx_buf_size
is meaningless in this case.

Use truesize of the first bufq in AF_XDP ZC, as there is only one. Disable
growing tail for regular splitq.

Fixes: ac8a861f632e ("idpf: prepare structures to support XDP")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-8-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/xdp.c   | 6 +++++-
 drivers/net/ethernet/intel/idpf/xsk.c   | 1 +
 drivers/net/ethernet/intel/libeth/xsk.c | 1 +
 include/net/libeth/xsk.h                | 3 +++
 4 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c
index 6ac9c6624c2a..cbccd4546768 100644
--- a/drivers/net/ethernet/intel/idpf/xdp.c
+++ b/drivers/net/ethernet/intel/idpf/xdp.c
@@ -47,12 +47,16 @@ static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg)
 {
 	const struct idpf_vport *vport = rxq->q_vector->vport;
 	const struct idpf_q_vec_rsrc *rsrc;
+	u32 frag_size = 0;
 	bool split;
 	int err;
 
+	if (idpf_queue_has(XSK, rxq))
+		frag_size = rxq->bufq_sets[0].bufq.truesize;
+
 	err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx,
 				 rxq->q_vector->napi.napi_id,
-				 rxq->rx_buf_size);
+				 frag_size);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c
index 676cbd80774d..d95d3efdfd36 100644
--- a/drivers/net/ethernet/intel/idpf/xsk.c
+++ b/drivers/net/ethernet/intel/idpf/xsk.c
@@ -403,6 +403,7 @@ int idpf_xskfq_init(struct idpf_buf_queue *bufq)
 	bufq->pending = fq.pending;
 	bufq->thresh = fq.thresh;
 	bufq->rx_buf_size = fq.buf_len;
+	bufq->truesize = fq.truesize;
 
 	if (!idpf_xskfq_refill(bufq))
 		netdev_err(bufq->pool->netdev,
diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c
index 846e902e31b6..4882951d5c9c 100644
--- a/drivers/net/ethernet/intel/libeth/xsk.c
+++ b/drivers/net/ethernet/intel/libeth/xsk.c
@@ -167,6 +167,7 @@ int libeth_xskfq_create(struct libeth_xskfq *fq)
 	fq->pending = fq->count;
 	fq->thresh = libeth_xdp_queue_threshold(fq->count);
 	fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool);
+	fq->truesize = xsk_pool_get_rx_frag_step(fq->pool);
 
 	return 0;
 }
diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index 481a7b28e6f2..82b5d21aae87 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp,
  * @pending: current number of XSkFQEs to refill
  * @thresh: threshold below which the queue is refilled
  * @buf_len: HW-writeable length per each buffer
+ * @truesize: step between consecutive buffers, 0 if none exists
  * @nid: ID of the closest NUMA node with memory
  */
 struct libeth_xskfq {
@@ -614,6 +615,8 @@ struct libeth_xskfq {
 	u32			thresh;
 
 	u32			buf_len;
+	u32			truesize;
+
 	int			nid;
 };
 

From f8e18abf183dbd636a8725532c7f5aa58957de84 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:49 +0100
Subject: [PATCH 0912/1303] net: enetc: use truesize as XDP RxQ info frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects truesize instead of DMA
write size. Different assumptions in enetc driver configuration lead to
negative tailroom.

Set frag_size to the same value as frame_sz.

Fixes: 2768b2e2f7d2 ("net: enetc: register XDP RX queues with frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-9-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 70768392912c..a146ceaf2ed6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3467,7 +3467,7 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	priv->rx_ring[i] = bdr;
 
 	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
-				 ENETC_RXB_DMA_SIZE_XDP);
+				 ENETC_RXB_TRUESIZE);
 	if (err)
 		goto free_vector;
 

From 8821e857759be9db3cde337ad328b71fe5c8a55f Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:50 +0100
Subject: [PATCH 0913/1303] xdp: produce a warning when calculated tailroom is
 negative
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many ethernet drivers report xdp Rx queue frag size as being the same as
DMA write size. However, the only user of this field, namely
bpf_xdp_frags_increase_tail(), clearly expects a truesize.

Such difference leads to unspecific memory corruption issues under certain
circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when
running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses
all DMA-writable space in 2 buffers. This would be fine, if only
rxq->frag_size was properly set to 4K, but value of 3K results in a
negative tailroom, because there is a non-zero page offset.

We are supposed to return -EINVAL and be done with it in such case, but due
to tailroom being stored as an unsigned int, it is reported to be somewhere
near UINT_MAX, resulting in a tail being grown, even if the requested
offset is too much (it is around 2K in the abovementioned test). This later
leads to all kinds of unspecific calltraces.

[ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6
[ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4
[ 7340.338179]  in libc.so.6[61c9d,7f4161aaf000+160000]
[ 7340.339230]  in xskxceiver[42b5,400000+69000]
[ 7340.340300]  likely on CPU 6 (core 0, socket 6)
[ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe
[ 7340.340888]  likely on CPU 3 (core 0, socket 3)
[ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7
[ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI
[ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy)
[ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014
[ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80
[ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89
[ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202
[ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010
[ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff
[ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0
[ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0
[ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500
[ 7340.418229] FS:  0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000
[ 7340.419489] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0
[ 7340.421237] PKRU: 55555554
[ 7340.421623] Call Trace:
[ 7340.421987]  <TASK>
[ 7340.422309]  ? softleaf_from_pte+0x77/0xa0
[ 7340.422855]  swap_pte_batch+0xa7/0x290
[ 7340.423363]  zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270
[ 7340.424102]  zap_pte_range+0x281/0x580
[ 7340.424607]  zap_pmd_range.isra.0+0xc9/0x240
[ 7340.425177]  unmap_page_range+0x24d/0x420
[ 7340.425714]  unmap_vmas+0xa1/0x180
[ 7340.426185]  exit_mmap+0xe1/0x3b0
[ 7340.426644]  __mmput+0x41/0x150
[ 7340.427098]  exit_mm+0xb1/0x110
[ 7340.427539]  do_exit+0x1b2/0x460
[ 7340.427992]  do_group_exit+0x2d/0xc0
[ 7340.428477]  get_signal+0x79d/0x7e0
[ 7340.428957]  arch_do_signal_or_restart+0x34/0x100
[ 7340.429571]  exit_to_user_mode_loop+0x8e/0x4c0
[ 7340.430159]  do_syscall_64+0x188/0x6b0
[ 7340.430672]  ? __do_sys_clone3+0xd9/0x120
[ 7340.431212]  ? switch_fpu_return+0x4e/0xd0
[ 7340.431761]  ? arch_exit_to_user_mode_prepare.isra.0+0xa1/0xc0
[ 7340.432498]  ? do_syscall_64+0xbb/0x6b0
[ 7340.433015]  ? __handle_mm_fault+0x445/0x690
[ 7340.433582]  ? count_memcg_events+0xd6/0x210
[ 7340.434151]  ? handle_mm_fault+0x212/0x340
[ 7340.434697]  ? do_user_addr_fault+0x2b4/0x7b0
[ 7340.435271]  ? clear_bhb_loop+0x30/0x80
[ 7340.435788]  ? clear_bhb_loop+0x30/0x80
[ 7340.436299]  ? clear_bhb_loop+0x30/0x80
[ 7340.436812]  ? clear_bhb_loop+0x30/0x80
[ 7340.437323]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 7340.437973] RIP: 0033:0x7f4161b14169
[ 7340.438468] Code: Unable to access opcode bytes at 0x7f4161b1413f.
[ 7340.439242] RSP: 002b:00007ffc6ebfa770 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
[ 7340.440173] RAX: fffffffffffffe00 RBX: 00000000000005a1 RCX: 00007f4161b14169
[ 7340.441061] RDX: 00000000000005a1 RSI: 0000000000000109 RDI: 00007f415bfff990
[ 7340.441943] RBP: 00007ffc6ebfa7a0 R08: 0000000000000000 R09: 00000000ffffffff
[ 7340.442824] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[ 7340.443707] R13: 0000000000000000 R14: 00007f415bfff990 R15: 00007f415bfff6c0
[ 7340.444586]  </TASK>
[ 7340.444922] Modules linked in: rfkill intel_rapl_msr intel_rapl_common intel_uncore_frequency_common skx_edac_common nfit libnvdimm kvm_intel vfat fat kvm snd_pcm irqbypass rapl iTCO_wdt snd_timer intel_pmc_bxt iTCO_vendor_support snd ixgbevf virtio_net soundcore i2c_i801 pcspkr libeth_xdp net_failover i2c_smbus lpc_ich failover libeth virtio_balloon joydev 9p fuse loop zram lz4hc_compress lz4_compress 9pnet_virtio 9pnet netfs ghash_clmulni_intel serio_raw qemu_fw_cfg
[ 7340.449650] ---[ end trace 0000000000000000 ]---

The issue can be fixed in all in-tree drivers, but we cannot just trust OOT
drivers to not do this. Therefore, make tailroom a signed int and produce a
warning when it is negative to prevent such mistakes in the future.

Fixes: bf25146a5595 ("bpf: add frags support to the bpf_xdp_adjust_tail() API")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-10-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index d6fafb3633b0..a77d23fe2359 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4150,13 +4150,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1];
 	struct xdp_rxq_info *rxq = xdp->rxq;
-	unsigned int tailroom;
+	int tailroom;
 
 	if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
 		return -EOPNOTSUPP;
 
 	tailroom = rxq->frag_size - skb_frag_size(frag) -
 		   skb_frag_off(frag) % rxq->frag_size;
+	WARN_ON_ONCE(tailroom < 0);
 	if (unlikely(offset > tailroom))
 		return -EINVAL;
 

From 0927780c90ce551869fb692279d66387a4b66af5 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Thu, 5 Mar 2026 14:18:56 +0800
Subject: [PATCH 0914/1303] sched_ext: Use READ_ONCE() for lock-free reads of
 module param variables

bypass_lb_cpu() reads scx_bypass_lb_intv_us and scx_slice_bypass_us
without holding any lock, in timer callback context where module
parameter writes via sysfs can happen concurrently:

    min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV;
                   ^^^^^^^^^^^^^^^^^^^^
                   plain read -- KCSAN data race

    if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us))
                                           ^^^^^^^^^^^^^^^^^
                                           plain read -- KCSAN data race

scx_bypass_lb_intv_us already uses READ_ONCE() in scx_bypass_lb_timerfn()
and scx_bypass() for its other lock-free read sites, leaving
bypass_lb_cpu() inconsistent. scx_slice_bypass_us has the same
lock-free access pattern in the same function.

Fix both plain reads by using READ_ONCE() to complete the concurrent
access annotation and make the code KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index c56de568ed94..10866bfb88bf 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3908,8 +3908,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq,
 	 * consider offloading iff the total queued duration is over the
 	 * threshold.
 	 */
-	min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV;
-	if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us))
+	min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV;
+	if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us)))
 		return 0;
 
 	raw_spin_rq_lock_irq(rq);

From 70f54f61a3d52af13b72248a63e98eddf4c990ac Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Thu, 5 Mar 2026 07:29:00 +0100
Subject: [PATCH 0915/1303] sched_ext: Document task ownership state machine

The task ownership state machine in sched_ext is quite hard to follow
from the code alone. The interaction of ownership states, memory
ordering rules and cross-CPU "lock dancing" makes the overall model
subtle.

Extend the documentation next to scx_ops_state to provide a more
structured and self-contained description of the state transitions and
their synchronization rules.

The new reference should make the code easier to reason about and
maintain and can help future contributors understand the overall
task-ownership workflow.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_internal.h | 114 +++++++++++++++++++++++++++++++-----
 1 file changed, 98 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 11ebb744d893..00b450597f3e 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = {
 };
 
 /*
- * sched_ext_entity->ops_state
+ * Task Ownership State Machine (sched_ext_entity->ops_state)
  *
- * Used to track the task ownership between the SCX core and the BPF scheduler.
- * State transitions look as follows:
+ * The sched_ext core uses this state machine to track task ownership
+ * between the SCX core and the BPF scheduler. This allows the BPF
+ * scheduler to dispatch tasks without strict ordering requirements, while
+ * the SCX core safely rejects invalid dispatches.
  *
- * NONE -> QUEUEING -> QUEUED -> DISPATCHING
- *   ^              |                 |
- *   |              v                 v
- *   \-------------------------------/
+ * State Transitions
  *
- * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call
- * sites for explanations on the conditions being waited upon and why they are
- * safe. Transitions out of them into NONE or QUEUED must store_release and the
- * waiters should load_acquire.
+ *       .------------> NONE (owned by SCX core)
+ *       |               |           ^
+ *       |       enqueue |           | direct dispatch
+ *       |               v           |
+ *       |           QUEUEING -------'
+ *       |               |
+ *       |       enqueue |
+ *       |     completes |
+ *       |               v
+ *       |            QUEUED (owned by BPF scheduler)
+ *       |               |
+ *       |      dispatch |
+ *       |               |
+ *       |               v
+ *       |          DISPATCHING
+ *       |               |
+ *       |      dispatch |
+ *       |     completes |
+ *       `---------------'
  *
- * Tracking scx_ops_state enables sched_ext core to reliably determine whether
- * any given task can be dispatched by the BPF scheduler at all times and thus
- * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler
- * to try to dispatch any task anytime regardless of its state as the SCX core
- * can safely reject invalid dispatches.
+ * State Descriptions
+ *
+ * - %SCX_OPSS_NONE:
+ *     Task is owned by the SCX core. It's either on a run queue, running,
+ *     or being manipulated by the core scheduler. The BPF scheduler has no
+ *     claim on this task.
+ *
+ * - %SCX_OPSS_QUEUEING:
+ *     Transitional state while transferring a task from the SCX core to
+ *     the BPF scheduler. The task's rq lock is held during this state.
+ *     Since QUEUEING is both entered and exited under the rq lock, dequeue
+ *     can never observe this state (it would be a BUG). When finishing a
+ *     dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion
+ *     path busy-waits for it to leave this state (via wait_ops_state())
+ *     before retrying.
+ *
+ * - %SCX_OPSS_QUEUED:
+ *     Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue)
+ *     and the BPF scheduler is responsible for dispatching it. A QSEQ
+ *     (queue sequence number) is embedded in this state to detect
+ *     dispatch/dequeue races: if a task is dequeued and re-enqueued, the
+ *     QSEQ changes and any in-flight dispatch operations targeting the old
+ *     QSEQ are safely ignored.
+ *
+ * - %SCX_OPSS_DISPATCHING:
+ *     Transitional state while transferring a task from the BPF scheduler
+ *     back to the SCX core. This state indicates the BPF scheduler has
+ *     selected the task for execution. When dequeue needs to take the task
+ *     off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path
+ *     busy-waits for it to leave this state (via wait_ops_state()) before
+ *     proceeding. Exits to %SCX_OPSS_NONE when dispatch completes.
+ *
+ * Memory Ordering
+ *
+ * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into
+ * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release()
+ * and waiters must use atomic_long_read_acquire(). This ensures proper
+ * synchronization between concurrent operations.
+ *
+ * Cross-CPU Task Migration
+ *
+ * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply
+ * grab the target CPU's rq lock because a concurrent dequeue might be
+ * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock
+ * (deadlock).
+ *
+ * The sched_ext core uses a "lock dancing" protocol coordinated by
+ * p->scx.holding_cpu. When moving a task to a different rq:
+ *
+ *   1. Verify task can be moved (CPU affinity, migration_disabled, etc.)
+ *   2. Set p->scx.holding_cpu to the current CPU
+ *   3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
+ *      is set, so clearing DISPATCHING first prevents the circular wait
+ *      (safe to lock the rq we need)
+ *   4. Unlock the current CPU's rq
+ *   5. Lock src_rq (where the task currently lives)
+ *   6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
+ *      race (dequeue clears holding_cpu to -1 when it takes the task), in
+ *      this case migration is aborted
+ *   7. If src_rq == dst_rq: clear holding_cpu and enqueue directly
+ *      into dst_rq's local DSQ (no lock swap needed)
+ *   8. Otherwise: call move_remote_task_to_local_dsq(), which releases
+ *      src_rq, locks dst_rq, and performs the deactivate/activate
+ *      migration cycle (dst_rq is held on return)
+ *   9. Unlock dst_rq and re-lock the current CPU's rq to restore
+ *      the lock state expected by the caller
+ *
+ * If any verification fails, abort the migration.
+ *
+ * This state tracking allows the BPF scheduler to try to dispatch any task
+ * at any time regardless of its state. The SCX core can safely
+ * reject/ignore invalid dispatches, simplifying the BPF scheduler
+ * implementation.
  */
 enum scx_ops_state {
 	SCX_OPSS_NONE,		/* owned by the SCX core */

From e07fc9e2da91f6d9eeafa2961be9dc09d65ed633 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Wed, 4 Mar 2026 16:22:21 +0000
Subject: [PATCH 0916/1303] KVM: arm64: Fix page leak in user_mem_abort() on
 atomic fault

When a guest performs an atomic/exclusive operation on memory lacking
the required attributes, user_mem_abort() injects a data abort and
returns early. However, it fails to release the reference to the
host page acquired via __kvm_faultin_pfn().

A malicious guest could repeatedly trigger this fault, leaking host
page references and eventually causing host memory exhaustion (OOM).

Fix this by consolidating the early error returns to a new out_put_page
label that correctly calls kvm_release_page_unused().

Fixes: 2937aeec9dc5 ("KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory")
Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Yuan Yao <yaoyuan@linux.alibaba.com>
Link: https://patch.msgid.link/20260304162222.836152-2-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/mmu.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ec2eee857208..e1d6a4f591a9 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1837,10 +1837,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && s2_force_noncacheable)
 		ret = -ENOEXEC;
 
-	if (ret) {
-		kvm_release_page_unused(page);
-		return ret;
-	}
+	if (ret)
+		goto out_put_page;
 
 	/*
 	 * Guest performs atomic/exclusive operations on memory with unsupported
@@ -1850,7 +1848,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 */
 	if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(vcpu))) {
 		kvm_inject_dabt_excl_atomic(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
+		ret = 1;
+		goto out_put_page;
 	}
 
 	if (nested)
@@ -1936,6 +1935,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		mark_page_dirty_in_slot(kvm, memslot, gfn);
 
 	return ret != -EAGAIN ? ret : 0;
+
+out_put_page:
+	kvm_release_page_unused(page);
+	return ret;
 }
 
 /* Resolve the access fault by making the page young again. */

From e31a374a99f5026df6ebff2a1c49492276e776fd Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 4 Mar 2026 19:15:48 +0100
Subject: [PATCH 0917/1303] fbdev: au1100fb: Fix build on MIPS64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix an error reported by the kernel test robot:
 au1100fb.c: error: implicit declaration of function 'KSEG1ADDR'; did you mean 'CKSEG1ADDR'?

arch/mips/include/asm/addrspace.h defines KSEG1ADDR only for 32 bit
configurations. So provide its compile-test stub also for 64bit mips builds.

Fixes: 6f366e86481a ("fbdev: au1100fb: Make driver compilable on non-mips platforms")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603042127.PT6LuKqi-lkp@intel.com/
Signed-off-by: Helge Deller <deller@gmx.de>
Acked-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
---
 drivers/video/fbdev/au1100fb.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 1a04154bc535..c54cfcd832bb 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -380,8 +380,12 @@ static struct au1100fb_panel known_lcd_panels[] =
 #define panel_is_color(panel) (panel->control_base & LCD_CONTROL_PC)
 #define panel_swap_rgb(panel) (panel->control_base & LCD_CONTROL_CCO)
 
-#if defined(CONFIG_COMPILE_TEST) && !defined(CONFIG_MIPS)
-/* This is only defined to be able to compile this driver on non-mips platforms */
+#if defined(CONFIG_COMPILE_TEST) && (!defined(CONFIG_MIPS) || defined(CONFIG_64BIT))
+/*
+ * KSEG1ADDR() is defined in arch/mips/include/asm/addrspace.h
+ * for 32 bit configurations. Provide a stub for compile testing
+ * on other platforms.
+ */
 #define KSEG1ADDR(x) (x)
 #endif
 

From 76e8173ba92e15eeb0421b7cdbaef20513193b51 Mon Sep 17 00:00:00 2001
From: Akash Goel <akash.goel@arm.com>
Date: Thu, 5 Mar 2026 11:07:23 +0000
Subject: [PATCH 0918/1303] drm/panthor: Correct the order of arguments passed
 to gem_sync

This commit corrects the order of arguments passed to panthor_gem_sync()
function, called when the SYNC_WAIT condition has to be evaluated for a
blocked GPU queue.

Fixes: cd2c9c3015e6 ("drm/panthor: Add flag to map GEM object Write-Back Cacheable")
Signed-off-by: Akash Goel <akash.goel@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://patch.msgid.link/20260305110723.2871733-1-akash.goel@arm.com
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/panthor/panthor_sched.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index bd703a2904a1..a70f1db0764e 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -893,14 +893,15 @@ panthor_queue_get_syncwait_obj(struct panthor_group *group, struct panthor_queue
 
 out_sync:
 	/* Make sure the CPU caches are invalidated before the seqno is read.
-	 * drm_gem_shmem_sync() is a NOP if map_wc=true, so no need to check
+	 * panthor_gem_sync() is a NOP if map_wc=true, so no need to check
 	 * it here.
 	 */
-	panthor_gem_sync(&bo->base.base, queue->syncwait.offset,
+	panthor_gem_sync(&bo->base.base,
+			 DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE,
+			 queue->syncwait.offset,
 			 queue->syncwait.sync64 ?
 			 sizeof(struct panthor_syncobj_64b) :
-			 sizeof(struct panthor_syncobj_32b),
-			 DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE);
+			 sizeof(struct panthor_syncobj_32b));
 
 	return queue->syncwait.kmap + queue->syncwait.offset;
 

From 35c3f72a2d55dbf52f28f4ecae51c76be1acf545 Mon Sep 17 00:00:00 2001
From: Tzung-Bi Shih <tzungbi@kernel.org>
Date: Fri, 6 Feb 2026 03:30:33 +0000
Subject: [PATCH 0919/1303] remoteproc: mediatek: Unprepare SCP clock during
 system suspend

Prior to commit d935187cfb27 ("remoteproc: mediatek: Break lock
dependency to prepare_lock"), `scp->clk` was prepared and enabled only
when it needs to communicate with the SCP.  The commit d935187cfb27
moved the prepare operation to remoteproc's prepare(), keeping the clock
prepared as long as the SCP is running.

The power consumption due to the prolonged clock preparation can be
negligible when the system is running, as SCP is designed to be a very
power efficient processor.

However, the clock remains prepared even when the system enters system
suspend.  This prevents the underlying clock controller (and potentially
the parent PLLs) from shutting down, which increases power consumption
and may block the system from entering deep sleep states.

Add suspend and resume callbacks.  Unprepare the clock in suspend() if
it was active and re-prepare it in resume() to ensure the clock is
properly disabled during system suspend, while maintaining the "always
prepared" semantics while the system is active.  The driver doesn't
implement .attach() callback, hence it only checks for RPROC_RUNNING.

Fixes: d935187cfb27 ("remoteproc: mediatek: Break lock dependency to prepare_lock")
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20260206033034.3031781-1-tzungbi@kernel.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/mtk_scp.c | 39 ++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index 4651311aeb07..bb6f6a16d895 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -1592,12 +1592,51 @@ static const struct of_device_id mtk_scp_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_scp_of_match);
 
+static int __maybe_unused scp_suspend(struct device *dev)
+{
+	struct mtk_scp *scp = dev_get_drvdata(dev);
+	struct rproc *rproc = scp->rproc;
+
+	/*
+	 * Only unprepare if the SCP is running and holding the clock.
+	 *
+	 * Note: `scp_ops` doesn't implement .attach() callback, hence
+	 * `rproc->state` can never be RPROC_ATTACHED.  Otherwise, it
+	 * should also be checked here.
+	 */
+	if (rproc->state == RPROC_RUNNING)
+		clk_unprepare(scp->clk);
+	return 0;
+}
+
+static int __maybe_unused scp_resume(struct device *dev)
+{
+	struct mtk_scp *scp = dev_get_drvdata(dev);
+	struct rproc *rproc = scp->rproc;
+
+	/*
+	 * Only prepare if the SCP was running and holding the clock.
+	 *
+	 * Note: `scp_ops` doesn't implement .attach() callback, hence
+	 * `rproc->state` can never be RPROC_ATTACHED.  Otherwise, it
+	 * should also be checked here.
+	 */
+	if (rproc->state == RPROC_RUNNING)
+		return clk_prepare(scp->clk);
+	return 0;
+}
+
+static const struct dev_pm_ops scp_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(scp_suspend, scp_resume)
+};
+
 static struct platform_driver mtk_scp_driver = {
 	.probe = scp_probe,
 	.remove = scp_remove,
 	.driver = {
 		.name = "mtk-scp",
 		.of_match_table = mtk_scp_of_match,
+		.pm = &scp_pm_ops,
 	},
 };
 

From 97e4567d39941248579da34b7fbb568e6659511e Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Sun, 8 Feb 2026 19:30:35 +0800
Subject: [PATCH 0920/1303] remoteproc: imx_rproc: Fix unreachable platform
 prepare_ops

Smatch reports unreachable code in imx_rproc_prepare(), where an early
return inside the reserved-memory parsing loop prevents platform
prepare_ops from being executed.

When of_reserved_mem_region_to_resource() fails, imx_rproc_prepare()
returns immediately, so the platform-specific prepare callback is never
called. As a result, prepare_ops such as imx_rproc_sm_lmm_prepare() on
i.MX95 have no chance to run.

This is problematic when Linux controls the M7 Logical Machine and is
responsible for preparing resources such as TCM. Without running the
platform prepare callback, loading the M7 ELF into TCM may fail if the
bootloader did not power up and initialize TCM.

Fix this by breaking out of the reserved-memory loop instead of
returning, allowing the platform prepare_ops to be executed as intended.

Fixes: edd2a9956055 ("remoteproc: imx_rproc: Introduce prepare ops for imx_rproc_dcfg")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-remoteproc/aYYXAa2Fj36XG4yQ@p14s/T/#t
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://lore.kernel.org/r/20260208-imx-rproc-fix-v1-1-ad74555eb9a4@nxp.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/imx_rproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index f5f916d67905..8c8ddbf995a4 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -617,7 +617,7 @@ static int imx_rproc_prepare(struct rproc *rproc)
 
 		err = of_reserved_mem_region_to_resource(np, i++, &res);
 		if (err)
-			return 0;
+			break;
 
 		/*
 		 * Ignore the first memory region which will be used vdev buffer.

From d5b8b0347fa8470b751a506fb801797e271d7548 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 4 Mar 2026 22:20:41 -0800
Subject: [PATCH 0921/1303] accel/amdxdna: Split mailbox channel create
 function

The management channel used for firmware control command submission is
currently created after the firmware is started. If channel creation
fails (for example, due to memory allocation failure or workqueue
creation interruption), the firmware remains in a pending state and is
unable to receive any control commands.

To avoid leaving the firmware in this inconsistent state, split
xdna_mailbox_create_channel() into two separate functions so that
resource allocation can be completed before interacting with the
hardware.
  xdna_mailbox_alloc_channel()
    Allocates memory and initializes the workqueue. This can be called
    earlier, before interacting with the hardware.
  xdna_mailbox_start_channel()
    Performs the hardware interaction required to start the channel.

Rename xdna_mailbox_destroy_channel() to xdna_mailbox_free_channel().
Ensure that xdna_mailbox_stop_channel() and xdna_mailbox_free_channel()
properly unwind the corresponding start and allocation steps, respectively.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260305062041.3954024-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_message.c    | 17 ++++-
 drivers/accel/amdxdna/aie2_pci.c        | 63 +++++++++-------
 drivers/accel/amdxdna/amdxdna_mailbox.c | 99 ++++++++++++-------------
 drivers/accel/amdxdna/amdxdna_mailbox.h | 31 ++++----
 4 files changed, 116 insertions(+), 94 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 22e1a85a7ae0..ffcf3be79e23 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -293,13 +293,20 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct
 	}
 
 	intr_reg = i2x.mb_head_ptr_reg + 4;
-	hwctx->priv->mbox_chann = xdna_mailbox_create_channel(ndev->mbox, &x2i, &i2x,
-							      intr_reg, ret);
+	hwctx->priv->mbox_chann = xdna_mailbox_alloc_channel(ndev->mbox);
 	if (!hwctx->priv->mbox_chann) {
 		XDNA_ERR(xdna, "Not able to create channel");
 		ret = -EINVAL;
 		goto del_ctx_req;
 	}
+
+	ret = xdna_mailbox_start_channel(hwctx->priv->mbox_chann, &x2i, &i2x,
+					 intr_reg, ret);
+	if (ret) {
+		XDNA_ERR(xdna, "Not able to create channel");
+		ret = -EINVAL;
+		goto free_channel;
+	}
 	ndev->hwctx_num++;
 
 	XDNA_DBG(xdna, "Mailbox channel irq: %d, msix_id: %d", ret, resp.msix_id);
@@ -307,6 +314,8 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct
 
 	return 0;
 
+free_channel:
+	xdna_mailbox_free_channel(hwctx->priv->mbox_chann);
 del_ctx_req:
 	aie2_destroy_context_req(ndev, hwctx->fw_ctx_id);
 	return ret;
@@ -322,7 +331,7 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc
 
 	xdna_mailbox_stop_channel(hwctx->priv->mbox_chann);
 	ret = aie2_destroy_context_req(ndev, hwctx->fw_ctx_id);
-	xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann);
+	xdna_mailbox_free_channel(hwctx->priv->mbox_chann);
 	XDNA_DBG(xdna, "Destroyed fw ctx %d", hwctx->fw_ctx_id);
 	hwctx->priv->mbox_chann = NULL;
 	hwctx->fw_ctx_id = -1;
@@ -921,7 +930,7 @@ void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev)
 		return;
 
 	xdna_mailbox_stop_channel(ndev->mgmt_chann);
-	xdna_mailbox_destroy_channel(ndev->mgmt_chann);
+	xdna_mailbox_free_channel(ndev->mgmt_chann);
 	ndev->mgmt_chann = NULL;
 }
 
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 977ce21eaf9f..4924a9da55b6 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -361,10 +361,29 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 	}
 	pci_set_master(pdev);
 
+	mbox_res.ringbuf_base = ndev->sram_base;
+	mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar);
+	mbox_res.mbox_base = ndev->mbox_base;
+	mbox_res.mbox_size = MBOX_SIZE(ndev);
+	mbox_res.name = "xdna_mailbox";
+	ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res);
+	if (!ndev->mbox) {
+		XDNA_ERR(xdna, "failed to create mailbox device");
+		ret = -ENODEV;
+		goto disable_dev;
+	}
+
+	ndev->mgmt_chann = xdna_mailbox_alloc_channel(ndev->mbox);
+	if (!ndev->mgmt_chann) {
+		XDNA_ERR(xdna, "failed to alloc channel");
+		ret = -ENODEV;
+		goto disable_dev;
+	}
+
 	ret = aie2_smu_init(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "failed to init smu, ret %d", ret);
-		goto disable_dev;
+		goto free_channel;
 	}
 
 	ret = aie2_psp_start(ndev->psp_hdl);
@@ -379,18 +398,6 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 		goto stop_psp;
 	}
 
-	mbox_res.ringbuf_base = ndev->sram_base;
-	mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar);
-	mbox_res.mbox_base = ndev->mbox_base;
-	mbox_res.mbox_size = MBOX_SIZE(ndev);
-	mbox_res.name = "xdna_mailbox";
-	ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res);
-	if (!ndev->mbox) {
-		XDNA_ERR(xdna, "failed to create mailbox device");
-		ret = -ENODEV;
-		goto stop_psp;
-	}
-
 	mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx);
 	if (mgmt_mb_irq < 0) {
 		ret = mgmt_mb_irq;
@@ -399,13 +406,13 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 	}
 
 	xdna_mailbox_intr_reg = ndev->mgmt_i2x.mb_head_ptr_reg + 4;
-	ndev->mgmt_chann = xdna_mailbox_create_channel(ndev->mbox,
-						       &ndev->mgmt_x2i,
-						       &ndev->mgmt_i2x,
-						       xdna_mailbox_intr_reg,
-						       mgmt_mb_irq);
-	if (!ndev->mgmt_chann) {
-		XDNA_ERR(xdna, "failed to create management mailbox channel");
+	ret = xdna_mailbox_start_channel(ndev->mgmt_chann,
+					 &ndev->mgmt_x2i,
+					 &ndev->mgmt_i2x,
+					 xdna_mailbox_intr_reg,
+					 mgmt_mb_irq);
+	if (ret) {
+		XDNA_ERR(xdna, "failed to start management mailbox channel");
 		ret = -EINVAL;
 		goto stop_psp;
 	}
@@ -413,37 +420,41 @@ static int aie2_hw_start(struct amdxdna_dev *xdna)
 	ret = aie2_mgmt_fw_init(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret);
-		goto destroy_mgmt_chann;
+		goto stop_fw;
 	}
 
 	ret = aie2_pm_init(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "failed to init pm, ret %d", ret);
-		goto destroy_mgmt_chann;
+		goto stop_fw;
 	}
 
 	ret = aie2_mgmt_fw_query(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "failed to query fw, ret %d", ret);
-		goto destroy_mgmt_chann;
+		goto stop_fw;
 	}
 
 	ret = aie2_error_async_events_alloc(ndev);
 	if (ret) {
 		XDNA_ERR(xdna, "Allocate async events failed, ret %d", ret);
-		goto destroy_mgmt_chann;
+		goto stop_fw;
 	}
 
 	ndev->dev_status = AIE2_DEV_START;
 
 	return 0;
 
-destroy_mgmt_chann:
-	aie2_destroy_mgmt_chann(ndev);
+stop_fw:
+	aie2_suspend_fw(ndev);
+	xdna_mailbox_stop_channel(ndev->mgmt_chann);
 stop_psp:
 	aie2_psp_stop(ndev->psp_hdl);
 fini_smu:
 	aie2_smu_fini(ndev);
+free_channel:
+	xdna_mailbox_free_channel(ndev->mgmt_chann);
+	ndev->mgmt_chann = NULL;
 disable_dev:
 	pci_disable_device(pdev);
 
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
index 235a94047530..46d844a73a94 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -460,26 +460,49 @@ int xdna_mailbox_send_msg(struct mailbox_channel *mb_chann,
 	return ret;
 }
 
-struct mailbox_channel *
-xdna_mailbox_create_channel(struct mailbox *mb,
-			    const struct xdna_mailbox_chann_res *x2i,
-			    const struct xdna_mailbox_chann_res *i2x,
-			    u32 iohub_int_addr,
-			    int mb_irq)
+struct mailbox_channel *xdna_mailbox_alloc_channel(struct mailbox *mb)
 {
 	struct mailbox_channel *mb_chann;
-	int ret;
-
-	if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) {
-		pr_err("Ring buf size must be power of 2");
-		return NULL;
-	}
 
 	mb_chann = kzalloc_obj(*mb_chann);
 	if (!mb_chann)
 		return NULL;
 
+	INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker);
+	mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME);
+	if (!mb_chann->work_q) {
+		MB_ERR(mb_chann, "Create workqueue failed");
+		goto free_chann;
+	}
 	mb_chann->mb = mb;
+
+	return mb_chann;
+
+free_chann:
+	kfree(mb_chann);
+	return NULL;
+}
+
+void xdna_mailbox_free_channel(struct mailbox_channel *mb_chann)
+{
+	destroy_workqueue(mb_chann->work_q);
+	kfree(mb_chann);
+}
+
+int
+xdna_mailbox_start_channel(struct mailbox_channel *mb_chann,
+			   const struct xdna_mailbox_chann_res *x2i,
+			   const struct xdna_mailbox_chann_res *i2x,
+			   u32 iohub_int_addr,
+			   int mb_irq)
+{
+	int ret;
+
+	if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) {
+		pr_err("Ring buf size must be power of 2");
+		return -EINVAL;
+	}
+
 	mb_chann->msix_irq = mb_irq;
 	mb_chann->iohub_int_addr = iohub_int_addr;
 	memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i));
@@ -489,61 +512,37 @@ xdna_mailbox_create_channel(struct mailbox *mb,
 	mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I);
 	mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X);
 
-	INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker);
-	mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME);
-	if (!mb_chann->work_q) {
-		MB_ERR(mb_chann, "Create workqueue failed");
-		goto free_and_out;
-	}
-
 	/* Everything look good. Time to enable irq handler */
 	ret = request_irq(mb_irq, mailbox_irq_handler, 0, MAILBOX_NAME, mb_chann);
 	if (ret) {
 		MB_ERR(mb_chann, "Failed to request irq %d ret %d", mb_irq, ret);
-		goto destroy_wq;
+		return ret;
 	}
 
 	mb_chann->bad_state = false;
 	mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0);
 
-	MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq);
-	return mb_chann;
-
-destroy_wq:
-	destroy_workqueue(mb_chann->work_q);
-free_and_out:
-	kfree(mb_chann);
-	return NULL;
-}
-
-int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann)
-{
-	struct mailbox_msg *mb_msg;
-	unsigned long msg_id;
-
-	MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
-	free_irq(mb_chann->msix_irq, mb_chann);
-	destroy_workqueue(mb_chann->work_q);
-	/* We can clean up and release resources */
-
-	xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg)
-		mailbox_release_msg(mb_chann, mb_msg);
-
-	xa_destroy(&mb_chann->chan_xa);
-
-	MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq);
-	kfree(mb_chann);
+	MB_DBG(mb_chann, "Mailbox channel started (irq: %d)", mb_chann->msix_irq);
 	return 0;
 }
 
 void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann)
 {
+	struct mailbox_msg *mb_msg;
+	unsigned long msg_id;
+
 	/* Disable an irq and wait. This might sleep. */
-	disable_irq(mb_chann->msix_irq);
+	free_irq(mb_chann->msix_irq, mb_chann);
 
 	/* Cancel RX work and wait for it to finish */
-	cancel_work_sync(&mb_chann->rx_work);
-	MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
+	drain_workqueue(mb_chann->work_q);
+
+	/* We can clean up and release resources */
+	xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg)
+		mailbox_release_msg(mb_chann, mb_msg);
+	xa_destroy(&mb_chann->chan_xa);
+
+	MB_DBG(mb_chann, "Mailbox channel stopped, irq: %d", mb_chann->msix_irq);
 }
 
 struct mailbox *xdnam_mailbox_create(struct drm_device *ddev,
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h
index ea367f2fb738..8b1e00945da4 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.h
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.h
@@ -74,9 +74,16 @@ struct mailbox *xdnam_mailbox_create(struct drm_device *ddev,
 				     const struct xdna_mailbox_res *res);
 
 /*
- * xdna_mailbox_create_channel() -- Create a mailbox channel instance
+ * xdna_mailbox_alloc_channel() -- alloc a mailbox channel
  *
- * @mailbox: the handle return from xdna_mailbox_create()
+ * @mb: mailbox handle
+ */
+struct mailbox_channel *xdna_mailbox_alloc_channel(struct mailbox *mb);
+
+/*
+ * xdna_mailbox_start_channel() -- start a mailbox channel instance
+ *
+ * @mb_chann: the handle return from xdna_mailbox_alloc_channel()
  * @x2i: host to firmware mailbox resources
  * @i2x: firmware to host mailbox resources
  * @xdna_mailbox_intr_reg: register addr of MSI-X interrupt
@@ -84,28 +91,24 @@ struct mailbox *xdnam_mailbox_create(struct drm_device *ddev,
  *
  * Return: If success, return a handle of mailbox channel. Otherwise, return NULL.
  */
-struct mailbox_channel *
-xdna_mailbox_create_channel(struct mailbox *mailbox,
-			    const struct xdna_mailbox_chann_res *x2i,
-			    const struct xdna_mailbox_chann_res *i2x,
-			    u32 xdna_mailbox_intr_reg,
-			    int mb_irq);
+int
+xdna_mailbox_start_channel(struct mailbox_channel *mb_chann,
+			   const struct xdna_mailbox_chann_res *x2i,
+			   const struct xdna_mailbox_chann_res *i2x,
+			   u32 xdna_mailbox_intr_reg,
+			   int mb_irq);
 
 /*
- * xdna_mailbox_destroy_channel() -- destroy mailbox channel
+ * xdna_mailbox_free_channel() -- free mailbox channel
  *
  * @mailbox_chann: the handle return from xdna_mailbox_create_channel()
- *
- * Return: if success, return 0. otherwise return error code
  */
-int xdna_mailbox_destroy_channel(struct mailbox_channel *mailbox_chann);
+void xdna_mailbox_free_channel(struct mailbox_channel *mailbox_chann);
 
 /*
  * xdna_mailbox_stop_channel() -- stop mailbox channel
  *
  * @mailbox_chann: the handle return from xdna_mailbox_create_channel()
- *
- * Return: if success, return 0. otherwise return error code
  */
 void xdna_mailbox_stop_channel(struct mailbox_channel *mailbox_chann);
 

From f42f9091be9e5ff57567a3945cfcdd498f475348 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:37 -0800
Subject: [PATCH 0922/1303] workqueue: Use POOL_BH instead of WQ_BH when
 checking pool flags

pr_cont_worker_id() checks pool->flags against WQ_BH, which is a
workqueue-level flag (defined in workqueue.h). Pool flags use a
separate namespace with POOL_* constants (defined in workqueue.c).
The correct constant is POOL_BH. Both WQ_BH and POOL_BH are defined
as (1 << 0) so this has no behavioral impact, but it is semantically
wrong and inconsistent with every other pool-level BH check in the
file.

Fixes: 4cb1ef64609f ("workqueue: Implement BH workqueues to eventually replace tasklets")
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aeaec79bc09c..1e5b6cb0fbda 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6274,7 +6274,7 @@ static void pr_cont_worker_id(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	if (pool->flags & WQ_BH)
+	if (pool->flags & POOL_BH)
 		pr_cont("bh%s",
 			pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
 	else

From 6037160e52d72028da68546fd270a7dcac130d85 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:38 -0800
Subject: [PATCH 0923/1303] workqueue: Rename pool->watchdog_ts to
 pool->last_progress_ts

The watchdog_ts name doesn't convey what the timestamp actually tracks.
This field tracks the last time a workqueue got progress.

Rename it to last_progress_ts to make it clear that it records when the
pool last made forward progress (started processing new work items).

No functional change.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1e5b6cb0fbda..687d5c55c617 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -190,7 +190,7 @@ struct worker_pool {
 	int			id;		/* I: pool ID */
 	unsigned int		flags;		/* L: flags */
 
-	unsigned long		watchdog_ts;	/* L: watchdog timestamp */
+	unsigned long		last_progress_ts;	/* L: last forward progress timestamp */
 	bool			cpu_stall;	/* WD: stalled cpu bound pool */
 
 	/*
@@ -1697,7 +1697,7 @@ static void __pwq_activate_work(struct pool_workqueue *pwq,
 	WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE));
 	trace_workqueue_activate_work(work);
 	if (list_empty(&pwq->pool->worklist))
-		pwq->pool->watchdog_ts = jiffies;
+		pwq->pool->last_progress_ts = jiffies;
 	move_linked_works(work, &pwq->pool->worklist, NULL);
 	__clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb);
 }
@@ -2348,7 +2348,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) {
 		if (list_empty(&pool->worklist))
-			pool->watchdog_ts = jiffies;
+			pool->last_progress_ts = jiffies;
 
 		trace_workqueue_activate_work(work);
 		insert_work(pwq, work, &pool->worklist, work_flags);
@@ -3352,7 +3352,7 @@ static void process_scheduled_works(struct worker *worker)
 	while ((work = list_first_entry_or_null(&worker->scheduled,
 						struct work_struct, entry))) {
 		if (first) {
-			worker->pool->watchdog_ts = jiffies;
+			worker->pool->last_progress_ts = jiffies;
 			first = false;
 		}
 		process_one_work(worker, work);
@@ -4850,7 +4850,7 @@ static int init_worker_pool(struct worker_pool *pool)
 	pool->cpu = -1;
 	pool->node = NUMA_NO_NODE;
 	pool->flags |= POOL_DISASSOCIATED;
-	pool->watchdog_ts = jiffies;
+	pool->last_progress_ts = jiffies;
 	INIT_LIST_HEAD(&pool->worklist);
 	INIT_LIST_HEAD(&pool->idle_list);
 	hash_init(pool->busy_hash);
@@ -6462,7 +6462,7 @@ static void show_one_worker_pool(struct worker_pool *pool)
 
 	/* How long the first pending work is waiting for a worker. */
 	if (!list_empty(&pool->worklist))
-		hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000;
+		hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000;
 
 	/*
 	 * Defer printing to avoid deadlocks in console drivers that
@@ -7691,7 +7691,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
 		else
 			touched = READ_ONCE(wq_watchdog_touched);
-		pool_ts = READ_ONCE(pool->watchdog_ts);
+		pool_ts = READ_ONCE(pool->last_progress_ts);
 
 		if (time_after(pool_ts, touched))
 			ts = pool_ts;

From e8e14ac7cfe437b896838e7f7d07c573965b4e4e Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:39 -0800
Subject: [PATCH 0924/1303] workqueue: Show in-flight work item duration in
 stall diagnostics

When diagnosing workqueue stalls, knowing how long each in-flight work
item has been executing is valuable. Add a current_start timestamp
(jiffies) to struct worker, set it when a work item begins execution in
process_one_work(), and print the elapsed wall-clock time in show_pwq().

Unlike current_at (which tracks CPU runtime and resets on wakeup for
CPU-intensive detection), current_start is never reset because the
diagnostic cares about total wall-clock time including sleeps.

Before: in-flight: 165:stall_work_fn [wq_stall]
After:  in-flight: 165:stall_work_fn [wq_stall] for 100s

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c          | 3 +++
 kernel/workqueue_internal.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 687d5c55c617..56d8af13843f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3204,6 +3204,7 @@ __acquires(&pool->lock)
 	worker->current_pwq = pwq;
 	if (worker->task)
 		worker->current_at = worker->task->se.sum_exec_runtime;
+	worker->current_start = jiffies;
 	work_data = *work_data_bits(work);
 	worker->current_color = get_work_color(work_data);
 
@@ -6359,6 +6360,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 			pr_cont(" %s", comma ? "," : "");
 			pr_cont_worker_id(worker);
 			pr_cont(":%ps", worker->current_func);
+			pr_cont(" for %us",
+				jiffies_to_msecs(jiffies - worker->current_start) / 1000);
 			list_for_each_entry(work, &worker->scheduled, entry)
 				pr_cont_work(false, work, &pcws);
 			pr_cont_work_flush(comma, (work_func_t)-1L, &pcws);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index f6275944ada7..8def1ddc5a1b 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -32,6 +32,7 @@ struct worker {
 	work_func_t		current_func;	/* K: function */
 	struct pool_workqueue	*current_pwq;	/* K: pwq */
 	u64			current_at;	/* K: runtime at start or last wakeup */
+	unsigned long		current_start;	/* K: start time of current work item */
 	unsigned int		current_color;	/* K: color */
 
 	int			sleeping;	/* S: is worker sleeping? */

From 8823eaef45da7f156a1396f40d53b985c511edef Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:40 -0800
Subject: [PATCH 0925/1303] workqueue: Show all busy workers in stall
 diagnostics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

show_cpu_pool_hog() only prints workers whose task is currently running
on the CPU (task_is_running()).  This misses workers that are busy
processing a work item but are sleeping or blocked — for example, a
worker that clears PF_WQ_WORKER and enters wait_event_idle().  Such a
worker still occupies a pool slot and prevents progress, yet produces
an empty backtrace section in the watchdog output.

This is happening on real arm64 systems, where
toggle_allocation_gate() IPIs every single CPU in the machine (which
lacks NMI), causing workqueue stalls that show empty backtraces because
toggle_allocation_gate() is sleeping in wait_event_idle().

Remove the task_is_running() filter so every in-flight worker in the
pool's busy_hash is dumped.  The busy_hash is protected by pool->lock,
which is already held.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 56d8af13843f..09b9ad78d566 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7583,9 +7583,9 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds
 
 /*
  * Show workers that might prevent the processing of pending work items.
- * The only candidates are CPU-bound workers in the running state.
- * Pending work items should be handled by another idle worker
- * in all other situations.
+ * A busy worker that is not running on the CPU (e.g. sleeping in
+ * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as
+ * effectively as a CPU-bound one, so dump every in-flight worker.
  */
 static void show_cpu_pool_hog(struct worker_pool *pool)
 {
@@ -7596,19 +7596,17 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
-		if (task_is_running(worker->task)) {
-			/*
-			 * Defer printing to avoid deadlocks in console
-			 * drivers that queue work while holding locks
-			 * also taken in their write paths.
-			 */
-			printk_deferred_enter();
+		/*
+		 * Defer printing to avoid deadlocks in console
+		 * drivers that queue work while holding locks
+		 * also taken in their write paths.
+		 */
+		printk_deferred_enter();
 
-			pr_info("pool %d:\n", pool->id);
-			sched_show_task(worker->task);
+		pr_info("pool %d:\n", pool->id);
+		sched_show_task(worker->task);
 
-			printk_deferred_exit();
-		}
+		printk_deferred_exit();
 	}
 
 	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
@@ -7619,7 +7617,7 @@ static void show_cpu_pools_hogs(void)
 	struct worker_pool *pool;
 	int pi;
 
-	pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n");
+	pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n");
 
 	rcu_read_lock();
 

From 9e83d5104a70d8545bad61a77e166190d9447e1d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:41 -0800
Subject: [PATCH 0926/1303] workqueue: Add stall detector sample module

Add a sample module under samples/workqueue/stall_detector/ that
reproduces a workqueue stall caused by PF_WQ_WORKER misuse.  The
module queues two work items on the same per-CPU pool, then clears
PF_WQ_WORKER and sleeps in wait_event_idle(), hiding from the
concurrency manager and stalling the second work item indefinitely.

This is useful for testing the workqueue watchdog stall diagnostics.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 samples/workqueue/stall_detector/Makefile   |  1 +
 samples/workqueue/stall_detector/wq_stall.c | 98 +++++++++++++++++++++
 2 files changed, 99 insertions(+)
 create mode 100644 samples/workqueue/stall_detector/Makefile
 create mode 100644 samples/workqueue/stall_detector/wq_stall.c

diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile
new file mode 100644
index 000000000000..8849e85e95bb
--- /dev/null
+++ b/samples/workqueue/stall_detector/Makefile
@@ -0,0 +1 @@
+obj-m += wq_stall.o
diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c
new file mode 100644
index 000000000000..6f4a497b1881
--- /dev/null
+++ b/samples/workqueue/stall_detector/wq_stall.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * wq_stall - Test module for the workqueue stall detector.
+ *
+ * Deliberately creates a workqueue stall so the watchdog fires and
+ * prints diagnostic output.  Useful for verifying that the stall
+ * detector correctly identifies stuck workers and produces useful
+ * backtraces.
+ *
+ * The stall is triggered by clearing PF_WQ_WORKER before sleeping,
+ * which hides the worker from the concurrency manager.  A second
+ * work item queued on the same pool then sits in the worklist with
+ * no worker available to process it.
+ *
+ * After ~30s the workqueue watchdog fires:
+ *   BUG: workqueue lockup - pool cpus=N ...
+ *
+ * Build:
+ *	make -C <kernel tree> M=samples/workqueue/stall_detector modules
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Breno Leitao <leitao@debian.org>
+ */
+
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+
+static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head);
+static atomic_t wake_condition = ATOMIC_INIT(0);
+static struct work_struct stall_work1;
+static struct work_struct stall_work2;
+
+static void stall_work2_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: second work item finally ran\n");
+}
+
+static void stall_work1_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: first work item running on cpu %d\n",
+		raw_smp_processor_id());
+
+	/*
+	 * Queue second item while we're still counted as running
+	 * (pool->nr_running > 0).  Since schedule_work() on a per-CPU
+	 * workqueue targets raw_smp_processor_id(), item 2 lands on the
+	 * same pool.  __queue_work -> kick_pool -> need_more_worker()
+	 * sees nr_running > 0 and does NOT wake a new worker.
+	 */
+	schedule_work(&stall_work2);
+
+	/*
+	 * Hide from the workqueue concurrency manager.  Without
+	 * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(),
+	 * so nr_running is never decremented and no replacement
+	 * worker is created.  Item 2 stays stuck in pool->worklist.
+	 */
+	current->flags &= ~PF_WQ_WORKER;
+
+	pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n");
+	pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n");
+	wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0);
+
+	/* Restore so process_one_work() cleanup works correctly */
+	current->flags |= PF_WQ_WORKER;
+	pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n");
+}
+
+static int __init wq_stall_init(void)
+{
+	pr_info("wq_stall: loading\n");
+
+	INIT_WORK(&stall_work1, stall_work1_fn);
+	INIT_WORK(&stall_work2, stall_work2_fn);
+	schedule_work(&stall_work1);
+
+	return 0;
+}
+
+static void __exit wq_stall_exit(void)
+{
+	pr_info("wq_stall: unloading\n");
+	atomic_set(&wake_condition, 1);
+	wake_up(&stall_wq_head);
+	flush_work(&stall_work1);
+	flush_work(&stall_work2);
+	pr_info("wq_stall: all work flushed, module unloaded\n");
+}
+
+module_init(wq_stall_init);
+module_exit(wq_stall_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse");
+MODULE_AUTHOR("Breno Leitao <leitao@debian.org>");

From 9f2c7349b2810c671badfc1adc804f711a83e420 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 5 Mar 2026 09:18:52 -0800
Subject: [PATCH 0927/1303] MAINTAINERS: Orphan Altera PCIe controller driver

Email to Joyce Ooi <joyce.ooi@intel.com> now bounces.  Remove the address
and mark the Altera PCIe controller driver as an orphan for now.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260305171852.3114177-1-dave.hansen@linux.intel.com
---
 MAINTAINERS | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..02768d27802c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20122,9 +20122,8 @@ F:	Documentation/devicetree/bindings/pci/marvell,armada-3700-pcie.yaml
 F:	drivers/pci/controller/pci-aardvark.c
 
 PCI DRIVER FOR ALTERA PCIE IP
-M:	Joyce Ooi <joyce.ooi@intel.com>
 L:	linux-pci@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	Documentation/devicetree/bindings/pci/altr,pcie-root-port.yaml
 F:	drivers/pci/controller/pcie-altera.c
 
@@ -20369,9 +20368,8 @@ S:	Supported
 F:	Documentation/PCI/pci-error-recovery.rst
 
 PCI MSI DRIVER FOR ALTERA MSI IP
-M:	Joyce Ooi <joyce.ooi@intel.com>
 L:	linux-pci@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	Documentation/devicetree/bindings/interrupt-controller/altr,msi-controller.yaml
 F:	drivers/pci/controller/pcie-altera-msi.c
 

From 1e972ec76e10cf9cdacf1db2fbf69f7216903a86 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 17:22:20 -0300
Subject: [PATCH 0928/1303] tools arch x86: Sync msr-index.h to pick
 MSR_{OMR_[0-3],CORE_PERF_GLOBAL_STATUS_SET}

To pick up the changes in:

  4e955c08d6dc76fb ("perf/x86/intel: Support the 4 new OMR MSRs introduced in DMR and NVL")
  736a2dcfdae72483 ("x86/CPU/AMD: Simplify the spectral chicken fix")
  56bb2736975068cc ("KVM: x86/pmu: Load/put mediated PMU context when entering/exiting guest")

Addressing this tools/perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

That makes the beautification scripts to pick some new entries:

  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before.txt
  $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after.txt
  $ diff -u before.txt after.txt
  --- before.txt	2026-03-04 17:21:39.165956041 -0300
  +++ after.txt	2026-03-04 17:21:52.479191640 -0300
  @@ -130,6 +130,11 @@
   	[0x0000038e] = "CORE_PERF_GLOBAL_STATUS",
   	[0x0000038f] = "CORE_PERF_GLOBAL_CTRL",
   	[0x00000390] = "CORE_PERF_GLOBAL_OVF_CTRL",
  +	[0x00000391] = "CORE_PERF_GLOBAL_STATUS_SET",
  +	[0x000003e0] = "OMR_0",
  +	[0x000003e1] = "OMR_1",
  +	[0x000003e2] = "OMR_2",
  +	[0x000003e3] = "OMR_3",
   	[0x000003f1] = "IA32_PEBS_ENABLE",
   	[0x000003f2] = "PEBS_DATA_CFG",
   	[0x000003f4] = "IA32_PEBS_BASE",
  $

Now one can use those strings in 'perf trace' to do filtering, e.g.:

  # perf trace -e msr:*_msr/max-stack=32/ --filter="msr==CORE_PERF_GLOBAL_STATUS_SET"

Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/msr-index.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 43adc38d31d5..da5275d8eda6 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -263,6 +263,11 @@
 #define MSR_SNOOP_RSP_0			0x00001328
 #define MSR_SNOOP_RSP_1			0x00001329
 
+#define MSR_OMR_0			0x000003e0
+#define MSR_OMR_1			0x000003e1
+#define MSR_OMR_2			0x000003e2
+#define MSR_OMR_3			0x000003e3
+
 #define MSR_LBR_SELECT			0x000001c8
 #define MSR_LBR_TOS			0x000001c9
 
@@ -1219,6 +1224,7 @@
 #define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+#define MSR_CORE_PERF_GLOBAL_STATUS_SET	0x00000391
 
 #define MSR_PERF_METRICS		0x00000329
 

From b3ce769203a99d6f3c6d6269ec09232a8c5da422 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 4 Mar 2026 11:06:12 -0800
Subject: [PATCH 0929/1303] perf disasm: Fix off-by-one bug in outside check

If a branch target points to one past the end of a function, the branch
should be treated as a branch to another function.

This can happen e.g. with a tail call to a function that is laid out
immediately after the caller.

Fixes: 751b1783da784299 ("perf annotate: Mark jumps to outher functions with the call arrow")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Peter Collingbourne <pcc@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://linux-review.googlesource.com/id/Ide471112e82d68177e0faf08ca411d9fcf0a7bdf
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/disasm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index ddcc488f2e5f..9e0420e14be1 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -384,7 +384,7 @@ static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct
 	start = map__unmap_ip(map, sym->start);
 	end = map__unmap_ip(map, sym->end);
 
-	ops->target.outside = target.addr < start || target.addr > end;
+	ops->target.outside = target.addr < start || target.addr >= end;
 
 	/*
 	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):

From c9d77f0a0c78eacdf6bbac07c494205a2c3053b4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 5 Mar 2026 17:16:07 -0300
Subject: [PATCH 0930/1303] tools headers: Update the syscall tables and
 unistd.h, to support the new 'rseq_slice_yield' syscall

Picking up the changes from these csets:

  2153b2e8917b73e9 ("sparc: Add architecture support for clone3")
  99d2592023e5d0a3 ("rseq: Implement sys_rseq_slice_yield()")
  4ac286c4a8d904c8 ("s390/syscalls: Switch to generic system call table generation")

This makes 'perf trace' support it, now its possible, for instance, to
do:

  # perf trace -e rseq_slice_yield --max-stack=16

Here is an example with the 'sendmmsg' syscall:

  root@x1:~# perf trace -e sendmmsg --max-stack 16 --max-events=1
       0.000 ( 0.062 ms): dbus-broker/1012 sendmmsg(fd: 150, mmsg: 0x7ffef57cca50, vlen: 1, flags: DONTWAIT|NOSIGNAL) = 1
                                         syscall_exit_to_user_mode_prepare ([kernel.kallsyms])
                                         syscall_exit_to_user_mode_prepare ([kernel.kallsyms])
                                         syscall_exit_to_user_mode ([kernel.kallsyms])
                                         do_syscall_64 ([kernel.kallsyms])
                                         entry_SYSCALL_64 ([kernel.kallsyms])
                                         [0x117ce7] (/usr/lib64/libc.so.6 (deleted))
  root@x1:~#

To do a system wide tracing of the new 'rseq_slice_yield' syscall with a
backtrace of at most 16 entries.

This addresses these perf tools build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
    diff -u tools/scripts/syscall.tbl scripts/syscall.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
    diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl
    diff -u tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl
    diff -u tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl

Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ludwig Rydberg <ludwig.rydberg@gaisler.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/unistd.h       |   5 +-
 .../perf/arch/arm/entry/syscalls/syscall.tbl  |   1 +
 .../arch/mips/entry/syscalls/syscall_n64.tbl  |   1 +
 .../arch/powerpc/entry/syscalls/syscall.tbl   |   1 +
 .../perf/arch/s390/entry/syscalls/syscall.tbl | 859 ++++++++----------
 tools/perf/arch/sh/entry/syscalls/syscall.tbl |   1 +
 .../arch/sparc/entry/syscalls/syscall.tbl     |   3 +-
 .../arch/x86/entry/syscalls/syscall_32.tbl    |   1 +
 .../arch/x86/entry/syscalls/syscall_64.tbl    |   1 +
 .../arch/xtensa/entry/syscalls/syscall.tbl    |   1 +
 tools/scripts/syscall.tbl                     |   1 +
 11 files changed, 406 insertions(+), 469 deletions(-)

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 942370b3f5d2..a627acc8fb5f 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr)
 #define __NR_listns 470
 __SYSCALL(__NR_listns, sys_listns)
 
+#define __NR_rseq_slice_yield 471
+__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
+
 #undef __NR_syscalls
-#define __NR_syscalls 471
+#define __NR_syscalls 472
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index fd09afae72a2..94351e22bfcf 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -485,3 +485,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 9b92bddf06b5..630aab9e5425 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -385,3 +385,4 @@
 468	n64	file_getattr			sys_file_getattr
 469	n64	file_setattr			sys_file_setattr
 470	n64	listns				sys_listns
+471	n64	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index ec4458cdb97b..4fcc7c58a105 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -561,3 +561,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	nospu	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 5863787ab036..09a7ef04d979 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -3,473 +3,398 @@
 # System call table for s390
 #
 # Format:
+# <nr> <abi> <syscall> <entry>
 #
-# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
-#
-# where <abi> can be common, 64, or 32
+# <abi> is always common.
 
-1    common	exit			sys_exit			sys_exit
-2    common	fork			sys_fork			sys_fork
-3    common	read			sys_read			compat_sys_s390_read
-4    common	write			sys_write			compat_sys_s390_write
-5    common	open			sys_open			compat_sys_open
-6    common	close			sys_close			sys_close
-7    common	restart_syscall		sys_restart_syscall		sys_restart_syscall
-8    common	creat			sys_creat			sys_creat
-9    common	link			sys_link			sys_link
-10   common	unlink			sys_unlink			sys_unlink
-11   common	execve			sys_execve			compat_sys_execve
-12   common	chdir			sys_chdir			sys_chdir
-13   32		time			-				sys_time32
-14   common	mknod			sys_mknod			sys_mknod
-15   common	chmod			sys_chmod			sys_chmod
-16   32		lchown			-				sys_lchown16
-19   common	lseek			sys_lseek			compat_sys_lseek
-20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			sys_mount
-22   common	umount			sys_oldumount			sys_oldumount
-23   32		setuid			-				sys_setuid16
-24   32		getuid			-				sys_getuid16
-25   32		stime			-				sys_stime32
-26   common	ptrace			sys_ptrace			compat_sys_ptrace
-27   common	alarm			sys_alarm			sys_alarm
-29   common	pause			sys_pause			sys_pause
-30   common	utime			sys_utime			sys_utime32
-33   common	access			sys_access			sys_access
-34   common	nice			sys_nice			sys_nice
-36   common	sync			sys_sync			sys_sync
-37   common	kill			sys_kill			sys_kill
-38   common	rename			sys_rename			sys_rename
-39   common	mkdir			sys_mkdir			sys_mkdir
-40   common	rmdir			sys_rmdir			sys_rmdir
-41   common	dup			sys_dup				sys_dup
-42   common	pipe			sys_pipe			sys_pipe
-43   common	times			sys_times			compat_sys_times
-45   common	brk			sys_brk				sys_brk
-46   32		setgid			-				sys_setgid16
-47   32		getgid			-				sys_getgid16
-48   common	signal			sys_signal			sys_signal
-49   32		geteuid			-				sys_geteuid16
-50   32		getegid			-				sys_getegid16
-51   common	acct			sys_acct			sys_acct
-52   common	umount2			sys_umount			sys_umount
-54   common	ioctl			sys_ioctl			compat_sys_ioctl
-55   common	fcntl			sys_fcntl			compat_sys_fcntl
-57   common	setpgid			sys_setpgid			sys_setpgid
-60   common	umask			sys_umask			sys_umask
-61   common	chroot			sys_chroot			sys_chroot
-62   common	ustat			sys_ustat			compat_sys_ustat
-63   common	dup2			sys_dup2			sys_dup2
-64   common	getppid			sys_getppid			sys_getppid
-65   common	getpgrp			sys_getpgrp			sys_getpgrp
-66   common	setsid			sys_setsid			sys_setsid
-67   common	sigaction		sys_sigaction			compat_sys_sigaction
-70   32		setreuid		-				sys_setreuid16
-71   32		setregid		-				sys_setregid16
-72   common	sigsuspend		sys_sigsuspend			sys_sigsuspend
-73   common	sigpending		sys_sigpending			compat_sys_sigpending
-74   common	sethostname		sys_sethostname			sys_sethostname
-75   common	setrlimit		sys_setrlimit			compat_sys_setrlimit
-76   32		getrlimit		-				compat_sys_old_getrlimit
-77   common	getrusage		sys_getrusage			compat_sys_getrusage
-78   common	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
-79   common	settimeofday		sys_settimeofday		compat_sys_settimeofday
-80   32		getgroups		-				sys_getgroups16
-81   32		setgroups		-				sys_setgroups16
-83   common	symlink			sys_symlink			sys_symlink
-85   common	readlink		sys_readlink			sys_readlink
-86   common	uselib			sys_uselib			sys_uselib
-87   common	swapon			sys_swapon			sys_swapon
-88   common	reboot			sys_reboot			sys_reboot
-89   common	readdir			-				compat_sys_old_readdir
-90   common	mmap			sys_old_mmap			compat_sys_s390_old_mmap
-91   common	munmap			sys_munmap			sys_munmap
-92   common	truncate		sys_truncate			compat_sys_truncate
-93   common	ftruncate		sys_ftruncate			compat_sys_ftruncate
-94   common	fchmod			sys_fchmod			sys_fchmod
-95   32		fchown			-				sys_fchown16
-96   common	getpriority		sys_getpriority			sys_getpriority
-97   common	setpriority		sys_setpriority			sys_setpriority
-99   common	statfs			sys_statfs			compat_sys_statfs
-100  common	fstatfs			sys_fstatfs			compat_sys_fstatfs
-101  32		ioperm			-				-
-102  common	socketcall		sys_socketcall			compat_sys_socketcall
-103  common	syslog			sys_syslog			sys_syslog
-104  common	setitimer		sys_setitimer			compat_sys_setitimer
-105  common	getitimer		sys_getitimer			compat_sys_getitimer
-106  common	stat			sys_newstat			compat_sys_newstat
-107  common	lstat			sys_newlstat			compat_sys_newlstat
-108  common	fstat			sys_newfstat			compat_sys_newfstat
-110  common	lookup_dcookie		-				-
-111  common	vhangup			sys_vhangup			sys_vhangup
-112  common	idle			-				-
-114  common	wait4			sys_wait4			compat_sys_wait4
-115  common	swapoff			sys_swapoff			sys_swapoff
-116  common	sysinfo			sys_sysinfo			compat_sys_sysinfo
-117  common	ipc			sys_s390_ipc			compat_sys_s390_ipc
-118  common	fsync			sys_fsync			sys_fsync
-119  common	sigreturn		sys_sigreturn			compat_sys_sigreturn
-120  common	clone			sys_clone			sys_clone
-121  common	setdomainname		sys_setdomainname		sys_setdomainname
-122  common	uname			sys_newuname			sys_newuname
-124  common	adjtimex		sys_adjtimex			sys_adjtimex_time32
-125  common	mprotect		sys_mprotect			sys_mprotect
-126  common	sigprocmask		sys_sigprocmask			compat_sys_sigprocmask
-127  common	create_module		-				-
-128  common	init_module		sys_init_module			sys_init_module
-129  common	delete_module		sys_delete_module		sys_delete_module
-130  common	get_kernel_syms		-				-
-131  common	quotactl		sys_quotactl			sys_quotactl
-132  common	getpgid			sys_getpgid			sys_getpgid
-133  common	fchdir			sys_fchdir			sys_fchdir
-134  common	bdflush			sys_ni_syscall			sys_ni_syscall
-135  common	sysfs			sys_sysfs			sys_sysfs
-136  common	personality		sys_s390_personality		sys_s390_personality
-137  common	afs_syscall		-				-
-138  32		setfsuid		-				sys_setfsuid16
-139  32		setfsgid		-				sys_setfsgid16
-140  32		_llseek			-				sys_llseek
-141  common	getdents		sys_getdents			compat_sys_getdents
-142  32		_newselect		-				compat_sys_select
-142  64		select			sys_select			-
-143  common	flock			sys_flock			sys_flock
-144  common	msync			sys_msync			sys_msync
-145  common	readv			sys_readv			sys_readv
-146  common	writev			sys_writev			sys_writev
-147  common	getsid			sys_getsid			sys_getsid
-148  common	fdatasync		sys_fdatasync			sys_fdatasync
-149  common	_sysctl			-				-
-150  common	mlock			sys_mlock			sys_mlock
-151  common	munlock			sys_munlock			sys_munlock
-152  common	mlockall		sys_mlockall			sys_mlockall
-153  common	munlockall		sys_munlockall			sys_munlockall
-154  common	sched_setparam		sys_sched_setparam		sys_sched_setparam
-155  common	sched_getparam		sys_sched_getparam		sys_sched_getparam
-156  common	sched_setscheduler	sys_sched_setscheduler		sys_sched_setscheduler
-157  common	sched_getscheduler	sys_sched_getscheduler		sys_sched_getscheduler
-158  common	sched_yield		sys_sched_yield			sys_sched_yield
-159  common	sched_get_priority_max	sys_sched_get_priority_max	sys_sched_get_priority_max
-160  common	sched_get_priority_min	sys_sched_get_priority_min	sys_sched_get_priority_min
-161  common	sched_rr_get_interval	sys_sched_rr_get_interval	sys_sched_rr_get_interval_time32
-162  common	nanosleep		sys_nanosleep			sys_nanosleep_time32
-163  common	mremap			sys_mremap			sys_mremap
-164  32		setresuid		-				sys_setresuid16
-165  32		getresuid		-				sys_getresuid16
-167  common	query_module		-				-
-168  common	poll			sys_poll			sys_poll
-169  common	nfsservctl		-				-
-170  32		setresgid		-				sys_setresgid16
-171  32		getresgid		-				sys_getresgid16
-172  common	prctl			sys_prctl			sys_prctl
-173  common	rt_sigreturn		sys_rt_sigreturn		compat_sys_rt_sigreturn
-174  common	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
-175  common	rt_sigprocmask		sys_rt_sigprocmask		compat_sys_rt_sigprocmask
-176  common	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
-177  common	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time32
-178  common	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
-179  common	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
-180  common	pread64			sys_pread64			compat_sys_s390_pread64
-181  common	pwrite64		sys_pwrite64			compat_sys_s390_pwrite64
-182  32		chown			-				sys_chown16
-183  common	getcwd			sys_getcwd			sys_getcwd
-184  common	capget			sys_capget			sys_capget
-185  common	capset			sys_capset			sys_capset
-186  common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
-187  common	sendfile		sys_sendfile64			compat_sys_sendfile
-188  common	getpmsg			-				-
-189  common	putpmsg			-				-
-190  common	vfork			sys_vfork			sys_vfork
-191  32		ugetrlimit		-				compat_sys_getrlimit
-191  64		getrlimit		sys_getrlimit			-
-192  32		mmap2			-				compat_sys_s390_mmap2
-193  32		truncate64		-				compat_sys_s390_truncate64
-194  32		ftruncate64		-				compat_sys_s390_ftruncate64
-195  32		stat64			-				compat_sys_s390_stat64
-196  32		lstat64			-				compat_sys_s390_lstat64
-197  32		fstat64			-				compat_sys_s390_fstat64
-198  32		lchown32		-				sys_lchown
-198  64		lchown			sys_lchown			-
-199  32		getuid32		-				sys_getuid
-199  64		getuid			sys_getuid			-
-200  32		getgid32		-				sys_getgid
-200  64		getgid			sys_getgid			-
-201  32		geteuid32		-				sys_geteuid
-201  64		geteuid			sys_geteuid			-
-202  32		getegid32		-				sys_getegid
-202  64		getegid			sys_getegid			-
-203  32		setreuid32		-				sys_setreuid
-203  64		setreuid		sys_setreuid			-
-204  32		setregid32		-				sys_setregid
-204  64		setregid		sys_setregid			-
-205  32		getgroups32		-				sys_getgroups
-205  64		getgroups		sys_getgroups			-
-206  32		setgroups32		-				sys_setgroups
-206  64		setgroups		sys_setgroups			-
-207  32		fchown32		-				sys_fchown
-207  64		fchown			sys_fchown			-
-208  32		setresuid32		-				sys_setresuid
-208  64		setresuid		sys_setresuid			-
-209  32		getresuid32		-				sys_getresuid
-209  64		getresuid		sys_getresuid			-
-210  32		setresgid32		-				sys_setresgid
-210  64		setresgid		sys_setresgid			-
-211  32		getresgid32		-				sys_getresgid
-211  64		getresgid		sys_getresgid			-
-212  32		chown32			-				sys_chown
-212  64		chown			sys_chown			-
-213  32		setuid32		-				sys_setuid
-213  64		setuid			sys_setuid			-
-214  32		setgid32		-				sys_setgid
-214  64		setgid			sys_setgid			-
-215  32		setfsuid32		-				sys_setfsuid
-215  64		setfsuid		sys_setfsuid			-
-216  32		setfsgid32		-				sys_setfsgid
-216  64		setfsgid		sys_setfsgid			-
-217  common	pivot_root		sys_pivot_root			sys_pivot_root
-218  common	mincore			sys_mincore			sys_mincore
-219  common	madvise			sys_madvise			sys_madvise
-220  common	getdents64		sys_getdents64			sys_getdents64
-221  32		fcntl64			-				compat_sys_fcntl64
-222  common	readahead		sys_readahead			compat_sys_s390_readahead
-223  32		sendfile64		-				compat_sys_sendfile64
-224  common	setxattr		sys_setxattr			sys_setxattr
-225  common	lsetxattr		sys_lsetxattr			sys_lsetxattr
-226  common	fsetxattr		sys_fsetxattr			sys_fsetxattr
-227  common	getxattr		sys_getxattr			sys_getxattr
-228  common	lgetxattr		sys_lgetxattr			sys_lgetxattr
-229  common	fgetxattr		sys_fgetxattr			sys_fgetxattr
-230  common	listxattr		sys_listxattr			sys_listxattr
-231  common	llistxattr		sys_llistxattr			sys_llistxattr
-232  common	flistxattr		sys_flistxattr			sys_flistxattr
-233  common	removexattr		sys_removexattr			sys_removexattr
-234  common	lremovexattr		sys_lremovexattr		sys_lremovexattr
-235  common	fremovexattr		sys_fremovexattr		sys_fremovexattr
-236  common	gettid			sys_gettid			sys_gettid
-237  common	tkill			sys_tkill			sys_tkill
-238  common	futex			sys_futex			sys_futex_time32
-239  common	sched_setaffinity	sys_sched_setaffinity		compat_sys_sched_setaffinity
-240  common	sched_getaffinity	sys_sched_getaffinity		compat_sys_sched_getaffinity
-241  common	tgkill			sys_tgkill			sys_tgkill
-243  common	io_setup		sys_io_setup			compat_sys_io_setup
-244  common	io_destroy		sys_io_destroy			sys_io_destroy
-245  common	io_getevents		sys_io_getevents		sys_io_getevents_time32
-246  common	io_submit		sys_io_submit			compat_sys_io_submit
-247  common	io_cancel		sys_io_cancel			sys_io_cancel
-248  common	exit_group		sys_exit_group			sys_exit_group
-249  common	epoll_create		sys_epoll_create		sys_epoll_create
-250  common	epoll_ctl		sys_epoll_ctl			sys_epoll_ctl
-251  common	epoll_wait		sys_epoll_wait			sys_epoll_wait
-252  common	set_tid_address		sys_set_tid_address		sys_set_tid_address
-253  common	fadvise64		sys_fadvise64_64		compat_sys_s390_fadvise64
-254  common	timer_create		sys_timer_create		compat_sys_timer_create
-255  common	timer_settime		sys_timer_settime		sys_timer_settime32
-256  common	timer_gettime		sys_timer_gettime		sys_timer_gettime32
-257  common	timer_getoverrun	sys_timer_getoverrun		sys_timer_getoverrun
-258  common	timer_delete		sys_timer_delete		sys_timer_delete
-259  common	clock_settime		sys_clock_settime		sys_clock_settime32
-260  common	clock_gettime		sys_clock_gettime		sys_clock_gettime32
-261  common	clock_getres		sys_clock_getres		sys_clock_getres_time32
-262  common	clock_nanosleep		sys_clock_nanosleep		sys_clock_nanosleep_time32
-264  32		fadvise64_64		-				compat_sys_s390_fadvise64_64
-265  common	statfs64		sys_statfs64			compat_sys_statfs64
-266  common	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
-267  common	remap_file_pages	sys_remap_file_pages		sys_remap_file_pages
-268  common	mbind			sys_mbind			sys_mbind
-269  common	get_mempolicy		sys_get_mempolicy		sys_get_mempolicy
-270  common	set_mempolicy		sys_set_mempolicy		sys_set_mempolicy
-271  common	mq_open			sys_mq_open			compat_sys_mq_open
-272  common	mq_unlink		sys_mq_unlink			sys_mq_unlink
-273  common	mq_timedsend		sys_mq_timedsend		sys_mq_timedsend_time32
-274  common	mq_timedreceive		sys_mq_timedreceive		sys_mq_timedreceive_time32
-275  common	mq_notify		sys_mq_notify			compat_sys_mq_notify
-276  common	mq_getsetattr		sys_mq_getsetattr		compat_sys_mq_getsetattr
-277  common	kexec_load		sys_kexec_load			compat_sys_kexec_load
-278  common	add_key			sys_add_key			sys_add_key
-279  common	request_key		sys_request_key			sys_request_key
-280  common	keyctl			sys_keyctl			compat_sys_keyctl
-281  common	waitid			sys_waitid			compat_sys_waitid
-282  common	ioprio_set		sys_ioprio_set			sys_ioprio_set
-283  common	ioprio_get		sys_ioprio_get			sys_ioprio_get
-284  common	inotify_init		sys_inotify_init		sys_inotify_init
-285  common	inotify_add_watch	sys_inotify_add_watch		sys_inotify_add_watch
-286  common	inotify_rm_watch	sys_inotify_rm_watch		sys_inotify_rm_watch
-287  common	migrate_pages		sys_migrate_pages		sys_migrate_pages
-288  common	openat			sys_openat			compat_sys_openat
-289  common	mkdirat			sys_mkdirat			sys_mkdirat
-290  common	mknodat			sys_mknodat			sys_mknodat
-291  common	fchownat		sys_fchownat			sys_fchownat
-292  common	futimesat		sys_futimesat			sys_futimesat_time32
-293  32		fstatat64		-				compat_sys_s390_fstatat64
-293  64		newfstatat		sys_newfstatat			-
-294  common	unlinkat		sys_unlinkat			sys_unlinkat
-295  common	renameat		sys_renameat			sys_renameat
-296  common	linkat			sys_linkat			sys_linkat
-297  common	symlinkat		sys_symlinkat			sys_symlinkat
-298  common	readlinkat		sys_readlinkat			sys_readlinkat
-299  common	fchmodat		sys_fchmodat			sys_fchmodat
-300  common	faccessat		sys_faccessat			sys_faccessat
-301  common	pselect6		sys_pselect6			compat_sys_pselect6_time32
-302  common	ppoll			sys_ppoll			compat_sys_ppoll_time32
-303  common	unshare			sys_unshare			sys_unshare
-304  common	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
-305  common	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
-306  common	splice			sys_splice			sys_splice
-307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
-308  common	tee			sys_tee				sys_tee
-309  common	vmsplice		sys_vmsplice			sys_vmsplice
-310  common	move_pages		sys_move_pages			sys_move_pages
-311  common	getcpu			sys_getcpu			sys_getcpu
-312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
-313  common	utimes			sys_utimes			sys_utimes_time32
-314  common	fallocate		sys_fallocate			compat_sys_s390_fallocate
-315  common	utimensat		sys_utimensat			sys_utimensat_time32
-316  common	signalfd		sys_signalfd			compat_sys_signalfd
-317  common	timerfd			-				-
-318  common	eventfd			sys_eventfd			sys_eventfd
-319  common	timerfd_create		sys_timerfd_create		sys_timerfd_create
-320  common	timerfd_settime		sys_timerfd_settime		sys_timerfd_settime32
-321  common	timerfd_gettime		sys_timerfd_gettime		sys_timerfd_gettime32
-322  common	signalfd4		sys_signalfd4			compat_sys_signalfd4
-323  common	eventfd2		sys_eventfd2			sys_eventfd2
-324  common	inotify_init1		sys_inotify_init1		sys_inotify_init1
-325  common	pipe2			sys_pipe2			sys_pipe2
-326  common	dup3			sys_dup3			sys_dup3
-327  common	epoll_create1		sys_epoll_create1		sys_epoll_create1
-328  common	preadv			sys_preadv			compat_sys_preadv
-329  common	pwritev			sys_pwritev			compat_sys_pwritev
-330  common	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
-331  common	perf_event_open		sys_perf_event_open		sys_perf_event_open
-332  common	fanotify_init		sys_fanotify_init		sys_fanotify_init
-333  common	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
-334  common	prlimit64		sys_prlimit64			sys_prlimit64
-335  common	name_to_handle_at	sys_name_to_handle_at		sys_name_to_handle_at
-336  common	open_by_handle_at	sys_open_by_handle_at		compat_sys_open_by_handle_at
-337  common	clock_adjtime		sys_clock_adjtime		sys_clock_adjtime32
-338  common	syncfs			sys_syncfs			sys_syncfs
-339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
-342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
-343  common	kcmp			sys_kcmp			sys_kcmp
-344  common	finit_module		sys_finit_module		sys_finit_module
-345  common	sched_setattr		sys_sched_setattr		sys_sched_setattr
-346  common	sched_getattr		sys_sched_getattr		sys_sched_getattr
-347  common	renameat2		sys_renameat2			sys_renameat2
-348  common	seccomp			sys_seccomp			sys_seccomp
-349  common	getrandom		sys_getrandom			sys_getrandom
-350  common	memfd_create		sys_memfd_create		sys_memfd_create
-351  common	bpf			sys_bpf				sys_bpf
-352  common	s390_pci_mmio_write	sys_s390_pci_mmio_write		sys_s390_pci_mmio_write
-353  common	s390_pci_mmio_read	sys_s390_pci_mmio_read		sys_s390_pci_mmio_read
-354  common	execveat		sys_execveat			compat_sys_execveat
-355  common	userfaultfd		sys_userfaultfd			sys_userfaultfd
-356  common	membarrier		sys_membarrier			sys_membarrier
-357  common	recvmmsg		sys_recvmmsg			compat_sys_recvmmsg_time32
-358  common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
-359  common	socket			sys_socket			sys_socket
-360  common	socketpair		sys_socketpair			sys_socketpair
-361  common	bind			sys_bind			sys_bind
-362  common	connect			sys_connect			sys_connect
-363  common	listen			sys_listen			sys_listen
-364  common	accept4			sys_accept4			sys_accept4
-365  common	getsockopt		sys_getsockopt			sys_getsockopt
-366  common	setsockopt		sys_setsockopt			sys_setsockopt
-367  common	getsockname		sys_getsockname			sys_getsockname
-368  common	getpeername		sys_getpeername			sys_getpeername
-369  common	sendto			sys_sendto			sys_sendto
-370  common	sendmsg			sys_sendmsg			compat_sys_sendmsg
-371  common	recvfrom		sys_recvfrom			compat_sys_recvfrom
-372  common	recvmsg			sys_recvmsg			compat_sys_recvmsg
-373  common	shutdown		sys_shutdown			sys_shutdown
-374  common	mlock2			sys_mlock2			sys_mlock2
-375  common	copy_file_range		sys_copy_file_range		sys_copy_file_range
-376  common	preadv2			sys_preadv2			compat_sys_preadv2
-377  common	pwritev2		sys_pwritev2			compat_sys_pwritev2
-378  common	s390_guarded_storage	sys_s390_guarded_storage	sys_s390_guarded_storage
-379  common	statx			sys_statx			sys_statx
-380  common	s390_sthyi		sys_s390_sthyi			sys_s390_sthyi
-381  common	kexec_file_load		sys_kexec_file_load		sys_kexec_file_load
-382  common	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
-383  common	rseq			sys_rseq			sys_rseq
-384  common	pkey_mprotect		sys_pkey_mprotect		sys_pkey_mprotect
-385  common	pkey_alloc		sys_pkey_alloc			sys_pkey_alloc
-386  common	pkey_free		sys_pkey_free			sys_pkey_free
+1	common	exit				sys_exit
+2	common	fork				sys_fork
+3	common	read				sys_read
+4	common	write				sys_write
+5	common	open				sys_open
+6	common	close				sys_close
+7	common	restart_syscall			sys_restart_syscall
+8	common	creat				sys_creat
+9	common	link				sys_link
+10	common	unlink				sys_unlink
+11	common	execve				sys_execve
+12	common	chdir				sys_chdir
+14	common	mknod				sys_mknod
+15	common	chmod				sys_chmod
+19	common	lseek				sys_lseek
+20	common	getpid				sys_getpid
+21	common	mount				sys_mount
+22	common	umount				sys_oldumount
+26	common	ptrace				sys_ptrace
+27	common	alarm				sys_alarm
+29	common	pause				sys_pause
+30	common	utime				sys_utime
+33	common	access				sys_access
+34	common	nice				sys_nice
+36	common	sync				sys_sync
+37	common	kill				sys_kill
+38	common	rename				sys_rename
+39	common	mkdir				sys_mkdir
+40	common	rmdir				sys_rmdir
+41	common	dup				sys_dup
+42	common	pipe				sys_pipe
+43	common	times				sys_times
+45	common	brk				sys_brk
+48	common	signal				sys_signal
+51	common	acct				sys_acct
+52	common	umount2				sys_umount
+54	common	ioctl				sys_ioctl
+55	common	fcntl				sys_fcntl
+57	common	setpgid				sys_setpgid
+60	common	umask				sys_umask
+61	common	chroot				sys_chroot
+62	common	ustat				sys_ustat
+63	common	dup2				sys_dup2
+64	common	getppid				sys_getppid
+65	common	getpgrp				sys_getpgrp
+66	common	setsid				sys_setsid
+67	common	sigaction			sys_sigaction
+72	common	sigsuspend			sys_sigsuspend
+73	common	sigpending			sys_sigpending
+74	common	sethostname			sys_sethostname
+75	common	setrlimit			sys_setrlimit
+77	common	getrusage			sys_getrusage
+78	common	gettimeofday			sys_gettimeofday
+79	common	settimeofday			sys_settimeofday
+83	common	symlink				sys_symlink
+85	common	readlink			sys_readlink
+86	common	uselib				sys_uselib
+87	common	swapon				sys_swapon
+88	common	reboot				sys_reboot
+89	common	readdir				sys_ni_syscall
+90	common	mmap				sys_old_mmap
+91	common	munmap				sys_munmap
+92	common	truncate			sys_truncate
+93	common	ftruncate			sys_ftruncate
+94	common	fchmod				sys_fchmod
+96	common	getpriority			sys_getpriority
+97	common	setpriority			sys_setpriority
+99	common	statfs				sys_statfs
+100	common	fstatfs				sys_fstatfs
+102	common	socketcall			sys_socketcall
+103	common	syslog				sys_syslog
+104	common	setitimer			sys_setitimer
+105	common	getitimer			sys_getitimer
+106	common	stat				sys_newstat
+107	common	lstat				sys_newlstat
+108	common	fstat				sys_newfstat
+110	common	lookup_dcookie			sys_ni_syscall
+111	common	vhangup				sys_vhangup
+112	common	idle				sys_ni_syscall
+114	common	wait4				sys_wait4
+115	common	swapoff				sys_swapoff
+116	common	sysinfo				sys_sysinfo
+117	common	ipc				sys_s390_ipc
+118	common	fsync				sys_fsync
+119	common	sigreturn			sys_sigreturn
+120	common	clone				sys_clone
+121	common	setdomainname			sys_setdomainname
+122	common	uname				sys_newuname
+124	common	adjtimex			sys_adjtimex
+125	common	mprotect			sys_mprotect
+126	common	sigprocmask			sys_sigprocmask
+127	common	create_module			sys_ni_syscall
+128	common	init_module			sys_init_module
+129	common	delete_module			sys_delete_module
+130	common	get_kernel_syms			sys_ni_syscall
+131	common	quotactl			sys_quotactl
+132	common	getpgid				sys_getpgid
+133	common	fchdir				sys_fchdir
+134	common	bdflush				sys_ni_syscall
+135	common	sysfs				sys_sysfs
+136	common	personality			sys_s390_personality
+137	common	afs_syscall			sys_ni_syscall
+141	common	getdents			sys_getdents
+142	common	select				sys_select
+143	common	flock				sys_flock
+144	common	msync				sys_msync
+145	common	readv				sys_readv
+146	common	writev				sys_writev
+147	common	getsid				sys_getsid
+148	common	fdatasync			sys_fdatasync
+149	common	_sysctl				sys_ni_syscall
+150	common	mlock				sys_mlock
+151	common	munlock				sys_munlock
+152	common	mlockall			sys_mlockall
+153	common	munlockall			sys_munlockall
+154	common	sched_setparam			sys_sched_setparam
+155	common	sched_getparam			sys_sched_getparam
+156	common	sched_setscheduler		sys_sched_setscheduler
+157	common	sched_getscheduler		sys_sched_getscheduler
+158	common	sched_yield			sys_sched_yield
+159	common	sched_get_priority_max		sys_sched_get_priority_max
+160	common	sched_get_priority_min		sys_sched_get_priority_min
+161	common	sched_rr_get_interval		sys_sched_rr_get_interval
+162	common	nanosleep			sys_nanosleep
+163	common	mremap				sys_mremap
+167	common	query_module			sys_ni_syscall
+168	common	poll				sys_poll
+169	common	nfsservctl			sys_ni_syscall
+172	common	prctl				sys_prctl
+173	common	rt_sigreturn			sys_rt_sigreturn
+174	common	rt_sigaction			sys_rt_sigaction
+175	common	rt_sigprocmask			sys_rt_sigprocmask
+176	common	rt_sigpending			sys_rt_sigpending
+177	common	rt_sigtimedwait			sys_rt_sigtimedwait
+178	common	rt_sigqueueinfo			sys_rt_sigqueueinfo
+179	common	rt_sigsuspend			sys_rt_sigsuspend
+180	common	pread64				sys_pread64
+181	common	pwrite64			sys_pwrite64
+183	common	getcwd				sys_getcwd
+184	common	capget				sys_capget
+185	common	capset				sys_capset
+186	common	sigaltstack			sys_sigaltstack
+187	common	sendfile			sys_sendfile64
+188	common	getpmsg				sys_ni_syscall
+189	common	putpmsg				sys_ni_syscall
+190	common	vfork				sys_vfork
+191	common	getrlimit			sys_getrlimit
+198	common	lchown				sys_lchown
+199	common	getuid				sys_getuid
+200	common	getgid				sys_getgid
+201	common	geteuid				sys_geteuid
+202	common	getegid				sys_getegid
+203	common	setreuid			sys_setreuid
+204	common	setregid			sys_setregid
+205	common	getgroups			sys_getgroups
+206	common	setgroups			sys_setgroups
+207	common	fchown				sys_fchown
+208	common	setresuid			sys_setresuid
+209	common	getresuid			sys_getresuid
+210	common	setresgid			sys_setresgid
+211	common	getresgid			sys_getresgid
+212	common	chown				sys_chown
+213	common	setuid				sys_setuid
+214	common	setgid				sys_setgid
+215	common	setfsuid			sys_setfsuid
+216	common	setfsgid			sys_setfsgid
+217	common	pivot_root			sys_pivot_root
+218	common	mincore				sys_mincore
+219	common	madvise				sys_madvise
+220	common	getdents64			sys_getdents64
+222	common	readahead			sys_readahead
+224	common	setxattr			sys_setxattr
+225	common	lsetxattr			sys_lsetxattr
+226	common	fsetxattr			sys_fsetxattr
+227	common	getxattr			sys_getxattr
+228	common	lgetxattr			sys_lgetxattr
+229	common	fgetxattr			sys_fgetxattr
+230	common	listxattr			sys_listxattr
+231	common	llistxattr			sys_llistxattr
+232	common	flistxattr			sys_flistxattr
+233	common	removexattr			sys_removexattr
+234	common	lremovexattr			sys_lremovexattr
+235	common	fremovexattr			sys_fremovexattr
+236	common	gettid				sys_gettid
+237	common	tkill				sys_tkill
+238	common	futex				sys_futex
+239	common	sched_setaffinity		sys_sched_setaffinity
+240	common	sched_getaffinity		sys_sched_getaffinity
+241	common	tgkill				sys_tgkill
+243	common	io_setup			sys_io_setup
+244	common	io_destroy			sys_io_destroy
+245	common	io_getevents			sys_io_getevents
+246	common	io_submit			sys_io_submit
+247	common	io_cancel			sys_io_cancel
+248	common	exit_group			sys_exit_group
+249	common	epoll_create			sys_epoll_create
+250	common	epoll_ctl			sys_epoll_ctl
+251	common	epoll_wait			sys_epoll_wait
+252	common	set_tid_address			sys_set_tid_address
+253	common	fadvise64			sys_fadvise64_64
+254	common	timer_create			sys_timer_create
+255	common	timer_settime			sys_timer_settime
+256	common	timer_gettime			sys_timer_gettime
+257	common	timer_getoverrun		sys_timer_getoverrun
+258	common	timer_delete			sys_timer_delete
+259	common	clock_settime			sys_clock_settime
+260	common	clock_gettime			sys_clock_gettime
+261	common	clock_getres			sys_clock_getres
+262	common	clock_nanosleep			sys_clock_nanosleep
+265	common	statfs64			sys_statfs64
+266	common	fstatfs64			sys_fstatfs64
+267	common	remap_file_pages		sys_remap_file_pages
+268	common	mbind				sys_mbind
+269	common	get_mempolicy			sys_get_mempolicy
+270	common	set_mempolicy			sys_set_mempolicy
+271	common	mq_open				sys_mq_open
+272	common	mq_unlink			sys_mq_unlink
+273	common	mq_timedsend			sys_mq_timedsend
+274	common	mq_timedreceive			sys_mq_timedreceive
+275	common	mq_notify			sys_mq_notify
+276	common	mq_getsetattr			sys_mq_getsetattr
+277	common	kexec_load			sys_kexec_load
+278	common	add_key				sys_add_key
+279	common	request_key			sys_request_key
+280	common	keyctl				sys_keyctl
+281	common	waitid				sys_waitid
+282	common	ioprio_set			sys_ioprio_set
+283	common	ioprio_get			sys_ioprio_get
+284	common	inotify_init			sys_inotify_init
+285	common	inotify_add_watch		sys_inotify_add_watch
+286	common	inotify_rm_watch		sys_inotify_rm_watch
+287	common	migrate_pages			sys_migrate_pages
+288	common	openat				sys_openat
+289	common	mkdirat				sys_mkdirat
+290	common	mknodat				sys_mknodat
+291	common	fchownat			sys_fchownat
+292	common	futimesat			sys_futimesat
+293	common	newfstatat			sys_newfstatat
+294	common	unlinkat			sys_unlinkat
+295	common	renameat			sys_renameat
+296	common	linkat				sys_linkat
+297	common	symlinkat			sys_symlinkat
+298	common	readlinkat			sys_readlinkat
+299	common	fchmodat			sys_fchmodat
+300	common	faccessat			sys_faccessat
+301	common	pselect6			sys_pselect6
+302	common	ppoll				sys_ppoll
+303	common	unshare				sys_unshare
+304	common	set_robust_list			sys_set_robust_list
+305	common	get_robust_list			sys_get_robust_list
+306	common	splice				sys_splice
+307	common	sync_file_range			sys_sync_file_range
+308	common	tee				sys_tee
+309	common	vmsplice			sys_vmsplice
+310	common	move_pages			sys_move_pages
+311	common	getcpu				sys_getcpu
+312	common	epoll_pwait			sys_epoll_pwait
+313	common	utimes				sys_utimes
+314	common	fallocate			sys_fallocate
+315	common	utimensat			sys_utimensat
+316	common	signalfd			sys_signalfd
+317	common	timerfd				sys_ni_syscall
+318	common	eventfd				sys_eventfd
+319	common	timerfd_create			sys_timerfd_create
+320	common	timerfd_settime			sys_timerfd_settime
+321	common	timerfd_gettime			sys_timerfd_gettime
+322	common	signalfd4			sys_signalfd4
+323	common	eventfd2			sys_eventfd2
+324	common	inotify_init1			sys_inotify_init1
+325	common	pipe2				sys_pipe2
+326	common	dup3				sys_dup3
+327	common	epoll_create1			sys_epoll_create1
+328	common	preadv				sys_preadv
+329	common	pwritev				sys_pwritev
+330	common	rt_tgsigqueueinfo		sys_rt_tgsigqueueinfo
+331	common	perf_event_open			sys_perf_event_open
+332	common	fanotify_init			sys_fanotify_init
+333	common	fanotify_mark			sys_fanotify_mark
+334	common	prlimit64			sys_prlimit64
+335	common	name_to_handle_at		sys_name_to_handle_at
+336	common	open_by_handle_at		sys_open_by_handle_at
+337	common	clock_adjtime			sys_clock_adjtime
+338	common	syncfs				sys_syncfs
+339	common	setns				sys_setns
+340	common	process_vm_readv		sys_process_vm_readv
+341	common	process_vm_writev		sys_process_vm_writev
+342	common	s390_runtime_instr		sys_s390_runtime_instr
+343	common	kcmp				sys_kcmp
+344	common	finit_module			sys_finit_module
+345	common	sched_setattr			sys_sched_setattr
+346	common	sched_getattr			sys_sched_getattr
+347	common	renameat2			sys_renameat2
+348	common	seccomp				sys_seccomp
+349	common	getrandom			sys_getrandom
+350	common	memfd_create			sys_memfd_create
+351	common	bpf				sys_bpf
+352	common	s390_pci_mmio_write		sys_s390_pci_mmio_write
+353	common	s390_pci_mmio_read		sys_s390_pci_mmio_read
+354	common	execveat			sys_execveat
+355	common	userfaultfd			sys_userfaultfd
+356	common	membarrier			sys_membarrier
+357	common	recvmmsg			sys_recvmmsg
+358	common	sendmmsg			sys_sendmmsg
+359	common	socket				sys_socket
+360	common	socketpair			sys_socketpair
+361	common	bind				sys_bind
+362	common	connect				sys_connect
+363	common	listen				sys_listen
+364	common	accept4				sys_accept4
+365	common	getsockopt			sys_getsockopt
+366	common	setsockopt			sys_setsockopt
+367	common	getsockname			sys_getsockname
+368	common	getpeername			sys_getpeername
+369	common	sendto				sys_sendto
+370	common	sendmsg				sys_sendmsg
+371	common	recvfrom			sys_recvfrom
+372	common	recvmsg				sys_recvmsg
+373	common	shutdown			sys_shutdown
+374	common	mlock2				sys_mlock2
+375	common	copy_file_range			sys_copy_file_range
+376	common	preadv2				sys_preadv2
+377	common	pwritev2			sys_pwritev2
+378	common	s390_guarded_storage		sys_s390_guarded_storage
+379	common	statx				sys_statx
+380	common	s390_sthyi			sys_s390_sthyi
+381	common	kexec_file_load			sys_kexec_file_load
+382	common	io_pgetevents			sys_io_pgetevents
+383	common	rseq				sys_rseq
+384	common	pkey_mprotect			sys_pkey_mprotect
+385	common	pkey_alloc			sys_pkey_alloc
+386	common	pkey_free			sys_pkey_free
 # room for arch specific syscalls
-392	64	semtimedop		sys_semtimedop			-
-393  common	semget			sys_semget			sys_semget
-394  common	semctl			sys_semctl			compat_sys_semctl
-395  common	shmget			sys_shmget			sys_shmget
-396  common	shmctl			sys_shmctl			compat_sys_shmctl
-397  common	shmat			sys_shmat			compat_sys_shmat
-398  common	shmdt			sys_shmdt 			sys_shmdt
-399  common	msgget			sys_msgget			sys_msgget
-400  common	msgsnd			sys_msgsnd			compat_sys_msgsnd
-401  common	msgrcv			sys_msgrcv			compat_sys_msgrcv
-402  common	msgctl			sys_msgctl			compat_sys_msgctl
-403	32	clock_gettime64		-				sys_clock_gettime
-404	32	clock_settime64		-				sys_clock_settime
-405	32	clock_adjtime64		-				sys_clock_adjtime
-406	32	clock_getres_time64	-				sys_clock_getres
-407	32	clock_nanosleep_time64	-				sys_clock_nanosleep
-408	32	timer_gettime64		-				sys_timer_gettime
-409	32	timer_settime64		-				sys_timer_settime
-410	32	timerfd_gettime64	-				sys_timerfd_gettime
-411	32	timerfd_settime64	-				sys_timerfd_settime
-412	32	utimensat_time64	-				sys_utimensat
-413	32	pselect6_time64		-				compat_sys_pselect6_time64
-414	32	ppoll_time64		-				compat_sys_ppoll_time64
-416	32	io_pgetevents_time64	-				compat_sys_io_pgetevents_time64
-417	32	recvmmsg_time64		-				compat_sys_recvmmsg_time64
-418	32	mq_timedsend_time64	-				sys_mq_timedsend
-419	32	mq_timedreceive_time64	-				sys_mq_timedreceive
-420	32	semtimedop_time64	-				sys_semtimedop
-421	32	rt_sigtimedwait_time64	-				compat_sys_rt_sigtimedwait_time64
-422	32	futex_time64		-				sys_futex
-423	32	sched_rr_get_interval_time64	-			sys_sched_rr_get_interval
-424  common	pidfd_send_signal	sys_pidfd_send_signal		sys_pidfd_send_signal
-425  common	io_uring_setup		sys_io_uring_setup              sys_io_uring_setup
-426  common	io_uring_enter		sys_io_uring_enter              sys_io_uring_enter
-427  common	io_uring_register	sys_io_uring_register           sys_io_uring_register
-428  common	open_tree		sys_open_tree			sys_open_tree
-429  common	move_mount		sys_move_mount			sys_move_mount
-430  common	fsopen			sys_fsopen			sys_fsopen
-431  common	fsconfig		sys_fsconfig			sys_fsconfig
-432  common	fsmount			sys_fsmount			sys_fsmount
-433  common	fspick			sys_fspick			sys_fspick
-434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
-435  common	clone3			sys_clone3			sys_clone3
-436  common	close_range		sys_close_range			sys_close_range
-437  common	openat2			sys_openat2			sys_openat2
-438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
-439  common	faccessat2		sys_faccessat2			sys_faccessat2
-440  common	process_madvise		sys_process_madvise		sys_process_madvise
-441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
-442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
-443  common	quotactl_fd		sys_quotactl_fd			sys_quotactl_fd
-444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
-445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
-446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
-447  common	memfd_secret		sys_memfd_secret		sys_memfd_secret
-448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
-449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
-450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
-451  common	cachestat		sys_cachestat			sys_cachestat
-452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
-453  common	map_shadow_stack	sys_map_shadow_stack		sys_map_shadow_stack
-454  common	futex_wake		sys_futex_wake			sys_futex_wake
-455  common	futex_wait		sys_futex_wait			sys_futex_wait
-456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
-457  common	statmount		sys_statmount			sys_statmount
-458  common	listmount		sys_listmount			sys_listmount
-459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
-460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
-461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
-462  common	mseal			sys_mseal			sys_mseal
-463  common	setxattrat		sys_setxattrat			sys_setxattrat
-464  common	getxattrat		sys_getxattrat			sys_getxattrat
-465  common	listxattrat		sys_listxattrat			sys_listxattrat
-466  common	removexattrat		sys_removexattrat		sys_removexattrat
-467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
-468  common	file_getattr		sys_file_getattr		sys_file_getattr
-469  common	file_setattr		sys_file_setattr		sys_file_setattr
-470  common	listns			sys_listns			sys_listns
+392	common	semtimedop			sys_semtimedop
+393	common	semget				sys_semget
+394	common	semctl				sys_semctl
+395	common	shmget				sys_shmget
+396	common	shmctl				sys_shmctl
+397	common	shmat				sys_shmat
+398	common	shmdt				sys_shmdt
+399	common	msgget				sys_msgget
+400	common	msgsnd				sys_msgsnd
+401	common	msgrcv				sys_msgrcv
+402	common	msgctl				sys_msgctl
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
+428	common	open_tree			sys_open_tree
+429	common	move_mount			sys_move_mount
+430	common	fsopen				sys_fsopen
+431	common	fsconfig			sys_fsconfig
+432	common	fsmount				sys_fsmount
+433	common	fspick				sys_fspick
+434	common	pidfd_open			sys_pidfd_open
+435	common	clone3				sys_clone3
+436	common	close_range			sys_close_range
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
+442	common	mount_setattr			sys_mount_setattr
+443	common	quotactl_fd			sys_quotactl_fd
+444	common	landlock_create_ruleset		sys_landlock_create_ruleset
+445	common	landlock_add_rule		sys_landlock_add_rule
+446	common	landlock_restrict_self		sys_landlock_restrict_self
+447	common	memfd_secret			sys_memfd_secret
+448	common	process_mrelease		sys_process_mrelease
+449	common	futex_waitv			sys_futex_waitv
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
+453	common	map_shadow_stack		sys_map_shadow_stack
+454	common	futex_wake			sys_futex_wake
+455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
+462	common	mseal				sys_mseal
+463	common	setxattrat			sys_setxattrat
+464	common	getxattrat			sys_getxattrat
+465	common	listxattrat			sys_listxattrat
+466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
+470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index 969c11325ade..70b315cbe710 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -474,3 +474,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 39aa26b6a50b..7e71bf7fcd14 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -480,7 +480,7 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	common	clone3				__sys_clone3
 436	common	close_range			sys_close_range
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
@@ -516,3 +516,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index e979a3eac7a3..f832ebd2d79b 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -476,3 +476,4 @@
 468	i386	file_getattr		sys_file_getattr
 469	i386	file_setattr		sys_file_setattr
 470	i386	listns			sys_listns
+471	i386	rseq_slice_yield	sys_rseq_slice_yield
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 8a4ac4841be6..524155d655da 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,6 +395,7 @@
 468	common	file_getattr		sys_file_getattr
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
+471	common	rseq_slice_yield	sys_rseq_slice_yield
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index 438a3b170402..a9bca4e484de 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index e74868be513c..7a42b32b6577 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -411,3 +411,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield

From 0693907ffaca001036009bc82dc334fb8e11540f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 5 Mar 2026 17:28:44 -0300
Subject: [PATCH 0931/1303] tools headers UAPI: Update tools' copy of
 linux/coresight-pmu.h

To get the comment changes in this commit:

  171efc70097a9f5f ("x86/ibs: Fix typo in dc_l2tlb_miss comment")

This silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/amd/ibs.h arch/x86/include/asm/amd/ibs.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/amd/ibs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h
index cbce54fec7b9..41e8abd72c8b 100644
--- a/tools/arch/x86/include/asm/amd/ibs.h
+++ b/tools/arch/x86/include/asm/amd/ibs.h
@@ -110,7 +110,7 @@ union ibs_op_data3 {
 		__u64	ld_op:1,			/* 0: load op */
 			st_op:1,			/* 1: store op */
 			dc_l1tlb_miss:1,		/* 2: data cache L1TLB miss */
-			dc_l2tlb_miss:1,		/* 3: data cache L2TLB hit in 2M page */
+			dc_l2tlb_miss:1,		/* 3: data cache L2TLB miss in 2M page */
 			dc_l1tlb_hit_2m:1,		/* 4: data cache L1TLB hit in 2M page */
 			dc_l1tlb_hit_1g:1,		/* 5: data cache L1TLB hit in 1G page */
 			dc_l2tlb_hit_2m:1,		/* 6: data cache L2TLB hit in 2M page */

From f2fa6cc736ef518628f6a9d1155f9ec24e0af4e7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 4 Mar 2026 16:01:19 -0800
Subject: [PATCH 0932/1303] rcutorture: Update due to x86 not supporting
 none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such rcutorture scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/bfe89f6c-3b63-40c6-aa6d-5f523e3e9a31@paulmck-laptop
---
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-N  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-T  | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-U  | 4 ++--
 tools/testing/selftests/rcutorture/configs/rcu/TASKS02 | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TINY01  | 4 ++--
 tools/testing/selftests/rcutorture/configs/rcu/TINY02  | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TRACE01 | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE04  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE05  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE06  | 5 ++++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE10  | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL | 4 +++-
 12 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 07f5e0a70ae7..f943cdfb0a74 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -2,7 +2,9 @@ CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
 CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
index c70cf0405f24..06e4d1030279 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
index bc9eeabaa1b1..71da6e3e9488 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
@@ -7,4 +8,3 @@ CONFIG_PREEMPT_DYNAMIC=n
 CONFIG_RCU_TRACE=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
index 2f9fcffff5ae..dd2bd4e08da4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 0953c52fcfd7..2be53bf60d65 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
@@ -11,4 +12,3 @@ CONFIG_RCU_TRACE=n
 #CHECK#CONFIG_RCU_STALL_COMMON=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index 30439f6fc20e..be8860342ef7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 18efab346381..8fb124c28f28 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -1,7 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=5
 CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 67caf4276bb0..ac857d5bcb22 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -1,10 +1,12 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_LAZY=y
 CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
 #CHECK#CONFIG_TREE_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 9f48c73709ec..61d15b1b54d1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -1,6 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TREE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index db27651de04b..0e090bb68a0f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -1,9 +1,12 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TREE_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 420632b030dc..b2ce37861e71 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -6,6 +6,7 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
 #CHECK#CONFIG_TREE_RCU=y
+CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
index 5d546efa68e8..696fba9968c6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
@@ -1,6 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n

From 59af2d5652e998fea64335de6145afb3c1e0c958 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:01 -0800
Subject: [PATCH 0933/1303] rcuscale: Update due to x86 not supporting
 none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such rcuscale scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-2-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/rcuscale/TINY    | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
index 0fa2dc086e10..c1a7d38823fb 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
index 0059592c7408..f3f1368b8386 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n

From 3c6ddb58f670baa584b22eef761aade77bd81b16 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:02 -0800
Subject: [PATCH 0934/1303] refscale: Update due to x86 not supporting
 none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such refscale scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-3-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT | 3 ++-
 tools/testing/selftests/rcutorture/configs/refscale/TINY      | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
index 67f9d2998afd..1f215e17cbae 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY
index 759343980b80..9a11b578ff34 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n

From 78c2ce0fd6ddb6c87aaa56b0d49c70e17df21e6d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:03 -0800
Subject: [PATCH 0935/1303] scftorture: Update due to x86 not supporting
 none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such scftorture scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-4-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
index 6133f54ce2a7..f9621e2770a4 100644
--- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n

From 150bceb3e0a4a30950279d91ea0e8cc69a736742 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 18 Feb 2026 16:21:55 -0600
Subject: [PATCH 0936/1303] accel: ethosu: Fix job submit error clean-up
 refcount underflows

If the job submit fails before adding the job to the scheduler queue
such as when the GEM buffer bounds checks fail, then doing a
ethosu_job_put() results in a pm_runtime_put_autosuspend() without the
corresponding pm_runtime_resume_and_get(). The dma_fence_put()'s are
also unnecessary, but seem to be harmless.

Split the ethosu_job_cleanup() function into 2 parts for the before
and after the job is queued.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-1-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/accel/ethosu/ethosu_job.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c
index 8598a3634340..ec85f4156744 100644
--- a/drivers/accel/ethosu/ethosu_job.c
+++ b/drivers/accel/ethosu/ethosu_job.c
@@ -143,17 +143,10 @@ static int ethosu_job_push(struct ethosu_job *job)
 	return ret;
 }
 
-static void ethosu_job_cleanup(struct kref *ref)
+static void ethosu_job_err_cleanup(struct ethosu_job *job)
 {
-	struct ethosu_job *job = container_of(ref, struct ethosu_job,
-						refcount);
 	unsigned int i;
 
-	pm_runtime_put_autosuspend(job->dev->base.dev);
-
-	dma_fence_put(job->done_fence);
-	dma_fence_put(job->inference_done_fence);
-
 	for (i = 0; i < job->region_cnt; i++)
 		drm_gem_object_put(job->region_bo[i]);
 
@@ -162,6 +155,19 @@ static void ethosu_job_cleanup(struct kref *ref)
 	kfree(job);
 }
 
+static void ethosu_job_cleanup(struct kref *ref)
+{
+	struct ethosu_job *job = container_of(ref, struct ethosu_job,
+						refcount);
+
+	pm_runtime_put_autosuspend(job->dev->base.dev);
+
+	dma_fence_put(job->done_fence);
+	dma_fence_put(job->inference_done_fence);
+
+	ethosu_job_err_cleanup(job);
+}
+
 static void ethosu_job_put(struct ethosu_job *job)
 {
 	kref_put(&job->refcount, ethosu_job_cleanup);
@@ -454,12 +460,16 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file
 		}
 	}
 	ret = ethosu_job_push(ejob);
+	if (!ret) {
+		ethosu_job_put(ejob);
+		return 0;
+	}
 
 out_cleanup_job:
 	if (ret)
 		drm_sched_job_cleanup(&ejob->base);
 out_put_job:
-	ethosu_job_put(ejob);
+	ethosu_job_err_cleanup(ejob);
 
 	return ret;
 }

From 838ae99f9a77a5724ee6d4e7b7b1eb079147f888 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 18 Feb 2026 16:21:56 -0600
Subject: [PATCH 0937/1303] accel: ethosu: Fix NPU_OP_ELEMENTWISE validation
 with scalar

The NPU_OP_ELEMENTWISE instruction uses a scalar value for IFM2 if the
IFM2_BROADCAST "scalar" mode is set. It is a bit (7) on the u65 and
part of a field (bits 3:0) on the u85. The driver was hardcoded to the
u85.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-2-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/accel/ethosu/ethosu_gem.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index 668c71d5ff45..ff5e58944138 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -417,7 +417,10 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 				return ret;
 			break;
 		case NPU_OP_ELEMENTWISE:
-			use_ifm2 = !((st.ifm2.broadcast == 8) || (param == 5) ||
+			use_scale = ethosu_is_u65(edev) ?
+				    (st.ifm2.broadcast & 0x80) :
+				    (st.ifm2.broadcast == 8);
+			use_ifm2 = !(use_scale || (param == 5) ||
 				(param == 6) || (param == 7) || (param == 0x24));
 			use_ifm = st.ifm.broadcast != 8;
 			ret = calc_sizes_elemwise(ddev, info, cmd, &st, use_ifm, use_ifm2);

From 021f1b77f70d62351bba67b050b8d784641d817f Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 18 Feb 2026 16:21:57 -0600
Subject: [PATCH 0938/1303] accel: ethosu: Handle possible underflow in IFM
 size calculations

If the command stream has larger padding sizes than the IFM and OFM
diminsions, then the calculations will underflow to a negative value.
The result is a very large region bounds which is caught on submit, but
it's better to catch it earlier.

Current mesa ethosu driver has a signedness bug which resulted in
padding of 127 (the max) and triggers this issue.

Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-3-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/accel/ethosu/ethosu_gem.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index ff5e58944138..7994e7073903 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -245,11 +245,14 @@ static int calc_sizes(struct drm_device *ddev,
 			((st->ifm.stride_kernel >> 1) & 0x1) + 1;
 		u32 stride_x = ((st->ifm.stride_kernel >> 5) & 0x2) +
 			(st->ifm.stride_kernel & 0x1) + 1;
-		u32 ifm_height = st->ofm.height[2] * stride_y +
+		s32 ifm_height = st->ofm.height[2] * stride_y +
 			st->ifm.height[2] - (st->ifm.pad_top + st->ifm.pad_bottom);
-		u32 ifm_width  = st->ofm.width * stride_x +
+		s32 ifm_width = st->ofm.width * stride_x +
 			st->ifm.width - (st->ifm.pad_left + st->ifm.pad_right);
 
+		if (ifm_height < 0 || ifm_width < 0)
+			return -EINVAL;
+
 		len = feat_matrix_length(info, &st->ifm, ifm_width,
 					 ifm_height, st->ifm.depth);
 		dev_dbg(ddev->dev, "op %d: IFM:%d:0x%llx-0x%llx\n",

From 7e459c41264fdd87b096ede8da796a302d569722 Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Thu, 5 Mar 2026 23:51:16 +0530
Subject: [PATCH 0939/1303] drm/msm/a8xx: Fix ubwc config related to swizzling

To disable l2/l3 swizzling in A8x, set the respective bits in both
GRAS_NC_MODE_CNTL and RB_CCU_NC_MODE_CNTL registers. This is required
for Glymur where it is recommended to keep l2/l3 swizzling disabled.

Fixes: 288a93200892 ("drm/msm/adreno: Introduce A8x GPU Support")
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Message-ID: <20260305-a8xx-ubwc-fix-v1-1-d99b6da4c5a9@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a8xx_gpu.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
index 5a320f5bde41..b1887e0cf698 100644
--- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
@@ -310,11 +310,21 @@ static void a8xx_set_ubwc_config(struct msm_gpu *gpu)
 	hbb = cfg->highest_bank_bit - 13;
 	hbb_hi = hbb >> 2;
 	hbb_lo = hbb & 3;
-	a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5);
-	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5);
+
+	a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL,
+			hbb << 5 |
+			level3_swizzling_dis << 4 |
+			level2_swizzling_dis << 3);
+
+	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL,
+			hbb << 5 |
+			level3_swizzling_dis << 4 |
+			level2_swizzling_dis << 3);
 
 	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL,
 			yuvnotcomptofc << 6 |
+			level3_swizzling_dis << 5 |
+			level2_swizzling_dis << 4 |
 			hbb_hi << 3 |
 			hbb_lo << 1);
 

From 4ce71cea574658f5c5c7412b1a3cc54efe4f9b50 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Thu, 5 Mar 2026 18:17:07 +0800
Subject: [PATCH 0940/1303] drm/msm/dpu: Correct the SA8775P
 intr_underrun/intr_underrun index

The intr_underrun and intr_vsync indices have been swapped, just simply
corrects them.

Cc: stable@vger.kernel.org
Fixes: b139c80d181c ("drm/msm/dpu: Add SA8775P support")
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Yongxing Mou <yongxing.mou@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/709209/
Link: https://lore.kernel.org/r/20260305-mdss_catalog-v5-2-06678ac39ac7@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
index 0f7b4a224e4c..42cf3bd5a12a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
@@ -366,8 +366,8 @@ static const struct dpu_intf_cfg sa8775p_intf[] = {
 		.type = INTF_NONE,
 		.controller_id = MSM_DP_CONTROLLER_0,	/* pair with intf_0 for DP MST */
 		.prog_fetch_lines_worst_case = 24,
-		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
-		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
 	}, {
 		.name = "intf_7", .id = INTF_7,
 		.base = 0x3b000, .len = 0x280,

From 7403e87c138475a74e5176176778f391d847f42d Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@oss.qualcomm.com>
Date: Tue, 3 Mar 2026 11:03:11 +0200
Subject: [PATCH 0941/1303] dt-bindings: display: msm: Fix reg ranges and
 clocks on Glymur

The Glymur platform has four DisplayPort controllers. The hardware
supports four streams (MST) per controller. However, on Glymur the first
three controllers only have two streams wired to the display subsystem,
while the fourth controller operates in single-stream mode.

Add a dedicated clause for the Glymur compatible to require the register
ranges for all four stream blocks, while allowing either one pixel clock
(for the single-stream controller) or two pixel clocks (for the remaining
controllers).

Update the Glymur MDSS schema example by adding the missing p2, p3,
mst2link and mst3link register blocks. Without these, the bindings
validation fails. Also replace the made-up register addresses with the
actual addresses from the first controller to match the SoC devicetree
description.

Cc: stable@vger.kernel.org # v6.19
Fixes: 8f63bf908213 ("dt-bindings: display: msm: Document the Glymur DiplayPort controller")
Fixes: 1aee577bbc60 ("dt-bindings: display: msm: Document the Glymur Mobile Display SubSystem")
Signed-off-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/708518/
Link: https://lore.kernel.org/r/20260303-glymur-fix-dp-bindings-reg-clocks-v4-1-1ebd9c7c2cee@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 .../bindings/display/msm/dp-controller.yaml   | 21 ++++++++++++++++++-
 .../display/msm/qcom,glymur-mdss.yaml         | 16 ++++++++------
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
index ebda78db87a6..02ddfaab5f56 100644
--- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
@@ -253,7 +253,6 @@ allOf:
             enum:
               # these platforms support 2 streams MST on some interfaces,
               # others are SST only
-              - qcom,glymur-dp
               - qcom,sc8280xp-dp
               - qcom,x1e80100-dp
     then:
@@ -310,6 +309,26 @@ allOf:
           minItems: 6
           maxItems: 8
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              # these platforms support 2 streams MST on some interfaces,
+              # others are SST only, but all controllers have 4 ports
+              - qcom,glymur-dp
+    then:
+      properties:
+        reg:
+          minItems: 9
+          maxItems: 9
+        clocks:
+          minItems: 5
+          maxItems: 6
+        clocks-names:
+          minItems: 5
+          maxItems: 6
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
index 2329ed96e6cb..64dde43373ac 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
@@ -176,13 +176,17 @@ examples:
                 };
             };
 
-            displayport-controller@ae90000 {
+            displayport-controller@af54000 {
                 compatible = "qcom,glymur-dp";
-                reg = <0xae90000 0x200>,
-                      <0xae90200 0x200>,
-                      <0xae90400 0x600>,
-                      <0xae91000 0x400>,
-                      <0xae91400 0x400>;
+                reg = <0xaf54000 0x200>,
+                      <0xaf54200 0x200>,
+                      <0xaf55000 0xc00>,
+                      <0xaf56000 0x400>,
+                      <0xaf57000 0x400>,
+                      <0xaf58000 0x400>,
+                      <0xaf59000 0x400>,
+                      <0xaf5a000 0x600>,
+                      <0xaf5b000 0x600>;
 
                 interrupt-parent = <&mdss>;
                 interrupts = <12>;

From fd941c787cbb402e8ebd84336f2a0026d5d0724d Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Thu, 26 Feb 2026 20:29:57 +0800
Subject: [PATCH 0942/1303] drm/msm/dsi/phy: fix hardware revision

The hardware revision for TSMC 3nm-based Qualcomm SOCs should be 7.2,
this can be confirmed from REG_DSI_7nm_PHY_CMN_REVISION_ID0, the value
is 0x27, which means hardware revision is 7.2

No functional change.

Fixes: 1337d7ebfb6d ("drm/msm/dsi/phy: Add support for SM8750")
Suggested-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707414/
Link: https://lore.kernel.org/r/20260226122958.22555-2-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 8cb0db3a9880..01182442dfd6 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -51,8 +51,8 @@
 #define DSI_PHY_7NM_QUIRK_V4_3		BIT(3)
 /* Hardware is V5.2 */
 #define DSI_PHY_7NM_QUIRK_V5_2		BIT(4)
-/* Hardware is V7.0 */
-#define DSI_PHY_7NM_QUIRK_V7_0		BIT(5)
+/* Hardware is V7.2 */
+#define DSI_PHY_7NM_QUIRK_V7_2		BIT(5)
 
 struct dsi_pll_config {
 	bool enable_ssc;
@@ -143,7 +143,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config
 
 	if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_PRE_V4_1) {
 		config->pll_clock_inverters = 0x28;
-	} else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	} else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (pll_freq < 163000000ULL)
 			config->pll_clock_inverters = 0xa0;
 		else if (pll_freq < 175000000ULL)
@@ -284,7 +284,7 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll)
 	}
 
 	if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (pll->vco_current_rate < 1557000000ULL)
 			vco_config_1 = 0x08;
 		else
@@ -699,7 +699,7 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 	case MSM_DSI_PHY_MASTER:
 		pll_7nm->slave = pll_7nm_list[(pll_7nm->phy->id + 1) % DSI_MAX];
 		/* v7.0: Enable ATB_EN0 and alternate clock output to external phy */
-		if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)
+		if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)
 			writel(0x07, base + REG_DSI_7nm_PHY_CMN_CTRL_5);
 		break;
 	case MSM_DSI_PHY_SLAVE:
@@ -987,7 +987,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	/* Request for REFGEN READY */
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) ||
 	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		writel(0x1, phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10);
 		udelay(500);
 	}
@@ -1021,7 +1021,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 		lane_ctrl0 = 0x1f;
 	}
 
-	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (phy->cphy_mode) {
 			/* TODO: different for second phy */
 			vreg_ctrl_0 = 0x57;
@@ -1097,7 +1097,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 
 	/* program CMN_CTRL_4 for minor_ver 2 chipsets*/
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) ||
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) ||
 	    (readl(base + REG_DSI_7nm_PHY_CMN_REVISION_ID0) & (0xf0)) == 0x20)
 		writel(0x04, base + REG_DSI_7nm_PHY_CMN_CTRL_4);
 
@@ -1213,7 +1213,7 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 	/* Turn off REFGEN Vote */
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) ||
 	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		writel(0x0, base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10);
 		wmb();
 		/* Delay to ensure HW removes vote before PHY shut down */
@@ -1502,7 +1502,7 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_8750_cfgs = {
 #endif
 	.io_start = { 0xae95000, 0xae97000 },
 	.num_dsi_phy = 2,
-	.quirks = DSI_PHY_7NM_QUIRK_V7_0,
+	.quirks = DSI_PHY_7NM_QUIRK_V7_2,
 };
 
 const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = {
@@ -1525,5 +1525,5 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = {
 #endif
 	.io_start = { 0x9ac1000, 0x9ac4000 },
 	.num_dsi_phy = 2,
-	.quirks = DSI_PHY_7NM_QUIRK_V7_0,
+	.quirks = DSI_PHY_7NM_QUIRK_V7_2,
 };

From 4355b13d46f696d687f42b982efed7570e03e532 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Wed, 25 Feb 2026 18:34:20 +0100
Subject: [PATCH 0943/1303] dt-bindings: display/msm: qcom,sm8750-mdss: Fix
 model typo

Fix obvious model typo (SM8650->SM8750) in the description.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Fixes: 6b93840116df ("dt-bindings: display/msm: qcom,sm8750-mdss: Add SM8750")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707192/
Link: https://lore.kernel.org/r/20260225173419.125565-2-krzysztof.kozlowski@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 .../devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml       | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
index d55fda9a523e..a38c2261ef1a 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
@@ -10,7 +10,7 @@ maintainers:
   - Krzysztof Kozlowski <krzk@kernel.org>
 
 description:
-  SM8650 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like
+  SM8750 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like
   DPU display controller, DSI and DP interfaces etc.
 
 $ref: /schemas/display/msm/mdss-common.yaml#

From e174dd14bf0beac811a5201e370ab26ce8c67f23 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Tue, 24 Feb 2026 15:29:56 +0800
Subject: [PATCH 0944/1303] rust: kbuild: emit dep-info into $(depfile)
 directly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 295d8398c67e ("kbuild: specify output names separately for
each emission type from rustc"), the preferred pattern is to ask rustc to
emit dependency information into $(depfile) directly, and after commit
2185242faddd ("kbuild: remove sed commands after rustc rules"), the
post-processing to remove comments is no longer necessary as fixdep can
handle comments directly. Thus, emit dep-info into $(depfile) directly and
remove the mv and sed invocation.

This fixes the issue where a non-ignored .d file is emitted during
compilation and removed shortly afterwards.

[ Like Gary mentioned in Zulip, this likely happened due to rebasing
  the builds part of the old `syn` work I had. - Miguel ]

Reported-by: Onur Özkan <work@onurozkan.dev>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/syn.20artifact.20being.20tracked.20by.20git/with/575467879
Fixes: 7dbe46c0b11d ("rust: kbuild: add proc macro library support")
Signed-off-by: Gary Guo <gary@garyguo.net>
Tested-by: Onur Özkan <work@onurozkan.dev>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260224072957.214979-1-gary@garyguo.net
[ Reworded for a couple of typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/rust/Makefile b/rust/Makefile
index 629b3bdd2b20..1500993d7ecc 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -526,11 +526,9 @@ quiet_cmd_rustc_procmacrolibrary = $(RUSTC_OR_CLIPPY_QUIET) PL $@
       cmd_rustc_procmacrolibrary = \
 	$(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \
 		$(filter-out $(skip_flags),$(rust_common_flags) $(rustc_target_flags)) \
-		--emit=dep-info,link --crate-type rlib -O \
+		--emit=dep-info=$(depfile) --emit=link=$@ --crate-type rlib -O \
 		--out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \
-		--crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<; \
-	mv $(objtree)/$(obj)/$(patsubst lib%.rlib,%,$(notdir $@)).d $(depfile); \
-	sed -i '/^\#/d' $(depfile)
+		--crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<
 
 $(obj)/libproc_macro2.rlib: private skip_clippy = 1
 $(obj)/libproc_macro2.rlib: private rustc_target_flags = $(proc_macro2-flags)

From dda135077ecc9f15c407f094dcfe7800376be867 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Thu, 26 Feb 2026 15:21:11 +0000
Subject: [PATCH 0945/1303] rust: build: remap path to avoid absolute path

When building with an out directory (O=), absolute paths can end up in the
file name in `#[track_caller]` or the panic message. This is not desirable
as this leaks the exact path being used to build the kernel and means that
the same location can appear in two forms (relative or absolute).

This is reported by Asahi [1] and is being workaround in [2] previously to
force everything to be absolute path. Using absolute path for everything
solves the inconsistency, however it does not address the reproducibility
issue. So, fix this by remap all absolute paths to srctree to relative path
instead.

This is previously attempted in commit dbdffaf50ff9 ("kbuild, rust: use
-fremap-path-prefix to make paths relative") but that was reverted as
remapping debug info causes some tool (e.g. objdump) to be unable to find
sources. Therefore, use `--remap-path-scope` to only remap macros but leave
debuginfo untouched. `--remap-path-scope` is only stable in Rust 1.95, so
use `rustc-option` to detect its presence. This feature has been available
as  `-Zremap-path-scope` for all versions that we support; however due to
bugs in the Rust compiler, it does not work reliably until 1.94. I opted to
not enable it for 1.94 as it's just a single version that we missed.

This change can be validated by building a kernel with O=, strip debug info
on vmlinux, and then check if the absolute path exists in `strings
vmlinux`, e.g. `strings vmlinux |grep \/home`.

Reported-by: Janne Grunau <j@jannau.net>
Reported-by: Asahi Lina <lina+kernel@asahilina.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/Per-call-site.20data.20and.20lock.20class.20keys/near/572466559 [1]
Link: https://github.com/AsahiLinux/linux/commit/54ab88878869036c9d6620101bfe17a81e88c2f9 [2]
Signed-off-by: Gary Guo <gary@garyguo.net>
Acked-by: Nicolas Schier <nsc@kernel.org> # kbuild
Link: https://patch.msgid.link/20260226152112.3222886-1-gary@kernel.org
[ Reworded for few typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile      | 3 +++
 rust/Makefile | 5 +++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 2446085983f7..73a39592f112 100644
--- a/Makefile
+++ b/Makefile
@@ -1113,6 +1113,9 @@ KBUILD_CFLAGS += -fno-builtin-wcslen
 # change __FILE__ to the relative path to the source directory
 ifdef building_out_of_srctree
 KBUILD_CPPFLAGS += -fmacro-prefix-map=$(srcroot)/=
+ifeq ($(call rustc-option-yn, --remap-path-scope=macro),y)
+KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/= --remap-path-scope=macro
+endif
 endif
 
 # include additional Makefiles when needed
diff --git a/rust/Makefile b/rust/Makefile
index 1500993d7ecc..9801af2e1e02 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -148,7 +148,8 @@ doctests_modifiers_workaround := $(rustdoc_modifiers_workaround)$(if $(call rust
 quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
       cmd_rustdoc = \
 	OBJTREE=$(abspath $(objtree)) \
-	$(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=%,$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \
+	$(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=% --remap-path-scope=%, \
+			$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \
 		$(rustc_target_flags) -L$(objtree)/$(obj) \
 		-Zunstable-options --generate-link-to-definition \
 		--output $(rustdoc_output) \
@@ -334,7 +335,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
 	rm -rf $(objtree)/$(obj)/test/doctests/kernel; \
 	mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \
 	OBJTREE=$(abspath $(objtree)) \
-	$(RUSTDOC) --test $(filter-out --remap-path-prefix=%,$(rust_flags)) \
+	$(RUSTDOC) --test $(filter-out --remap-path-prefix=% --remap-path-scope=%,$(rust_flags)) \
 		-L$(objtree)/$(obj) --extern ffi --extern pin_init \
 		--extern kernel --extern build_error --extern macros \
 		--extern bindings --extern uapi \

From a075082a15e7f5c4889d0cbb51a4041c332cb00c Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Mon, 2 Mar 2026 15:04:14 +0100
Subject: [PATCH 0946/1303] rust: pin-init: internal: init: remove
 `#[disable_initialized_field_access]`

Gary noticed [1] that the initializer macros as well as the `[Pin]Init`
traits cannot support unaligned fields, since they use operations that
require aligned pointers. This means that any code using structs with
unaligned fields in pin-init is unsound.

By default, the `init!` macro generates references to initialized fields,
which makes the compiler check that those fields are aligned.  However,
we added the `#[disable_initialized_field_access]` attribute to avoid
this behavior in commit ceca298c53f9 ("rust: pin-init: internal: init:
add escape hatch for referencing initialized fields"). Thus remove the
`#[disable_initialized_field_access]` attribute from `init!`, which is
the only safe way to create an initializer handling unaligned fields.

If support for in-place initializing structs with unaligned fields is
required in the future, we could figure out a solution. This is tracked
in [2].

Reported-by: Gary Guo <gary@garyguo.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1]
Link: https://github.com/Rust-for-Linux/pin-init/issues/112 [2]
Fixes: ceca298c53f9 ("rust: pin-init: internal: init: add escape hatch for referencing initialized fields")
Signed-off-by: Benno Lossin <lossin@kernel.org>
Acked-by: Janne Grunau <j@jannau.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://patch.msgid.link/20260302140424.4097655-1-lossin@kernel.org
[ Adjusted tags and reworded as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 39 ++++++------------------------
 1 file changed, 8 insertions(+), 31 deletions(-)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index 42936f915a07..da53adc44ecf 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -62,7 +62,6 @@ fn ident(&self) -> Option<&Ident> {
 
 enum InitializerAttribute {
     DefaultError(DefaultErrorAttribute),
-    DisableInitializedFieldAccess,
 }
 
 struct DefaultErrorAttribute {
@@ -86,6 +85,7 @@ pub(crate) fn expand(
     let error = error.map_or_else(
         || {
             if let Some(default_error) = attrs.iter().fold(None, |acc, attr| {
+                #[expect(irrefutable_let_patterns)]
                 if let InitializerAttribute::DefaultError(DefaultErrorAttribute { ty }) = attr {
                     Some(ty.clone())
                 } else {
@@ -145,15 +145,7 @@ fn assert_zeroable<T: ?::core::marker::Sized>(_: *mut T)
     };
     // `mixed_site` ensures that the data is not accessible to the user-controlled code.
     let data = Ident::new("__data", Span::mixed_site());
-    let init_fields = init_fields(
-        &fields,
-        pinned,
-        !attrs
-            .iter()
-            .any(|attr| matches!(attr, InitializerAttribute::DisableInitializedFieldAccess)),
-        &data,
-        &slot,
-    );
+    let init_fields = init_fields(&fields, pinned, &data, &slot);
     let field_check = make_field_check(&fields, init_kind, &path);
     Ok(quote! {{
         // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return
@@ -236,7 +228,6 @@ fn get_init_kind(rest: Option<(Token![..], Expr)>, dcx: &mut DiagCtxt) -> InitKi
 fn init_fields(
     fields: &Punctuated<InitializerField, Token![,]>,
     pinned: bool,
-    generate_initialized_accessors: bool,
     data: &Ident,
     slot: &Ident,
 ) -> TokenStream {
@@ -272,13 +263,6 @@ fn init_fields(
                         unsafe { &mut (*#slot).#ident }
                     }
                 };
-                let accessor = generate_initialized_accessors.then(|| {
-                    quote! {
-                        #(#cfgs)*
-                        #[allow(unused_variables)]
-                        let #ident = #accessor;
-                    }
-                });
                 quote! {
                     #(#attrs)*
                     {
@@ -286,7 +270,9 @@ fn init_fields(
                         // SAFETY: TODO
                         unsafe { #write(::core::ptr::addr_of_mut!((*#slot).#ident), #value_ident) };
                     }
-                    #accessor
+                    #(#cfgs)*
+                    #[allow(unused_variables)]
+                    let #ident = #accessor;
                 }
             }
             InitializerKind::Init { ident, value, .. } => {
@@ -326,20 +312,15 @@ fn init_fields(
                         },
                     )
                 };
-                let accessor = generate_initialized_accessors.then(|| {
-                    quote! {
-                        #(#cfgs)*
-                        #[allow(unused_variables)]
-                        let #ident = #accessor;
-                    }
-                });
                 quote! {
                     #(#attrs)*
                     {
                         let #init = #value;
                         #value_init
                     }
-                    #accessor
+                    #(#cfgs)*
+                    #[allow(unused_variables)]
+                    let #ident = #accessor;
                 }
             }
             InitializerKind::Code { block: value, .. } => quote! {
@@ -466,10 +447,6 @@ fn parse(input: syn::parse::ParseStream<'_>) -> syn::Result<Self> {
                 if a.path().is_ident("default_error") {
                     a.parse_args::<DefaultErrorAttribute>()
                         .map(InitializerAttribute::DefaultError)
-                } else if a.path().is_ident("disable_initialized_field_access") {
-                    a.meta
-                        .require_path_only()
-                        .map(|_| InitializerAttribute::DisableInitializedFieldAccess)
                 } else {
                     Err(syn::Error::new_spanned(a, "unknown initializer attribute"))
                 }

From 580cc37b1de4fcd9997c48d7080e744533f09f36 Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Mon, 2 Mar 2026 15:04:15 +0100
Subject: [PATCH 0947/1303] rust: pin-init: internal: init: document
 load-bearing fact of field accessors

The functions `[Pin]Init::__[pinned_]init` and `ptr::write` called from
the `init!` macro require the passed pointer to be aligned. This fact is
ensured by the creation of field accessors to previously initialized
fields.

Since we missed this very important fact from the beginning [1],
document it in the code.

Link: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1]
Fixes: 90e53c5e70a6 ("rust: add pin-init API core")
Cc: <stable@vger.kernel.org> # 6.6.y, 6.12.y: 42415d163e5d: rust: pin-init: add references to previously initialized fields
Cc: <stable@vger.kernel.org> # 6.6.y, 6.12.y, 6.18.y, 6.19.y
Signed-off-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260302140424.4097655-2-lossin@kernel.org
[ Updated Cc: stable@ tags as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index da53adc44ecf..738f62c8105c 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -251,6 +251,10 @@ fn init_fields(
                 });
                 // Again span for better diagnostics
                 let write = quote_spanned!(ident.span()=> ::core::ptr::write);
+                // NOTE: the field accessor ensures that the initialized field is properly aligned.
+                // Unaligned fields will cause the compiler to emit E0793. We do not support
+                // unaligned fields since `Init::__init` requires an aligned pointer; the call to
+                // `ptr::write` below has the same requirement.
                 let accessor = if pinned {
                     let project_ident = format_ident!("__project_{ident}");
                     quote! {
@@ -278,6 +282,10 @@ fn init_fields(
             InitializerKind::Init { ident, value, .. } => {
                 // Again span for better diagnostics
                 let init = format_ident!("init", span = value.span());
+                // NOTE: the field accessor ensures that the initialized field is properly aligned.
+                // Unaligned fields will cause the compiler to emit E0793. We do not support
+                // unaligned fields since `Init::__init` requires an aligned pointer; the call to
+                // `ptr::write` below has the same requirement.
                 let (value_init, accessor) = if pinned {
                     let project_ident = format_ident!("__project_{ident}");
                     (

From f76a93241d71fbba8425e3967097b498c29264ed Mon Sep 17 00:00:00 2001
From: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Date: Tue, 3 Mar 2026 17:25:12 -0300
Subject: [PATCH 0948/1303] net: dsa: realtek: rtl8365mb: remove ifOutDiscards
 from rx_packets

rx_packets should report the number of frames successfully received:
unicast + multicast + broadcast. Subtracting ifOutDiscards (a TX
counter) is incorrect and can undercount RX packets. RX drops are
already reported via rx_dropped (e.g. etherStatsDropEvents), so
there is no need to adjust rx_packets.

This patch removes the subtraction of ifOutDiscards from rx_packets
in rtl8365mb_stats_update().

Link: https://lore.kernel.org/netdev/878777925.105015.1763423928520@mail.yahoo.com/
Fixes: 4af2950c50c8 ("net: dsa: realtek-smi: add rtl8365mb subdriver for RTL8365MB-VC")
Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260303-realtek_namiltd_fix2-v1-1-bfa433d3401e@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8365mb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index f938a3f701cc..31fa94dac627 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -1480,8 +1480,7 @@ static void rtl8365mb_stats_update(struct realtek_priv *priv, int port)
 
 	stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifInMulticastPkts] +
-			    cnt[RTL8365MB_MIB_ifInBroadcastPkts] -
-			    cnt[RTL8365MB_MIB_ifOutDiscards];
+			    cnt[RTL8365MB_MIB_ifInBroadcastPkts];
 
 	stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifOutMulticastPkts] +

From 048efe129a297256d3c2088cf8d79515ff5ec864 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Thu, 5 Mar 2026 21:57:06 -0300
Subject: [PATCH 0949/1303] smb: client: fix oops due to uninitialised var in
 smb2_unlink()

If SMB2_open_init() or SMB2_close_init() fails (e.g. reconnect), the
iovs set @rqst will be left uninitialised, hence calling
SMB2_open_free(), SMB2_close_free() or smb2_set_related() on them will
oops.

Fix this by initialising @close_iov and @open_iov before setting them
in @rqst.

Reported-by: Thiago Becker <tbecker@redhat.com>
Fixes: 1cf9f2a6a544 ("smb: client: handle unlink(2) of files open by different clients")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 1c4663ed7e69..5280c5c869ad 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1216,6 +1216,7 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	memset(resp_buftype, 0, sizeof(resp_buftype));
 	memset(rsp_iov, 0, sizeof(rsp_iov));
 
+	memset(open_iov, 0, sizeof(open_iov));
 	rqst[0].rq_iov = open_iov;
 	rqst[0].rq_nvec = ARRAY_SIZE(open_iov);
 
@@ -1240,14 +1241,15 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	creq = rqst[0].rq_iov[0].iov_base;
 	creq->ShareAccess = FILE_SHARE_DELETE_LE;
 
+	memset(&close_iov, 0, sizeof(close_iov));
 	rqst[1].rq_iov = &close_iov;
 	rqst[1].rq_nvec = 1;
 
 	rc = SMB2_close_init(tcon, server, &rqst[1],
 			     COMPOUND_FID, COMPOUND_FID, false);
-	smb2_set_related(&rqst[1]);
 	if (rc)
 		goto err_free;
+	smb2_set_related(&rqst[1]);
 
 	if (retries) {
 		/* Back-off before retry */

From 8565617a8599dd17b96b7bf7e1eb19809ac6ae5e Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Fri, 16 Jan 2026 10:57:31 +0100
Subject: [PATCH 0950/1303] KVM: riscv: Fix Spectre-v1 in APLIC interrupt
 handling

Guests can control IRQ indices via MMIO. Sanitize them with
array_index_nospec() to prevent speculative out-of-bounds access
to the aplic->irqs[] array.

Similar to arm64 commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible
spectre-v1 in vgic_get_irq()") and x86 commit 8c86405f606c ("KVM: x86:
Protect ioapic_read_indirect() from Spectre-v1/L1TF attacks").

Fixes: 74967aa208e2 ("RISC-V: KVM: Add in-kernel emulation of AIA APLIC")
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260116095731.24555-1-lukas.gerlach@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_aplic.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index d1e50bf5c351..3464f3351df7 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -10,6 +10,7 @@
 #include <linux/irqchip/riscv-aplic.h>
 #include <linux/kvm_host.h>
 #include <linux/math.h>
+#include <linux/nospec.h>
 #include <linux/spinlock.h>
 #include <linux/swab.h>
 #include <kvm/iodev.h>
@@ -45,7 +46,7 @@ static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return 0;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = irqd->sourcecfg;
@@ -61,7 +62,7 @@ static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	if (val & APLIC_SOURCECFG_D)
 		val = 0;
@@ -81,7 +82,7 @@ static u32 aplic_read_target(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return 0;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = irqd->target;
@@ -97,7 +98,7 @@ static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	val &= APLIC_TARGET_EIID_MASK |
 	       (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) |
@@ -116,7 +117,7 @@ static bool aplic_read_pending(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false;
@@ -132,7 +133,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -170,7 +171,7 @@ static bool aplic_read_enabled(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false;
@@ -186,7 +187,7 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	if (enabled)
@@ -205,7 +206,7 @@ static bool aplic_read_input(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -254,7 +255,7 @@ static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last)
 	for (irq = first; irq <= last; irq++) {
 		if (!irq || aplic->nr_irqs <= irq)
 			continue;
-		irqd = &aplic->irqs[irq];
+		irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 		raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -283,7 +284,7 @@ int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level)
 
 	if (!aplic || !source || (aplic->nr_irqs <= source))
 		return -ENODEV;
-	irqd = &aplic->irqs[source];
+	irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)];
 	ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false;
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);

From dec9ed9944349643874d482238ca2437d4f47b61 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Mon, 2 Feb 2026 04:00:59 +0000
Subject: [PATCH 0951/1303] RISC-V: KVM: Fix use-after-free in
 kvm_riscv_gstage_get_leaf()

While fuzzing KVM on RISC-V, a use-after-free was observed in
kvm_riscv_gstage_get_leaf(),  where ptep_get() dereferences a
freed gstage page table page during gfn unmap.

The crash manifests as:
  use-after-free in ptep_get include/linux/pgtable.h:340 [inline]
  use-after-free in kvm_riscv_gstage_get_leaf arch/riscv/kvm/gstage.c:89
  Call Trace:
    ptep_get include/linux/pgtable.h:340 [inline]
    kvm_riscv_gstage_get_leaf+0x2ea/0x358 arch/riscv/kvm/gstage.c:89
    kvm_riscv_gstage_unmap_range+0xf0/0x308 arch/riscv/kvm/gstage.c:265
    kvm_unmap_gfn_range+0x168/0x1fc arch/riscv/kvm/mmu.c:256
    kvm_mmu_unmap_gfn_range virt/kvm/kvm_main.c:724 [inline]
  page last free pid 808 tgid 808 stack trace:
    kvm_riscv_mmu_free_pgd+0x1b6/0x26a arch/riscv/kvm/mmu.c:457
    kvm_arch_flush_shadow_all+0x1a/0x24 arch/riscv/kvm/mmu.c:134
    kvm_flush_shadow_all virt/kvm/kvm_main.c:344 [inline]

The UAF is caused by gstage page table walks running concurrently with
gstage pgd teardown. In particular, kvm_unmap_gfn_range() can traverse
gstage page tables while kvm_arch_flush_shadow_all() frees the pgd,
leading to use-after-free of page table pages.

Fix the issue by serializing gstage unmap and pgd teardown with
kvm->mmu_lock. Holding mmu_lock ensures that gstage page tables
remain valid for the duration of unmap operations and prevents
concurrent frees.

This matches existing RISC-V KVM usage of mmu_lock to protect gstage
map/unmap operations, e.g. kvm_riscv_mmu_iounmap.

Fixes: dd82e35638d67f ("RISC-V: KVM: Factor-out g-stage page table management")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260202040059.1801167-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/mmu.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 0b75eb2a1820..87c8f41482c5 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -245,6 +245,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	struct kvm_gstage gstage;
+	bool mmu_locked;
 
 	if (!kvm->arch.pgd)
 		return false;
@@ -253,9 +254,12 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	gstage.flags = 0;
 	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
 	gstage.pgd = kvm->arch.pgd;
+	mmu_locked = spin_trylock(&kvm->mmu_lock);
 	kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT,
 				     (range->end - range->start) << PAGE_SHIFT,
 				     range->may_block);
+	if (mmu_locked)
+		spin_unlock(&kvm->mmu_lock);
 	return false;
 }
 

From c28eb189e481f5dac993d1907710716a9b561890 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Thu, 26 Feb 2026 08:51:19 +0000
Subject: [PATCH 0952/1303] RISC-V: KVM: Fix null pointer dereference in
 kvm_riscv_vcpu_aia_rmw_topei()

kvm_riscv_vcpu_aia_rmw_topei() assumes that the per-vCPU IMSIC state has
been initialized once AIA is reported as available and initialized at
the VM level. This assumption does not always hold.

Under fuzzed ioctl sequences, a guest may access the IMSIC TOPEI CSR
before the vCPU IMSIC state is set up. In this case,
vcpu->arch.aia_context.imsic_state is still NULL, and the TOPEI RMW path
dereferences it unconditionally, leading to a host kernel crash.

The crash manifests as:
  Unable to handle kernel paging request at virtual address
  dfffffff0000000e
  ...
  kvm_riscv_vcpu_aia_imsic_rmw arch/riscv/kvm/aia_imsic.c:909
  kvm_riscv_vcpu_aia_rmw_topei arch/riscv/kvm/aia.c:231
  csr_insn arch/riscv/kvm/vcpu_insn.c:208
  system_opcode_insn arch/riscv/kvm/vcpu_insn.c:281
  kvm_riscv_vcpu_virtual_insn arch/riscv/kvm/vcpu_insn.c:355
  kvm_riscv_vcpu_exit arch/riscv/kvm/vcpu_exit.c:230
  kvm_arch_vcpu_ioctl_run arch/riscv/kvm/vcpu.c:1008
  ...

Fix this by explicitly checking whether the vCPU IMSIC state has been
initialized before handling TOPEI CSR accesses. If not, forward the CSR
emulation to user space.

Fixes: db8b7e97d6137 ("RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260226085119.643295-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_imsic.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 06752fa24798..8786f52cf65a 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -908,6 +908,10 @@ int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel,
 	int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC;
 	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
 
+	/* If IMSIC vCPU state not initialized then forward to user space */
+	if (!imsic)
+		return KVM_INSN_EXIT_TO_USER_SPACE;
+
 	if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) {
 		/* Read pending and enabled interrupt with highest priority */
 		topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix,

From 5c1bb07871119eae6434c640e5e645a74d54a222 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?=
 <radim.krcmar@oss.qualcomm.com>
Date: Fri, 27 Feb 2026 13:46:16 +0000
Subject: [PATCH 0953/1303] RISC-V: KVM: fix off-by-one array access in SBI PMU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The indexed array only has RISCV_KVM_MAX_COUNTERS elements.
The out-of-bound access could have been performed by a guest,
but it could only access another guest accessible data.

Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf")
Signed-off-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260227134617.23378-1-radim.krcmar@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index 4d8d5e9aa53d..aec6b293968b 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -520,7 +520,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx,
 {
 	struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu);
 
-	if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) {
+	if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) {
 		retdata->err_val = SBI_ERR_INVALID_PARAM;
 		return 0;
 	}

From 721ead7757125d66ec9b4ad98939a13d25e0b473 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Mon, 2 Mar 2026 13:27:03 +0000
Subject: [PATCH 0954/1303] RISC-V: KVM: Fix use-after-free in
 kvm_riscv_aia_aplic_has_attr()

Fuzzer reports a KASAN use-after-free bug triggered by a race
between KVM_HAS_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls on
the AIA device. The root cause is that aia_has_attr() invokes
kvm_riscv_aia_aplic_has_attr() without holding dev->kvm->lock, while
a concurrent aia_set_attr() may call aia_init() under that lock. When
aia_init() fails after kvm_riscv_aia_aplic_init() has succeeded, it
calls kvm_riscv_aia_aplic_cleanup() in its fail_cleanup_imsics path,
which frees both aplic_state and aplic_state->irqs. The concurrent
has_attr path can then dereference the freed aplic->irqs in
aplic_read_pending():
	irqd = &aplic->irqs[irq];   /* UAF here */

KASAN report:
 BUG: KASAN: slab-use-after-free in aplic_read_pending
             arch/riscv/kvm/aia_aplic.c:119 [inline]
 BUG: KASAN: slab-use-after-free in aplic_read_pending_word
             arch/riscv/kvm/aia_aplic.c:351 [inline]
 BUG: KASAN: slab-use-after-free in aplic_mmio_read_offset
             arch/riscv/kvm/aia_aplic.c:406
 Read of size 8 at addr ff600000ba965d58 by task 9498
 Call Trace:
  aplic_read_pending arch/riscv/kvm/aia_aplic.c:119 [inline]
  aplic_read_pending_word arch/riscv/kvm/aia_aplic.c:351 [inline]
  aplic_mmio_read_offset arch/riscv/kvm/aia_aplic.c:406
  kvm_riscv_aia_aplic_has_attr arch/riscv/kvm/aia_aplic.c:566
  aia_has_attr arch/riscv/kvm/aia_device.c:469
 allocated by task 9473:
  kvm_riscv_aia_aplic_init arch/riscv/kvm/aia_aplic.c:583
  aia_init arch/riscv/kvm/aia_device.c:248 [inline]
  aia_set_attr arch/riscv/kvm/aia_device.c:334
 freed by task 9473:
  kvm_riscv_aia_aplic_cleanup arch/riscv/kvm/aia_aplic.c:644
  aia_init arch/riscv/kvm/aia_device.c:292 [inline]
  aia_set_attr arch/riscv/kvm/aia_device.c:334

Fix this race by acquiring dev->kvm->lock in aia_has_attr() before
calling kvm_riscv_aia_aplic_has_attr(), consistent with the locking
pattern used in aia_get_attr() and aia_set_attr().

Fixes: 289a007b98b06d ("RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip")
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260302132703.1721415-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index b195a93add1c..fb901947aefe 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -437,7 +437,7 @@ static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 
 static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
-	int nr_vcpus;
+	int nr_vcpus, r = -ENXIO;
 
 	switch (attr->group) {
 	case KVM_DEV_RISCV_AIA_GRP_CONFIG:
@@ -466,12 +466,15 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		}
 		break;
 	case KVM_DEV_RISCV_AIA_GRP_APLIC:
-		return kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr);
+		mutex_lock(&dev->kvm->lock);
+		r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr);
+		mutex_unlock(&dev->kvm->lock);
+		break;
 	case KVM_DEV_RISCV_AIA_GRP_IMSIC:
 		return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
 	}
 
-	return -ENXIO;
+	return r;
 }
 
 struct kvm_device_ops kvm_riscv_aia_device_ops = {

From 7120a9d9e0232ad3c661a100973c57328f462b80 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Wed, 4 Mar 2026 08:08:04 +0000
Subject: [PATCH 0955/1303] RISC-V: KVM: Fix potential UAF in
 kvm_riscv_aia_imsic_has_attr()

The KVM_DEV_RISCV_AIA_GRP_APLIC branch of aia_has_attr() was identified
to have a race condition with concurrent KVM_SET_DEVICE_ATTR ioctls,
leading to a use-after-free bug.

Upon analyzing the code, it was discovered that the
KVM_DEV_RISCV_AIA_GRP_IMSIC branch of aia_has_attr() suffers from the same
lack of synchronization. It invokes kvm_riscv_aia_imsic_has_attr() without
holding dev->kvm->lock.

While aia_has_attr() is running, a concurrent aia_set_attr() could call
aia_init() under the dev->kvm->lock. If aia_init() fails, it may trigger
kvm_riscv_vcpu_aia_imsic_cleanup(), which frees imsic_state. Without proper
locking, kvm_riscv_aia_imsic_has_attr() could attempt to access imsic_state
while it is being deallocated.

Although this specific path has not yet been reported by a fuzzer, it
is logically identical to the APLIC issue. Fix this by acquiring the
dev->kvm->lock before calling kvm_riscv_aia_imsic_has_attr(), ensuring
consistency with the locking pattern used for other AIA attribute groups.

Fixes: 5463091a51cf ("RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260304080804.2281721-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index fb901947aefe..9a45c85239fe 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -471,7 +471,10 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		mutex_unlock(&dev->kvm->lock);
 		break;
 	case KVM_DEV_RISCV_AIA_GRP_IMSIC:
-		return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
+		mutex_lock(&dev->kvm->lock);
+		r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
+		mutex_unlock(&dev->kvm->lock);
+		break;
 	}
 
 	return r;

From b342166cbcf96a8c846db96529e75dc2d2420d58 Mon Sep 17 00:00:00 2001
From: Wang Yechao <wang.yechao255@zte.com.cn>
Date: Thu, 26 Feb 2026 19:12:31 +0800
Subject: [PATCH 0956/1303] RISC-V: KVM: Skip THP support check during dirty
 logging

When dirty logging is enabled, guest stage mappings are forced to
PAGE_SIZE granularity. Changing the mapping page size at this point
is incorrect.

Fixes: ed7ae7a34bea ("RISC-V: KVM: Transparent huge page support")
Signed-off-by: Wang Yechao <wang.yechao255@zte.com.cn>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260226191231140_X1Juus7s2kgVlc0ZyW_K@zte.com.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 87c8f41482c5..088d33ba90ed 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -539,7 +539,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		goto out_unlock;
 
 	/* Check if we are backed by a THP and thus use block mapping if possible */
-	if (vma_pagesize == PAGE_SIZE)
+	if (!logging && (vma_pagesize == PAGE_SIZE))
 		vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa);
 
 	if (writable) {

From f9e26fc325411a34555ad07ddf0a19ff72ea06d4 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:41 +0100
Subject: [PATCH 0957/1303] KVM: riscv: Fix Spectre-v1 in ONE_REG register
 access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled register indices from the ONE_REG ioctl are used to
index into arrays of register values. Sanitize them with
array_index_nospec() to prevent speculative out-of-bounds access.

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-1-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index e7ab6cb00646..a4c8703a96a9 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
@@ -127,6 +128,7 @@ static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *g
 	    kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr))
 		return -ENOENT;
 
+	kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr));
 	*guest_ext = kvm_isa_ext_arr[kvm_ext];
 	switch (*guest_ext) {
 	case RISCV_ISA_EXT_SMNPM:
@@ -443,13 +445,16 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    KVM_REG_RISCV_CORE);
+	unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long);
 	unsigned long reg_val;
 
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
 		reg_val = cntx->sepc;
 	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
@@ -476,13 +481,16 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    KVM_REG_RISCV_CORE);
+	unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long);
 	unsigned long reg_val;
 
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
@@ -507,10 +515,13 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu,
 					  unsigned long *out_val)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		kvm_riscv_vcpu_flush_interrupts(vcpu);
 		*out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
@@ -526,10 +537,13 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
 					  unsigned long reg_val)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		reg_val &= VSIP_VALID_MASK;
 		reg_val <<= VSIP_TO_HVIP_SHIFT;
@@ -548,11 +562,14 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu,
 						   unsigned long reg_val)
 {
 	struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
+		sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) /
-		sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -EINVAL;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	((unsigned long *)csr)[reg_num] = reg_val;
 	return 0;
 }
@@ -562,11 +579,14 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu,
 					    unsigned long *out_val)
 {
 	struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
+		sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) /
-		sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -EINVAL;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	*out_val = ((unsigned long *)csr)[reg_num];
 	return 0;
 }

From ec87a82ca8740891bce9e93e79ea2cd6c2d70ac8 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:42 +0100
Subject: [PATCH 0958/1303] KVM: riscv: Fix Spectre-v1 in AIA CSR access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled indices are used to access AIA CSR registers.
Sanitize them with array_index_nospec() to prevent speculative
out-of-bounds access.

Similar to x86 commit 8c86405f606c ("KVM: x86: Protect
ioapic_read_indirect() from Spectre-v1/L1TF attacks") and arm64
commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible spectre-v1
in vgic_get_irq()").

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-2-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index cac3c2b51d72..38de97d2f5b8 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -13,6 +13,7 @@
 #include <linux/irqchip/riscv-imsic.h>
 #include <linux/irqdomain.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
 #include <asm/cpufeature.h>
@@ -182,10 +183,13 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
 			       unsigned long *out_val)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	*out_val = 0;
 	if (kvm_riscv_aia_available())
 		*out_val = ((unsigned long *)csr)[reg_num];
@@ -198,10 +202,13 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 			       unsigned long val)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (kvm_riscv_aia_available()) {
 		((unsigned long *)csr)[reg_num] = val;
 

From 8f0c15c4b14f27dd9bd35971adb9c908241f2f63 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:43 +0100
Subject: [PATCH 0959/1303] KVM: riscv: Fix Spectre-v1 in floating-point
 register access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled indices are used to index into floating-point registers.
Sanitize them with array_index_nospec() to prevent speculative
out-of-bounds access.

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-3-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_fp.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
index 030904d82b58..bd5a9e7e7165 100644
--- a/arch/riscv/kvm/vcpu_fp.c
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 #include <asm/cpufeature.h>
 
@@ -93,9 +94,11 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
 			reg_val = &cntx->fp.f.fcsr;
 		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
-			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) {
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.f.f));
 			reg_val = &cntx->fp.f.f[reg_num];
-		else
+		} else
 			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
@@ -107,6 +110,8 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
 			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 				return -EINVAL;
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.d.f));
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
 			return -ENOENT;
@@ -138,9 +143,11 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
 			reg_val = &cntx->fp.f.fcsr;
 		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
-			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) {
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.f.f));
 			reg_val = &cntx->fp.f.f[reg_num];
-		else
+		} else
 			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
@@ -152,6 +159,8 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
 			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 				return -EINVAL;
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.d.f));
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
 			return -ENOENT;

From 2dda6a9e09ee4f3c30ea72ba949a6ea781205e3a Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:44 +0100
Subject: [PATCH 0960/1303] KVM: riscv: Fix Spectre-v1 in PMU counter access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Guest-controlled counter indices received via SBI ecalls are used to
index into the PMC array. Sanitize them with array_index_nospec()
to prevent speculative out-of-bounds access.

Similar to x86 commit 13c5183a4e64 ("KVM: x86: Protect MSR-based
index computations in pmu.h from Spectre-v1/L1TF attacks").

Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf")
Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-4-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_pmu.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index aec6b293968b..e873430e596b 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/perf/riscv_pmu.h>
 #include <asm/csr.h>
 #include <asm/kvm_vcpu_sbi.h>
@@ -87,7 +88,8 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 
 static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code)
 {
-	return hw_event_perf_map[sbi_event_code];
+	return hw_event_perf_map[array_index_nospec(sbi_event_code,
+						    SBI_PMU_HW_GENERAL_MAX)];
 }
 
 static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code)
@@ -218,6 +220,7 @@ static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return -EINVAL;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[cidx];
 
 	if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW)
@@ -244,6 +247,7 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return -EINVAL;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[cidx];
 
 	if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) {
@@ -525,6 +529,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return 0;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	retdata->out_val = kvpmu->pmc[cidx].cinfo.value;
 
 	return 0;
@@ -559,7 +564,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 	}
 	/* Start the counters that have been configured and requested by the guest */
 	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
-		pmc_index = i + ctr_base;
+		pmc_index = array_index_nospec(i + ctr_base,
+					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
 			continue;
 		/* The guest started the counter again. Reset the overflow status */
@@ -630,7 +636,8 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 
 	/* Stop the counters that have been configured and requested by the guest */
 	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
-		pmc_index = i + ctr_base;
+		pmc_index = array_index_nospec(i + ctr_base,
+					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
 			continue;
 		pmc = &kvpmu->pmc[pmc_index];
@@ -761,6 +768,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba
 		}
 	}
 
+	ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[ctr_idx];
 	pmc->idx = ctr_idx;
 

From 45700a743af3b7402cb7238860a25c62f0498ab4 Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:47 +0530
Subject: [PATCH 0961/1303] RISC-V: KVM: Fix error code returned for Smstateen
 ONE_REG

Return -ENOENT for Smstateen ONE_REG when:
1) Smstateen is not enabled for a VCPU
2) ONE_REG id is out of range

This will make Smstateen ONE_REG error codes consistent
with other ONE_REG interfaces of KVM RISC-V.

Fixes: c04913f2b54e ("RISCV: KVM: Add sstateen0 to ONE_REG")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-2-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index a4c8703a96a9..45ecc0082e90 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -565,8 +565,10 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu,
 	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
 		sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN))
+		return -ENOENT;
 	if (reg_num >= regs_max)
-		return -EINVAL;
+		return -ENOENT;
 
 	reg_num = array_index_nospec(reg_num, regs_max);
 
@@ -582,8 +584,10 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu,
 	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
 		sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN))
+		return -ENOENT;
 	if (reg_num >= regs_max)
-		return -EINVAL;
+		return -ENOENT;
 
 	reg_num = array_index_nospec(reg_num, regs_max);
 
@@ -615,10 +619,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, &reg_val);
 		break;
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
-		rc = -EINVAL;
-		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
-			rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num,
-							      &reg_val);
+		rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, &reg_val);
 		break;
 	default:
 		rc = -ENOENT;
@@ -660,10 +661,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val);
 		break;
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
-		rc = -EINVAL;
-		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
-			rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num,
-							      reg_val);
+		rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val);
 		break;
 	default:
 		rc = -ENOENT;

From 24433b2b5c74a9fee7baa3a97a1947446868901d Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:48 +0530
Subject: [PATCH 0962/1303] RISC-V: KVM: Fix error code returned for Ssaia
 ONE_REG

Return -ENOENT for Ssaia ONE_REG when Ssaia is not enabled
for a VCPU.

This will make Ssaia ONE_REG error codes consistent with
other ONE_REG interfaces of KVM RISC-V.

Fixes: 2a88f38cd58d ("RISC-V: KVM: return ENOENT in *_one_reg() when reg is unknown")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-3-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 38de97d2f5b8..5ec503288555 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -185,6 +185,8 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
+		return -ENOENT;
 	if (reg_num >= regs_max)
 		return -ENOENT;
 
@@ -204,6 +206,8 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
+		return -ENOENT;
 	if (reg_num >= regs_max)
 		return -ENOENT;
 

From c61ec3e8cc5d46fa269434a9ec16ca36d362e0dd Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:49 +0530
Subject: [PATCH 0963/1303] RISC-V: KVM: Check host Ssaia extension when
 creating AIA irqchip

The KVM user-space may create KVM AIA irqchip before checking
VCPU Ssaia extension availability so KVM AIA irqchip must fail
when host does not have Ssaia extension.

Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-4-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 9a45c85239fe..49c71d3cdb00 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -11,6 +11,7 @@
 #include <linux/irqchip/riscv-imsic.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
+#include <linux/cpufeature.h>
 
 static int aia_create(struct kvm_device *dev, u32 type)
 {
@@ -22,6 +23,9 @@ static int aia_create(struct kvm_device *dev, u32 type)
 	if (irqchip_in_kernel(kvm))
 		return -EEXIST;
 
+	if (!riscv_isa_extension_available(NULL, SSAIA))
+		return -ENODEV;
+
 	ret = -EBUSY;
 	if (kvm_trylock_all_vcpus(kvm))
 		return ret;

From 54fcd2f95f8d216183965a370ec69e1aab14f5da Mon Sep 17 00:00:00 2001
From: Carlos Maiolino <cem@kernel.org>
Date: Wed, 4 Mar 2026 19:54:27 +0100
Subject: [PATCH 0964/1303] xfs: fix returned valued from xfs_defer_can_append

xfs_defer_can_append returns a bool, it shouldn't be returning
a NULL.

Found by code inspection.

Fixes: 4dffb2cbb483 ("xfs: allow pausing of pending deferred work items")
Cc: <stable@vger.kernel.org> # v6.8
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Souptick Joarder <souptick.joarder@hpe.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_defer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 472c261163ed..c6909716b041 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -809,7 +809,7 @@ xfs_defer_can_append(
 
 	/* Paused items cannot absorb more work */
 	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
-		return NULL;
+		return false;
 
 	/* Already full? */
 	if (ops->max_items && dfp->dfp_count >= ops->max_items)

From ee0e6e69a772d601e152e5368a1da25d656122a8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 5 Mar 2026 18:48:05 -0800
Subject: [PATCH 0965/1303] ata: libata-eh: Fix detection of deferred qc
 timeouts

If the ata_qc_for_each_raw() loop finishes without finding a matching SCSI
command for any QC, the variable qc will hold a pointer to the last element
examined, which has the tag i == ATA_MAX_QUEUE - 1. This qc can match the
port deferred QC (ap->deferred_qc).

If that happens, the condition qc == ap->deferred_qc evaluates to true
despite the loop not breaking with a match on the SCSI command for this QC.
In that case, the error handler mistakenly intercepts a command that has
not been issued yet and that has not timed out, and thus erroneously
returning a timeout error.

Fix the problem by checking for i < ATA_MAX_QUEUE in addition to
qc == ap->deferred_qc.

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Assisted-by: Gemini:gemini-3.1-pro
Fixes: eddb98ad9364 ("ata: libata-eh: correctly handle deferred qc timeouts")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
[cassel: modified commit log as suggested by Damien]
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-eh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 563432400f72..23be85418b3b 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -647,7 +647,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 				break;
 		}
 
-		if (qc == ap->deferred_qc) {
+		if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) {
 			/*
 			 * This is a deferred command that timed out while
 			 * waiting for the command queue to drain. Since the qc

From 8e732934fb81282be41602550e7e07baf265e972 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 3 Mar 2026 23:36:10 +0100
Subject: [PATCH 0966/1303] parisc: Increase initial mapping to 64 MB with
 KALLSYMS

The 32MB initial kernel mapping can become too small when CONFIG_KALLSYMS
is used. Increase the mapping to 64 MB in this case.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/include/asm/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 2c139a4dbf4b..17afe7a59edf 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -85,7 +85,7 @@ extern void __update_cache(pte_t pte);
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#if defined(CONFIG_64BIT)
+#if defined(CONFIG_64BIT) || defined(CONFIG_KALLSYMS)
 #define KERNEL_INITIAL_ORDER	26	/* 1<<26 = 64MB */
 #else
 #define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */

From 17c144f1104bfc29a3ce3f7d0931a1bfb7a3558c Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 3 Mar 2026 23:36:11 +0100
Subject: [PATCH 0967/1303] parisc: Check kernel mapping earlier at bootup

The check if the initial mapping is sufficient needs to happen much
earlier during bootup. Move this test directly to the start_parisc()
function and use native PDC iodc functions to print the warning, because
panic() and printk() are not functional yet.

This fixes boot when enabling various KALLSYSMS options which need
much more space.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/kernel/setup.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index ace483b6f19a..d3e17a7a8901 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -120,14 +120,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	printk(KERN_CONT ".\n");
 
-	/*
-	 * Check if initial kernel page mappings are sufficient.
-	 * panic early if not, else we may access kernel functions
-	 * and variables which can't be reached.
-	 */
-	if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
-		panic("KERNEL_INITIAL_ORDER too small!");
-
 #ifdef CONFIG_64BIT
 	if(parisc_narrow_firmware) {
 		printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n");
@@ -279,6 +271,18 @@ void __init start_parisc(void)
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
 
+	/*
+	 * Check if initial kernel page mapping is sufficient.
+	 * Print warning if not, because we may access kernel functions and
+	 * variables which can't be reached yet through the initial mappings.
+	 * Note that the panic() and printk() functions are not functional
+	 * yet, so we need to use direct iodc() firmware calls instead.
+	 */
+	const char warn1[] = "CRITICAL: Kernel may crash because "
+			     "KERNEL_INITIAL_ORDER is too small.\n";
+	if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
+		pdc_iodc_print(warn1, sizeof(warn1) - 1);
+
 	/* check QEMU/SeaBIOS marker in PAGE0 */
 	running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
 

From 8475d8fe21ec9c7eb2faca555fbc5b68cf0d2597 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 4 Mar 2026 22:24:18 +0100
Subject: [PATCH 0968/1303] parisc: Fix initial page table creation for boot

The KERNEL_INITIAL_ORDER value defines the initial size (usually 32 or
64 MB) of the page table during bootup. Up until now the whole area was
initialized with PTE entries, but there was no check if we filled too
many entries.  Change the code to fill up with so many entries that the
"_end" symbol can be reached by the kernel, but not more entries than
actually fit into the initial PTE tables.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/kernel/head.S | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index 96e0264ac961..9188c8d87437 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -56,6 +56,7 @@ ENTRY(parisc_kernel_start)
 
 	.import __bss_start,data
 	.import __bss_stop,data
+	.import __end,data
 
 	load32		PA(__bss_start),%r3
 	load32		PA(__bss_stop),%r4
@@ -149,7 +150,11 @@ $cpu_ok:
 	 * everything ... it will get remapped correctly later */
 	ldo		0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */
 	load32		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
-	load32		PA(pg0),%r1
+	load32		PA(_end),%r1
+	SHRREG		%r1,PAGE_SHIFT,%r1  /* %r1 is PFN count for _end symbol */
+	cmpb,<<,n	%r11,%r1,1f
+	copy		%r1,%r11	/* %r1 PFN count smaller than %r11 */
+1:	load32		PA(pg0),%r1
 
 $pgt_fill_loop:
 	STREGM          %r3,ASM_PTE_ENTRY_SIZE(%r1)

From 244acf1976b889b80b234982a70e9550c6f0bab7 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Wed, 4 Mar 2026 16:22:22 +0000
Subject: [PATCH 0969/1303] KVM: arm64: Fix vma_shift staleness on nested
 hwpoison path

When user_mem_abort() handles a nested stage-2 fault, it truncates
vma_pagesize to respect the guest's mapping size. However, the local
variable vma_shift is never updated to match this new size.

If the underlying host page turns out to be hardware poisoned,
kvm_send_hwpoison_signal() is called with the original, larger
vma_shift instead of the actual mapping size. This signals incorrect
poison boundaries to userspace and breaks hugepage memory poison
containment for nested VMs.

Update vma_shift to match the truncated vma_pagesize when operating
on behalf of a nested hypervisor.

Fixes: fd276e71d1e7 ("KVM: arm64: nv: Handle shadow stage 2 page faults")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260304162222.836152-3-tabba@google.com
[maz: simplified vma_shift assignment from the original patch]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/mmu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index e1d6a4f591a9..17d64a1e11e5 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1751,6 +1751,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 		force_pte = (max_map_size == PAGE_SIZE);
 		vma_pagesize = min_t(long, vma_pagesize, max_map_size);
+		vma_shift = __ffs(vma_pagesize);
 	}
 
 	/*

From 3599c714c08c324f0fcfa392bfb857c92c575400 Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Fri, 6 Mar 2026 15:44:22 +0800
Subject: [PATCH 0970/1303] KVM: arm64: Remove the redundant ISB in
 __kvm_at_s1e2()

We already have an ISB in __kvm_at() to make the address translation result
visible to subsequent reads of PAR_EL1. Remove the redundant one right
after it.

Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260306074422.47694-1-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/at.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 6588ea251ed7..c5c5644b1878 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1504,8 +1504,6 @@ int __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 			fail = true;
 		}
 
-		isb();
-
 		if (!fail)
 			par = read_sysreg_par();
 

From 25966fc097691e5c925ad080f64a2f19c5fd940a Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Thu, 5 Mar 2026 14:31:46 -0500
Subject: [PATCH 0971/1303] ublk: fix NULL pointer dereference in
 ublk_ctrl_set_size()

ublk_ctrl_set_size() unconditionally dereferences ub->ub_disk via
set_capacity_and_notify() without checking if it is NULL.

ub->ub_disk is NULL before UBLK_CMD_START_DEV completes (it is only
assigned in ublk_ctrl_start_dev()) and after UBLK_CMD_STOP_DEV runs
(ublk_detach_disk() sets it to NULL). Since the UBLK_CMD_UPDATE_SIZE
handler performs no state validation, a user can trigger a NULL pointer
dereference by sending UPDATE_SIZE to a device that has been added but
not yet started, or one that has been stopped.

Fix this by checking ub->ub_disk under ub->mutex before dereferencing
it, and returning -ENODEV if the disk is not available.

Fixes: 98b995660bff ("ublk: Add UBLK_U_CMD_UPDATE_SIZE")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c13cda58a7c6..03edabdf8977 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -5003,15 +5003,22 @@ static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header)
 	return 0;
 }
 
-static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header)
+static int ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header)
 {
 	struct ublk_param_basic *p = &ub->params.basic;
 	u64 new_size = header->data[0];
+	int ret = 0;
 
 	mutex_lock(&ub->mutex);
+	if (!ub->ub_disk) {
+		ret = -ENODEV;
+		goto out;
+	}
 	p->dev_sectors = new_size;
 	set_capacity_and_notify(ub->ub_disk, p->dev_sectors);
+out:
 	mutex_unlock(&ub->mutex);
+	return ret;
 }
 
 struct count_busy {
@@ -5331,8 +5338,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_end_recovery(ub, &header);
 		break;
 	case UBLK_CMD_UPDATE_SIZE:
-		ublk_ctrl_set_size(ub, &header);
-		ret = 0;
+		ret = ublk_ctrl_set_size(ub, &header);
 		break;
 	case UBLK_CMD_QUIESCE_DEV:
 		ret = ublk_ctrl_quiesce_dev(ub, &header);

From 97c5550b763171dbef61e6239cab372b9f9cd4a2 Mon Sep 17 00:00:00 2001
From: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Date: Thu, 5 Mar 2026 15:26:29 -0800
Subject: [PATCH 0972/1303] arm64: contpte: fix set_access_flags() no-op check
 for SMMU/ATS faults

contpte_ptep_set_access_flags() compared the gathered ptep_get() value
against the requested entry to detect no-ops. ptep_get() ORs AF/dirty
from all sub-PTEs in the CONT block, so a dirty sibling can make the
target appear already-dirty. When the gathered value matches entry, the
function returns 0 even though the target sub-PTE still has PTE_RDONLY
set in hardware.

For a CPU with FEAT_HAFDBS this gathered view is fine, since hardware may
set AF/dirty on any sub-PTE and CPU TLB behavior is effectively gathered
across the CONT range. But page-table walkers that evaluate each
descriptor individually (e.g. a CPU without DBM support, or an SMMU
without HTTU, or with HA/HD disabled in CD.TCR) can keep faulting on the
unchanged target sub-PTE, causing an infinite fault loop.

Gathering can therefore cause false no-ops when only a sibling has been
updated:
 - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared)
 - read faults:  target still lacks PTE_AF

Fix by checking each sub-PTE against the requested AF/dirty/write state
(the same bits consumed by __ptep_set_access_flags()), using raw
per-PTE values rather than the gathered ptep_get() view, before
returning no-op. Keep using the raw target PTE for the write-bit unfold
decision.

Per Arm ARM (DDI 0487) D8.7.1 ("The Contiguous bit"), any sub-PTE in a CONT
range may become the effective cached translation and software must
maintain consistent attributes across the range.

Fixes: 4602e5757bcc ("arm64/mm: wire up PTE_CONT for user mappings")
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Acked-by: Balbir Singh <balbirs@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/contpte.c | 53 +++++++++++++++++++++++++++++++++++++----
 1 file changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index b929a455103f..1519d090d5ea 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -599,6 +599,27 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
 
+static bool contpte_all_subptes_match_access_flags(pte_t *ptep, pte_t entry)
+{
+	pte_t *cont_ptep = contpte_align_down(ptep);
+	/*
+	 * PFNs differ per sub-PTE. Match only bits consumed by
+	 * __ptep_set_access_flags(): AF, DIRTY and write permission.
+	 */
+	const pteval_t cmp_mask = PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
+	pteval_t entry_cmp = pte_val(entry) & cmp_mask;
+	int i;
+
+	for (i = 0; i < CONT_PTES; i++) {
+		pteval_t pte_cmp = pte_val(__ptep_get(cont_ptep + i)) & cmp_mask;
+
+		if (pte_cmp != entry_cmp)
+			return false;
+	}
+
+	return true;
+}
+
 int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep,
 					pte_t entry, int dirty)
@@ -608,13 +629,37 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 	int i;
 
 	/*
-	 * Gather the access/dirty bits for the contiguous range. If nothing has
-	 * changed, its a noop.
+	 * Check whether all sub-PTEs in the CONT block already match the
+	 * requested access flags/write permission, using raw per-PTE values
+	 * rather than the gathered ptep_get() view.
+	 *
+	 * __ptep_set_access_flags() can update AF, dirty and write
+	 * permission, but only to make the mapping more permissive.
+	 *
+	 * ptep_get() gathers AF/dirty state across the whole CONT block,
+	 * which is correct for a CPU with FEAT_HAFDBS. But page-table
+	 * walkers that evaluate each descriptor individually (e.g. a CPU
+	 * without DBM support, or an SMMU without HTTU, or with HA/HD
+	 * disabled in CD.TCR) can keep faulting on the target sub-PTE if
+	 * only a sibling has been updated. Gathering can therefore cause
+	 * false no-ops when only a sibling has been updated:
+	 *  - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared)
+	 *  - read faults:  target still lacks PTE_AF
+	 *
+	 * Per Arm ARM (DDI 0487) D8.7.1, any sub-PTE in a CONT range may
+	 * become the effective cached translation, so all entries must have
+	 * consistent attributes. Check the full CONT block before returning
+	 * no-op, and when any sub-PTE mismatches, proceed to update the whole
+	 * range.
 	 */
-	orig_pte = pte_mknoncont(ptep_get(ptep));
-	if (pte_val(orig_pte) == pte_val(entry))
+	if (contpte_all_subptes_match_access_flags(ptep, entry))
 		return 0;
 
+	/*
+	 * Use raw target pte (not gathered) for write-bit unfold decision.
+	 */
+	orig_pte = pte_mknoncont(__ptep_get(ptep));
+
 	/*
 	 * We can fix up access/dirty bits without having to unfold the contig
 	 * range. But if the write bit is changing, we must unfold.

From d87c828daa7ead9763416f75cc416496969cf1dc Mon Sep 17 00:00:00 2001
From: Yifan Wu <wuyifan50@huawei.com>
Date: Thu, 5 Mar 2026 09:36:37 +0800
Subject: [PATCH 0973/1303] selftest/arm64: Fix sve2p1_sigill() to hwcap test

The FEAT_SVE2p1 is indicated by ID_AA64ZFR0_EL1.SVEver. However,
the BFADD requires the FEAT_SVE_B16B16, which is indicated by
ID_AA64ZFR0_EL1.B16B16. This could cause the test to incorrectly
fail on a CPU that supports FEAT_SVE2.1 but not FEAT_SVE_B16B16.

LD1Q Gather load quadwords which is decoded from SVE encodings and
implied by FEAT_SVE2p1.

Fixes: c5195b027d29 ("kselftest/arm64: Add SVE 2.1 to hwcap test")
Signed-off-by: Yifan Wu <wuyifan50@huawei.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 tools/testing/selftests/arm64/abi/hwcap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9d2df1f3e6bb..c2661a312fc9 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -475,8 +475,8 @@ static void sve2_sigill(void)
 
 static void sve2p1_sigill(void)
 {
-	/* BFADD Z0.H, Z0.H, Z0.H */
-	asm volatile(".inst 0x65000000" : : : "z0");
+	/* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */
+	asm volatile(".inst 0xC400A000" : : : "z0");
 }
 
 static void sve2p2_sigill(void)

From f9fb44b0ecefc1f218db56661ed66d4e8d67317d Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:09 -0800
Subject: [PATCH 0974/1303] objtool/klp: Fix detection of corrupt static
 branch/call entries

Patching a function which references a static key living in a kernel
module is unsupported due to ordering issues inherent to late module
patching:

  1) Load a livepatch module which has a __jump_table entry which needs
     a klp reloc to reference static key K which lives in module M.

  2) The __jump_table klp reloc does *not* get resolved because module M
     is not yet loaded.

  3) jump_label_add_module() corrupts memory (or causes a panic) when
     dereferencing the uninitialized pointer to key K.

validate_special_section_klp_reloc() intends to prevent that from ever
happening by catching it at build time.  However, it incorrectly assumes
the special section entry's reloc symbol references have already been
converted from section symbols to object symbols, causing the validation
to miss corruption in extracted static branch/call table entries.

Make sure the references have been properly converted before doing the
validation.

Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files")
Reported-by: Song Liu <song@kernel.org>
Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/124ad747b751df0df1725eff89de8332e3fb26d6.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index 9f1f4011eb9c..d94632e80955 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1364,6 +1364,9 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		const char *sym_modname;
 		struct export *export;
 
+		if (convert_reloc_sym(e->patched, reloc))
+			continue;
+
 		/* Static branch/call keys are always STT_OBJECT */
 		if (reloc->sym->type != STT_OBJECT) {
 

From e476bb277cf91b7ac3ea803ec78a4f0791bddec3 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:10 -0800
Subject: [PATCH 0975/1303] objtool/klp: Disable unsupported pr_debug() usage

Instead of erroring out on unsupported pr_debug() (e.g., when patching a
module), issue a warning and make it inert, similar to how unsupported
tracepoints are currently handled.

Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/3a7db3a5b7d4abf9b2534803a74e2e7231322738.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index d94632e80955..9ff65b01882b 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1334,18 +1334,18 @@ static bool should_keep_special_sym(struct elf *elf, struct symbol *sym)
  * be applied after static branch/call init, resulting in code corruption.
  *
  * Validate a special section entry to avoid that.  Note that an inert
- * tracepoint is harmless enough, in that case just skip the entry and print a
- * warning.  Otherwise, return an error.
+ * tracepoint or pr_debug() is harmless enough, in that case just skip the
+ * entry and print a warning.  Otherwise, return an error.
  *
- * This is only a temporary limitation which will be fixed when livepatch adds
- * support for submodules: fully self-contained modules which are embedded in
- * the top-level livepatch module's data and which can be loaded on demand when
- * their corresponding to-be-patched module gets loaded.  Then klp relocs can
- * be retired.
+ * TODO: This is only a temporary limitation which will be fixed when livepatch
+ * adds support for submodules: fully self-contained modules which are embedded
+ * in the top-level livepatch module's data and which can be loaded on demand
+ * when their corresponding to-be-patched module gets loaded.  Then klp relocs
+ * can be retired.
  *
  * Return:
  *   -1: error: validation failed
- *    1: warning: tracepoint skipped
+ *    1: warning: disabled tracepoint or pr_debug()
  *    0: success
  */
 static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym)
@@ -1403,6 +1403,13 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 				continue;
 			}
 
+			if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) {
+				WARN("%s: disabling unsupported pr_debug()",
+				     code_sym->name);
+				ret = 1;
+				continue;
+			}
+
 			ERROR("%s+0x%lx: unsupported static branch key %s.  Use static_key_enabled() instead",
 			      code_sym->name, code_offset, reloc->sym->name);
 			return -1;

From 11c2adcd1fa2a9380a507db1e57c8542bfc81827 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:11 -0800
Subject: [PATCH 0976/1303] objtool/klp: Avoid NULL pointer dereference when
 printing code symbol name

Fix a hypothetical NULL pointer defereference of the 'code_sym'
variable.  In theory this should never happen.

Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/64116517bc93851a98fe366ea0a4d807f4c70aab.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index 9ff65b01882b..a3198a63c2f0 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1352,7 +1352,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 {
 	bool static_branch = !strcmp(sym->sec->name, "__jump_table");
 	bool static_call   = !strcmp(sym->sec->name, ".static_call_sites");
-	struct symbol *code_sym = NULL;
+	const char *code_sym = NULL;
 	unsigned long code_offset = 0;
 	struct reloc *reloc;
 	int ret = 0;
@@ -1372,7 +1372,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 
 			/* Save code location which can be printed below */
 			if (reloc->sym->type == STT_FUNC && !code_sym) {
-				code_sym = reloc->sym;
+				code_sym = reloc->sym->name;
 				code_offset = reloc_addend(reloc);
 			}
 
@@ -1395,23 +1395,26 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		if (!strcmp(sym_modname, "vmlinux"))
 			continue;
 
+		if (!code_sym)
+			code_sym = "<unknown>";
+
 		if (static_branch) {
 			if (strstarts(reloc->sym->name, "__tracepoint_")) {
 				WARN("%s: disabling unsupported tracepoint %s",
-				     code_sym->name, reloc->sym->name + 13);
+				     code_sym, reloc->sym->name + 13);
 				ret = 1;
 				continue;
 			}
 
 			if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) {
 				WARN("%s: disabling unsupported pr_debug()",
-				     code_sym->name);
+				     code_sym);
 				ret = 1;
 				continue;
 			}
 
 			ERROR("%s+0x%lx: unsupported static branch key %s.  Use static_key_enabled() instead",
-			      code_sym->name, code_offset, reloc->sym->name);
+			      code_sym, code_offset, reloc->sym->name);
 			return -1;
 		}
 
@@ -1422,7 +1425,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		}
 
 		ERROR("%s()+0x%lx: unsupported static call key %s.  Use KLP_STATIC_CALL() instead",
-		      code_sym->name, code_offset, reloc->sym->name);
+		      code_sym, code_offset, reloc->sym->name);
 		return -1;
 	}
 

From 32234049107d012703d50547e815f198f147968b Mon Sep 17 00:00:00 2001
From: HONG Yifan <elsk@google.com>
Date: Tue, 3 Mar 2026 01:03:39 +0000
Subject: [PATCH 0977/1303] objtool: Use HOSTCFLAGS for HAVE_XXHASH test

Previously, HAVE_XXHASH is tested by invoking HOSTCC without HOSTCFLAGS.

Consider the following scenario:

- The host machine has libxxhash installed
- We build the kernel with HOSTCFLAGS containing a --sysroot that does
  not have xxhash.h (for hermetic builds)

In this case, HAVE_XXHASH is set to y, but when it builds objtool with
HOSTCFLAGS, because the --sysroot does not contain xxhash.h, the
following error is raised:

<...>/common/tools/objtool/include/objtool/checksum_types.h:12:10: fatal error: 'xxhash.h' file not found
   12 | #include <xxhash.h>
      |          ^~~~~~~~~~

To resolve the error, we test HAVE_XXHASH by invoking HOSTCC with
HOSTCFLAGS.

Signed-off-by: HONG Yifan <elsk@google.com>
Reviewed-by: Carlos Llamas <cmllamas@google.com>
Link: https://patch.msgid.link/20260303010340.306164-1-elsk@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6964175abdfd..b8b8529f8ea9 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -13,7 +13,7 @@ endif
 
 ifeq ($(ARCH_HAS_KLP),y)
 	HAVE_XXHASH = $(shell printf "$(pound)include <xxhash.h>\nXXH3_state_t *state;int main() {}" | \
-		      $(HOSTCC) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n)
+		      $(HOSTCC) $(HOSTCFLAGS) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n)
 	ifeq ($(HAVE_XXHASH),y)
 		BUILD_KLP	 := y
 		LIBXXHASH_CFLAGS := $(shell $(HOSTPKG_CONFIG) libxxhash --cflags 2>/dev/null) \

From 356e4b2f5b80f757965f3f4d0219c81fca91b6f2 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Wed, 4 Mar 2026 19:31:20 -0800
Subject: [PATCH 0978/1303] objtool: Fix data alignment in elf_add_data()

Any data added to a section needs to be aligned in accordance with the
section's sh_addralign value.  Particularly strings added to a .str1.8
section.  Otherwise you may get some funky strings.

Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files")
Link: https://patch.msgid.link/d962fc0ca24fa0825cca8dad71932dccdd9312a9.1772681234.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 2c02c7b49265..3da90686350d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -1375,7 +1375,7 @@ void *elf_add_data(struct elf *elf, struct section *sec, const void *data, size_
 		memcpy(sec->data->d_buf, data, size);
 
 	sec->data->d_size = size;
-	sec->data->d_align = 1;
+	sec->data->d_align = sec->sh.sh_addralign;
 
 	offset = ALIGN(sec->sh.sh_size, sec->sh.sh_addralign);
 	sec->sh.sh_size = offset + size;

From 1fd1dc41724319406b0aff221a352a400b0ddfc5 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Wed, 4 Mar 2026 19:31:21 -0800
Subject: [PATCH 0979/1303] objtool: Fix ERROR_INSN() error message

Confusingly, ERROR_INSN() shows "warning:" instead of "error:".  Fix that.

Link: https://patch.msgid.link/c4fe793bb3d23fac2c636b2511059af1158410e2.1772681234.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/include/objtool/warn.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h
index 2b27b54096b8..fa8b7d292e83 100644
--- a/tools/objtool/include/objtool/warn.h
+++ b/tools/objtool/include/objtool/warn.h
@@ -107,7 +107,7 @@ static inline char *offstr(struct section *sec, unsigned long offset)
 #define ERROR_ELF(format, ...) __WARN_ELF(ERROR_STR, format, ##__VA_ARGS__)
 #define ERROR_GLIBC(format, ...) __WARN_GLIBC(ERROR_STR, format, ##__VA_ARGS__)
 #define ERROR_FUNC(sec, offset, format, ...) __WARN_FUNC(ERROR_STR, sec, offset, format, ##__VA_ARGS__)
-#define ERROR_INSN(insn, format, ...) WARN_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__)
+#define ERROR_INSN(insn, format, ...) ERROR_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__)
 
 extern bool debug;
 extern int indent;

From 7fe44c4388146bdbb3c5932d81a26d9fa0fd3ec9 Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Fri, 6 Mar 2026 10:49:18 +0000
Subject: [PATCH 0980/1303] bpf: drop kthread_exit from noreturn_deny

kthread_exit became a macro to do_exit in commit 28aaa9c39945
("kthread: consolidate kthread exit paths to prevent use-after-free"),
so there is no kthread_exit function BTF ID to resolve. Remove it from
noreturn_deny to avoid resolve_btfids unresolved symbol warnings.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 401d6c4960ec..8db79e593156 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25261,7 +25261,6 @@ BTF_ID(func, __x64_sys_exit_group)
 BTF_ID(func, do_exit)
 BTF_ID(func, do_group_exit)
 BTF_ID(func, kthread_complete_and_exit)
-BTF_ID(func, kthread_exit)
 BTF_ID(func, make_task_dead)
 BTF_SET_END(noreturn_deny)
 

From 8ce8d0524c136f60a1bddb0951db2999342d7217 Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Fri, 6 Mar 2026 10:30:51 +0000
Subject: [PATCH 0981/1303] sched_ext: Documentation: Mention scheduling class
 precedence

Mention the scheduling class precedence of fair and sched_ext to
clear up how sched_ext partial mode works.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/scheduler/sched-ext.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index 9e2882d937b4..100d45963781 100644
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -58,7 +58,8 @@ in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and
 However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is
 set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled
 by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and
-``SCHED_IDLE`` policies are scheduled by the fair-class scheduler.
+``SCHED_IDLE`` policies are scheduled by the fair-class scheduler which has
+higher sched_class precedence than ``SCHED_EXT``.
 
 Terminating the sched_ext scheduler program, triggering `SysRq-S`, or
 detection of any internal error including stalled runnable tasks aborts the

From 98c790b100764102d877e9339471b8c4c9233f2c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 6 Mar 2026 02:46:42 -0800
Subject: [PATCH 0982/1303] workqueue: Rename show_cpu_pool{s,}_hog{s,}() to
 reflect broadened scope
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

show_cpu_pool_hog() and show_cpu_pools_hogs() no longer only dump CPU
hogs — since commit 8823eaef45da ("workqueue: Show all busy workers in
stall diagnostics"), they dump every in-flight worker in the pool's
busy_hash.

Rename them to show_cpu_pool_busy_workers() and
show_cpu_pools_busy_workers() to accurately describe what they do.

Also fix the pr_info() message to say "stalled worker pools" instead of
"stalled CPU-bound worker pools", since sleeping/blocked workers are now
included.

No functional change.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 09b9ad78d566..b77119d71641 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7587,7 +7587,7 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds
  * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as
  * effectively as a CPU-bound one, so dump every in-flight worker.
  */
-static void show_cpu_pool_hog(struct worker_pool *pool)
+static void show_cpu_pool_busy_workers(struct worker_pool *pool)
 {
 	struct worker *worker;
 	unsigned long irq_flags;
@@ -7612,18 +7612,18 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 }
 
-static void show_cpu_pools_hogs(void)
+static void show_cpu_pools_busy_workers(void)
 {
 	struct worker_pool *pool;
 	int pi;
 
-	pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n");
+	pr_info("Showing backtraces of busy workers in stalled worker pools:\n");
 
 	rcu_read_lock();
 
 	for_each_pool(pool, pi) {
 		if (pool->cpu_stall)
-			show_cpu_pool_hog(pool);
+			show_cpu_pool_busy_workers(pool);
 
 	}
 
@@ -7720,7 +7720,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		show_all_workqueues();
 
 	if (cpu_pool_stall)
-		show_cpu_pools_hogs();
+		show_cpu_pools_busy_workers();
 
 	if (lockup_detected)
 		panic_on_wq_watchdog(max_stall_time);

From 1dde502587657045b267f179d7a1ecc7b8a1a265 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Fri, 6 Mar 2026 04:50:55 +0000
Subject: [PATCH 0983/1303] sched_ext: Use READ_ONCE() for scx_slice_bypass_us
 in scx_bypass()

Commit 0927780c90ce ("sched_ext: Use READ_ONCE() for lock-free reads
of module param variables") annotated the plain reads of
scx_slice_bypass_us and scx_bypass_lb_intv_us in bypass_lb_cpu(), but
missed a third site in scx_bypass():

  WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC);

scx_slice_bypass_us is a module parameter writable via sysfs in
process context through set_slice_us() -> param_set_uint_minmax(),
which performs a plain store without holding bypass_lock. scx_bypass()
reads the variable under bypass_lock, but since the writer does not
take that lock, the two accesses are concurrent.

WRITE_ONCE() only applies volatile semantics to the store of
scx_slice_dfl -- the val expression containing scx_slice_bypass_us is
evaluated as a plain read, providing no protection against concurrent
writes.

Wrap the read with READ_ONCE() to complete the annotation started by
commit 0927780c90ce and make the access KCSAN-clean, consistent with
the existing READ_ONCE(scx_slice_bypass_us) in bypass_lb_cpu().

Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 10866bfb88bf..f323df7be180 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4137,7 +4137,7 @@ static void scx_bypass(bool bypass)
 		WARN_ON_ONCE(scx_bypass_depth <= 0);
 		if (scx_bypass_depth != 1)
 			goto unlock;
-		WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC);
+		WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC);
 		bypass_timestamp = ktime_get_ns();
 		if (sch)
 			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);

From ca174c705db52db3cc842e754fd25a5f50eb702d Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 5 Mar 2026 14:53:29 -0500
Subject: [PATCH 0984/1303] cgroup/cpuset: Call rebuild_sched_domains()
 directly in hotplug

Besides deferring the call to housekeeping_update(), commit 6df415aa46ec
("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug
to workqueue") also defers the rebuild_sched_domains() call to
the workqueue. So a new offline CPU may still be in a sched domain
or new online CPU not showing up in the sched domains for a short
transition period. That could be a problem in some corner cases and
can be the cause of a reported test failure[1]. Fix it by calling
rebuild_sched_domains_cpuslocked() directly in hotplug as before. If
isolated partition invalidation or recreation is being done, the
housekeeping_update() call to update the housekeeping cpumasks will
still be deferred to a workqueue.

In commit 3bfe47967191 ("cgroup/cpuset: Move
housekeeping_update()/rebuild_sched_domains() together"),
housekeeping_update() is called before rebuild_sched_domains() because
it needs to access the HK_TYPE_DOMAIN housekeeping cpumask. That is now
changed to use the static HK_TYPE_DOMAIN_BOOT cpumask as HK_TYPE_DOMAIN
cpumask is now changeable at run time.  As a result, we can move the
rebuild_sched_domains() call before housekeeping_update() with
the slight advantage that it will be done in the same cpus_read_lock
critical section without the possibility of interference by a concurrent
cpu hot add/remove operation.

As it doesn't make sense to acquire cpuset_mutex/cpuset_top_mutex after
calling housekeeping_update() and immediately release them again, move
the cpuset_full_unlock() operation inside update_hk_sched_domains()
and rename it to cpuset_update_sd_hk_unlock() to signify that it will
release the full set of locks.

[1] https://lore.kernel.org/lkml/1a89aceb-48db-4edd-a730-b445e41221fe@nvidia.com

Fixes: 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue")
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 59 ++++++++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index e200de7c60b6..d21868455341 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -879,7 +879,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	/*
 	 * Cgroup v2 doesn't support domain attributes, just set all of them
 	 * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a
-	 * subset of HK_TYPE_DOMAIN housekeeping CPUs.
+	 * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs.
 	 */
 	for (i = 0; i < ndoms; i++) {
 		/*
@@ -888,7 +888,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 */
 		if (!csa || csa[i] == &top_cpuset)
 			cpumask_and(doms[i], top_cpuset.effective_cpus,
-				    housekeeping_cpumask(HK_TYPE_DOMAIN));
+				    housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
 		else
 			cpumask_copy(doms[i], csa[i]->effective_cpus);
 		if (dattr)
@@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
+ * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock
  *
- * Update housekeeping cpumasks and rebuild sched domains if necessary.
- * This should be called at the end of cpuset or hotplug actions.
+ * Update housekeeping cpumasks and rebuild sched domains if necessary and
+ * then do a cpuset_full_unlock().
+ * This should be called at the end of cpuset operation.
  */
-static void update_hk_sched_domains(void)
+static void cpuset_update_sd_hk_unlock(void)
+	__releases(&cpuset_mutex)
+	__releases(&cpuset_top_mutex)
 {
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
+
 	if (update_housekeeping) {
-		/* Updating HK cpumasks implies rebuild sched domains */
 		update_housekeeping = false;
-		force_sd_rebuild = true;
 		cpumask_copy(isolated_hk_cpus, isolated_cpus);
 
 		/*
@@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void)
 		mutex_unlock(&cpuset_mutex);
 		cpus_read_unlock();
 		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
-		cpus_read_lock();
-		mutex_lock(&cpuset_mutex);
+		mutex_unlock(&cpuset_top_mutex);
+	} else {
+		cpuset_full_unlock();
 	}
-	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 }
 
 /*
- * Work function to invoke update_hk_sched_domains()
+ * Work function to invoke cpuset_update_sd_hk_unlock()
  */
 static void hk_sd_workfn(struct work_struct *work)
 {
 	cpuset_full_lock();
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 }
 
 /**
@@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 
 	free_cpuset(trialcs);
 out_unlock:
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
 	return retval ?: nbytes;
@@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 	return retval ?: nbytes;
 }
 
@@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 }
 
 static void cpuset_css_free(struct cgroup_subsys_state *css)
@@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-
 	/*
-	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
-	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
-	 * cpumask can correctly reflect what is in isolated_cpus.
+	 * rebuild_sched_domains() will always be called directly if needed
+	 * to make sure that newly added or removed CPU will be reflected in
+	 * the sched domains. However, if isolated partition invalidation
+	 * or recreation is being done (update_housekeeping set), a work item
+	 * will be queued to call housekeeping_update() to update the
+	 * corresponding housekeeping cpumasks after some slight delay.
 	 *
 	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
 	 * is still pending. Before the pending bit is cleared, the work data
@@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void)
 	 * previously queued work. Since hk_sd_workfn() doesn't use the work
 	 * item at all, this is not a problem.
 	 */
-	if (update_housekeeping || force_sd_rebuild)
-		queue_work(system_unbound_wq, &hk_sd_work);
+	if (force_sd_rebuild)
+		rebuild_sched_domains_cpuslocked();
+	if (update_housekeeping)
+		queue_work(system_dfl_wq, &hk_sd_work);
 
 	free_tmpmasks(ptmp);
 }

From 0b2758f48f22b173963f39e553d0ecd05f3b4433 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 6 Mar 2026 09:10:36 -0800
Subject: [PATCH 0985/1303] Require (reasonably) normal mappings for
 MADV_DOFORK

This came up as a result of the tracing fix pull request, and commit
e39bb9e02b68 ("tracing: Fix WARN_ON in tracing_buffers_mmap_close") in
particular.

The use of MADV_DOFORK confused the ring buffer mapping reference
counting just because it was unexpected, since the mapping was
originally done with VM_DONTCOPY.

The tracing code may well be the only case of this (and fixed it all by
just using the mmap open callback to unconfuse itself), but it's just
strange that we allow MADV_DOFORK on special mappings where the kernel
has set the "don't copy this" bit.

The code already disallowed it for VM_IO mappings (going back to the
original commit f822566165dd: "madvise MADV_DONTFORK/MADV_DOFORK"), so
just extend it to any of the VM_SPECIAL cases (which includes
VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP in addition to VM_IO).

We could also allow MADV_DOFORK only on mappings that had been marked
DONTFORK by the user.  But that would require us to track that
(presumably with another VM_xyz bit), so let's just do this trivial and
straightforward modifications.

If anybody notices, Lorenzo will be boarding Flying Pig Airlines.

Suggested-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Link: https://lore.kernel.org/all/a8907468-d7e9-4727-af28-66d905093230@kernel.org/
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/madvise.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index c0370d9b4e23..dbb69400786d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1389,7 +1389,7 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior)
 		new_flags |= VM_DONTCOPY;
 		break;
 	case MADV_DOFORK:
-		if (new_flags & VM_IO)
+		if (new_flags & VM_SPECIAL)
 			return -EINVAL;
 		new_flags &= ~VM_DONTCOPY;
 		break;

From 457965c13f0837a289c9164b842d0860133f6274 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 5 Mar 2026 11:33:39 -0800
Subject: [PATCH 0986/1303] tracing: Add NULL pointer check to
 trigger_data_free()

If trigger_data_alloc() fails and returns NULL, event_hist_trigger_parse()
jumps to the out_free error path. While kfree() safely handles a NULL
pointer, trigger_data_free() does not. This causes a NULL pointer
dereference in trigger_data_free() when evaluating
data->cmd_ops->set_filter.

Fix the problem by adding a NULL pointer check to trigger_data_free().

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Cc: Miaoqian Lin <linmq006@gmail.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://patch.msgid.link/20260305193339.2810953-1-linux@roeck-us.net
Fixes: 0550069cc25f ("tracing: Properly process error handling in event_hist_trigger_parse()")
Assisted-by: Gemini:gemini-3.1-pro
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_trigger.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index fecbd679d432..d5230b759a2d 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -50,6 +50,9 @@ static int trigger_kthread_fn(void *ignore)
 
 void trigger_data_free(struct event_trigger_data *data)
 {
+	if (!data)
+		return;
+
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 

From e4eb11b34d6c84f398d8f08d7cb4d6c38e739dd2 Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Sat, 7 Mar 2026 00:32:38 +0800
Subject: [PATCH 0987/1303] drm/msm/dsi: fix pclk rate calculation for bonded
 dsi

Recently, we round up new_hdisplay once at most, for bonded dsi, we
may need twice, since they are independent links, we should round up
each half separately. This also aligns with the hdisplay we program
later in dsi_timing_setup()

Example:
	full_hdisplay = 1904, dsc_bpp = 8, bpc = 8
	new_full_hdisplay = DIV_ROUND_UP(1904 * 8, 8 * 3) = 635

if we use half display
	new_half_hdisplay = DIV_ROUND_UP(952 * 8, 8 * 3) = 318
	new_full_display = 636

Fixes: 7c9e4a554d4a ("drm/msm/dsi: Reduce pclk rate for compression")
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/709716/
Link: https://lore.kernel.org/r/20260306163255.215456-1-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index e8e83ee61eb0..db6da99375a1 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -584,13 +584,30 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
  *  FIXME: Reconsider this if/when CMD mode handling is rewritten to use
  *  transfer time and data overhead as a starting point of the calculations.
  */
-static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode,
-		const struct drm_dsc_config *dsc)
+static unsigned long
+dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode,
+				const struct drm_dsc_config *dsc,
+				bool is_bonded_dsi)
 {
-	int new_hdisplay = DIV_ROUND_UP(mode->hdisplay * drm_dsc_get_bpp_int(dsc),
-			dsc->bits_per_component * 3);
+	int hdisplay, new_hdisplay, new_htotal;
 
-	int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
+	/*
+	 * For bonded DSI, split hdisplay across two links and round up each
+	 * half separately, passing the full hdisplay would only round up once.
+	 * This also aligns with the hdisplay we program later in
+	 * dsi_timing_setup()
+	 */
+	hdisplay = mode->hdisplay;
+	if (is_bonded_dsi)
+		hdisplay /= 2;
+
+	new_hdisplay = DIV_ROUND_UP(hdisplay * drm_dsc_get_bpp_int(dsc),
+				    dsc->bits_per_component * 3);
+
+	if (is_bonded_dsi)
+		new_hdisplay *= 2;
+
+	new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
 
 	return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal);
 }
@@ -603,7 +620,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
 	pclk_rate = mode->clock * 1000u;
 
 	if (dsc)
-		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc);
+		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc, is_bonded_dsi);
 
 	/*
 	 * For bonded DSI mode, the current DRM mode has the complete width of the

From 0e16181704e37330069c24cea143f15b7b298da3 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 5 Mar 2026 09:28:05 -0800
Subject: [PATCH 0988/1303] MAINTAINERS: Remove bouncing T7XX reviewer

This reviewer's email no longer works. Remove it from MAINTAINERS.

Cc: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Cc: Liu Haijun <haijun.liu@mediatek.com>
Cc: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Cc: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Link: https://patch.msgid.link/20260305172806.3118806-1-dave.hansen@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b277d5bf3d1..4f8e772808c7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16358,7 +16358,6 @@ F:	net/dsa/tag_mtk.c
 
 MEDIATEK T7XX 5G WWAN MODEM DRIVER
 M:	Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
-R:	Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com>
 R:	Liu Haijun <haijun.liu@mediatek.com>
 R:	Ricardo Martinez <ricardo.martinez@linux.intel.com>
 L:	netdev@vger.kernel.org

From 3b1679e086bb869ca02722f6bd29b3573a6a0e7e Mon Sep 17 00:00:00 2001
From: Andrei-Alexandru Tachici <andrei-alexandru.tachici@oss.qualcomm.com>
Date: Mon, 2 Mar 2026 11:27:34 +0100
Subject: [PATCH 0989/1303] tracing: Fix enabling multiple events on the kernel
 command line and bootconfig

Multiple events can be enabled on the kernel command line via a comma
separator. But if the are specified one at a time, then only the last
event is enabled. This is because the event names are saved in a temporary
buffer, and each call by the init cmdline code will reset that buffer.

This also affects names in the boot config file, as it may call the
callback multiple times with an example of:

  kernel.trace_event = ":mod:rproc_qcom_common", ":mod:qrtr", ":mod:qcom_aoss"

Change the cmdline callback function to append a comma and the next value
if the temporary buffer already has content.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260302-trace-events-allow-multiple-modules-v1-1-ce4436e37fb8@oss.qualcomm.com
Signed-off-by: Andrei-Alexandru Tachici <andrei-alexandru.tachici@oss.qualcomm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b7343fdfd7b0..249d1cba72c0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -4493,7 +4493,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 
 static __init int setup_trace_event(char *str)
 {
-	strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	if (bootup_event_buf[0] != '\0')
+		strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE);
+
+	strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE);
+
 	trace_set_ring_buffer_expanded(NULL);
 	disable_tracing_selftest("running event tracing");
 

From cb47c882c31334aadc13ace80781728ed22a05ee Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Tue, 3 Mar 2026 21:10:11 -0500
Subject: [PATCH 0990/1303] drm/amd/pm: add missing od setting
 PP_OD_FEATURE_ZERO_FAN_BIT for smu v13

add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v13.0.0/13.0.7

Fixes: cfffd980bf21 ("drm/amd/pm: add zero RPM OD setting support for SMU13")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 576a10797b607ee9e4068218daf367b481564120)
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 3 ++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index b32c053950c9..a8d63d4d1f6e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2222,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index f08cfa510a8a..5500a0f12f0e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2224,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)

From 9d4837a26149355ffe3a1f80de80531eafdd3353 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Tue, 3 Mar 2026 21:14:10 -0500
Subject: [PATCH 0991/1303] drm/amd/pm: add missing od setting
 PP_OD_FEATURE_ZERO_FAN_BIT for smu v14

add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v14.0.2/14.0.3

Fixes: 9710b84e2a6a ("drm/amd/pm: add overdrive support on smu v14.0.2/3")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1b5cf07d80bb16d1593579ccdb23f08ea4262c14)
---
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 9994d4369da8..73762d9b5969 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)

From 062ea905fff7756b2e87143ffccaece5cdb44267 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 4 Mar 2026 14:07:40 -0600
Subject: [PATCH 0992/1303] drm/amd: Fix NULL pointer dereference in device
 cleanup

When GPU initialization fails due to an unsupported HW block
IP blocks may have a NULL version pointer. During cleanup in
amdgpu_device_fini_hw, the code calls amdgpu_device_set_pg_state and
amdgpu_device_set_cg_state which iterate over all IP blocks and access
adev->ip_blocks[i].version without NULL checks, leading to a kernel
NULL pointer dereference.

Add NULL checks for adev->ip_blocks[i].version in both
amdgpu_device_set_cg_state and amdgpu_device_set_pg_state to prevent
dereferencing NULL pointers during GPU teardown when initialization has
failed.

Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b7ac77468cda92eecae560b05f62f997a12fe2f2)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3e19b51a2763..10b10bac8b18 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3247,6 +3247,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip CG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3286,6 +3288,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev,
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip PG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||

From 52289ce48ef1f8a81cd39df1574098356e3c9d4c Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Date: Thu, 5 Mar 2026 13:16:36 +0200
Subject: [PATCH 0993/1303] drm/amdgpu: Fix kernel-doc comments for some LUT
 properties

The following members of struct amdgpu_mode_info do not have valid
references in the related kernel-doc sections:

 - plane_shaper_lut_property
 - plane_shaper_lut_size_property,
 - plane_lut3d_size_property

Correct all affected comment blocks.

Fixes: f545d82479b4 ("drm/amd/display: add plane shaper LUT and TF driver-specific properties")
Fixes: 671994e3bf33 ("drm/amd/display: add plane 3D LUT driver-specific properties")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ec5708d6e547f7efe2f009073bfa98dbc4c5c2ac)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index dc8d2f52c7d6..e244c12ceb23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -368,15 +368,15 @@ struct amdgpu_mode_info {
 
 	struct drm_property *plane_ctm_property;
 	/**
-	 * @shaper_lut_property: Plane property to set pre-blending shaper LUT
-	 * that converts color content before 3D LUT. If
-	 * plane_shaper_tf_property != Identity TF, AMD color module will
+	 * @plane_shaper_lut_property: Plane property to set pre-blending
+	 * shaper LUT that converts color content before 3D LUT.
+	 * If plane_shaper_tf_property != Identity TF, AMD color module will
 	 * combine the user LUT values with pre-defined TF into the LUT
 	 * parameters to be programmed.
 	 */
 	struct drm_property *plane_shaper_lut_property;
 	/**
-	 * @shaper_lut_size_property: Plane property for the size of
+	 * @plane_shaper_lut_size_property: Plane property for the size of
 	 * pre-blending shaper LUT as supported by the driver (read-only).
 	 */
 	struct drm_property *plane_shaper_lut_size_property;
@@ -400,10 +400,10 @@ struct amdgpu_mode_info {
 	 */
 	struct drm_property *plane_lut3d_property;
 	/**
-	 * @plane_degamma_lut_size_property: Plane property to define the max
-	 * size of 3D LUT as supported by the driver (read-only). The max size
-	 * is the max size of one dimension and, therefore, the max number of
-	 * entries for 3D LUT array is the 3D LUT size cubed;
+	 * @plane_lut3d_size_property: Plane property to define the max size
+	 * of 3D LUT as supported by the driver (read-only). The max size is
+	 * the max size of one dimension and, therefore, the max number of
+	 * entries for 3D LUT array is the 3D LUT size cubed.
 	 */
 	struct drm_property *plane_lut3d_size_property;
 	/**

From a6571045cf06c4aa749b4801382ae96650e2f0e1 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Wed, 4 Mar 2026 18:45:45 -0500
Subject: [PATCH 0994/1303] drm/amdgpu: fix gpu idle power consumption issue
 for gfx v12

Older versions of the MES firmware may cause abnormal GPU power consumption.
When performing inference tasks on the GPU (e.g., with Ollama using ROCm),
the GPU may show abnormal power consumption in idle state and incorrect GPU load information.
This issue has been fixed in firmware version 0x8b and newer.

Closes: https://github.com/ROCm/ROCm/issues/5706
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4e22a5fe6ea6e0b057e7f246df4ac3ff8bfbc46a)
---
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 5bfa5d1d0b36..023c7345ea54 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	int i;
 	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt;
+	uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ?
+		(mes->sched_version & AMDGPU_MES_VERSION_MASK) :
+		(mes->kiq_version & AMDGPU_MES_VERSION_MASK);
 
 	memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt));
 
@@ -785,7 +788,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	 * handling support, other queue will not use the oversubscribe timer.
 	 * handling  mode - 0: disabled; 1: basic version; 2: basic+ version
 	 */
-	mes_set_hw_res_pkt.oversubscription_timer = 50;
+	mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50;
 	mes_set_hw_res_pkt.unmapped_doorbell_handling = 1;
 
 	if (amdgpu_mes_log_enable) {

From 72ecb1dae72775fa9fea0159d8445d620a0a2295 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 5 Mar 2026 09:06:11 -0600
Subject: [PATCH 0995/1303] drm/amd: Fix a few more NULL pointer dereference in
 device cleanup

I found a few more paths that cleanup fails due to a NULL version pointer
on unsupported hardware.

Add NULL checks as applicable.

Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f5a05f8414fc10f307eb965f303580c7778f8dd2)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 10b10bac8b18..761ee5ebb4f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3497,6 +3497,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (!adev->ip_blocks[i].version->funcs->early_fini)
 			continue;
 
@@ -3574,6 +3576,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
 
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_ucode_free_bo(adev);
 			amdgpu_free_static_csa(&adev->virt.csa_obj);
@@ -3600,6 +3604,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->funcs->late_fini)
 			adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]);
 		adev->ip_blocks[i].status.late_initialized = false;

From 2a0596d516870951ce0e8edf510e48c87cb80761 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sat, 7 Mar 2026 02:21:01 +0800
Subject: [PATCH 0996/1303] sched_ext: Documentation: Update sched-ext.rst

- Remove CONFIG_PAHOLE_HAS_BTF_TAG from required config list
- Document ext_idle.c as the built-in idle CPU selection policy
- Add descriptions for example schedulers in tools/sched_ext/

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/scheduler/sched-ext.rst | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index 100d45963781..d74c2c2b9ef3 100644
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -43,7 +43,6 @@ options should be enabled to use sched_ext:
     CONFIG_DEBUG_INFO_BTF=y
     CONFIG_BPF_JIT_ALWAYS_ON=y
     CONFIG_BPF_JIT_DEFAULT_ON=y
-    CONFIG_PAHOLE_HAS_BTF_TAG=y
 
 sched_ext is used only when the BPF scheduler is loaded and running.
 
@@ -346,6 +345,8 @@ Where to Look
   The functions prefixed with ``scx_bpf_`` can be called from the BPF
   scheduler.
 
+* ``kernel/sched/ext_idle.c`` contains the built-in idle CPU selection policy.
+
 * ``tools/sched_ext/`` hosts example BPF scheduler implementations.
 
   * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a
@@ -354,13 +355,35 @@ Where to Look
   * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five
     levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``.
 
+  * ``scx_central[.bpf].c``: A central FIFO scheduler where all scheduling
+    decisions are made on one CPU, demonstrating ``LOCAL_ON`` dispatching,
+    tickless operation, and kthread preemption.
+
+  * ``scx_cpu0[.bpf].c``: A scheduler that queues all tasks to a shared DSQ
+    and only dispatches them on CPU0 in FIFO order. Useful for testing bypass
+    behavior.
+
+  * ``scx_flatcg[.bpf].c``: A flattened cgroup hierarchy scheduler
+    implementing hierarchical weight-based cgroup CPU control by compounding
+    each cgroup's share at every level into a single flat scheduling layer.
+
+  * ``scx_pair[.bpf].c``: A core-scheduling example that always makes
+    sibling CPU pairs execute tasks from the same CPU cgroup.
+
+  * ``scx_sdt[.bpf].c``: A variation of ``scx_simple`` demonstrating BPF
+    arena memory management for per-task data.
+
+  * ``scx_userland[.bpf].c``: A minimal scheduler demonstrating user space
+    scheduling. Tasks with CPU affinity are direct-dispatched in FIFO order;
+    all others are scheduled in user space by a simple vruntime scheduler.
+
 ABI Instability
 ===============
 
 The APIs provided by sched_ext to BPF schedulers programs have no stability
 guarantees. This includes the ops table callbacks and constants defined in
 ``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in
-``kernel/sched/ext.c``.
+``kernel/sched/ext.c`` and ``kernel/sched/ext_idle.c``.
 
 While we will attempt to provide a relatively stable API surface when
 possible, they are subject to change without warning between kernel

From a72f73c4dd9b209c53cf8b03b6e97fcefad4262c Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 6 Mar 2026 20:22:35 +0100
Subject: [PATCH 0997/1303] cgroup: Don't expose dead tasks in cgroup

Once a task exits it has its state set to TASK_DEAD and then it is
removed from the cgroup it belonged to. The last step happens on the task
gets out of its last schedule() invocation and is delayed on PREEMPT_RT
due to locking constraints.

As a result it is possible to receive a pid via waitpid() of a task
which is still listed in cgroup.procs for the cgroup it belonged
to. This is something that systemd does not expect and as a result it
waits for its exit until a time out occurs.
This can also be reproduced on !PREEMPT_RT kernel with a significant
delay in do_exit() after exit_notify().

Hide the task from the output which have PF_EXITING set which is done
before the parent is notified. Keeping zombies with live threads
shouldn't break anything (suggested by Tejun).

Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/all/20260219164648.3014-1-spasswolf@web.de/
Tested-by: Bert Karwatzki <spasswolf@web.de>
Fixes: 9311e6c29b34 ("cgroup: Fix sleeping from invalid context warning on PREEMPT_RT")
Cc: stable@vger.kernel.org # v6.19+
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cgroup.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index be1d71dda317..01fc2a93f3ef 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5109,6 +5109,12 @@ static void css_task_iter_advance(struct css_task_iter *it)
 		return;
 
 	task = list_entry(it->task_pos, struct task_struct, cg_list);
+	/*
+	 * Hide tasks that are exiting but not yet removed. Keep zombie
+	 * leaders with live threads visible.
+	 */
+	if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live))
+		goto repeat;
 
 	if (it->flags & CSS_TASK_ITER_PROCS) {
 		/* if PROCS, skip over tasks which aren't group leaders */

From 224a0d284c3caf1951302d1744a714784febed71 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 11:45:49 +0100
Subject: [PATCH 0998/1303] net: mctp: fix device leak on probe failure

Driver core holds a reference to the USB interface and its parent USB
device while the interface is bound to a driver and there is no need to
take additional references unless the structures are needed after
disconnect.

This driver takes a reference to the USB device during probe but does
not to release it on probe failures.

Drop the redundant device reference to fix the leak, reduce cargo
culting, make it easier to spot drivers where an extra reference is
needed, and reduce the risk of further memory leaks.

Fixes: 0791c0327a6e ("net: mctp: Add MCTP USB transport driver")
Cc: stable@vger.kernel.org	# 6.15
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://patch.msgid.link/20260305104549.16110-1-johan@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mctp/mctp-usb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c
index ef860cfc629f..3b5dff144177 100644
--- a/drivers/net/mctp/mctp-usb.c
+++ b/drivers/net/mctp/mctp-usb.c
@@ -329,7 +329,7 @@ static int mctp_usb_probe(struct usb_interface *intf,
 	SET_NETDEV_DEV(netdev, &intf->dev);
 	dev = netdev_priv(netdev);
 	dev->netdev = netdev;
-	dev->usbdev = usb_get_dev(interface_to_usbdev(intf));
+	dev->usbdev = interface_to_usbdev(intf);
 	dev->intf = intf;
 	usb_set_intfdata(intf, dev);
 
@@ -365,7 +365,6 @@ static void mctp_usb_disconnect(struct usb_interface *intf)
 	mctp_unregister_netdev(dev->netdev);
 	usb_free_urb(dev->tx_urb);
 	usb_free_urb(dev->rx_urb);
-	usb_put_dev(dev->usbdev);
 	free_netdev(dev->netdev);
 }
 

From 45fc134bcfadde456639c1b1e206e6918d69a553 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Mar 2026 15:13:53 +0800
Subject: [PATCH 0999/1303] bonding: do not set usable_slaves for broadcast
 mode

After commit e0caeb24f538 ("net: bonding: update the slave array for broadcast mode"),
broadcast mode will also set all_slaves and usable_slaves during
bond_enslave(). But if we also set updelay, during enslave, the
slave init state will be BOND_LINK_BACK. And later
bond_update_slave_arr() will alloc usable_slaves but add nothing.
This will cause bond_miimon_inspect() to have ignore_updelay
always true. So the updelay will be always ignored. e.g.

[    6.498368] bond0: (slave veth2): link status definitely down, disabling slave
[    7.536371] bond0: (slave veth2): link status up, enabling it in 0 ms
[    7.536402] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex

To fix it, we can either always call bond_update_slave_arr() on every
place when link changes. Or, let's just not set usable_slaves for
broadcast mode.

Fixes: e0caeb24f538 ("net: bonding: update the slave array for broadcast mode")
Reported-by: Liang Li <liali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-1-f72eb2e454d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 14ed91391fcc..93a32a368d31 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5069,13 +5069,18 @@ static void bond_set_slave_arr(struct bonding *bond,
 {
 	struct bond_up_slave *usable, *all;
 
-	usable = rtnl_dereference(bond->usable_slaves);
-	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
-	kfree_rcu(usable, rcu);
-
 	all = rtnl_dereference(bond->all_slaves);
 	rcu_assign_pointer(bond->all_slaves, all_slaves);
 	kfree_rcu(all, rcu);
+
+	if (BOND_MODE(bond) == BOND_MODE_BROADCAST) {
+		kfree_rcu(usable_slaves, rcu);
+		return;
+	}
+
+	usable = rtnl_dereference(bond->usable_slaves);
+	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
+	kfree_rcu(usable, rcu);
 }
 
 static void bond_reset_slave_arr(struct bonding *bond)

From 3348be7978f450ede0c308a4e8416ac716cf1015 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Mar 2026 15:13:54 +0800
Subject: [PATCH 1000/1303] bonding: handle BOND_LINK_FAIL, BOND_LINK_BACK as
 valid link states

Before the fixed commit, we check slave->new_link during commit
state, which values are only BOND_LINK_{NOCHANGE, UP, DOWN}. After
the commit, we start using slave->link_new_state, which state also could
be BOND_LINK_{FAIL, BACK}.

For example, when we set updelay/downdelay, after a failover,
the slave->link_new_state could be set to BOND_LINK_{FAIL, BACK} in
bond_miimon_inspect(). And later in bond_miimon_commit(), it will treat
it as invalid and print an error, which would cause confusion for users.

[  106.440254] bond0: (slave veth2): link status down for interface, disabling it in 200 ms
[  106.440265] bond0: (slave veth2): invalid new link 1 on slave
[  106.648276] bond0: (slave veth2): link status definitely down, disabling slave
[  107.480271] bond0: (slave veth2): link status up, enabling it in 200 ms
[  107.480288] bond0: (slave veth2): invalid new link 3 on slave
[  107.688302] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex

Let's handle BOND_LINK_{FAIL, BACK} as valid link states.

Fixes: 1899bb325149 ("bonding: fix state transition issue in link monitoring")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-2-f72eb2e454d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 93a32a368d31..444519078da3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2801,8 +2801,14 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+		case BOND_LINK_BACK:
+			slave_dbg(bond->dev, slave->dev, "link_new_state %d on slave\n",
+				  slave->link_new_state);
+			continue;
+
 		default:
-			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
+			slave_err(bond->dev, slave->dev, "invalid link_new_state %d on slave\n",
 				  slave->link_new_state);
 			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 

From 55f854dd5bdd8e19b936a00ef1f8d776ac32c7b0 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 4 Mar 2026 14:43:38 +0100
Subject: [PATCH 1001/1303] qmi_wwan: allow max_mtu above hard_mtu to control
 rx_urb_size

Commit c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu")
capped net->max_mtu to the device's hard_mtu in usbnet_probe(). While
this correctly prevents oversized packets on standard USB network
devices, it breaks the qmi_wwan driver.

qmi_wwan relies on userspace (e.g. ModemManager) setting a large MTU on
the wwan0 interface to configure rx_urb_size via usbnet_change_mtu().
QMI modems negotiate USB transfer sizes of 16,383 or 32,767 bytes, and
the USB receive buffers must be sized accordingly. With max_mtu capped
to hard_mtu (~1500 bytes), userspace can no longer raise the MTU, the
receive buffers remain small, and download speeds drop from >300 Mbps
to ~0.8 Mbps.

Introduce a FLAG_NOMAXMTU driver flag that allows individual usbnet
drivers to opt out of the max_mtu cap. Set this flag in qmi_wwan's
driver_info structures to restore the previous behavior for QMI devices,
while keeping the safety fix in place for all other usbnet drivers.

Fixes: c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/lkml/CAPh3n803k8JcBPV5qEzUB-oKzWkAs-D5CU7z=Vd_nLRCr5ZqQg@mail.gmail.com/
Reported-by: Koen Vandeputte <koen.vandeputte@citymesh.com>
Tested-by: Daniele Palmas <dnlplm@gmail.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Link: https://patch.msgid.link/20260304134338.1785002-1-lvivier@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 4 ++--
 drivers/net/usb/usbnet.c   | 7 ++++---
 include/linux/usb/usbnet.h | 1 +
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 3a4985b582cb..05acac10cd2b 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -928,7 +928,7 @@ static int qmi_wwan_resume(struct usb_interface *intf)
 
 static const struct driver_info	qmi_wwan_info = {
 	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
+	.flags		= FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP,
 	.bind		= qmi_wwan_bind,
 	.unbind		= qmi_wwan_unbind,
 	.manage_power	= qmi_wwan_manage_power,
@@ -937,7 +937,7 @@ static const struct driver_info	qmi_wwan_info = {
 
 static const struct driver_info	qmi_wwan_info_quirk_dtr = {
 	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
+	.flags		= FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP,
 	.bind		= qmi_wwan_bind,
 	.unbind		= qmi_wwan_unbind,
 	.manage_power	= qmi_wwan_manage_power,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ed86ba87ca4e..b72ba0803392 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1829,11 +1829,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod)
 		if ((dev->driver_info->flags & FLAG_NOARP) != 0)
 			net->flags |= IFF_NOARP;
 
-		if (net->max_mtu > (dev->hard_mtu - net->hard_header_len))
+		if ((dev->driver_info->flags & FLAG_NOMAXMTU) == 0 &&
+		    net->max_mtu > (dev->hard_mtu - net->hard_header_len))
 			net->max_mtu = dev->hard_mtu - net->hard_header_len;
 
-		if (net->mtu > net->max_mtu)
-			net->mtu = net->max_mtu;
+		if (net->mtu > (dev->hard_mtu - net->hard_header_len))
+			net->mtu = dev->hard_mtu - net->hard_header_len;
 
 	} else if (!info->in || !info->out)
 		status = usbnet_get_endpoints(dev, udev);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index b0e84896e6ac..bbf799ccf3b3 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -132,6 +132,7 @@ struct driver_info {
 #define FLAG_MULTI_PACKET	0x2000
 #define FLAG_RX_ASSEMBLE	0x4000	/* rx packets may span >1 frames */
 #define FLAG_NOARP		0x8000	/* device can't do ARP */
+#define FLAG_NOMAXMTU		0x10000	/* allow max_mtu above hard_mtu */
 
 	/* init device ... can sleep, or cause probe() failure */
 	int	(*bind)(struct usbnet *, struct usb_interface *);

From aed763abf0e905b4b8d747d1ba9e172961572f57 Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Thu, 5 Mar 2026 10:10:19 +0200
Subject: [PATCH 1002/1303] net/mlx5: Fix deadlock between devlink lock and
 esw->wq

esw->work_queue executes esw_functions_changed_event_handler ->
esw_vfs_changed_event_handler and acquires the devlink lock.

.eswitch_mode_set (acquires devlink lock in devlink_nl_pre_doit) ->
mlx5_devlink_eswitch_mode_set -> mlx5_eswitch_disable_locked ->
mlx5_eswitch_event_handler_unregister -> flush_workqueue deadlocks
when esw_vfs_changed_event_handler executes.

Fix that by no longer flushing the work to avoid the deadlock, and using
a generation counter to keep track of work relevance. This avoids an old
handler manipulating an esw that has undergone one or more mode changes:
- the counter is incremented in mlx5_eswitch_event_handler_unregister.
- the counter is read and passed to the ephemeral mlx5_host_work struct.
- the work handler takes the devlink lock and bails out if the current
  generation is different than the one it was scheduled to operate on.
- mlx5_eswitch_cleanup does the final draining before destroying the wq.

No longer flushing the workqueue has the side effect of maybe no longer
cancelling pending vport_change_handler work items, but that's ok since
those are disabled elsewhere:
- mlx5_eswitch_disable_locked disables the vport eq notifier.
- mlx5_esw_vport_disable disarms the HW EQ notification and marks
  vport->enabled under state_lock to false to prevent pending vport
  handler from doing anything.
- mlx5_eswitch_cleanup destroys the workqueue and makes sure all events
  are disabled/finished.

Fixes: f1bc646c9a06 ("net/mlx5: Use devl_ API in mlx5_esw_offloads_devlink_port_register")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305081019.1811100-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c  |  7 ++++---
 .../net/ethernet/mellanox/mlx5/core/eswitch.h  |  2 ++
 .../mellanox/mlx5/core/eswitch_offloads.c      | 18 +++++++++++++-----
 3 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d3af87a94a18..123c96716a54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1072,10 +1072,11 @@ static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw)
 
 static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw)
 {
-	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS &&
+	    mlx5_eswitch_is_funcs_handler(esw->dev)) {
 		mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
-
-	flush_workqueue(esw->work_queue);
+		atomic_inc(&esw->esw_funcs.generation);
+	}
 }
 
 static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6841caef02d1..c2563bee74df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -335,10 +335,12 @@ struct esw_mc_addr { /* SRIOV only */
 struct mlx5_host_work {
 	struct work_struct	work;
 	struct mlx5_eswitch	*esw;
+	int			work_gen;
 };
 
 struct mlx5_esw_functions {
 	struct mlx5_nb		nb;
+	atomic_t		generation;
 	bool			host_funcs_disabled;
 	u16			num_vfs;
 	u16			num_ec_vfs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1366f6e489bd..8c5e48d001be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3582,22 +3582,28 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 }
 
 static void
-esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
+esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen,
+			      const u32 *out)
 {
 	struct devlink *devlink;
 	bool host_pf_disabled;
 	u16 new_num_vfs;
 
+	devlink = priv_to_devlink(esw->dev);
+	devl_lock(devlink);
+
+	/* Stale work from one or more mode changes ago. Bail out. */
+	if (work_gen != atomic_read(&esw->esw_funcs.generation))
+		goto unlock;
+
 	new_num_vfs = MLX5_GET(query_esw_functions_out, out,
 			       host_params_context.host_num_of_vfs);
 	host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
 				    host_params_context.host_pf_disabled);
 
 	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
-		return;
+		goto unlock;
 
-	devlink = priv_to_devlink(esw->dev);
-	devl_lock(devlink);
 	/* Number of VFs can only change from "0 to x" or "x to 0". */
 	if (esw->esw_funcs.num_vfs > 0) {
 		mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
@@ -3612,6 +3618,7 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
 		}
 	}
 	esw->esw_funcs.num_vfs = new_num_vfs;
+unlock:
 	devl_unlock(devlink);
 }
 
@@ -3628,7 +3635,7 @@ static void esw_functions_changed_event_handler(struct work_struct *work)
 	if (IS_ERR(out))
 		goto out;
 
-	esw_vfs_changed_event_handler(esw, out);
+	esw_vfs_changed_event_handler(esw, host_work->work_gen, out);
 	kvfree(out);
 out:
 	kfree(host_work);
@@ -3648,6 +3655,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
 	esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);
 
 	host_work->esw = esw;
+	host_work->work_gen = atomic_read(&esw_funcs->generation);
 
 	INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
 	queue_work(esw->work_queue, &host_work->work);

From 24b2795f9683e092dc22a68f487e7aaaf2ddafea Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:30 +0200
Subject: [PATCH 1003/1303] net/mlx5: Fix crash when moving to switchdev mode

When moving to switchdev mode when the device doesn't support IPsec,
we try to clean up the IPsec resources anyway which causes the crash
below, fix that by correctly checking for IPsec support before trying
to clean up its resources.

[27642.515799] WARNING: arch/x86/mm/fault.c:1276 at
do_user_addr_fault+0x18a/0x680, CPU#4: devlink/6490
[27642.517159] Modules linked in: xt_conntrack xt_MASQUERADE
ip6table_nat ip6table_filter ip6_tables iptable_nat nf_nat xt_addrtype
rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl nfnetlink
zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi
scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core
ib_core
[27642.521358] CPU: 4 UID: 0 PID: 6490 Comm: devlink Not tainted
6.19.0-rc5_for_upstream_min_debug_2026_01_14_16_47 #1 NONE
[27642.522923] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
[27642.524528] RIP: 0010:do_user_addr_fault+0x18a/0x680
[27642.525362] Code: ff 0f 84 75 03 00 00 48 89 ee 4c 89 e7 e8 5e b9 22
00 49 89 c0 48 85 c0 0f 84 a8 02 00 00 f7 c3 60 80 00 00 74 22 31 c9 eb
   ae <0f> 0b 48 83 c4 10 48 89 ea 48 89 de 4c 89 f7 5b 5d 41 5c 41 5d
41
[27642.528166] RSP: 0018:ffff88810770f6b8 EFLAGS: 00010046
[27642.529038] RAX: 0000000000000000 RBX: 0000000000000002 RCX:
ffff88810b980f00
[27642.530158] RDX: 00000000000000a0 RSI: 0000000000000002 RDI:
ffff88810770f728
[27642.531270] RBP: 00000000000000a0 R08: 0000000000000000 R09:
0000000000000000
[27642.532383] R10: 0000000000000000 R11: 0000000000000000 R12:
ffff888103f3c4c0
[27642.533499] R13: 0000000000000000 R14: ffff88810770f728 R15:
0000000000000000
[27642.534614] FS:  00007f197c741740(0000) GS:ffff88856a94c000(0000)
knlGS:0000000000000000
[27642.535915] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[27642.536858] CR2: 00000000000000a0 CR3: 000000011334c003 CR4:
0000000000172eb0
[27642.537982] Call Trace:
[27642.538466]  <TASK>
[27642.538907]  exc_page_fault+0x76/0x140
[27642.539583]  asm_exc_page_fault+0x22/0x30
[27642.540282] RIP: 0010:_raw_spin_lock_irqsave+0x10/0x30
[27642.541134] Code: 07 85 c0 75 11 ba ff 00 00 00 f0 0f b1 17 75 06 b8
01 00 00 00 c3 31 c0 c3 90 0f 1f 44 00 00 53 9c 5b fa 31 c0 ba 01 00 00
   00 <f0> 0f b1 17 75 05 48 89 d8 5b c3 89 c6 e8 7e 02 00 00 48 89 d8
      5b
[27642.543936] RSP: 0018:ffff88810770f7d8 EFLAGS: 00010046
[27642.544803] RAX: 0000000000000000 RBX: 0000000000000202 RCX:
ffff888113ad96d8
[27642.545916] RDX: 0000000000000001 RSI: ffff88810770f818 RDI:
00000000000000a0
[27642.547027] RBP: 0000000000000098 R08: 0000000000000400 R09:
ffff88810b980f00
[27642.548140] R10: 0000000000000001 R11: ffff888101845a80 R12:
00000000000000a8
[27642.549263] R13: ffffffffa02a9060 R14: 00000000000000a0 R15:
ffff8881130d8a40
[27642.550379]  complete_all+0x20/0x90
[27642.551010]  mlx5e_ipsec_disable_events+0xb6/0xf0 [mlx5_core]
[27642.552022]  mlx5e_nic_disable+0x12d/0x220 [mlx5_core]
[27642.552929]  mlx5e_detach_netdev+0x66/0xf0 [mlx5_core]
[27642.553822]  mlx5e_netdev_change_profile+0x5b/0x120 [mlx5_core]
[27642.554821]  mlx5e_vport_rep_load+0x419/0x590 [mlx5_core]
[27642.555757]  ? xa_load+0x53/0x90
[27642.556361]  __esw_offloads_load_rep+0x54/0x70 [mlx5_core]
[27642.557328]  mlx5_esw_offloads_rep_load+0x45/0xd0 [mlx5_core]
[27642.558320]  esw_offloads_enable+0xb4b/0xc90 [mlx5_core]
[27642.559247]  mlx5_eswitch_enable_locked+0x34e/0x4f0 [mlx5_core]
[27642.560257]  ? mlx5_rescan_drivers_locked+0x222/0x2d0 [mlx5_core]
[27642.561284]  mlx5_devlink_eswitch_mode_set+0x5ac/0x9c0 [mlx5_core]
[27642.562334]  ? devlink_rate_set_ops_supported+0x21/0x3a0
[27642.563220]  devlink_nl_eswitch_set_doit+0x67/0xe0
[27642.564026]  genl_family_rcv_msg_doit+0xe0/0x130
[27642.564816]  genl_rcv_msg+0x183/0x290
[27642.565466]  ? __devlink_nl_pre_doit.isra.0+0x160/0x160
[27642.566329]  ? devlink_nl_eswitch_get_doit+0x290/0x290
[27642.567181]  ? devlink_nl_pre_doit_parent_dev_optional+0x20/0x20
[27642.568147]  ? genl_family_rcv_msg_dumpit+0xf0/0xf0
[27642.568966]  netlink_rcv_skb+0x4b/0xf0
[27642.569629]  genl_rcv+0x24/0x40
[27642.570215]  netlink_unicast+0x255/0x380
[27642.570901]  ? __alloc_skb+0xfa/0x1e0
[27642.571560]  netlink_sendmsg+0x1f3/0x420
[27642.572249]  __sock_sendmsg+0x38/0x60
[27642.572911]  __sys_sendto+0x119/0x180
[27642.573561]  ? __sys_recvmsg+0x5c/0xb0
[27642.574227]  __x64_sys_sendto+0x20/0x30
[27642.574904]  do_syscall_64+0x55/0xc10
[27642.575554]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[27642.576391] RIP: 0033:0x7f197c85e807
[27642.577050] Code: c7 c0 ff ff ff ff eb be 66 2e 0f 1f 84 00 00 00 00
00 90 f3 0f 1e fa 80 3d 45 08 0d 00 00 41 89 ca 74 10 b8 2c 00 00 00 0f
   05 <48> 3d 00 f0 ff ff 77 69 c3 55 48 89 e5 53 48 83 ec 38 44 89 4d
      d0
[27642.579846] RSP: 002b:00007ffebd4e2248 EFLAGS: 00000202 ORIG_RAX:
000000000000002c
[27642.581082] RAX: ffffffffffffffda RBX: 000055cfcd9cd2a0 RCX:
00007f197c85e807
[27642.582200] RDX: 0000000000000038 RSI: 000055cfcd9cd490 RDI:
0000000000000003
[27642.583320] RBP: 00007ffebd4e2290 R08: 00007f197c942200 R09:
000000000000000c
[27642.584437] R10: 0000000000000000 R11: 0000000000000202 R12:
0000000000000000
[27642.585555] R13: 000055cfcd9cd490 R14: 00007ffebd4e45d1 R15:
000055cfcd9cd2a0
[27642.586671]  </TASK>
[27642.587121] ---[ end trace 0000000000000000 ]---
[27642.587910] BUG: kernel NULL pointer dereference, address:
00000000000000a0

Fixes: 664f76be38a1 ("net/mlx5: Fix IPsec cleanup over MPV device")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 197a1c6930c0..329608c59313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -2912,7 +2912,7 @@ void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv)
 		goto out;
 
 	peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp);
-	if (peer_priv)
+	if (peer_priv && peer_priv->ipsec)
 		complete_all(&peer_priv->ipsec->comp);
 
 	mlx5_devcom_for_each_peer_end(priv->devcom);

From 76324e4041c0efb4808702b05426d7a0a7d8df5b Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:31 +0200
Subject: [PATCH 1004/1303] net/mlx5: Fix peer miss rules host disabled checks

The check on mlx5_esw_host_functions_enabled(esw->dev) for adding VF
peer miss rules is incorrect. These rules match traffic from peer's VFs,
so the local device's host function status is irrelevant. Remove this
check to ensure peer VF traffic is properly handled regardless of local
host configuration.

Also fix the PF peer miss rule deletion to be symmetric with the add
path, so only attempt to delete the rule if it was actually created.

Fixes: 520369ef43a8 ("net/mlx5: Support disabling host PFs")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 27 +++++++++----------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8c5e48d001be..7a9ee36b8dca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1241,21 +1241,17 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 		flows[peer_vport->index] = flow;
 	}
 
-	if (mlx5_esw_host_functions_enabled(esw->dev)) {
-		mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
-					   mlx5_core_max_vfs(peer_dev)) {
-			esw_set_peer_miss_rule_source_port(esw, peer_esw,
-							   spec,
-							   peer_vport->vport);
-
-			flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
-						   spec, &flow_act, &dest, 1);
-			if (IS_ERR(flow)) {
-				err = PTR_ERR(flow);
-				goto add_vf_flow_err;
-			}
-			flows[peer_vport->index] = flow;
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev)) {
+		esw_set_peer_miss_rule_source_port(esw, peer_esw, spec,
+						   peer_vport->vport);
+		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_vf_flow_err;
 		}
+		flows[peer_vport->index] = flow;
 	}
 
 	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
@@ -1347,7 +1343,8 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev) &&
+	    mlx5_esw_host_functions_enabled(peer_dev)) {
 		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
 		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}

From 1633111d69053512d099658d4a05fc736fab36b0 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:32 +0200
Subject: [PATCH 1005/1303] net/mlx5e: Fix DMA FIFO desync on error CQE SQ
 recovery

In case of a TX error CQE, a recovery flow is triggered,
mlx5e_reset_txqsq_cc_pc() resets dma_fifo_cc to 0 but not dma_fifo_pc,
desyncing the DMA FIFO producer and consumer.

After recovery, the producer pushes new DMA entries at the old
dma_fifo_pc, while the consumer reads from position 0.
This causes us to unmap stale DMA addresses from before the recovery.

The DMA FIFO is a purely software construct with no HW counterpart.
At the point of reset, all WQEs have been flushed so dma_fifo_cc is
already equal to dma_fifo_pc. There is no need to reset either counter,
similar to how skb_fifo pc/cc are untouched.

Remove the 'dma_fifo_cc = 0' reset.

This fixes the following WARNING:
    WARNING: CPU: 0 PID: 0 at drivers/iommu/dma-iommu.c:1240 iommu_dma_unmap_page+0x79/0x90
    Modules linked in: mlx5_vdpa vringh vdpa bonding mlx5_ib mlx5_vfio_pci ipip mlx5_fwctl tunnel4 mlx5_core ib_ipoib geneve ip6_gre ip_gre gre nf_tables ip6_tunnel rdma_ucm ib_uverbs ib_umad vfio_pci vfio_pci_core act_mirred act_skbedit act_vlan vhost_net vhost tap ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress vhost_iotlb iptable_raw tunnel6 vfio_iommu_type1 vfio openvswitch nsh rpcsec_gss_krb5 auth_rpcgss oid_registry xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter overlay zram zsmalloc rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core fuse [last unloaded: nf_tables]
    CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.13.0-rc5_for_upstream_min_debug_2024_12_30_21_33 #1
    Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
    RIP: 0010:iommu_dma_unmap_page+0x79/0x90
    Code: 2b 4d 3b 21 72 26 4d 3b 61 08 73 20 49 89 d8 44 89 f9 5b 4c 89 f2 4c 89 e6 48 89 ef 5d 41 5c 41 5d 41 5e 41 5f e9 c7 ae 9e ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 66 2e 0f 1f 84 00 00 00 00
    Call Trace:
     <IRQ>
     ? __warn+0x7d/0x110
     ? iommu_dma_unmap_page+0x79/0x90
     ? report_bug+0x16d/0x180
     ? handle_bug+0x4f/0x90
     ? exc_invalid_op+0x14/0x70
     ? asm_exc_invalid_op+0x16/0x20
     ? iommu_dma_unmap_page+0x79/0x90
     ? iommu_dma_unmap_page+0x2e/0x90
     dma_unmap_page_attrs+0x10d/0x1b0
     mlx5e_tx_wi_dma_unmap+0xbe/0x120 [mlx5_core]
     mlx5e_poll_tx_cq+0x16d/0x690 [mlx5_core]
     mlx5e_napi_poll+0x8b/0xac0 [mlx5_core]
     __napi_poll+0x24/0x190
     net_rx_action+0x32a/0x3b0
     ? mlx5_eq_comp_int+0x7e/0x270 [mlx5_core]
     ? notifier_call_chain+0x35/0xa0
     handle_softirqs+0xc9/0x270
     irq_exit_rcu+0x71/0xd0
     common_interrupt+0x7f/0xa0
     </IRQ>
     <TASK>
     asm_common_interrupt+0x22/0x40

Fixes: db75373c91b0 ("net/mlx5e: Recover Send Queue (SQ) from error state")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 60ba840e00fa..afdeb1b3d425 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -47,7 +47,6 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
 		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
 		  sq->sqn, sq->cc, sq->pc);
 	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
 	sq->pc = 0;
 }
 

From db25c42c2e1f9c0d136420fff5e5700f7e771a6f Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:33 +0200
Subject: [PATCH 1006/1303] net/mlx5e: RX, Fix XDP multi-buf frag counting for
 striding RQ

XDP multi-buf programs can modify the layout of the XDP buffer when the
program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The
referenced commit in the fixes tag corrected the assumption in the mlx5
driver that the XDP buffer layout doesn't change during a program
execution. However, this fix introduced another issue: the dropped
fragments still need to be counted on the driver side to avoid page
fragment reference counting issues.

The issue was discovered by the drivers/net/xdp.py selftest,
more specifically the test_xdp_native_tx_mb:
- The mlx5 driver allocates a page_pool page and initializes it with
  a frag counter of 64 (pp_ref_count=64) and the internal frag counter
  to 0.
- The test sends one packet with no payload.
- On RX (mlx5e_skb_from_cqe_mpwrq_nonlinear()), mlx5 configures the XDP
  buffer with the packet data starting in the first fragment which is the
  page mentioned above.
- The XDP program runs and calls bpf_xdp_pull_data() which moves the
  header into the linear part of the XDP buffer. As the packet doesn't
  contain more data, the program drops the tail fragment since it no
  longer contains any payload (pp_ref_count=63).
- mlx5 device skips counting this fragment. Internal frag counter
  remains 0.
- mlx5 releases all 64 fragments of the page but page pp_ref_count is
  63 => negative reference counting error.

Resulting splat during the test:

  WARNING: CPU: 0 PID: 188225 at ./include/net/page_pool/helpers.h:297 mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core]
  Modules linked in: [...]
  CPU: 0 UID: 0 PID: 188225 Comm: ip Not tainted 6.18.0-rc7_for_upstream_min_debug_2025_12_08_11_44 #1 NONE
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
  RIP: 0010:mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core]
  [...]
  Call Trace:
   <TASK>
   mlx5e_free_rx_mpwqe+0x20a/0x250 [mlx5_core]
   mlx5e_dealloc_rx_mpwqe+0x37/0xb0 [mlx5_core]
   mlx5e_free_rx_descs+0x11a/0x170 [mlx5_core]
   mlx5e_close_rq+0x78/0xa0 [mlx5_core]
   mlx5e_close_queues+0x46/0x2a0 [mlx5_core]
   mlx5e_close_channel+0x24/0x90 [mlx5_core]
   mlx5e_close_channels+0x5d/0xf0 [mlx5_core]
   mlx5e_safe_switch_params+0x2ec/0x380 [mlx5_core]
   mlx5e_change_mtu+0x11d/0x490 [mlx5_core]
   mlx5e_change_nic_mtu+0x19/0x30 [mlx5_core]
   netif_set_mtu_ext+0xfc/0x240
   do_setlink.isra.0+0x226/0x1100
   rtnl_newlink+0x7a9/0xba0
   rtnetlink_rcv_msg+0x220/0x3c0
   netlink_rcv_skb+0x4b/0xf0
   netlink_unicast+0x255/0x380
   netlink_sendmsg+0x1f3/0x420
   __sock_sendmsg+0x38/0x60
   ____sys_sendmsg+0x1e8/0x240
   ___sys_sendmsg+0x7c/0xb0
   [...]
   __sys_sendmsg+0x5f/0xb0
   do_syscall_64+0x55/0xc70

The problem applies for XDP_PASS as well which is handled in a different
code path in the driver.

This patch fixes the issue by doing page frag counting on all the
original XDP buffer fragments for all relevant XDP actions (XDP_TX ,
XDP_REDIRECT and XDP_PASS). This is basically reverting to the original
counting before the commit in the fixes tag.

As frag_page is still pointing to the original tail, the nr_frags
parameter to xdp_update_skb_frags_info() needs to be calculated
in a different way to reflect the new nr_frags.

Fixes: 87bcef158ac1 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for striding RQ")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Cc: Amery Hung <ameryhung@gmail.com>
Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index efcfcddab376..40e53a612989 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1957,14 +1957,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	if (prog) {
 		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u8 new_nr_frags;
 		u32 len;
 
 		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
-				frag_page -= old_nr_frags - sinfo->nr_frags;
-
 				for (pfp = head_page; pfp < frag_page; pfp++)
 					pfp->frags++;
 
@@ -1975,13 +1974,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		nr_frags_free = old_nr_frags - sinfo->nr_frags;
-		if (unlikely(nr_frags_free)) {
-			frag_page -= nr_frags_free;
+		new_nr_frags = sinfo->nr_frags;
+		nr_frags_free = old_nr_frags - new_nr_frags;
+		if (unlikely(nr_frags_free))
 			truesize -= (nr_frags_free - 1) * PAGE_SIZE +
 				ALIGN(pg_consumed_bytes,
 				      BIT(rq->mpwqe.log_stride_sz));
-		}
 
 		len = mxbuf->xdp.data_end - mxbuf->xdp.data;
 
@@ -2003,7 +2001,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			struct mlx5e_frag_page *pagep;
 
 			/* sinfo->nr_frags is reset by build_skb, calculate again. */
-			xdp_update_skb_frags_info(skb, frag_page - head_page,
+			xdp_update_skb_frags_info(skb, new_nr_frags,
 						  sinfo->xdp_frags_size,
 						  truesize,
 						  xdp_buff_get_skb_flags(&mxbuf->xdp));

From a6413e6f6c9d9bb9833324cb3753582f7bc0f2fa Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:34 +0200
Subject: [PATCH 1007/1303] net/mlx5e: RX, Fix XDP multi-buf frag counting for
 legacy RQ

XDP multi-buf programs can modify the layout of the XDP buffer when the
program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The
referenced commit in the fixes tag corrected the assumption in the mlx5
driver that the XDP buffer layout doesn't change during a program
execution. However, this fix introduced another issue: the dropped
fragments still need to be counted on the driver side to avoid page
fragment reference counting issues.

Such issue can be observed with the
test_xdp_native_adjst_tail_shrnk_data selftest when using a payload of
3600 and shrinking by 256 bytes (an upcoming selftest patch): the last
fragment gets released by the XDP code but doesn't get tracked by the
driver. This results in a negative pp_ref_count during page release and
the following splat:

  WARNING: include/net/page_pool/helpers.h:297 at mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core], CPU#12: ip/3137
  Modules linked in: [...]
  CPU: 12 UID: 0 PID: 3137 Comm: ip Not tainted 6.19.0-rc3+ #12 NONE
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
  RIP: 0010:mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core]
  [...]
  Call Trace:
   <TASK>
   mlx5e_dealloc_rx_wqe+0xcb/0x1a0 [mlx5_core]
   mlx5e_free_rx_descs+0x7f/0x110 [mlx5_core]
   mlx5e_close_rq+0x50/0x60 [mlx5_core]
   mlx5e_close_queues+0x36/0x2c0 [mlx5_core]
   mlx5e_close_channel+0x1c/0x50 [mlx5_core]
   mlx5e_close_channels+0x45/0x80 [mlx5_core]
   mlx5e_safe_switch_params+0x1a5/0x230 [mlx5_core]
   mlx5e_change_mtu+0xf3/0x2f0 [mlx5_core]
   netif_set_mtu_ext+0xf1/0x230
   do_setlink.isra.0+0x219/0x1180
   rtnl_newlink+0x79f/0xb60
   rtnetlink_rcv_msg+0x213/0x3a0
   netlink_rcv_skb+0x48/0xf0
   netlink_unicast+0x24a/0x350
   netlink_sendmsg+0x1ee/0x410
   __sock_sendmsg+0x38/0x60
   ____sys_sendmsg+0x232/0x280
   ___sys_sendmsg+0x78/0xb0
   __sys_sendmsg+0x5f/0xb0
   [...]
   do_syscall_64+0x57/0xc50

This patch fixes the issue by doing page frag counting on all the
original XDP buffer fragments for all relevant XDP actions (XDP_TX ,
XDP_REDIRECT and XDP_PASS). This is basically reverting to the original
counting before the commit in the fixes tag.

As frag_page is still pointing to the original tail, the nr_frags
parameter to xdp_update_skb_frags_info() needs to be calculated
in a different way to reflect the new nr_frags.

Fixes: afd5ba577c10 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for legacy RQ")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Link: https://patch.msgid.link/20260305142634.1813208-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 40e53a612989..268e20884757 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1589,6 +1589,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	struct skb_shared_info *sinfo;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
+	u8 nr_frags_free = 0;
 	struct sk_buff *skb;
 	dma_addr_t addr;
 	u32 truesize;
@@ -1631,15 +1632,13 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u8 old_nr_frags = sinfo->nr_frags;
 
 		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT,
 						 rq->flags)) {
 				struct mlx5e_wqe_frag_info *pwi;
 
-				wi -= old_nr_frags - sinfo->nr_frags;
-
 				for (pwi = head_wi; pwi < wi; pwi++)
 					pwi->frag_page->frags++;
 			}
@@ -1647,10 +1646,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		}
 
 		nr_frags_free = old_nr_frags - sinfo->nr_frags;
-		if (unlikely(nr_frags_free)) {
-			wi -= nr_frags_free;
+		if (unlikely(nr_frags_free))
 			truesize -= nr_frags_free * frag_info->frag_stride;
-		}
 	}
 
 	skb = mlx5e_build_linear_skb(
@@ -1666,7 +1663,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	if (xdp_buff_has_frags(&mxbuf->xdp)) {
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
-		xdp_update_skb_frags_info(skb, wi - head_wi - 1,
+		xdp_update_skb_frags_info(skb, wi - head_wi - nr_frags_free - 1,
 					  sinfo->xdp_frags_size, truesize,
 					  xdp_buff_get_skb_flags(&mxbuf->xdp));
 

From 5c3398a54266541610c8d0a7082e654e9ff3e259 Mon Sep 17 00:00:00 2001
From: Jian Zhang <zhangjian.3032@bytedance.com>
Date: Thu, 5 Mar 2026 14:06:55 +0800
Subject: [PATCH 1008/1303] net: ncsi: fix skb leak in error paths

Early return paths in NCSI RX and AEN handlers fail to release
the received skb, resulting in a memory leak.

Specifically, ncsi_aen_handler() returns on invalid AEN packets
without consuming the skb. Similarly, ncsi_rcv_rsp() exits early
when failing to resolve the NCSI device, response handler, or
request, leaving the skb unfreed.

CC: stable@vger.kernel.org
Fixes: 7a82ecf4cfb8 ("net/ncsi: NCSI AEN packet handler")
Fixes: 138635cc27c9 ("net/ncsi: NCSI response packet handler")
Signed-off-by: Jian Zhang <zhangjian.3032@bytedance.com>
Link: https://patch.msgid.link/20260305060656.3357250-1-zhangjian.3032@bytedance.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ncsi/ncsi-aen.c |  3 ++-
 net/ncsi/ncsi-rsp.c | 16 ++++++++++++----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 62fb1031763d..040a31557201 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -224,7 +224,8 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb)
 	if (!nah) {
 		netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n",
 			    h->type);
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out;
 	}
 
 	ret = ncsi_validate_aen_pkt(h, nah->payload);
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 271ec6c3929e..fbd84bc8026a 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -1176,8 +1176,10 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	/* Find the NCSI device */
 	nd = ncsi_find_dev(orig_dev);
 	ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL;
-	if (!ndp)
-		return -ENODEV;
+	if (!ndp) {
+		ret = -ENODEV;
+		goto err_free_skb;
+	}
 
 	/* Check if it is AEN packet */
 	hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb);
@@ -1199,7 +1201,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	if (!nrh) {
 		netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n",
 			   hdr->type);
-		return -ENOENT;
+		ret = -ENOENT;
+		goto err_free_skb;
 	}
 
 	/* Associate with the request */
@@ -1207,7 +1210,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	nr = &ndp->requests[hdr->id];
 	if (!nr->used) {
 		spin_unlock_irqrestore(&ndp->lock, flags);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_free_skb;
 	}
 
 	nr->rsp = skb;
@@ -1261,4 +1265,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 out:
 	ncsi_free_request(nr);
 	return ret;
+
+err_free_skb:
+	kfree_skb(skb);
+	return ret;
 }

From 0cc0c2e661af418bbf7074179ea5cfffc0a5c466 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 4 Mar 2026 12:42:18 +0800
Subject: [PATCH 1009/1303] net/sched: teql: fix NULL pointer dereference in
 iptunnel_xmit on TEQL slave xmit

teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit
through slave devices, but does not update skb->dev to the slave device
beforehand.

When a gretap tunnel is a TEQL slave, the transmit path reaches
iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0
master) and later calls iptunnel_xmit_stats(dev, pkt_len). This
function does:

    get_cpu_ptr(dev->tstats)

Since teql_master_setup() does not set dev->pcpu_stat_type to
NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats
for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes
NULL + __per_cpu_offset[cpu], resulting in a page fault.

 BUG: unable to handle page fault for address: ffff8880e6659018
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 68bc067 P4D 68bc067 PUD 0
 Oops: Oops: 0002 [#1] SMP KASAN PTI
 RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89)
 Call Trace:
  <TASK>
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  __gre_xmit (net/ipv4/ip_gre.c:478)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  teql_master_xmit (net/sched/sch_teql.c:319)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  neigh_direct_output (net/core/neighbour.c:1660)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  __ip_finish_output.part.0 (net/ipv4/ip_output.c:315)
  ip_mc_output (net/ipv4/ip_output.c:369)
  ip_send_skb (net/ipv4/ip_output.c:1508)
  udp_send_skb (net/ipv4/udp.c:1195)
  udp_sendmsg (net/ipv4/udp.c:1485)
  inet_sendmsg (net/ipv4/af_inet.c:859)
  __sys_sendto (net/socket.c:2206)

Fix this by setting skb->dev = slave before calling
netdev_start_xmit(), so that tunnel xmit functions see the correct
slave device with properly allocated tstats.

Fixes: 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260304044216.3517851-3-bestswngs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_teql.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 6e4bdaa876ed..783300d8b019 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -315,6 +315,7 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
 			if (__netif_tx_trylock(slave_txq)) {
 				unsigned int length = qdisc_pkt_len(skb);
 
+				skb->dev = slave;
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
 				    netdev_start_xmit(skb, slave, slave_txq, false) ==
 				    NETDEV_TX_OK) {

From 976703cae7375898b445fc40d14faf849e916a4b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 5 Mar 2026 00:08:59 +0200
Subject: [PATCH 1010/1303] net: dsa: sja1105: reorder sja1105_reload_cbs() and
 phylink_replay_link_end()

Move phylink_replay_link_end() as the last locked operation under
sja1105_static_config_reload(). The purpose is to be able to goto
this step from the error path of intermediate steps (we must call
phylink_replay_link_end()).

sja1105_reload_cbs() notably does not depend on port states or link
speeds. See commit 954ad9bf13c4 ("net: dsa: sja1105: fix bandwidth
discrepancy between tc-cbs software and offload") which has discussed
this issue specifically.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260304220900.3865120-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 94d17b06da40..bf720d96bad8 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2339,13 +2339,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 			goto out;
 	}
 
+	rc = sja1105_reload_cbs(priv);
+
 	dsa_switch_for_each_available_port(dp, ds)
 		if (dp->pl)
 			phylink_replay_link_end(dp->pl);
-
-	rc = sja1105_reload_cbs(priv);
-	if (rc < 0)
-		goto out;
 out:
 	mutex_unlock(&priv->mgmt_lock);
 	mutex_unlock(&priv->fdb_lock);

From ce2da643f00af3111f1fffe2adea8506592ef6e5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 5 Mar 2026 00:09:00 +0200
Subject: [PATCH 1011/1303] net: dsa: sja1105: ensure phylink_replay_link_end()
 will not be missed

Most errors that can occur in sja1105_static_config_reload() are fatal
(example: fail to communicate with hardware), but not all are.

For example, sja1105_static_config_upload() -> kcalloc() may fail, and
if that happens, we have called phylink_replay_link_begin() but never
phylink_replay_link_end().

Under that circumstance, all port phylink instances are left in a state
where the resolver is stopped with the PHYLINK_DISABLE_REPLAY bit set.
We have effectively disabled link management with no way to recover from
this condition.

Avoid that situation by ensuring phylink_replay_link_begin() is always
paired with phylink_replay_link_end(), regardless of whether we faced
any errors during switch reset, configuration reload and general state
reload.

Fixes: 0b2edc531e0b ("net: dsa: sja1105: let phylink help with the replay of link callbacks")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260304220900.3865120-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index bf720d96bad8..c72c2bfdcffb 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2341,10 +2341,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 
 	rc = sja1105_reload_cbs(priv);
 
+out:
 	dsa_switch_for_each_available_port(dp, ds)
 		if (dp->pl)
 			phylink_replay_link_end(dp->pl);
-out:
+
 	mutex_unlock(&priv->mgmt_lock);
 	mutex_unlock(&priv->fdb_lock);
 

From 4245a79003adf30e67f8e9060915bd05cb31d142 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 5 Mar 2026 12:31:01 +0000
Subject: [PATCH 1012/1303] rxrpc, afs: Fix missing error pointer check after
 rxrpc_kernel_lookup_peer()

rxrpc_kernel_lookup_peer() can also return error pointers in addition to
NULL, so just checking for NULL is not sufficient.

Fix this by:

 (1) Changing rxrpc_kernel_lookup_peer() to return -ENOMEM rather than NULL
     on allocation failure.

 (2) Making the callers in afs use IS_ERR() and PTR_ERR() to pass on the
     error code returned.

Fixes: 72904d7b9bfb ("rxrpc, afs: Allow afs to pin rxrpc_peer objects")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/368272.1772713861@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/addr_list.c   | 8 ++++----
 net/rxrpc/af_rxrpc.c | 8 +++++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index a936f9ea5610..63bf096b721a 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -298,8 +298,8 @@ int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist,
 	srx.transport.sin.sin_addr.s_addr = xdr;
 
 	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
-	if (!peer)
-		return -ENOMEM;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
 
 	for (i = 0; i < alist->nr_ipv4; i++) {
 		if (peer == alist->addrs[i].peer) {
@@ -342,8 +342,8 @@ int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
 	memcpy(&srx.transport.sin6.sin6_addr, xdr, 16);
 
 	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
-	if (!peer)
-		return -ENOMEM;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
 
 	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
 		if (peer == alist->addrs[i].peer) {
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0c2c68c4b07e..0f90272ac254 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -267,12 +267,13 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * Lookup or create a remote transport endpoint record for the specified
  * address.
  *
- * Return: The peer record found with a reference, %NULL if no record is found
- * or a negative error code if the address is invalid or unsupported.
+ * Return: The peer record found with a reference or a negative error code if
+ * the address is invalid or unsupported.
  */
 struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
 					    struct sockaddr_rxrpc *srx, gfp_t gfp)
 {
+	struct rxrpc_peer *peer;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
@@ -280,7 +281,8 @@ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	return rxrpc_lookup_peer(rx->local, srx, gfp);
+	peer = rxrpc_lookup_peer(rx->local, srx, gfp);
+	return peer ?: ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(rxrpc_kernel_lookup_peer);
 

From fbc7aef517d8765e4c425d2792409bb9bf2e1f13 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:24 -0800
Subject: [PATCH 1013/1303] bpf: Fix u32/s32 bounds when ranges cross min/max
 boundary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Same as in __reg64_deduce_bounds(), refine s32/u32 ranges
in __reg32_deduce_bounds() in the following situations:

- s32 range crosses U32_MAX/0 boundary, positive part of the s32 range
  overlaps with u32 range:

  0                                                   U32_MAX
  |  [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]              |
  |----------------------------|----------------------------|
  |xxxxx s32 range xxxxxxxxx]                       [xxxxxxx|
  0                     S32_MAX S32_MIN                    -1

- s32 range crosses U32_MAX/0 boundary, negative part of the s32 range
  overlaps with u32 range:

  0                                                   U32_MAX
  |              [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]  |
  |----------------------------|----------------------------|
  |xxxxxxxxx]                       [xxxxxxxxxxxx s32 range |
  0                     S32_MAX S32_MIN                    -1

- No refinement if ranges overlap in two intervals.

This helps for e.g. consider the following program:

   call %[bpf_get_prandom_u32];
   w0 &= 0xffffffff;
   if w0 < 0x3 goto 1f;    // on fall-through u32 range [3..U32_MAX]
   if w0 s> 0x1 goto 1f;   // on fall-through s32 range [S32_MIN..1]
   if w0 s< 0x0 goto 1f;   // range can be narrowed to  [S32_MIN..-1]
   r10 = 0;
1: ...;

The reg_bounds.c selftest is updated to incorporate identical logic,
refinement based on non-overflowing range halves:

  ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪
  ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1]))

Reported-by: Andrea Righi <arighi@nvidia.com>
Reported-by: Emil Tsalapatis <emil@etsalapatis.com>
Closes: https://lore.kernel.org/bpf/aakqucg4vcujVwif@gpd4/T/
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-1-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                         | 24 +++++++
 .../selftests/bpf/prog_tests/reg_bounds.c     | 62 +++++++++++++++++--
 2 files changed, 82 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 401d6c4960ec..f960b382fdb3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2511,6 +2511,30 @@ static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
 	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
 		reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value);
 		reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value);
+	} else {
+		if (reg->u32_max_value < (u32)reg->s32_min_value) {
+			/* See __reg64_deduce_bounds() for detailed explanation.
+			 * Refine ranges in the following situation:
+			 *
+			 * 0                                                   U32_MAX
+			 * |  [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]              |
+			 * |----------------------------|----------------------------|
+			 * |xxxxx s32 range xxxxxxxxx]                       [xxxxxxx|
+			 * 0                     S32_MAX S32_MIN                    -1
+			 */
+			reg->s32_min_value = (s32)reg->u32_min_value;
+			reg->u32_max_value = min_t(u32, reg->u32_max_value, reg->s32_max_value);
+		} else if ((u32)reg->s32_max_value < reg->u32_min_value) {
+			/*
+			 * 0                                                   U32_MAX
+			 * |              [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]  |
+			 * |----------------------------|----------------------------|
+			 * |xxxxxxxxx]                       [xxxxxxxxxxxx s32 range |
+			 * 0                     S32_MAX S32_MIN                    -1
+			 */
+			reg->s32_max_value = (s32)reg->u32_max_value;
+			reg->u32_min_value = max_t(u32, reg->u32_min_value, reg->s32_min_value);
+		}
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 0322f817d07b..04938d0d431b 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -422,15 +422,69 @@ static bool is_valid_range(enum num_t t, struct range x)
 	}
 }
 
-static struct range range_improve(enum num_t t, struct range old, struct range new)
+static struct range range_intersection(enum num_t t, struct range old, struct range new)
 {
 	return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b));
 }
 
+/*
+ * Result is precise when 'x' and 'y' overlap or form a continuous range,
+ * result is an over-approximation if 'x' and 'y' do not overlap.
+ */
+static struct range range_union(enum num_t t, struct range x, struct range y)
+{
+	if (!is_valid_range(t, x))
+		return y;
+	if (!is_valid_range(t, y))
+		return x;
+	return range(t, min_t(t, x.a, y.a), max_t(t, x.b, y.b));
+}
+
+/*
+ * This function attempts to improve x range intersecting it with y.
+ * range_cast(... to_t ...) looses precision for ranges that pass to_t
+ * min/max boundaries. To avoid such precision loses this function
+ * splits both x and y into halves corresponding to non-overflowing
+ * sub-ranges: [0, smin] and [smax, -1].
+ * Final result is computed as follows:
+ *
+ *   ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪
+ *   ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1]))
+ *
+ * Precision might still be lost if final union is not a continuous range.
+ */
+static struct range range_refine_in_halves(enum num_t x_t, struct range x,
+					   enum num_t y_t, struct range y)
+{
+	struct range x_pos, x_neg, y_pos, y_neg, r_pos, r_neg;
+	u64 smax, smin, neg_one;
+
+	if (t_is_32(x_t)) {
+		smax = (u64)(u32)S32_MAX;
+		smin = (u64)(u32)S32_MIN;
+		neg_one = (u64)(u32)(s32)(-1);
+	} else {
+		smax = (u64)S64_MAX;
+		smin = (u64)S64_MIN;
+		neg_one = U64_MAX;
+	}
+	x_pos = range_intersection(x_t, x, range(x_t, 0, smax));
+	x_neg = range_intersection(x_t, x, range(x_t, smin, neg_one));
+	y_pos = range_intersection(y_t, y, range(x_t, 0, smax));
+	y_neg = range_intersection(y_t, y, range(y_t, smin, neg_one));
+	r_pos = range_intersection(x_t, x_pos, range_cast(y_t, x_t, y_pos));
+	r_neg = range_intersection(x_t, x_neg, range_cast(y_t, x_t, y_neg));
+	return range_union(x_t, r_pos, r_neg);
+
+}
+
 static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y)
 {
 	struct range y_cast;
 
+	if (t_is_32(x_t) == t_is_32(y_t))
+		x = range_refine_in_halves(x_t, x, y_t, y);
+
 	y_cast = range_cast(y_t, x_t, y);
 
 	/* If we know that
@@ -444,7 +498,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 	 */
 	if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX  && y_cast.b <= S32_MAX &&
 	    (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX)
-		return range_improve(x_t, x, y_cast);
+		return range_intersection(x_t, x, y_cast);
 
 	/* the case when new range knowledge, *y*, is a 32-bit subregister
 	 * range, while previous range knowledge, *x*, is a full register
@@ -462,7 +516,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 		x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b));
 		if (!is_valid_range(x_t, x_swap))
 			return x;
-		return range_improve(x_t, x, x_swap);
+		return range_intersection(x_t, x, x_swap);
 	}
 
 	if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
@@ -480,7 +534,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 	}
 
 	/* otherwise, plain range cast and intersection works */
-	return range_improve(x_t, x, y_cast);
+	return range_intersection(x_t, x, y_cast);
 }
 
 /* =======================

From f81fdfd16771e266753146bd83f6dd23515ebee9 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:25 -0800
Subject: [PATCH 1014/1303] selftests/bpf: test refining u32/s32 bounds when
 ranges cross min/max boundary

Two test cases for signed/unsigned 32-bit bounds refinement
when s32 range crosses the sign boundary:
- s32 range [S32_MIN..1] overlapping with u32 range [3..U32_MAX],
  s32 range tail before sign boundary overlaps with u32 range.
- s32 range [-3..5] overlapping with u32 range [0..S32_MIN+3],
  s32 range head after the sign boundary overlaps with u32 range.

This covers both branches added in the __reg32_deduce_bounds().

Also, crossing_32_bit_signed_boundary_2() no longer triggers invariant
violations.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Reviewed-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-2-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/verifier_bounds.c     | 39 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 97065a26cf70..e526315c718a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1148,7 +1148,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
 __success __retval(0)
-__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
+__flag(BPF_F_TEST_REG_INVARIANTS)
 __naked void crossing_32_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -2000,4 +2000,41 @@ __naked void bounds_refinement_multiple_overlaps(void *ctx)
 	: __clobber_all);
 }
 
+SEC("socket")
+__success
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void signed_unsigned_intersection32_case1(void *ctx)
+{
+	asm volatile("									\
+	call %[bpf_get_prandom_u32];							\
+	w0 &= 0xffffffff;								\
+	if w0 < 0x3 goto 1f;		/* on fall-through u32 range [3..U32_MAX]  */	\
+	if w0 s> 0x1 goto 1f;		/* on fall-through s32 range [S32_MIN..1]  */	\
+	if w0 s< 0x0 goto 1f;		/* range can be narrowed to  [S32_MIN..-1] */	\
+	r10 = 0;			/* thus predicting the jump. */			\
+1:	exit;										\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void signed_unsigned_intersection32_case2(void *ctx)
+{
+	asm volatile("									\
+	call %[bpf_get_prandom_u32];							\
+	w0 &= 0xffffffff;								\
+	if w0 > 0x80000003 goto 1f;	/* on fall-through u32 range [0..S32_MIN+3] */	\
+	if w0 s< -3 goto 1f;		/* on fall-through s32 range [-3..S32_MAX] */	\
+	if w0 s> 5 goto 1f;		/* on fall-through s32 range [-3..5] */		\
+	if w0 <= 5 goto 1f;		/* range can be narrowed to  [0..5] */		\
+	r10 = 0;			/* thus predicting the jump */			\
+1:	exit;										\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";

From d87c9305a8841b312b14ca0c360a563ef60b2a5b Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:26 -0800
Subject: [PATCH 1015/1303] Revert "selftests/bpf: Update reg_bound range
 refinement logic"

This reverts commit da653de268d32a80e135c9eb960a8147c186f1bc.
Removed logic is now covered by range_refine_in_halves()
which handles both 32-bit and 64-bit refinements.

Suggested-by: Paul Chaignon <paul.chaignon@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-3-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/reg_bounds.c  | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 04938d0d431b..cb8dd2f63296 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -519,20 +519,6 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 		return range_intersection(x_t, x, x_swap);
 	}
 
-	if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
-		if (x_t == S64 && x.a > x.b) {
-			if (x.b < y.a && x.a <= y.b)
-				return range(x_t, x.a, y.b);
-			if (x.a > y.b && x.b >= y.a)
-				return range(x_t, y.a, x.b);
-		} else if (x_t == U64 && y.a > y.b) {
-			if (y.b < x.a && y.a <= x.b)
-				return range(x_t, y.a, x.b);
-			if (y.a > x.b && y.b >= x.a)
-				return range(x_t, x.a, y.b);
-		}
-	}
-
 	/* otherwise, plain range cast and intersection works */
 	return range_intersection(x_t, x, y_cast);
 }

From 3aa1417803c1833cbd5bacb7e6a6489a196f2519 Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Thu, 5 Mar 2026 14:39:38 +0800
Subject: [PATCH 1016/1303] net: spacemit: Fix error handling in
 emac_alloc_rx_desc_buffers()

Even if we get a dma_mapping_error() while mapping an RX buffer, we
should still update rx_ring->head to ensure that the buffers we were
able to allocate and map are used. Fix this by breaking out to the
existing code after the loop, analogous to the existing handling for skb
allocation failure.

Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC")
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-1-e4e434d65055@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/spacemit/k1_emac.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c
index 338a2637b1da..5a5cb61be08c 100644
--- a/drivers/net/ethernet/spacemit/k1_emac.c
+++ b/drivers/net/ethernet/spacemit/k1_emac.c
@@ -565,7 +565,9 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv)
 						  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&priv->pdev->dev, rx_buf->dma_addr)) {
 			dev_err_ratelimited(&ndev->dev, "Mapping skb failed\n");
-			goto err_free_skb;
+			dev_kfree_skb_any(skb);
+			rx_buf->skb = NULL;
+			break;
 		}
 
 		rx_desc_addr = &((struct emac_desc *)rx_ring->desc_addr)[i];
@@ -590,10 +592,6 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv)
 
 	rx_ring->head = i;
 	return;
-
-err_free_skb:
-	dev_kfree_skb_any(skb);
-	rx_buf->skb = NULL;
 }
 
 /* Returns number of packets received */

From 86292155bea578ebab0ca3b65d4d87ecd8a0e9ea Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Thu, 5 Mar 2026 14:39:39 +0800
Subject: [PATCH 1017/1303] net: spacemit: Fix error handling in
 emac_tx_mem_map()

The DMA mappings were leaked on mapping error. Free them with the
existing emac_free_tx_buf() function.

Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC")
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-2-e4e434d65055@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/spacemit/k1_emac.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c
index 5a5cb61be08c..15d43e4a748b 100644
--- a/drivers/net/ethernet/spacemit/k1_emac.c
+++ b/drivers/net/ethernet/spacemit/k1_emac.c
@@ -733,7 +733,7 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb)
 	struct emac_desc tx_desc, *tx_desc_addr;
 	struct device *dev = &priv->pdev->dev;
 	struct emac_tx_desc_buffer *tx_buf;
-	u32 head, old_head, frag_num, f;
+	u32 head, old_head, frag_num, f, i;
 	bool buf_idx;
 
 	frag_num = skb_shinfo(skb)->nr_frags;
@@ -801,6 +801,15 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb)
 
 err_free_skb:
 	dev_dstats_tx_dropped(priv->ndev);
+
+	i = old_head;
+	while (i != head) {
+		emac_free_tx_buf(priv, i);
+
+		if (++i == tx_ring->total_cnt)
+			i = 0;
+	}
+
 	dev_kfree_skb_any(skb);
 }
 

From d008ba8be8984760e36d7dcd4adbd5a41a645708 Mon Sep 17 00:00:00 2001
From: Calvin Owens <calvin@wbinvd.org>
Date: Fri, 6 Mar 2026 19:19:25 -0800
Subject: [PATCH 1018/1303] tracing: Fix trace_buf_size= cmdline parameter with
 sizes >= 2G

Some of the sizing logic through tracer_alloc_buffers() uses int
internally, causing unexpected behavior if the user passes a value that
does not fit in an int (on my x86 machine, the result is uselessly tiny
buffers).

Fix by plumbing the parameter's real type (unsigned long) through to the
ring buffer allocation functions, which already use unsigned long.

It has always been possible to create larger ring buffers via the sysfs
interface: this only affects the cmdline parameter.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/bff42a4288aada08bdf74da3f5b67a2c28b761f8.1772852067.git.calvin@wbinvd.org
Fixes: 73c5162aa362 ("tracing: keep ring buffer to minimum size till used")
Signed-off-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1e7c032a72d2..ebd996f8710e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9350,7 +9350,7 @@ static void setup_trace_scratch(struct trace_array *tr,
 }
 
 static int
-allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size)
+allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size)
 {
 	enum ring_buffer_flags rb_flags;
 	struct trace_scratch *tscratch;
@@ -9405,7 +9405,7 @@ static void free_trace_buffer(struct array_buffer *buf)
 	}
 }
 
-static int allocate_trace_buffers(struct trace_array *tr, int size)
+static int allocate_trace_buffers(struct trace_array *tr, unsigned long size)
 {
 	int ret;
 
@@ -10769,7 +10769,7 @@ __init static void enable_instances(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	int ring_buf_size;
+	unsigned long ring_buf_size;
 	int ret = -ENOMEM;
 
 

From 2658a1720a1944fbaeda937000ad2b3c3dfaf1bb Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:02:47 -0800
Subject: [PATCH 1019/1303] bpf: collect only live registers in linked regs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix an inconsistency between func_states_equal() and
collect_linked_regs():
- regsafe() uses check_ids() to verify that cached and current states
  have identical register id mapping.
- func_states_equal() calls regsafe() only for registers computed as
  live by compute_live_registers().
- clean_live_states() is supposed to remove dead registers from cached
  states, but it can skip states belonging to an iterator-based loop.
- collect_linked_regs() collects all registers sharing the same id,
  ignoring the marks computed by compute_live_registers().
  Linked registers are stored in the state's jump history.
- backtrack_insn() marks all linked registers for an instruction
  as precise whenever one of the linked registers is precise.

The above might lead to a scenario:
- There is an instruction I with register rY known to be dead at I.
- Instruction I is reached via two paths: first A, then B.
- On path A:
  - There is an id link between registers rX and rY.
  - Checkpoint C is created at I.
  - Linked register set {rX, rY} is saved to the jump history.
  - rX is marked as precise at I, causing both rX and rY
    to be marked precise at C.
- On path B:
  - There is no id link between registers rX and rY,
    otherwise register states are sub-states of those in C.
  - Because rY is dead at I, check_ids() returns true.
  - Current state is considered equal to checkpoint C,
    propagate_precision() propagates spurious precision
    mark for register rY along the path B.
  - Depending on a program, this might hit verifier_bug()
    in the backtrack_insn(), e.g. if rY ∈  [r1..r5]
    and backtrack_insn() spots a function call.

The reproducer program is in the next patch.
This was hit by sched_ext scx_lavd scheduler code.

Changes in tests:
- verifier_scalar_ids.c selftests need modification to preserve
  some registers as live for __msg() checks.
- exceptions_assert.c adjusted to match changes in the verifier log,
  R0 is dead after conditional instruction and thus does not get
  range.
- precise.c adjusted to match changes in the verifier log, register r9
  is dead after comparison and it's range is not important for test.

Reported-by: Emil Tsalapatis <emil@etsalapatis.com>
Fixes: 0fb3cf6110a5 ("bpf: use register liveness information for func_states_equal")
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-linked-regs-and-propagate-precision-v1-1-18e859be570d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                         | 13 ++++-
 .../selftests/bpf/progs/exceptions_assert.c   | 34 +++++------
 .../selftests/bpf/progs/verifier_scalar_ids.c | 56 ++++++++++++++-----
 .../testing/selftests/bpf/verifier/precise.c  |  8 +--
 4 files changed, 73 insertions(+), 38 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f960b382fdb3..836ceb128d19 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17359,17 +17359,24 @@ static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_st
  * in verifier state, save R in linked_regs if R->id == id.
  * If there are too many Rs sharing same id, reset id for leftover Rs.
  */
-static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id,
+static void collect_linked_regs(struct bpf_verifier_env *env,
+				struct bpf_verifier_state *vstate,
+				u32 id,
 				struct linked_regs *linked_regs)
 {
+	struct bpf_insn_aux_data *aux = env->insn_aux_data;
 	struct bpf_func_state *func;
 	struct bpf_reg_state *reg;
+	u16 live_regs;
 	int i, j;
 
 	id = id & ~BPF_ADD_CONST;
 	for (i = vstate->curframe; i >= 0; i--) {
+		live_regs = aux[frame_insn_idx(vstate, i)].live_regs_before;
 		func = vstate->frame[i];
 		for (j = 0; j < BPF_REG_FP; j++) {
+			if (!(live_regs & BIT(j)))
+				continue;
 			reg = &func->regs[j];
 			__collect_linked_regs(linked_regs, reg, id, i, j, true);
 		}
@@ -17584,9 +17591,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 * if parent state is created.
 	 */
 	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id)
-		collect_linked_regs(this_branch, src_reg->id, &linked_regs);
+		collect_linked_regs(env, this_branch, src_reg->id, &linked_regs);
 	if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
-		collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
+		collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs);
 	if (linked_regs.cnt > 1) {
 		err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
 		if (err)
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index a01c2736890f..858af5988a38 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -18,43 +18,43 @@
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0=0xffffffff80000000")
+__msg("R{{.}}=0xffffffff80000000")
 check_assert(s64, ==, eq_int_min, INT_MIN);
-__msg(": R0=0x7fffffff")
+__msg("R{{.}}=0x7fffffff")
 check_assert(s64, ==, eq_int_max, INT_MAX);
-__msg(": R0=0")
+__msg("R{{.}}=0")
 check_assert(s64, ==, eq_zero, 0);
-__msg(": R0=0x8000000000000000 R1=0x8000000000000000")
+__msg("R{{.}}=0x8000000000000000")
 check_assert(s64, ==, eq_llong_min, LLONG_MIN);
-__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff")
+__msg("R{{.}}=0x7fffffffffffffff")
 check_assert(s64, ==, eq_llong_max, LLONG_MAX);
 
-__msg(": R0=scalar(id=1,smax=0x7ffffffe)")
+__msg("R{{.}}=scalar(id=1,smax=0x7ffffffe)")
 check_assert(s64, <, lt_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, <, lt_zero, 0);
-__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff")
+__msg("R{{.}}=scalar(id=1,smax=0xffffffff7fffffff")
 check_assert(s64, <, lt_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smax=0x7fffffff)")
+__msg("R{{.}}=scalar(id=1,smax=0x7fffffff)")
 check_assert(s64, <=, le_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smax=0)")
+__msg("R{{.}}=scalar(id=1,smax=0)")
 check_assert(s64, <=, le_zero, 0);
-__msg(": R0=scalar(id=1,smax=0xffffffff80000000")
+__msg("R{{.}}=scalar(id=1,smax=0xffffffff80000000")
 check_assert(s64, <=, le_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >, gt_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >, gt_zero, 0);
-__msg(": R0=scalar(id=1,smin=0xffffffff80000001")
+__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000001")
 check_assert(s64, >, gt_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >=, ge_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >=, ge_zero, 0);
-__msg(": R0=scalar(id=1,smin=0xffffffff80000000")
+__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000000")
 check_assert(s64, >=, ge_neg, INT_MIN);
 
 SEC("?tc")
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 3072fee9a448..58c7704d61cd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -40,6 +40,9 @@ __naked void linked_regs_bpf_k(void)
 	 */
 	"r3 = r10;"
 	"r3 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -73,6 +76,9 @@ __naked void linked_regs_bpf_x_src(void)
 	 */
 	"r4 = r10;"
 	"r4 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -106,6 +112,10 @@ __naked void linked_regs_bpf_x_dst(void)
 	 */
 	"r4 = r10;"
 	"r4 += r3;"
+	/* Mark r1 and r2 as alive. */
+	"r0 = r0;"
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -143,6 +153,9 @@ __naked void linked_regs_broken_link(void)
 	 */
 	"r3 = r10;"
 	"r3 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -156,16 +169,16 @@ __naked void linked_regs_broken_link(void)
  */
 SEC("socket")
 __success __log_level(2)
-__msg("12: (0f) r2 += r1")
+__msg("17: (0f) r2 += r1")
 /* Current state */
-__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ")
-__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10")
+__msg("frame2: last_idx 17 first_idx 14 subseq_idx -1 ")
+__msg("frame2: regs=r1 stack= before 16: (bf) r2 = r10")
 __msg("frame2: parent state regs=r1 stack=")
 __msg("frame1: parent state regs= stack=")
 __msg("frame0: parent state regs= stack=")
 /* Parent state */
-__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ")
-__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0")
+__msg("frame2: last_idx 13 first_idx 13 subseq_idx 14 ")
+__msg("frame2: regs=r1 stack= before 13: (25) if r1 > 0x7 goto pc+0")
 __msg("frame2: parent state regs=r1 stack=")
 /* frame1.r{6,7} are marked because mark_precise_scalar_ids()
  * looks for all registers with frame2.r1.id in the current state
@@ -173,20 +186,20 @@ __msg("frame2: parent state regs=r1 stack=")
 __msg("frame1: parent state regs=r6,r7 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10")
-__msg("frame2: regs=r1 stack= before 8: (85) call pc+1")
+__msg("frame2: last_idx 9 first_idx 9 subseq_idx 13")
+__msg("frame2: regs=r1 stack= before 9: (85) call pc+3")
 /* frame1.r1 is marked because of backtracking of call instruction */
 __msg("frame1: parent state regs=r1,r6,r7 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8")
-__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1")
-__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1")
+__msg("frame1: last_idx 8 first_idx 7 subseq_idx 9")
+__msg("frame1: regs=r1,r6,r7 stack= before 8: (bf) r7 = r1")
+__msg("frame1: regs=r1,r6 stack= before 7: (bf) r6 = r1")
 __msg("frame1: parent state regs=r1 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6")
-__msg("frame1: regs=r1 stack= before 4: (85) call pc+1")
+__msg("frame1: last_idx 4 first_idx 4 subseq_idx 7")
+__msg("frame1: regs=r1 stack= before 4: (85) call pc+2")
 __msg("frame0: parent state regs=r1,r6 stack=")
 /* Parent state */
 __msg("frame0: last_idx 3 first_idx 1 subseq_idx 4")
@@ -204,6 +217,7 @@ __naked void precision_many_frames(void)
 	"r1 = r0;"
 	"r6 = r0;"
 	"call precision_many_frames__foo;"
+	"r6 = r6;" /* mark r6 as live */
 	"exit;"
 	:
 	: __imm(bpf_ktime_get_ns)
@@ -220,6 +234,8 @@ void precision_many_frames__foo(void)
 	"r6 = r1;"
 	"r7 = r1;"
 	"call precision_many_frames__bar;"
+	"r6 = r6;" /* mark r6 as live */
+	"r7 = r7;" /* mark r7 as live */
 	"exit"
 	::: __clobber_all);
 }
@@ -229,6 +245,8 @@ void precision_many_frames__bar(void)
 {
 	asm volatile (
 	"if r1 > 7 goto +0;"
+	"r6 = 0;" /* mark r6 as live */
+	"r7 = 0;" /* mark r7 as live */
 	/* force r1 to be precise, this eventually marks:
 	 * - bar frame r1
 	 * - foo frame r{1,6,7}
@@ -340,6 +358,8 @@ __naked void precision_two_ids(void)
 	"r3 += r7;"
 	/* force r9 to be precise, this also marks r8 */
 	"r3 += r9;"
+	"r6 = r6;" /* mark r6 as live */
+	"r8 = r8;" /* mark r8 as live */
 	"exit;"
 	:
 	: __imm(bpf_ktime_get_ns)
@@ -353,7 +373,7 @@ __flag(BPF_F_TEST_STATE_FREQ)
  * collect_linked_regs() can't tie more than 6 registers for a single insn.
  */
 __msg("8: (25) if r0 > 0x7 goto pc+0         ; R0=scalar(id=1")
-__msg("9: (bf) r6 = r6                       ; R6=scalar(id=2")
+__msg("14: (bf) r6 = r6                      ; R6=scalar(id=2")
 /* check that r{0-5} are marked precise after 'if' */
 __msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
 __msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
@@ -372,6 +392,12 @@ __naked void linked_regs_too_many_regs(void)
 	"r6 = r0;"
 	/* propagate range for r{0-6} */
 	"if r0 > 7 goto +0;"
+	/* keep r{1-5} live */
+	"r1 = r1;"
+	"r2 = r2;"
+	"r3 = r3;"
+	"r4 = r4;"
+	"r5 = r5;"
 	/* make r6 appear in the log */
 	"r6 = r6;"
 	/* force r0 to be precise,
@@ -517,7 +543,7 @@ __naked void check_ids_in_regsafe_2(void)
 	"*(u64*)(r10 - 8) = r1;"
 	/* r9 = pointer to stack */
 	"r9 = r10;"
-	"r9 += -8;"
+	"r9 += -16;"
 	/* r8 = ktime_get_ns() */
 	"call %[bpf_ktime_get_ns];"
 	"r8 = r0;"
@@ -538,6 +564,8 @@ __naked void check_ids_in_regsafe_2(void)
 	"if r7 > 4 goto l2_%=;"
 	/* Access memory at r9[r6] */
 	"r9 += r6;"
+	"r9 += r7;"
+	"r9 += r8;"
 	"r0 = *(u8*)(r9 + 0);"
 "l2_%=:"
 	"r0 = 0;"
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 061d98f6e9bb..a9242103dc47 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -44,9 +44,9 @@
 	mark_precise: frame0: regs=r2 stack= before 23\
 	mark_precise: frame0: regs=r2 stack= before 22\
 	mark_precise: frame0: regs=r2 stack= before 20\
-	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 10\
-	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r2 stack= before 19\
 	mark_precise: frame0: regs=r9 stack= before 18\
 	mark_precise: frame0: regs=r8,r9 stack= before 17\
 	mark_precise: frame0: regs=r0,r9 stack= before 15\
@@ -107,9 +107,9 @@
 	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 20 first_idx 20\
 	mark_precise: frame0: regs=r2 stack= before 20\
-	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 17\
-	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r2 stack= before 19\
 	mark_precise: frame0: regs=r9 stack= before 18\
 	mark_precise: frame0: regs=r8,r9 stack= before 17\
 	mark_precise: frame0: parent state regs= stack=:",

From 223ffb6a3d0582522455e83ccf7ad2d3a753e039 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:02:48 -0800
Subject: [PATCH 1020/1303] selftests/bpf: add reproducer for spurious
 precision propagation through calls

Add a test for the scenario described in the previous commit:
an iterator loop with two paths where one ties r2/r7 via
shared scalar id and skips a call, while the other goes
through the call. Precision marks from the linked registers
get spuriously propagated to the call path via
propagate_precision(), hitting "backtracking call unexpected
regs" in backtrack_insn().

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-linked-regs-and-propagate-precision-v1-2-18e859be570d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../bpf/progs/verifier_linked_scalars.c       | 64 +++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
index 2ef346c827c2..7bf7dbfd237d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
@@ -363,4 +363,68 @@ void alu32_negative_offset(void)
 	__sink(path[0]);
 }
 
+void dummy_calls(void)
+{
+	bpf_iter_num_new(0, 0, 0);
+	bpf_iter_num_next(0);
+	bpf_iter_num_destroy(0);
+}
+
+SEC("socket")
+__success
+__flag(BPF_F_TEST_STATE_FREQ)
+int spurious_precision_marks(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile(
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 4f;"
+		"r7 = *(u32 *)(r0 + 0);"
+		"r8 = *(u32 *)(r0 + 0);"
+		/* This jump can't be predicted and does not change r7 or r8 state. */
+		"if r7 > r8 goto 2f;"
+		/* Branch explored first ties r2 and r7 as having the same id. */
+		"r2 = r7;"
+		"goto 3f;"
+	"2:"
+		/* Branch explored second does not tie r2 and r7 but has a function call. */
+		"call %[bpf_get_prandom_u32];"
+	"3:"
+		/*
+		 * A checkpoint.
+		 * When first branch is explored, this would inject linked registers
+		 * r2 and r7 into the jump history.
+		 * When second branch is explored, this would be a cache hit point,
+		 * triggering propagate_precision().
+		 */
+		"if r7 <= 42 goto +0;"
+		/*
+		 * Mark r7 as precise using an if condition that is always true.
+		 * When reached via the second branch, this triggered a bug in the backtrack_insn()
+		 * because r2 (tied to r7) was propagated as precise to a call.
+		 */
+		"if r7 <= 0xffffFFFF goto +0;"
+		"goto 1b;"
+	"4:"
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_common, "r7", "r8"
+	);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

From 73cdf24e81e4eba52a40a6b10c6cf285d0ac23fd Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:24 +0530
Subject: [PATCH 1021/1303] powerpc64: make clang cross-build friendly

ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on toolchain support for
-fpatchable-function-entry option. The current script that checks
for this support only handles GCC. Rename the script and extend it
to detect support for -fpatchable-function-entry with Clang as well,
allowing clean cross-compilation with Clang toolchains.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-2-hbathini@linux.ibm.com
---
 arch/powerpc/Kconfig                                          | 4 ++--
 ...e-function-entry.sh => check-fpatchable-function-entry.sh} | 0
 2 files changed, 2 insertions(+), 2 deletions(-)
 rename arch/powerpc/tools/{gcc-check-fpatchable-function-entry.sh => check-fpatchable-function-entry.sh} (100%)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ad7a2fe63a2a..10240cb80904 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -573,8 +573,8 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
 	depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2)
 	depends on $(cc-option,-fpatchable-function-entry=2)
 	def_bool y if PPC32
-	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
-	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) $(CLANG_FLAGS) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
 
 config PPC_FTRACE_OUT_OF_LINE
 	def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY
diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/check-fpatchable-function-entry.sh
similarity index 100%
rename from arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
rename to arch/powerpc/tools/check-fpatchable-function-entry.sh

From 875612a7745013a43c67493cb0583ee3f7476344 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:25 +0530
Subject: [PATCH 1022/1303] powerpc64/ftrace: fix OOL stub count with clang

The total number of out-of-line (OOL) stubs required for function
tracing is determined using the following command:

    $(OBJDUMP) -r -j __patchable_function_entries vmlinux.o

While this works correctly with GNU objdump, llvm-objdump does not
list the expected relocation records for this section. Fix this by
using the -d option and counting R_PPC64_ADDR64 relocation entries.
This works as desired with both objdump and llvm-objdump.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-3-hbathini@linux.ibm.com
---
 arch/powerpc/tools/ftrace-gen-ool-stubs.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
index bac186bdf64a..9218d43aeb54 100755
--- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
+++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
@@ -15,9 +15,9 @@ if [ -z "$is_64bit" ]; then
 	RELOCATION=R_PPC_ADDR32
 fi
 
-num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+num_ool_stubs_total=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" |
 		      grep -c "$RELOCATION")
-num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" |
 			 grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION")
 num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext))
 

From db54c28702f7270e74dce36c84cb0db4cec96389 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:26 +0530
Subject: [PATCH 1023/1303] powerpc64/ftrace: workaround clang recording GEP in
 __patchable_function_entries

Support for -fpatchable-function-entry on ppc64le was added in Clang
with [1]. However, when no prefix NOPs are specified - as is the case
with CONFIG_PPC_FTRACE_OUT_OF_LINE - the first NOP is emitted at LEP,
but Clang records the Global Entry Point (GEP) unlike GCC which does
record the Local Entry Point (LEP). Issue [2] has been raised to align
Clang's behavior with GCC. As a temporary workaround to ensure ftrace
initialization works as expected with Clang, derive the LEP using
ppc_function_entry() for kernel symbols and by looking for the below
module GEP sequence for module addresses, until [2] is resolved:

	ld	r2, -8(r12)
	add	r2, r2, r12

[1] https://github.com/llvm/llvm-project/pull/151569
[2] https://github.com/llvm/llvm-project/issues/163706

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-4-hbathini@linux.ibm.com
---
 arch/powerpc/kernel/trace/ftrace.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 841d077e2825..1b2f293e7dcb 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -37,11 +37,29 @@ unsigned long ftrace_call_adjust(unsigned long addr)
 	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
 		return 0;
 
-	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
-	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
-		addr += MCOUNT_INSN_SIZE;
-		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+		if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 			addr += MCOUNT_INSN_SIZE;
+			if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+				addr += MCOUNT_INSN_SIZE;
+		} else if (IS_ENABLED(CONFIG_CC_IS_CLANG) && IS_ENABLED(CONFIG_PPC64)) {
+			/*
+			 * addr points to global entry point though the NOP was emitted at local
+			 * entry point due to https://github.com/llvm/llvm-project/issues/163706
+			 * Handle that here with ppc_function_entry() for kernel symbols while
+			 * adjusting module addresses in the else case, by looking for the below
+			 * module global entry point sequence:
+			 *	ld    r2, -8(r12)
+			 *	add   r2, r2, r12
+			 */
+			if (is_kernel_text(addr) || is_kernel_inittext(addr))
+				addr = ppc_function_entry((void *)addr);
+			else if ((ppc_inst_val(ppc_inst_read((u32 *)addr)) ==
+				  PPC_RAW_LD(_R2, _R12, -8)) &&
+				 (ppc_inst_val(ppc_inst_read((u32 *)(addr+4))) ==
+				  PPC_RAW_ADD(_R2, _R2, _R12)))
+				addr += 8;
+		}
 	}
 
 	return addr;

From 521bd39d9d28ce54cbfec7f9b89c94ad4fdb8350 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:25 +0530
Subject: [PATCH 1024/1303] powerpc64/bpf: do not increment tailcall count when
 prog is NULL

Do not increment tailcall count, if tailcall did not succeed due to
missing BPF program.

Fixes: ce0761419fae ("powerpc/bpf: Implement support for tail calls")
Cc: stable@vger.kernel.org
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-2-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp64.c | 39 +++++++++++++++++--------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index b1a3945ccc9f..44ce8a8783f9 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -522,9 +522,30 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 
 	/*
 	 * tail_call_info++; <- Actual value of tcc here
+	 * Writeback this updated value only if tailcall succeeds.
 	 */
 	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1));
 
+	/* prog = array->ptrs[index]; */
+	EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_2), b2p_index, 8));
+	EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), b2p_bpf_array));
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			offsetof(struct bpf_array, ptrs)));
+
+	/*
+	 * if (prog == NULL)
+	 *   goto out;
+	 */
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), 0));
+	PPC_BCC_SHORT(COND_EQ, out);
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			offsetof(struct bpf_prog, bpf_func)));
+	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			  FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size));
+	EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_2)));
+
 	/*
 	 * Before writing updated tail_call_info, distinguish if current frame
 	 * is storing a reference to tail_call_info or actual tcc value in
@@ -539,24 +560,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	/* Writeback updated value to tail_call_info */
 	EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0));
 
-	/* prog = array->ptrs[index]; */
-	EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8));
-	EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), b2p_bpf_array));
-	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_array, ptrs)));
-
-	/*
-	 * if (prog == NULL)
-	 *   goto out;
-	 */
-	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), 0));
-	PPC_BCC_SHORT(COND_EQ, out);
-
-	/* goto *(prog->bpf_func + prologue_size); */
-	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_prog, bpf_func)));
-	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1),
-			FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size));
-	EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1)));
-
 	/* tear down stack, restore NVRs, ... */
 	bpf_jit_emit_common_epilogue(image, ctx);
 

From 157820264ac3dadfafffad63184b883eb28f9ae0 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:26 +0530
Subject: [PATCH 1025/1303] powerpc64/bpf: fix the address returned by
 bpf_get_func_ip

bpf_get_func_ip() helper function returns the address of the traced
function. It relies on the IP address stored at ctx - 16 by the bpf
trampoline. On 64-bit powerpc, this address is recovered from LR
accounting for OOL trampoline. But the address stored here was off
by 4-bytes. Ensure the address is the actual start of the traced
function.

Reported-by: Abhishek Dubey <adubey@linux.ibm.com>
Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.org
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-3-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 52162e4a7f84..95f208229b09 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -785,9 +785,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 *       retval_off             [ return value      ]
 	 *                              [ reg argN          ]
 	 *                              [ ...               ]
-	 *       regs_off               [ reg_arg1          ] prog ctx context
-	 *       nregs_off              [ args count        ]
-	 *       ip_off                 [ traced function   ]
+	 *       regs_off               [ reg_arg1          ] prog_ctx
+	 *       nregs_off              [ args count        ] ((u64 *)prog_ctx)[-1]
+	 *       ip_off                 [ traced function   ] ((u64 *)prog_ctx)[-2]
 	 *                              [ ...               ]
 	 *       run_ctx_off            [ bpf_tramp_run_ctx ]
 	 *                              [ reg argN          ]
@@ -895,7 +895,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
 
-	/* Save our return address */
+	/* Save our LR/return address */
 	EMIT(PPC_RAW_MFLR(_R3));
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
@@ -903,24 +903,34 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
 
 	/*
-	 * Save ip address of the traced function.
-	 * We could recover this from LR, but we will need to address for OOL trampoline,
-	 * and optional GEP area.
+	 * Derive IP address of the traced function.
+	 * In case of CONFIG_PPC_FTRACE_OUT_OF_LINE or BPF program, LR points to the instruction
+	 * after the 'bl' instruction in the OOL stub. Refer to ftrace_init_ool_stub() and
+	 * bpf_arch_text_poke() for OOL stub of kernel functions and bpf programs respectively.
+	 * Relevant stub sequence:
+	 *
+	 *               bl <tramp>
+	 *   LR (R3) =>  mtlr r0
+	 *               b <func_addr+4>
+	 *
+	 * Recover kernel function/bpf program address from the unconditional
+	 * branch instruction at the end of OOL stub.
 	 */
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) {
 		EMIT(PPC_RAW_LWZ(_R4, _R3, 4));
 		EMIT(PPC_RAW_SLWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_SRAWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_ADD(_R3, _R3, _R4));
-		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 	}
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
 
-	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		/* Fake our LR for unwind */
+		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+	}
 
 	/* Save function arg count -- see bpf_get_func_arg_cnt() */
 	EMIT(PPC_RAW_LI(_R3, nr_regs));

From 3727d6ec13665c1d99bf6dedb107104368ba42b4 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:27 +0530
Subject: [PATCH 1026/1303] powerpc64/bpf: use consistent tailcall offset in
 trampoline

Ideally, the offset used to load the tail call info field and to find
the pass by reference address for tail call field should be the same.
But while setting up the tail call info in the trampoline, this was
not followed. This can be misleading and can lead to unpredictable
results if and when bpf_has_stack_frame() ends up returning true
for trampoline frame. Since commit 15513beeb673 ("powerpc64/bpf:
Moving tail_call_cnt to bottom of frame") and commit 2ed2d8f6fb38
("powerpc64/bpf: Support tailcalls with subprogs") ensured tail call
field is at the bottom of the stack frame for BPF programs as well as
BPF trampoline, avoid relying on bpf_jit_stack_tailcallinfo_offset()
and bpf_has_stack_frame() for trampoline frame and always calculate
tail call field offset with reference to older frame.

Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs")
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-4-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit.h        |  5 -----
 arch/powerpc/net/bpf_jit_comp.c   | 12 +++++-------
 arch/powerpc/net/bpf_jit_comp64.c |  5 ++++-
 3 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 82bbf63f0e57..7354e1d72f79 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -81,9 +81,6 @@
 
 #ifdef CONFIG_PPC64
 
-/* for gpr non volatile registers BPG_REG_6 to 10 */
-#define BPF_PPC_STACK_SAVE	(6 * 8)
-
 /* If dummy pass (!image), account for maximum possible instructions */
 #define PPC_LI64(d, i)		do {					      \
 	if (!image)							      \
@@ -219,8 +216,6 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
 			  struct codegen_context *ctx, int insn_idx,
 			  int jmp_off, int dst_reg, u32 code);
-
-int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx);
 #endif
 
 #endif
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 95f208229b09..a4aa1e4c9f1c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -642,15 +642,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 						int bpf_dummy_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/* See Generated stack layout */
-		int tailcallinfo_offset = BPF_PPC_TAILCALL;
-
 		/*
 		 * func_frame_offset =                                   ...(1)
 		 *      bpf_dummy_frame_size + trampoline_frame_size
 		 */
 		EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset));
-		EMIT(PPC_RAW_LD(_R3, _R4, -tailcallinfo_offset));
+		/* Refer to trampoline's Generated stack layout */
+		EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL));
 
 		/*
 		 * Setting the tail_call_info in trampoline's frame
@@ -658,7 +656,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 */
 		EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
-		EMIT(PPC_RAW_ADDI(_R3, _R4, bpf_jit_stack_tailcallinfo_offset(ctx)));
+		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
 		/*
 		 * From ...(1) above:
 		 * trampoline_frame_bottom =                            ...(2)
@@ -666,14 +664,14 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 *
 		 * Using ...(2) derived above:
 		 * trampoline_tail_call_info_offset =                  ...(3)
-		 *      trampoline_frame_bottom - tailcallinfo_offset
+		 *      trampoline_frame_bottom - BPF_PPC_TAILCALL
 		 *
 		 * From ...(3):
 		 * Use trampoline_tail_call_info_offset to write reference of main's
 		 * tail_call_info in trampoline frame.
 		 */
 		EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size)
-								- tailcallinfo_offset));
+								- BPF_PPC_TAILCALL));
 	} else {
 		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
 		EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 44ce8a8783f9..7655be76f537 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -42,6 +42,9 @@
  * exception boundary.
  */
 
+/* BPF non-volatile registers save area size */
+#define BPF_PPC_STACK_SAVE	(6 * 8)
+
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS	24
 /*
@@ -148,7 +151,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx)
 	}
 }
 
-int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx)
+static int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx)
 {
 	return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE;
 }

From 2d347d10f8e20e28a9eab52edf55079ae1ec0aae Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:28 +0530
Subject: [PATCH 1027/1303] powerpc64/bpf: remove BPF redzone protection in
 trampoline stack

Since bpf2bpf tailcall support is enabled for 64-bit powerpc with
kernel commit 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with
subprogs"), 'tailcalls/tailcall_bpf2bpf_hierarchy_fexit' BPF selftest
is triggering "corrupted stack end detected inside scheduler" with the
config option CONFIG_SCHED_STACK_END_CHECK enabled. While reviewing
the stack layout for BPF trampoline, observed that the dummy frame is
trying to protect the redzone of BPF program. This is because tail
call info and NVRs save area are in redzone at the time of tailcall
as the current BPF program stack frame is teared down before the
tailcall. But saving this redzone in the dummy frame of trampoline
is unnecessary because of the follow reasons:

  1) Firstly, trampoline can be attached to BPF entry/main program
     or subprog. But prologue part of the BPF entry/main program,
     where the trampoline attachpoint is, is skipped during tailcall.
     So, protecting the redzone does not arise when the trampoline is
     not even triggered in this scenario.
  2) In case of subprog, the caller's stackframe is already setup
     and the subprog's stackframe is yet to be setup. So, nothing
     on the redzone to be protected.

Also, using dummy frame in BPF trampoline, wastes critically scarce
kernel stack space, especially in tailcall sequence, for marginal
benefit in stack unwinding. So, drop setting up the dummy frame.
Instead, save return address in bpf trampoline frame and use it as
appropriate. Pruning this unnecessary stack usage mitigates the
likelihood of stack overflow in scenarios where bpf2bpf tailcalls
and fexit programs are mixed.

Reported-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs")
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-5-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c | 89 ++++++++++++---------------------
 1 file changed, 33 insertions(+), 56 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index a4aa1e4c9f1c..85457bcb2040 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -638,15 +638,10 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context
  * for the traced function (BPF subprog/callee) to fetch it.
  */
 static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_context *ctx,
-						int func_frame_offset,
-						int bpf_dummy_frame_size, int r4_off)
+						int bpf_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/*
-		 * func_frame_offset =                                   ...(1)
-		 *      bpf_dummy_frame_size + trampoline_frame_size
-		 */
-		EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset));
+		EMIT(PPC_RAW_LD(_R4, _R1, bpf_frame_size));
 		/* Refer to trampoline's Generated stack layout */
 		EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL));
 
@@ -657,21 +652,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
 		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
+
 		/*
-		 * From ...(1) above:
-		 * trampoline_frame_bottom =                            ...(2)
-		 *      func_frame_offset - bpf_dummy_frame_size
-		 *
-		 * Using ...(2) derived above:
-		 * trampoline_tail_call_info_offset =                  ...(3)
-		 *      trampoline_frame_bottom - BPF_PPC_TAILCALL
-		 *
-		 * From ...(3):
-		 * Use trampoline_tail_call_info_offset to write reference of main's
-		 * tail_call_info in trampoline frame.
+		 * Trampoline's tail_call_info is at the same offset, as that of
+		 * any bpf program, with reference to previous frame. Update the
+		 * address of main's tail_call_info in trampoline frame.
 		 */
-		EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size)
-								- BPF_PPC_TAILCALL));
+		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size - BPF_PPC_TAILCALL));
 	} else {
 		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
 		EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
@@ -679,7 +666,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 }
 
 static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx,
-						 int func_frame_offset, int r4_off)
+						 int bpf_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC32)) {
 		/*
@@ -690,12 +677,12 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont
 	}
 }
 
-static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset,
-				     int nr_regs, int regs_off)
+static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx,
+				     int bpf_frame_size, int nr_regs, int regs_off)
 {
 	int param_save_area_offset;
 
-	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset = bpf_frame_size;
 	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
 
 	for (int i = 0; i < nr_regs; i++) {
@@ -718,11 +705,11 @@ static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context
 
 /* Used when we call into the traced function. Replicate parameter save area */
 static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx,
-					      int func_frame_offset, int nr_regs, int regs_off)
+					      int bpf_frame_size, int nr_regs, int regs_off)
 {
 	int param_save_area_offset;
 
-	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset = bpf_frame_size;
 	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
 
 	for (int i = 8; i < nr_regs; i++) {
@@ -739,10 +726,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 					 void *func_addr)
 {
 	int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0;
-	int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset;
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+	int i, ret, nr_regs, retaddr_off, bpf_frame_size = 0;
 	struct codegen_context codegen_ctx, *ctx;
 	u32 *image = (u32 *)rw_image;
 	ppc_inst_t branch_insn;
@@ -768,16 +755,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 * Generated stack layout:
 	 *
 	 * func prev back chain         [ back chain        ]
-	 *                              [                   ]
-	 * bpf prog redzone/tailcallcnt [ ...               ] 64 bytes (64-bit powerpc)
-	 *                              [                   ] --
-	 * LR save area                 [ r0 save (64-bit)  ]   | header
-	 *                              [ r0 save (32-bit)  ]   |
-	 * dummy frame for unwind       [ back chain 1      ] --
 	 *                              [ tail_call_info    ] optional - 64-bit powerpc
 	 *                              [ padding           ] align stack frame
 	 *       r4_off                 [ r4 (tailcallcnt)  ] optional - 32-bit powerpc
 	 *       alt_lr_off             [ real lr (ool stub)] optional - actual lr
+	 *       retaddr_off            [ return address    ]
 	 *                              [ r26               ]
 	 *       nvr_off                [ r25               ] nvr save area
 	 *       retval_off             [ return value      ]
@@ -841,6 +823,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	nvr_off = bpf_frame_size;
 	bpf_frame_size += 2 * SZL;
 
+	/* Save area for return address */
+	retaddr_off = bpf_frame_size;
+	bpf_frame_size += SZL;
+
 	/* Optional save area for actual LR in case of ool ftrace */
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		alt_lr_off = bpf_frame_size;
@@ -867,16 +853,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	/* Padding to align stack frame, if any */
 	bpf_frame_size = round_up(bpf_frame_size, SZL * 2);
 
-	/* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */
-	bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64;
-
-	/* Offset to the traced function's stack frame */
-	func_frame_offset = bpf_dummy_frame_size + bpf_frame_size;
-
-	/* Create dummy frame for unwind, store original return value */
+	/*  Store original return value */
 	EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF));
-	/* Protect red zone where tail call count goes */
-	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size));
 
 	/* Create our stack frame */
 	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size));
@@ -891,14 +869,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2)
 		EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
 
-	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
+	bpf_trampoline_save_args(image, ctx, bpf_frame_size, nr_regs, regs_off);
 
 	/* Save our LR/return address */
 	EMIT(PPC_RAW_MFLR(_R3));
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
 	else
-		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off));
 
 	/*
 	 * Derive IP address of the traced function.
@@ -925,9 +903,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
 
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
-		/* Fake our LR for unwind */
+		/* Fake our LR for BPF_TRAMP_F_CALL_ORIG case */
 		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
-		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off));
 	}
 
 	/* Save function arg count -- see bpf_get_func_arg_cnt() */
@@ -966,20 +944,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	/* Call the traced function */
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/*
-		 * The address in LR save area points to the correct point in the original function
+		 * retaddr on trampoline stack points to the correct point in the original function
 		 * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction
 		 * sequence
 		 */
-		EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_LL(_R3, _R1, retaddr_off));
 		EMIT(PPC_RAW_MTCTR(_R3));
 
 		/* Replicate tail_call_cnt before calling the original BPF prog */
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
-			bpf_trampoline_setup_tail_call_info(image, ctx, func_frame_offset,
-								bpf_dummy_frame_size, r4_off);
+			bpf_trampoline_setup_tail_call_info(image, ctx, bpf_frame_size, r4_off);
 
 		/* Restore args */
-		bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off);
+		bpf_trampoline_restore_args_stack(image, ctx, bpf_frame_size, nr_regs, regs_off);
 
 		/* Restore TOC for 64-bit */
 		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
@@ -993,7 +970,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 		/* Restore updated tail_call_cnt */
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
-			bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+			bpf_trampoline_restore_tail_call_cnt(image, ctx, bpf_frame_size, r4_off);
 
 		/* Reserve space to patch branch instruction to skip fexit progs */
 		if (ro_image) /* image is NULL for dummy pass */
@@ -1045,7 +1022,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_LD(_R2, _R1, 24));
 	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* Skip the traced function and return to parent */
-		EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+		EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 		EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 		EMIT(PPC_RAW_MTLR(_R0));
 		EMIT(PPC_RAW_BLR());
@@ -1053,13 +1030,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 			EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off));
 			EMIT(PPC_RAW_MTLR(_R0));
-			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 			EMIT(PPC_RAW_BLR());
 		} else {
-			EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF));
+			EMIT(PPC_RAW_LL(_R0, _R1, retaddr_off));
 			EMIT(PPC_RAW_MTCTR(_R0));
-			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 			EMIT(PPC_RAW_MTLR(_R0));
 			EMIT(PPC_RAW_BCTR());

From 51b8de4b3d27ec12128fa2405e526c527a77ae65 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:29 +0530
Subject: [PATCH 1028/1303] powerpc64/bpf: fix handling of BPF stack in
 exception callback

Exception callback reuses the stack frame of exception boundary. When
exception boundary and exception callback programs have different BPF
stack depth, the current stack unwind in exception callback will fail.
Adjust the stack frame size of exception callback, in its prologue,
if its BPF stack depth is different from that of exception boundary.

Reported-by: bot+bpf-ci@kernel.org
Closes: https://lore.kernel.org/bpf/2a310e86a59eb4c44c3ac9e5647814469d9c955580c9c0f1b3d9ca4a44717a34@mail.kernel.org/
Fixes: 11d45eee9f42 ("powerpc64/bpf: Additional NVR handling for bpf_throw")
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-6-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp64.c | 36 +++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 7655be76f537..04e76440d1ad 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -32,14 +32,15 @@
  *
  *		[	prev sp		] <-------------
  *		[    tail_call_info	] 8		|
- *		[   nv gpr save area	] 6*8 + (12*8)	|
+ *		[   nv gpr save area	] (6 * 8)	|
+ *		[ addl. nv gpr save area] (12 * 8)	| <--- exception boundary/callback program
  *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
  * sp (r1) --->	[    stack pointer	] --------------
  *
- * Additional (12*8) in 'nv gpr save area' only in case of
- * exception boundary.
+ * Additional (12 * 8) in 'nv gpr save area' only in case of
+ * exception boundary/callback.
  */
 
 /* BPF non-volatile registers save area size */
@@ -51,7 +52,7 @@
  * for additional non volatile registers(r14-r25) to be saved
  * at exception boundary
  */
-#define BPF_PPC_EXC_STACK_SAVE (12*8)
+#define BPF_PPC_EXC_STACK_SAVE (12 * 8)
 
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
 #define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + \
@@ -128,12 +129,13 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
  *		[    tail_call_info	] 8
- *		[   nv gpr save area	] 6*8 + (12*8)
+ *		[   nv gpr save area	] (6 * 8)
+ *		[ addl. nv gpr save area] (12 * 8) <--- exception boundary/callback program
  *		[    local_tmp_var	] 24
  *		[   unused red zone	] 224
  *
- * Additional (12*8) in 'nv gpr save area' only in case of
- * exception boundary.
+ * Additional (12 * 8) in 'nv gpr save area' only in case of
+ * exception boundary/callback.
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
 {
@@ -240,10 +242,6 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 
 	if (bpf_has_stack_frame(ctx) && !ctx->exception_cb) {
 		/*
-		 * exception_cb uses boundary frame after stack walk.
-		 * It can simply use redzone, this optimization reduces
-		 * stack walk loop by one level.
-		 *
 		 * We need a stack frame, but we don't necessarily need to
 		 * save/restore LR unless we call other functions
 		 */
@@ -287,6 +285,22 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		 * program(main prog) as third arg
 		 */
 		EMIT(PPC_RAW_MR(_R1, _R5));
+		/*
+		 * Exception callback reuses the stack frame of exception boundary.
+		 * But BPF stack depth of exception callback and exception boundary
+		 * don't have to be same. If BPF stack depth is different, adjust the
+		 * stack frame size considering BPF stack depth of exception callback.
+		 * The non-volatile register save area remains unchanged. These non-
+		 * volatile registers are restored in exception callback's epilogue.
+		 */
+		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R5, 0));
+		EMIT(PPC_RAW_SUB(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_1), _R1));
+		EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			-BPF_PPC_EXC_STACKFRAME));
+		EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), ctx->stack_size));
+		PPC_BCC_CONST_SHORT(COND_EQ, 12);
+		EMIT(PPC_RAW_MR(_R1, bpf_to_ppc(TMP_REG_1)));
+		EMIT(PPC_RAW_STDU(_R1, _R1, -(BPF_PPC_EXC_STACKFRAME + ctx->stack_size)));
 	}
 
 	/*

From 01b6ac72729610ae732ca2a66e3a642e23f6cd60 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:30 +0530
Subject: [PATCH 1029/1303] powerpc64/bpf: fix kfunc call support

Commit 61688a82e047 ("powerpc/bpf: enable kfunc call") inadvertently
enabled kfunc call support for 32-bit powerpc but that support will
not be possible until ABI mismatch between 32-bit powerpc and eBPF is
handled in 32-bit powerpc JIT code. Till then, advertise support only
for 64-bit powerpc. Also, in powerpc ABI, caller needs to extend the
arguments properly based on signedness. The JIT code is responsible
for handling this explicitly for kfunc calls as verifier can't handle
this for each architecture-specific ABI needs. But this was not taken
care of while kfunc call support was enabled for powerpc. Fix it by
handling this with bpf_jit_find_kfunc_model() and using zero_extend()
& sign_extend() helper functions.

Fixes: 61688a82e047 ("powerpc/bpf: enable kfunc call")
Cc: stable@vger.kernel.org
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-7-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c   |   2 +-
 arch/powerpc/net/bpf_jit_comp64.c | 101 +++++++++++++++++++++++++++---
 2 files changed, 94 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 85457bcb2040..a62a9a92b7b5 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -450,7 +450,7 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 
 bool bpf_jit_supports_kfunc_call(void)
 {
-	return true;
+	return IS_ENABLED(CONFIG_PPC64);
 }
 
 bool bpf_jit_supports_arena(void)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 04e76440d1ad..c5e26d231cd5 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -499,6 +499,83 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *
 	return 0;
 }
 
+static int zero_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size)
+{
+	switch (size) {
+	case 1:
+		 /* zero-extend 8 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 56));
+		return 0;
+	case 2:
+		 /* zero-extend 16 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 48));
+		return 0;
+	case 4:
+		 /* zero-extend 32 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 32));
+		fallthrough;
+	case 8:
+		/* Nothing to do */
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+static int sign_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size)
+{
+	switch (size) {
+	case 1:
+		 /* sign-extend 8 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+		return 0;
+	case 2:
+		 /* sign-extend 16 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+		return 0;
+	case 4:
+		 /* sign-extend 32 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
+		fallthrough;
+	case 8:
+		/* Nothing to do */
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+/*
+ * Handle powerpc ABI expectations from caller:
+ *   - Unsigned arguments are zero-extended.
+ *   - Signed arguments are sign-extended.
+ */
+static int prepare_for_kfunc_call(const struct bpf_prog *fp, u32 *image,
+				  struct codegen_context *ctx,
+				  const struct bpf_insn *insn)
+{
+	const struct btf_func_model *m = bpf_jit_find_kfunc_model(fp, insn);
+	int i;
+
+	if (!m)
+		return -1;
+
+	for (i = 0; i < m->nr_args; i++) {
+		/* Note that BPF ABI only allows up to 5 args for kfuncs */
+		u32 reg = bpf_to_ppc(BPF_REG_1 + i), size = m->arg_size[i];
+
+		if (!(m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG)) {
+			if (zero_extend(image, ctx, reg, reg, size))
+				return -1;
+		} else {
+			if (sign_extend(image, ctx, reg, reg, size))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
 static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
 {
 	/*
@@ -1143,14 +1220,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 				/* special mov32 for zext */
 				EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
 				break;
-			} else if (off == 8) {
-				EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
-			} else if (off == 16) {
-				EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
-			} else if (off == 32) {
-				EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
-			} else if (dst_reg != src_reg)
-				EMIT(PPC_RAW_MR(dst_reg, src_reg));
+			}
+			if (off == 0) {
+				/* MOV */
+				if (dst_reg != src_reg)
+					EMIT(PPC_RAW_MR(dst_reg, src_reg));
+			} else {
+				/* MOVSX: dst = (s8,s16,s32)src (off = 8,16,32) */
+				if (sign_extend(image, ctx, src_reg, dst_reg, off / 8))
+					return -1;
+			}
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
 		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
@@ -1618,6 +1697,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 			if (ret < 0)
 				return ret;
 
+			/* Take care of powerpc ABI requirements before kfunc call */
+			if (insn[i].src_reg == BPF_PSEUDO_KFUNC_CALL) {
+				if (prepare_for_kfunc_call(fp, image, ctx, &insn[i]))
+					return -1;
+			}
+
 			ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 			if (ret)
 				return ret;

From 202d23eeccd4b12047869538d6fb91d1e42c4ddd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 17:04:08 +0100
Subject: [PATCH 1030/1303] dt-bindings: powerpc: Add Freescale/NXP MPC83xx
 SoCs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new binding for MPC83xx platforms, describing the board compatible
strings used in currently existing device trees.

Note that the SoC bus is called immr@... in many existing devicetrees,
but this contradicts the simple-bus binding.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-ppcyaml-soc-v5-1-2982d5a857bc@posteo.net
---
 .../bindings/powerpc/fsl/fsl,mpc83xx.yaml     | 93 +++++++++++++++++++
 1 file changed, 93 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml

diff --git a/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml
new file mode 100644
index 000000000000..9e37d155c582
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/powerpc/fsl/fsl,mpc83xx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale PowerQUICC II Pro (MPC83xx) platforms
+
+maintainers:
+  - J. Neuschäfer <j.ne@posteo.net>
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+      - description: MPC83xx Reference Design Boards
+        items:
+          - enum:
+              - fsl,mpc8308rdb
+              - fsl,mpc8315erdb
+              - fsl,mpc8360rdk
+              - fsl,mpc8377rdb
+              - fsl,mpc8377wlan
+              - fsl,mpc8378rdb
+              - fsl,mpc8379rdb
+
+      - description: MPC8313E Reference Design Board
+        items:
+          - const: MPC8313ERDB
+          - const: MPC831xRDB
+          - const: MPC83xxRDB
+
+      - description: MPC8323E Reference Design Board
+        items:
+          - const: MPC8323ERDB
+          - const: MPC832xRDB
+          - const: MPC83xxRDB
+
+      - description: MPC8349E-mITX(-GP) Reference Design Platform
+        items:
+          - enum:
+              - MPC8349EMITX
+              - MPC8349EMITXGP
+          - const: MPC834xMITX
+          - const: MPC83xxMITX
+
+      - description: Keymile KMETER1 board
+        const: keymile,KMETER1
+
+      - description: MPC8308 P1M board
+        const: denx,mpc8308_p1m
+
+patternProperties:
+  "^soc@.*$":
+    type: object
+    properties:
+      compatible:
+        oneOf:
+          - items:
+              - enum:
+                  - fsl,mpc8315-immr
+                  - fsl,mpc8308-immr
+              - const: simple-bus
+          - items:
+              - const: fsl,mpc8360-immr
+              - const: fsl,immr
+              - const: fsl,soc
+              - const: simple-bus
+          - const: simple-bus
+
+additionalProperties: true
+
+examples:
+  - |
+    / {
+        compatible = "fsl,mpc8315erdb";
+        model = "MPC8315E-RDB";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        soc@e0000000 {
+            compatible = "fsl,mpc8315-immr", "simple-bus";
+            reg = <0xe0000000 0x00000200>;
+            #address-cells = <1>;
+            #size-cells = <1>;
+            device_type = "soc";
+            ranges = <0 0xe0000000 0x00100000>;
+            bus-frequency = <0>;
+        };
+    };
+
+...

From 691417ffe7821721e0a28bd25ad8c0dc0d4ae4ad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:31:42 +0100
Subject: [PATCH 1031/1303] powerpc: 83xx: km83xx: Fix keymile vendor prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When kmeter.c was refactored into km83xx.c in 2011, the "keymile" vendor
prefix was changed to upper-case "Keymile". The devicetree at
arch/powerpc/boot/dts/kmeter1.dts never underwent the same change,
suggesting that this was simply a mistake.

Fixes: 93e2b95c81042d ("powerpc/83xx: rename and update kmeter1")
Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Reviewed-by: Heiko Schocher <hs@nabladev.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-keymile-v1-1-463a11e71702@posteo.net
---
 arch/powerpc/platforms/83xx/km83xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 2b5d187d9b62..9ef8fb39dd1b 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -155,8 +155,8 @@ machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices);
 
 /* list of the supported boards */
 static char *board[] __initdata = {
-	"Keymile,KMETER1",
-	"Keymile,kmpbec8321",
+	"keymile,KMETER1",
+	"keymile,kmpbec8321",
 	NULL
 };
 

From 38ce944d47b717cac6b5f2bae9dd247f87f21ac7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:51 +0100
Subject: [PATCH 1032/1303] powerpc: dts: mpc8313erdb: Use IRQ_TYPE_* macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This increases readability, because "0x8" isn't very descriptive.

mpc8313erdb.dtb remains identical after this patch.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-1-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8313erdb.dts | 59 +++++++++++++++------------
 1 file changed, 34 insertions(+), 25 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 09508b4c8c73..137217d377e9 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -6,6 +6,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	model = "MPC8313ERDB";
@@ -48,7 +49,7 @@ localbus@e0005000 {
 		#size-cells = <1>;
 		compatible = "fsl,mpc8313-elbc", "fsl,elbc", "simple-bus";
 		reg = <0xe0005000 0x1000>;
-		interrupts = <77 0x8>;
+		interrupts = <77 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
 
 		// CS0 and CS1 are swapped when
@@ -118,7 +119,7 @@ i2c@3000 {
 				cell-index = <0>;
 				compatible = "fsl-i2c";
 				reg = <0x3000 0x100>;
-				interrupts = <14 0x8>;
+				interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-parent = <&ipic>;
 				dfsrr;
 				rtc@68 {
@@ -131,7 +132,7 @@ crypto@30000 {
 				compatible = "fsl,sec2.2", "fsl,sec2.1",
 				             "fsl,sec2.0";
 				reg = <0x30000 0x10000>;
-				interrupts = <11 0x8>;
+				interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-parent = <&ipic>;
 				fsl,num-channels = <1>;
 				fsl,channel-fifo-len = <24>;
@@ -146,7 +147,7 @@ i2c@3100 {
 			cell-index = <1>;
 			compatible = "fsl-i2c";
 			reg = <0x3100 0x100>;
-			interrupts = <15 0x8>;
+			interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			dfsrr;
 		};
@@ -155,7 +156,7 @@ spi@7000 {
 			cell-index = <0>;
 			compatible = "fsl,spi";
 			reg = <0x7000 0x1000>;
-			interrupts = <16 0x8>;
+			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			mode = "cpu";
 		};
@@ -167,7 +168,7 @@ usb@23000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupt-parent = <&ipic>;
-			interrupts = <38 0x8>;
+			interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
 			phy_type = "utmi_wide";
 			sleep = <&pmc 0x00300000>;
 		};
@@ -175,7 +176,8 @@ usb@23000 {
 		ptp_clock@24E00 {
 			compatible = "fsl,etsec-ptp";
 			reg = <0x24E00 0xB0>;
-			interrupts = <12 0x8 13 0x8>;
+			interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
+				     <13 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = < &ipic >;
 			fsl,tclk-period = <10>;
 			fsl,tmr-prsc    = <100>;
@@ -197,7 +199,9 @@ enet0: ethernet@24000 {
 			compatible = "gianfar";
 			reg = <0x24000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <37 0x8 36 0x8 35 0x8>;
+			interrupts = <37 IRQ_TYPE_LEVEL_LOW>,
+				     <36 IRQ_TYPE_LEVEL_LOW>,
+				     <35 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = < &tbi0 >;
 			/* Vitesse 7385 isn't on the MDIO bus */
@@ -211,7 +215,7 @@ mdio@520 {
 				reg = <0x520 0x20>;
 				phy4: ethernet-phy@4 {
 					interrupt-parent = <&ipic>;
-					interrupts = <20 0x8>;
+					interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
 					reg = <0x4>;
 				};
 				tbi0: tbi-phy@11 {
@@ -231,7 +235,9 @@ enet1: ethernet@25000 {
 			reg = <0x25000 0x1000>;
 			ranges = <0x0 0x25000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <34 0x8 33 0x8 32 0x8>;
+			interrupts = <34 IRQ_TYPE_LEVEL_LOW>,
+				     <33 IRQ_TYPE_LEVEL_LOW>,
+				     <32 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = < &tbi1 >;
 			phy-handle = < &phy4 >;
@@ -259,7 +265,7 @@ serial0: serial@4500 {
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4500 0x100>;
 			clock-frequency = <0>;
-			interrupts = <9 0x8>;
+			interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -269,15 +275,12 @@ serial1: serial@4600 {
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4600 0x100>;
 			clock-frequency = <0>;
-			interrupts = <10 0x8>;
+			interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		/* IPIC
-		 * interrupts cell = <intr #, sense>
-		 * sense values match linux IORESOURCE_IRQ_* defines:
-		 * sense == 8: Level, low assertion
-		 * sense == 2: Edge, high-to-low change
+		 * interrupts cell = <intr #, type>
 		 */
 		ipic: pic@700 {
 			interrupt-controller;
@@ -290,7 +293,7 @@ ipic: pic@700 {
 		pmc: power@b00 {
 			compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
 			reg = <0xb00 0x100 0xa00 0x100>;
-			interrupts = <80 8>;
+			interrupts = <80 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 
@@ -306,14 +309,20 @@ pmc: power@b00 {
 		gtm1: timer@500 {
 			compatible = "fsl,mpc8313-gtm", "fsl,gtm";
 			reg = <0x500 0x100>;
-			interrupts = <90 8 78 8 84 8 72 8>;
+			interrupts = <90 IRQ_TYPE_LEVEL_LOW>,
+				     <78 IRQ_TYPE_LEVEL_LOW>,
+				     <84 IRQ_TYPE_LEVEL_LOW>,
+				     <72 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		timer@600 {
 			compatible = "fsl,mpc8313-gtm", "fsl,gtm";
 			reg = <0x600 0x100>;
-			interrupts = <91 8 79 8 85 8 73 8>;
+			interrupts = <91 IRQ_TYPE_LEVEL_LOW>,
+				     <79 IRQ_TYPE_LEVEL_LOW>,
+				     <85 IRQ_TYPE_LEVEL_LOW>,
+				     <73 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 	};
@@ -341,7 +350,7 @@ pci0: pci@e0008500 {
 					 0x7800 0x0 0x0 0x3 &ipic 17 0x8
 					 0x7800 0x0 0x0 0x4 &ipic 18 0x8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <66 0x8>;
+			interrupts = <66 IRQ_TYPE_LEVEL_LOW>;
 			bus-range = <0x0 0x0>;
 			ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000
 				  0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000
@@ -363,14 +372,14 @@ dma@82a8 {
 			reg = <0xe00082a8 4>;
 			ranges = <0 0xe0008100 0x1a8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <71 8>;
+			interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 
 			dma-channel@0 {
 				compatible = "fsl,mpc8313-dma-channel",
 				             "fsl,elo-dma-channel";
 				reg = <0 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <0>;
 			};
 
@@ -379,7 +388,7 @@ dma-channel@80 {
 				             "fsl,elo-dma-channel";
 				reg = <0x80 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <1>;
 			};
 
@@ -388,7 +397,7 @@ dma-channel@100 {
 				             "fsl,elo-dma-channel";
 				reg = <0x100 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <2>;
 			};
 
@@ -397,7 +406,7 @@ dma-channel@180 {
 				             "fsl,elo-dma-channel";
 				reg = <0x180 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <3>;
 			};
 		};

From 4f439747811977d05a87da65c1ae11246d4f4dee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:52 +0100
Subject: [PATCH 1033/1303] powerpc: dts: mpc8315erdb: Use IRQ_TYPE_* macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This increases readability, because "0x8" isn't very descriptive.

mpc8315erdb.dtb remains identical after this patch.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-2-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 111 ++++++++++++++------------
 1 file changed, 59 insertions(+), 52 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index a8f68d6e50b0..1957b6687b29 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -50,7 +50,7 @@ localbus@e0005000 {
 		#size-cells = <1>;
 		compatible = "fsl,mpc8315-elbc", "fsl,elbc", "simple-bus";
 		reg = <0xe0005000 0x1000>;
-		interrupts = <77 0x8>;
+		interrupts = <77 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
 
 		// CS0 and CS1 are swapped when
@@ -112,7 +112,7 @@ i2c@3000 {
 			cell-index = <0>;
 			compatible = "fsl-i2c";
 			reg = <0x3000 0x100>;
-			interrupts = <14 0x8>;
+			interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
@@ -133,7 +133,7 @@ spi@7000 {
 			cell-index = <0>;
 			compatible = "fsl,spi";
 			reg = <0x7000 0x1000>;
-			interrupts = <16 0x8>;
+			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			mode = "cpu";
 		};
@@ -145,35 +145,35 @@ dma@82a8 {
 			reg = <0x82a8 4>;
 			ranges = <0 0x8100 0x1a8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <71 8>;
+			interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			cell-index = <0>;
 			dma-channel@0 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0 0x80>;
 				cell-index = <0>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@80 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x80 0x80>;
 				cell-index = <1>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@100 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x100 0x80>;
 				cell-index = <2>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@180 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x180 0x28>;
 				cell-index = <3>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 		};
 
@@ -183,7 +183,7 @@ usb@23000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupt-parent = <&ipic>;
-			interrupts = <38 0x8>;
+			interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
 			phy_type = "utmi";
 		};
 
@@ -197,7 +197,9 @@ enet0: ethernet@24000 {
 			reg = <0x24000 0x1000>;
 			ranges = <0x0 0x24000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <32 0x8 33 0x8 34 0x8>;
+			interrupts = <32 IRQ_TYPE_LEVEL_LOW>,
+				     <33 IRQ_TYPE_LEVEL_LOW>,
+				     <34 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = <&tbi0>;
 			phy-handle = < &phy0 >;
@@ -238,7 +240,9 @@ enet1: ethernet@25000 {
 			reg = <0x25000 0x1000>;
 			ranges = <0x0 0x25000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 0x8 36 0x8 37 0x8>;
+			interrupts = <35 IRQ_TYPE_LEVEL_LOW>,
+				     <36 IRQ_TYPE_LEVEL_LOW>,
+				     <37 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = <&tbi1>;
 			phy-handle = < &phy1 >;
@@ -263,7 +267,7 @@ serial0: serial@4500 {
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4500 0x100>;
 			clock-frequency = <133333333>;
-			interrupts = <9 0x8>;
+			interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -273,7 +277,7 @@ serial1: serial@4600 {
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4600 0x100>;
 			clock-frequency = <133333333>;
-			interrupts = <10 0x8>;
+			interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -282,7 +286,7 @@ crypto@30000 {
 				     "fsl,sec2.4", "fsl,sec2.2", "fsl,sec2.1",
 				     "fsl,sec2.0";
 			reg = <0x30000 0x10000>;
-			interrupts = <11 0x8>;
+			interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,num-channels = <4>;
 			fsl,channel-fifo-len = <24>;
@@ -294,7 +298,7 @@ sata@18000 {
 			compatible = "fsl,mpc8315-sata", "fsl,pq-sata";
 			reg = <0x18000 0x1000>;
 			cell-index = <1>;
-			interrupts = <44 0x8>;
+			interrupts = <44 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -302,14 +306,17 @@ sata@19000 {
 			compatible = "fsl,mpc8315-sata", "fsl,pq-sata";
 			reg = <0x19000 0x1000>;
 			cell-index = <2>;
-			interrupts = <45 0x8>;
+			interrupts = <45 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		gtm1: timer@500 {
 			compatible = "fsl,mpc8315-gtm", "fsl,gtm";
 			reg = <0x500 0x100>;
-			interrupts = <90 8 78 8 84 8 72 8>;
+			interrupts = <90 IRQ_TYPE_LEVEL_LOW>,
+				     <78 IRQ_TYPE_LEVEL_LOW>,
+				     <84 IRQ_TYPE_LEVEL_LOW>,
+				     <72 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			clock-frequency = <133333333>;
 		};
@@ -317,16 +324,16 @@ gtm1: timer@500 {
 		timer@600 {
 			compatible = "fsl,mpc8315-gtm", "fsl,gtm";
 			reg = <0x600 0x100>;
-			interrupts = <91 8 79 8 85 8 73 8>;
+			interrupts = <91 IRQ_TYPE_LEVEL_LOW>,
+				     <79 IRQ_TYPE_LEVEL_LOW>,
+				     <85 IRQ_TYPE_LEVEL_LOW>,
+				     <73 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			clock-frequency = <133333333>;
 		};
 
 		/* IPIC
-		 * interrupts cell = <intr #, sense>
-		 * sense values match linux IORESOURCE_IRQ_* defines:
-		 * sense == 8: Level, low assertion
-		 * sense == 2: Edge, high-to-low change
+		 * interrupts cell = <intr #, type>
 		 */
 		ipic: interrupt-controller@700 {
 			interrupt-controller;
@@ -340,14 +347,14 @@ ipic-msi@7c0 {
 			compatible = "fsl,ipic-msi";
 			reg = <0x7c0 0x40>;
 			msi-available-ranges = <0 0x100>;
-			interrupts = <0x43 0x8
-				      0x4  0x8
-				      0x51 0x8
-				      0x52 0x8
-				      0x56 0x8
-				      0x57 0x8
-				      0x58 0x8
-				      0x59 0x8>;
+			interrupts = <0x43 IRQ_TYPE_LEVEL_LOW
+				      0x4  IRQ_TYPE_LEVEL_LOW
+				      0x51 IRQ_TYPE_LEVEL_LOW
+				      0x52 IRQ_TYPE_LEVEL_LOW
+				      0x56 IRQ_TYPE_LEVEL_LOW
+				      0x57 IRQ_TYPE_LEVEL_LOW
+				      0x58 IRQ_TYPE_LEVEL_LOW
+				      0x59 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = < &ipic >;
 		};
 
@@ -355,7 +362,7 @@ pmc: power@b00 {
 			compatible = "fsl,mpc8315-pmc", "fsl,mpc8313-pmc",
 				     "fsl,mpc8349-pmc";
 			reg = <0xb00 0x100 0xa00 0x100>;
-			interrupts = <80 8>;
+			interrupts = <80 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 		};
@@ -374,24 +381,24 @@ pci0: pci@e0008500 {
 		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
 		interrupt-map = <
 				/* IDSEL 0x0E -mini PCI */
-				 0x7000 0x0 0x0 0x1 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x2 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x3 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x4 &ipic 18 0x8
+				 0x7000 0x0 0x0 0x1 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x2 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x3 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x4 &ipic 18 IRQ_TYPE_LEVEL_LOW
 
 				/* IDSEL 0x0F -mini PCI */
-				 0x7800 0x0 0x0 0x1 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x2 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x3 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x4 &ipic 17 0x8
+				 0x7800 0x0 0x0 0x1 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x3 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW
 
 				/* IDSEL 0x10 - PCI slot */
-				 0x8000 0x0 0x0 0x1 &ipic 48 0x8
-				 0x8000 0x0 0x0 0x2 &ipic 17 0x8
-				 0x8000 0x0 0x0 0x3 &ipic 48 0x8
-				 0x8000 0x0 0x0 0x4 &ipic 17 0x8>;
+				 0x8000 0x0 0x0 0x1 &ipic 48 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x3 &ipic 48 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
-		interrupts = <66 0x8>;
+		interrupts = <66 IRQ_TYPE_LEVEL_LOW>;
 		bus-range = <0x0 0x0>;
 		ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000
 			  0x42000000 0 0x80000000 0x80000000 0 0x10000000
@@ -417,10 +424,10 @@ pci1: pcie@e0009000 {
 		          0x01000000 0 0x00000000 0xb1000000 0 0x00800000>;
 		bus-range = <0 255>;
 		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <0 0 0 1 &ipic 1 8
-				 0 0 0 2 &ipic 1 8
-				 0 0 0 3 &ipic 1 8
-				 0 0 0 4 &ipic 1 8>;
+		interrupt-map = <0 0 0 1 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 2 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 3 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 4 &ipic 1 IRQ_TYPE_LEVEL_LOW>;
 		clock-frequency = <0>;
 
 		pcie@0 {
@@ -448,10 +455,10 @@ pci2: pcie@e000a000 {
 			  0x01000000 0 0x00000000 0xd1000000 0 0x00800000>;
 		bus-range = <0 255>;
 		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <0 0 0 1 &ipic 2 8
-				 0 0 0 2 &ipic 2 8
-				 0 0 0 3 &ipic 2 8
-				 0 0 0 4 &ipic 2 8>;
+		interrupt-map = <0 0 0 1 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 2 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 3 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 4 &ipic 2 IRQ_TYPE_LEVEL_LOW>;
 		clock-frequency = <0>;
 
 		pcie@0 {

From 31618e0e21c4633c365b26e6d45cae2084f4245b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:53 +0100
Subject: [PATCH 1034/1303] powerpc: dts: mpc8315erdb: Rename LED nodes to
 comply with schema
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The leds-gpio.yaml schema requires that GPIO LED nodes contain "led",
and preferably start with "led-"

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-3-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 1957b6687b29..f4938a7292b9 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -478,12 +478,12 @@ pcie@0 {
 	leds {
 		compatible = "gpio-leds";
 
-		pwr {
+		led-pwr {
 			gpios = <&mcu_pio 0 0>;
 			default-state = "on";
 		};
 
-		hdd {
+		led-hdd {
 			gpios = <&mcu_pio 1 0>;
 			linux,default-trigger = "disk-activity";
 		};

From fde54f1a4dc7bfd83908380c0b4b6a830a0f9e01 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:54 +0100
Subject: [PATCH 1035/1303] powerpc: dts: mpc8315erdb: Add missing #cells
 properties to SPI bus
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These properties are required by the spi-controller binding.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-4-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index f4938a7292b9..0b087180e181 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -135,6 +135,8 @@ spi@7000 {
 			reg = <0x7000 0x1000>;
 			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 			mode = "cpu";
 		};
 

From 6373a2b5c878e920341d7bda84ac1126f72e6a68 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:55 +0100
Subject: [PATCH 1036/1303] powerpc: dts: mpc83xx: Add unit addresses to
 /memory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes dtschema warnings such as the following:

  arch/powerpc/boot/dts/mpc8315erdb.dtb: /: memory: False schema
  does not allow {'device_type': ['memory'], 'reg': [[0, 134217728]]}

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-5-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/asp834x-redboot.dts | 2 +-
 arch/powerpc/boot/dts/mpc8308_p1m.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8308rdb.dts      | 2 +-
 arch/powerpc/boot/dts/mpc8313erdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8315erdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc832x_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8349emitx.dts    | 2 +-
 arch/powerpc/boot/dts/mpc8349emitxgp.dts  | 2 +-
 arch/powerpc/boot/dts/mpc8377_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8377_wlan.dts    | 2 +-
 arch/powerpc/boot/dts/mpc8378_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8379_rdb.dts     | 2 +-
 12 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts
index 33ddb17d1876..c541bd367983 100644
--- a/arch/powerpc/boot/dts/asp834x-redboot.dts
+++ b/arch/powerpc/boot/dts/asp834x-redboot.dts
@@ -37,7 +37,7 @@ PowerPC,8347@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x8000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts
index 2638555afcc4..41f917f97dab 100644
--- a/arch/powerpc/boot/dts/mpc8308_p1m.dts
+++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts
@@ -37,7 +37,7 @@ PowerPC,8308@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts
index af2ed8380a86..39ed26fba410 100644
--- a/arch/powerpc/boot/dts/mpc8308rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8308rdb.dts
@@ -38,7 +38,7 @@ PowerPC,8308@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 137217d377e9..c9fe4dabc80a 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -39,7 +39,7 @@ PowerPC,8313@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 0b087180e181..7ba1159f8803 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -40,7 +40,7 @@ PowerPC,8315@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index ba7caaf98fd5..06f134490d95 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -38,7 +38,7 @@ PowerPC,8323@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index 13f17232ba83..12d33cb55b72 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -39,7 +39,7 @@ PowerPC,8349@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index eae0afd5abbc..2998a233a790 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -37,7 +37,7 @@ PowerPC,8349@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index f137ccb8cfde..fb311a7eb9f2 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -39,7 +39,7 @@ PowerPC,8377@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts
index ce254dd74dd0..f736a15cceff 100644
--- a/arch/powerpc/boot/dts/mpc8377_wlan.dts
+++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts
@@ -40,7 +40,7 @@ PowerPC,8377@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x20000000>;	// 512MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index 19e5473d4161..32c49622b404 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -39,7 +39,7 @@ PowerPC,8378@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index 61519acca228..07deb89c5a9b 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -37,7 +37,7 @@ PowerPC,8379@0 {
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};

From 35e4f2a17eb40288f9bcdb09549fa04a63a96279 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 2 Mar 2026 01:39:48 +0100
Subject: [PATCH 1037/1303] powerpc/pseries: Correct MSI allocation tracking

The per-device MSI allocation calculation in pseries_irq_domain_alloc()
is clearly wrong. It can still happen to work when nr_irqs is 1.

Correct it.

Fixes: c0215e2d72de ("powerpc/pseries: Fix MSI-X allocation failure when quota is exceeded")
Cc: stable@vger.kernel.org
Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
[maddy: Fixed Nilay's reviewed-by tag]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260302003948.1452016-1-namcao@linutronix.de
---
 arch/powerpc/platforms/pseries/msi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 64ffc6476ad6..8285b9a29fbf 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -605,7 +605,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 					      &pseries_msi_irq_chip, pseries_dev);
 	}
 
-	pseries_dev->msi_used++;
+	pseries_dev->msi_used += nr_irqs;
 	return 0;
 
 out:

From 57ccf5ccdc56954f2a91a7f66684fd31c566bde5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 7 Mar 2026 04:53:32 -1000
Subject: [PATCH 1038/1303] sched_ext: Fix enqueue_task_scx() truncation of
 upper enqueue flags

enqueue_task_scx() takes int enq_flags from the sched_class interface.
SCX enqueue flags starting at bit 32 (SCX_ENQ_PREEMPT and above) are
silently truncated when passed through activate_task(). extra_enq_flags
was added as a workaround - storing high bits in rq->scx.extra_enq_flags
and OR-ing them back in enqueue_task_scx(). However, the OR target is
still the int parameter, so the high bits are lost anyway.

The current impact is limited as the only affected flag is SCX_ENQ_PREEMPT
which is informational to the BPF scheduler - its loss means the scheduler
doesn't know about preemption but doesn't cause incorrect behavior.

Fix by renaming the int parameter to core_enq_flags and introducing a
u64 enq_flags local that merges both sources. All downstream functions
already take u64 enq_flags.

Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f323df7be180..174e3650d7fe 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
 }
 
-static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
+static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags)
 {
 	struct scx_sched *sch = scx_root;
 	int sticky_cpu = p->scx.sticky_cpu;
+	u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags;
 
 	if (enq_flags & ENQUEUE_WAKEUP)
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
 
-	enq_flags |= rq->scx.extra_enq_flags;
-
 	if (sticky_cpu >= 0)
 		p->scx.sticky_cpu = -1;
 

From 4ce7ada40c008fa21b7e52ab9d04e8746e2e9325 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Wed, 4 Mar 2026 08:46:03 -0800
Subject: [PATCH 1039/1303] scsi: core: Fix error handling for
 scsi_alloc_sdev()

After scsi_sysfs_device_initialize() was called, error paths must call
__scsi_remove_device().

Fixes: 1ac22c8eae81 ("scsi: core: Fix refcount leak for tagset_refcnt")
Cc: stable@vger.kernel.org
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260304164603.51528-1-junxiao.bi@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_scan.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 2cfcf1f5d6a4..7b11bc7de0e3 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -360,12 +360,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * default device queue depth to figure out sbitmap shift
 	 * since we use this queue depth most of times.
 	 */
-	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
-		kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
-		put_device(&starget->dev);
-		kfree(sdev);
-		goto out;
-	}
+	if (scsi_realloc_sdev_budget_map(sdev, depth))
+		goto out_device_destroy;
 
 	scsi_change_queue_depth(sdev, depth);
 

From b0bd84c39289ef6a6c3827dd52c875659291970a Mon Sep 17 00:00:00 2001
From: Wang Shuaiwei <wangshuaiwei1@xiaomi.com>
Date: Sat, 7 Mar 2026 11:51:28 +0800
Subject: [PATCH 1040/1303] scsi: ufs: core: Fix SError in ufshcd_rtc_work()
 during UFS suspend

In __ufshcd_wl_suspend(), cancel_delayed_work_sync() is called to cancel
the UFS RTC work, but it is placed after ufshcd_vops_suspend(hba, pm_op,
POST_CHANGE). This creates a race condition where ufshcd_rtc_work() can
still be running while ufshcd_vops_suspend() is executing. When
UFSHCD_CAP_CLK_GATING is not supported, the condition
!hba->clk_gating.active_reqs is always true, causing ufshcd_update_rtc()
to be executed. Since ufshcd_vops_suspend() typically performs clock
gating operations, executing ufshcd_update_rtc() at that moment triggers
an SError. The kernel panic trace is as follows:

Kernel panic - not syncing: Asynchronous SError Interrupt
Call trace:
 dump_backtrace+0xec/0x128
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0xa0
 dump_stack+0x18/0x24
 panic+0x148/0x374
 nmi_panic+0x3c/0x8c
 arm64_serror_panic+0x64/0x8c
 do_serror+0xc4/0xc8
 el1h_64_error_handler+0x34/0x4c
 el1h_64_error+0x68/0x6c
 el1_interrupt+0x20/0x58
 el1h_64_irq_handler+0x18/0x24
 el1h_64_irq+0x68/0x6c
 ktime_get+0xc4/0x12c
 ufshcd_mcq_sq_stop+0x4c/0xec
 ufshcd_mcq_sq_cleanup+0x64/0x1dc
 ufshcd_clear_cmd+0x38/0x134
 ufshcd_issue_dev_cmd+0x298/0x4d0
 ufshcd_exec_dev_cmd+0x1a4/0x1c4
 ufshcd_query_attr+0xbc/0x19c
 ufshcd_rtc_work+0x10c/0x1c8
 process_scheduled_works+0x1c4/0x45c
 worker_thread+0x32c/0x3e8
 kthread+0x120/0x1d8
 ret_from_fork+0x10/0x20

Fix this by moving cancel_delayed_work_sync() before the call to
ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE), ensuring the UFS RTC work is
fully completed or cancelled at that point.

Cc: Bean Huo <beanhuo@iokpp.de>
Fixes: 6bf999e0eb41 ("scsi: ufs: core: Add UFS RTC support")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Wang Shuaiwei <wangshuaiwei1@xiaomi.com>
Link: https://patch.msgid.link/20260307035128.3419687-1-wangshuaiwei1@xiaomi.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 899e663fea6e..9ceb6d6d479d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10066,6 +10066,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	}
 
 	flush_work(&hba->eeh_work);
+	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 
 	ret = ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE);
 	if (ret)
@@ -10120,7 +10121,6 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	if (ret)
 		goto set_link_active;
 
-	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 	goto out;
 
 set_link_active:

From c0b7da13a04bd70ef6070bfb9ea85f582294560a Mon Sep 17 00:00:00 2001
From: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Date: Tue, 10 Feb 2026 11:08:22 +0100
Subject: [PATCH 1041/1303] scsi: qla2xxx: Completely fix fcport double free

In qla24xx_els_dcmd_iocb() sp->free is set to qla2x00_els_dcmd_sp_free().
When an error happens, this function is called by qla2x00_sp_release(),
when kref_put() releases the first and the last reference.

qla2x00_els_dcmd_sp_free() frees fcport by calling qla2x00_free_fcport().
Doing it one more time after kref_put() is a bad idea.

Fixes: 82f522ae0d97 ("scsi: qla2xxx: Fix double free of fcport")
Fixes: 4895009c4bb7 ("scsi: qla2xxx: Prevent command send on chip reset")
Signed-off-by: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Signed-off-by: Farhat Abbas <fabbas@cloudlinux.com>
Link: https://patch.msgid.link/aYsDln9NFQQsPDgg@vova-pc
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 9038f6723444..dbe3cd4e274c 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2751,7 +2751,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	if (!elsio->u.els_logo.els_logo_pyld) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
-		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2776,7 +2775,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	if (rval != QLA_SUCCESS) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
-		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 

From 8ddc0c26916574395447ebf4cff684314f6873a9 Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Thu, 5 Mar 2026 14:40:39 +0800
Subject: [PATCH 1042/1303] scsi: hisi_sas: Fix NULL pointer exception during
 user_scan()

user_scan() invokes updated sas_user_scan() for channel 0, and if
successful, iteratively scans remaining channels (1 to shost->max_channel)
via scsi_scan_host_selected() in commit 37c4e72b0651 ("scsi: Fix
sas_user_scan() to handle wildcard and multi-channel scans"). However,
hisi_sas supports only one channel, and the current value of max_channel is
1. sas_user_scan() for channel 1 will trigger the following NULL pointer
exception:

[  441.554662] Unable to handle kernel NULL pointer dereference at virtual address 00000000000008b0
[  441.554699] Mem abort info:
[  441.554710]   ESR = 0x0000000096000004
[  441.554718]   EC = 0x25: DABT (current EL), IL = 32 bits
[  441.554723]   SET = 0, FnV = 0
[  441.554726]   EA = 0, S1PTW = 0
[  441.554730]   FSC = 0x04: level 0 translation fault
[  441.554735] Data abort info:
[  441.554737]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[  441.554742]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[  441.554747]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[  441.554752] user pgtable: 4k pages, 48-bit VAs, pgdp=00000828377a6000
[  441.554757] [00000000000008b0] pgd=0000000000000000, p4d=0000000000000000
[  441.554769] Internal error: Oops: 0000000096000004 [#1]  SMP
[  441.629589] Modules linked in: arm_spe_pmu arm_smmuv3_pmu tpm_tis_spi hisi_uncore_sllc_pmu hisi_uncore_pa_pmu hisi_uncore_l3c_pmu hisi_uncore_hha_pmu hisi_uncore_ddrc_pmu hisi_uncore_cpa_pmu hns3_pmu hisi_ptt hisi_pcie_pmu tpm_tis_core spidev spi_hisi_sfc_v3xx hisi_uncore_pmu spi_dw_mmio fuse hclge hclge_common hisi_sec2 hisi_hpre hisi_zip hisi_qm hns3 hisi_sas_v3_hw sm3_ce sbsa_gwdt hnae3 hisi_sas_main uacce hisi_dma i2c_hisi dm_mirror dm_region_hash dm_log dm_mod
[  441.670819] CPU: 46 UID: 0 PID: 6994 Comm: bash Kdump: loaded Not tainted 7.0.0-rc2+ #84 PREEMPT
[  441.691327] pstate: 81400009 (Nzcv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[  441.698277] pc : sas_find_dev_by_rphy+0x44/0x118
[  441.702896] lr : sas_find_dev_by_rphy+0x3c/0x118
[  441.707502] sp : ffff80009abbba40
[  441.710805] x29: ffff80009abbba40 x28: ffff082819a40008 x27: ffff082810c37c08
[  441.717930] x26: ffff082810c37c28 x25: ffff082819a40290 x24: ffff082810c37c00
[  441.725054] x23: 0000000000000000 x22: 0000000000000001 x21: ffff082819a40000
[  441.732179] x20: ffff082819a40290 x19: 0000000000000000 x18: 0000000000000020
[  441.739304] x17: 0000000000000000 x16: ffffb5dad6bda690 x15: 00000000ffffffff
[  441.746428] x14: ffff082814c3b26c x13: 00000000ffffffff x12: ffff082814c3b26a
[  441.753553] x11: 00000000000000c0 x10: 000000000000003a x9 : ffffb5dad5ea94f4
[  441.760678] x8 : 000000000000003a x7 : ffff80009abbbab0 x6 : 0000000000000030
[  441.767802] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
[  441.774926] x2 : ffff08280f35a300 x1 : ffffb5dad7127180 x0 : 0000000000000000
[  441.782053] Call trace:
[  441.784488]  sas_find_dev_by_rphy+0x44/0x118 (P)
[  441.789095]  sas_target_alloc+0x24/0xb0
[  441.792920]  scsi_alloc_target+0x290/0x330
[  441.797010]  __scsi_scan_target+0x88/0x258
[  441.801096]  scsi_scan_channel+0x74/0xb8
[  441.805008]  scsi_scan_host_selected+0x170/0x188
[  441.809615]  sas_user_scan+0xfc/0x148
[  441.813267]  store_scan+0x10c/0x180
[  441.816743]  dev_attr_store+0x20/0x40
[  441.820398]  sysfs_kf_write+0x84/0xa8
[  441.824054]  kernfs_fop_write_iter+0x130/0x1c8
[  441.828487]  vfs_write+0x2c0/0x370
[  441.831880]  ksys_write+0x74/0x118
[  441.835271]  __arm64_sys_write+0x24/0x38
[  441.839182]  invoke_syscall+0x50/0x120
[  441.842919]  el0_svc_common.constprop.0+0xc8/0xf0
[  441.847611]  do_el0_svc+0x24/0x38
[  441.850913]  el0_svc+0x38/0x158
[  441.854043]  el0t_64_sync_handler+0xa0/0xe8
[  441.858214]  el0t_64_sync+0x1ac/0x1b0
[  441.861865] Code: aa1303e0 97ff70a8 34ffff80 d10a4273 (f9445a75)
[  441.867946] ---[ end trace 0000000000000000 ]---

Therefore, set max_channel to 0.

Fixes: e21fe3a52692 ("scsi: hisi_sas: add initialisation for v3 pci-based controller")
Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://patch.msgid.link/20260305064039.4096775-1-liyihang9@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 2 +-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 30a9c6612651..c2b082f1252c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2578,7 +2578,7 @@ int hisi_sas_probe(struct platform_device *pdev,
 	shost->transportt = hisi_sas_stt;
 	shost->max_id = HISI_SAS_MAX_DEVICES;
 	shost->max_lun = ~0;
-	shost->max_channel = 1;
+	shost->max_channel = 0;
 	shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN;
 	if (hisi_hba->hw->slot_index_alloc) {
 		shost->can_queue = HISI_SAS_MAX_COMMANDS;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 2f9e01717ef3..f69efc6494b8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4993,7 +4993,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->transportt = hisi_sas_stt;
 	shost->max_id = HISI_SAS_MAX_DEVICES;
 	shost->max_lun = ~0;
-	shost->max_channel = 1;
+	shost->max_channel = 0;
 	shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN;
 	shost->can_queue = HISI_SAS_UNRESERVED_IPTT;
 	shost->cmd_per_lun = HISI_SAS_UNRESERVED_IPTT;

From b0dcdcb9ae757c8a8ba2fb24d34f8d147bae707b Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Wed, 4 Mar 2026 17:47:30 -0800
Subject: [PATCH 1043/1303] resolve_btfids: Fix linker flags detection

The "|| echo -lzstd" default makes zstd an unconditional link
dependency of resolve_btfids. On systems where libzstd-dev is not
installed and pkg-config fails, the linker fails:

  ld: cannot find -lzstd: No such file or directory

libzstd is a transitive dependency of libelf, so the -lzstd flag is
strictly necessary only for static builds [1].

Remove ZSTD_LIBS variable, and instead set LIBELF_LIBS depending on
whether the build is static or not. Use $(HOSTPKG_CONFIG) as primary
source of the flags list.

Also add a default value for HOSTPKG_CONFIG in case it's not built via
the toplevel Makefile. Pass it from selftests/bpf too.

[1] https://lore.kernel.org/bpf/4ff82800-2daa-4b9f-95a9-6f512859ee70@linux.dev/

Reported-by: BPF CI Bot (Claude Opus 4.6) <bot+bpf-ci@kernel.org>
Reported-by: Vitaly Chikunov <vt@altlinux.org>
Closes: https://lore.kernel.org/bpf/aaWqMcK-2AQw5dx8@altlinux.org/
Fixes: 4021848a903e ("selftests/bpf: Pass through build flags to bpftool and resolve_btfids")
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/20260305014730.3123382-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/Makefile    | 9 +++++++--
 tools/testing/selftests/bpf/Makefile | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index ef083602b73a..7672208f65e4 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -23,6 +23,7 @@ RM      ?= rm
 HOSTCC  ?= gcc
 HOSTLD  ?= ld
 HOSTAR  ?= ar
+HOSTPKG_CONFIG ?= pkg-config
 CROSS_COMPILE =
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
@@ -63,10 +64,14 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU
 		    $(abspath $@) install_headers
 
 LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
+
+ifneq ($(filter -static,$(EXTRA_LDFLAGS)),)
+LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs --static 2>/dev/null || echo -lelf -lzstd)
+else
 LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+endif
 
 ZLIB_LIBS  := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz)
-ZSTD_LIBS  := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd)
 
 HOSTCFLAGS_resolve_btfids += -g \
           -I$(srctree)/tools/include \
@@ -76,7 +81,7 @@ HOSTCFLAGS_resolve_btfids += -g \
           $(LIBELF_FLAGS) \
           -Wall -Werror
 
-LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS)
+LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS)
 
 export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 72a9ba41f95e..d5acbeba0383 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -409,6 +409,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
 		EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \
+		HOSTPKG_CONFIG=$(PKG_CONFIG) \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by

From 75aa996ea63f8656b668f8d9acb2c7a77c055e7f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 6 Mar 2026 12:19:19 +0100
Subject: [PATCH 1044/1303] s390: Revert "s390/irq/idle: Remove psw bits early"

This reverts commit d8b5cf9c63143fae54a734c41e3bb55cf3f365c7.

Mikhail Zaslonko reported that linux-next doesn't boot anymore [2]. Reason
for this is recent change [2] was supposed to slightly optimize the irq
entry/exit path by removing some psw bits early in case of an idle exit.

This however is incorrect since irqentry_exit() requires the correct old
psw state at irq entry. Otherwise the embedded regs_irqs_disabled() will
not provide the correct result.

With linux-next and HRTIMER_REARM_DEFERRED this leads to the observed boot
problems, however the commit is broken in any case.

Revert the commit which introduced this.

Thanks to Peter Zijlstra for pointing out that this is a bug in the s390
entry code.

Fixes: d8b5cf9c6314 ("s390/irq/idle: Remove psw bits early") [1]
Reported-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Closes: https://lore.kernel.org/r/af549a19-db99-4b16-8511-bf315177a13e@linux.ibm.com/ [2]
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Tested-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260306111919.362559-1-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/irq.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 7fdf960191d3..d10a17e6531d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -147,10 +147,8 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle) {
+	if (from_idle)
 		update_timer_idle();
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
-	}
 
 	irq_enter_rcu();
 
@@ -176,6 +174,9 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -185,10 +186,8 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle) {
+	if (from_idle)
 		update_timer_idle();
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
-	}
 
 	irq_enter_rcu();
 
@@ -210,6 +209,9 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)

From 598bbefa8032cc58b564a81d1ad68bd815c8dc0f Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@linux.ibm.com>
Date: Fri, 27 Feb 2026 14:30:51 +0100
Subject: [PATCH 1045/1303] s390/zcrypt: Enable AUTOSEL_DOM for CCA serialnr
 sysfs attribute

The serialnr sysfs attribute for CCA cards when queried always
used the default domain for sending the request down to the card.
If for any reason exactly this default domain is disabled then
the attribute code fails to retrieve the CCA info and the sysfs
entry shows an empty string. Works as designed but the serial
number is a card attribute and thus it does not matter which
domain is used for the query. So if there are other domains on
this card available, these could be used.

So extend the code to use AUTOSEL_DOM for the domain value to
address any online domain within the card for querying the cca
info and thus show the serialnr as long as there is one domain
usable regardless of the default domain setting.

Fixes: 8f291ebf3270 ("s390/zcrypt: enable card/domain autoselect on ep11 cprbs")
Suggested-by: Ingo Franzki <ifranzki@linux.ibm.com>
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Reviewed-by: Ingo Franzki <ifranzki@linux.ibm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 drivers/s390/crypto/zcrypt_ccamisc.c | 12 +++++++-----
 drivers/s390/crypto/zcrypt_cex4.c    |  3 +--
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 573bad1d6d86..37a157a1d969 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -1639,11 +1639,13 @@ int cca_get_info(u16 cardnr, u16 domain, struct cca_info *ci, u32 xflags)
 
 	memset(ci, 0, sizeof(*ci));
 
-	/* get first info from zcrypt device driver about this apqn */
-	rc = zcrypt_device_status_ext(cardnr, domain, &devstat);
-	if (rc)
-		return rc;
-	ci->hwtype = devstat.hwtype;
+	/* if specific domain given, fetch status and hw info for this apqn */
+	if (domain != AUTOSEL_DOM) {
+		rc = zcrypt_device_status_ext(cardnr, domain, &devstat);
+		if (rc)
+			return rc;
+		ci->hwtype = devstat.hwtype;
+	}
 
 	/*
 	 * Prep memory for rule array and var array use.
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index e9a984903bff..e7b0ed26a9ec 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -85,8 +85,7 @@ static ssize_t cca_serialnr_show(struct device *dev,
 
 	memset(&ci, 0, sizeof(ci));
 
-	if (ap_domain_index >= 0)
-		cca_get_info(ac->id, ap_domain_index, &ci, 0);
+	cca_get_info(ac->id, AUTOSEL_DOM, &ci, 0);
 
 	return sysfs_emit(buf, "%s\n", ci.serial);
 }

From 6da5e537f5afe091658e846da1949d7e557d2ade Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 7 Mar 2026 19:11:51 +0000
Subject: [PATCH 1046/1303] KVM: arm64: vgic: Pick EOIcount deactivations from
 AP-list tail

Valentine reports that their guests fail to boot correctly, losing
interrupts, and indicates that the wrong interrupt gets deactivated.

What happens here is that if the maintenance interrupt is slow enough
to kick us out of the guest, extra interrupts can be activated from
the LRs. We then exit and proceed to handle EOIcount deactivations,
picking active interrupts from the AP list. But we start from the
top of the list, potentially deactivating interrupts that were in
the LRs, while EOIcount only denotes deactivation of interrupts that
are not present in an LR.

Solve this by tracking the last interrupt that made it in the LRs,
and start the EOIcount deactivation walk *after* that interrupt.
Since this only makes sense while the vcpu is loaded, stash this
in the per-CPU host state.

Huge thanks to Valentine for doing all the detective work and
providing an initial patch.

Fixes: 3cfd59f81e0f3 ("KVM: arm64: GICv3: Handle LR overflow when EOImode==0")
Fixes: 281c6c06e2a7b ("KVM: arm64: GICv2: Handle LR overflow when EOImode==0")
Reported-by: Valentine Burley <valentine.burley@collabora.com>
Tested-by: Valentine Burley <valentine.burley@collabora.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20260307115955.369455-1-valentine.burley@collabora.com
Link: https://patch.msgid.link/20260307191151.3781182-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/include/asm/kvm_host.h |  3 +++
 arch/arm64/kvm/vgic/vgic-v2.c     |  4 ++--
 arch/arm64/kvm/vgic/vgic-v3.c     | 12 ++++++------
 arch/arm64/kvm/vgic/vgic.c        |  6 ++++++
 4 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2ca264b3db5f..70cb9cfd760a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -784,6 +784,9 @@ struct kvm_host_data {
 	/* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
 	unsigned int debug_brps;
 	unsigned int debug_wrps;
+
+	/* Last vgic_irq part of the AP list recorded in an LR */
+	struct vgic_irq *last_lr_irq;
 };
 
 struct kvm_host_psci_config {
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index 585491fbda80..cafa3cb32bda 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -115,7 +115,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2;
 	u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
@@ -123,7 +123,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]);
 
 	/* See the GICv3 equivalent for the EOIcount handling rationale */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u32 lr;
 
 		if (!eoicount) {
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 386ddf69a9c5..6a355eca1934 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
 	u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
@@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	/*
 	 * EOIMode=0: use EOIcount to emulate deactivation. We are
 	 * guaranteed to deactivate in reverse order of the activation, so
-	 * just pick one active interrupt after the other in the ap_list,
-	 * and replay the deactivation as if the CPU was doing it. We also
-	 * rely on priority drop to have taken place, and the list to be
-	 * sorted by priority.
+	 * just pick one active interrupt after the other in the tail part
+	 * of the ap_list, past the LRs, and replay the deactivation as if
+	 * the CPU was doing it. We also rely on priority drop to have taken
+	 * place, and the list to be sorted by priority.
 	 */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u64 lr;
 
 		/*
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 430aa98888fd..e22b79cfff96 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -814,6 +814,9 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
 
 static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
 {
+	if (!*host_data_ptr(last_lr_irq))
+		return;
+
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_fold_lr_state(vcpu);
 	else
@@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 	if (irqs_outside_lrs(&als))
 		vgic_sort_ap_list(vcpu);
 
+	*host_data_ptr(last_lr_irq) = NULL;
+
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		scoped_guard(raw_spinlock,  &irq->irq_lock) {
 			if (likely(vgic_target_oracle(irq) == vcpu)) {
 				vgic_populate_lr(vcpu, irq, count++);
+				*host_data_ptr(last_lr_irq) = irq;
 			}
 		}
 

From 08da98f18f4f99aa16838397b76086d2d1d364b3 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:34 +0000
Subject: [PATCH 1047/1303] rust: ptr: add `KnownSize` trait to support DST
 size info extraction

Add a `KnownSize` trait which is used obtain a size from a raw pointer's
metadata. This makes it possible to obtain size information on a raw slice
pointer. This is similar to Rust `core::mem::size_of_val_raw` which is not
yet stable.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://patch.msgid.link/20260302164239.284084-2-gary@kernel.org
[ Fix wording in doc-comment. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/lib.rs |  1 +
 rust/kernel/ptr.rs | 27 ++++++++++++++++++++++++++-
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 3da92f18f4ee..510cc7fe4961 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -20,6 +20,7 @@
 #![feature(generic_nonzero)]
 #![feature(inline_const)]
 #![feature(pointer_is_aligned)]
+#![feature(slice_ptr_len)]
 //
 // Stable since Rust 1.80.0.
 #![feature(slice_flatten)]
diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs
index 5b6a382637fe..e91de5f0d78f 100644
--- a/rust/kernel/ptr.rs
+++ b/rust/kernel/ptr.rs
@@ -2,7 +2,10 @@
 
 //! Types and functions to work with pointers and addresses.
 
-use core::mem::align_of;
+use core::mem::{
+    align_of,
+    size_of, //
+};
 use core::num::NonZero;
 
 /// Type representing an alignment, which is always a power of two.
@@ -225,3 +228,25 @@ fn align_up(self, alignment: Alignment) -> Option<Self> {
 }
 
 impl_alignable_uint!(u8, u16, u32, u64, usize);
+
+/// Trait to represent compile-time known size information.
+///
+/// This is a generalization of [`size_of`] that works for dynamically sized types.
+pub trait KnownSize {
+    /// Get the size of an object of this type in bytes, with the metadata of the given pointer.
+    fn size(p: *const Self) -> usize;
+}
+
+impl<T> KnownSize for T {
+    #[inline(always)]
+    fn size(_: *const Self) -> usize {
+        size_of::<T>()
+    }
+}
+
+impl<T> KnownSize for [T] {
+    #[inline(always)]
+    fn size(p: *const Self) -> usize {
+        p.len() * size_of::<T>()
+    }
+}

From f41941aab3acd33f13d65a2ae496329bc8ae4de0 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:35 +0000
Subject: [PATCH 1048/1303] rust: ptr: add projection infrastructure

Add a generic infrastructure for performing field and index projections on
raw pointers. This will form the basis of performing I/O projections.

Pointers manipulations are intentionally using the safe wrapping variants
instead of the unsafe variants, as the latter requires pointers to be
inside an allocation which is not necessarily true for I/O pointers.

This projection macro protects against rogue `Deref` implementation, which
can causes the projected pointer to be outside the bounds of starting
pointer. This is extremely unlikely and Rust has a lint to catch this, but
is unsoundness regardless. The protection works by inducing type inference
ambiguity when `Deref` is implemented.

This projection macro also stops projecting into unaligned fields (i.e.
fields of `#[repr(packed)]` structs), as misaligned pointers require
special handling. This is implemented by attempting to create reference to
projected field inside a `if false` block. Despite being unreachable, Rust
still checks that they're not unaligned fields.

The projection macro supports both fallible and infallible index
projections. These are described in detail inside the documentation.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://patch.msgid.link/20260302164239.284084-3-gary@kernel.org
[ * Add intro-doc links where possible,
  * Fix typos and slightly improve wording, e.g. "as documentation
    describes" -> "as the documentation of [`Self::proj`] describes",
  * Add an empty line between regular and safety comments, before
    examples, and between logically independent comments,
  * Capitalize various safety comments.

    - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/lib.rs            |   3 +
 rust/kernel/ptr.rs            |   3 +
 rust/kernel/ptr/projection.rs | 305 ++++++++++++++++++++++++++++++++++
 scripts/Makefile.build        |   4 +-
 4 files changed, 314 insertions(+), 1 deletion(-)
 create mode 100644 rust/kernel/ptr/projection.rs

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 510cc7fe4961..d93292d47420 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -38,6 +38,9 @@
 #![feature(const_ptr_write)]
 #![feature(const_refs_to_cell)]
 //
+// Stable since Rust 1.84.0.
+#![feature(strict_provenance)]
+//
 // Expected to become stable.
 #![feature(arbitrary_self_types)]
 //
diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs
index e91de5f0d78f..bdc2d79ff669 100644
--- a/rust/kernel/ptr.rs
+++ b/rust/kernel/ptr.rs
@@ -2,6 +2,9 @@
 
 //! Types and functions to work with pointers and addresses.
 
+pub mod projection;
+pub use crate::project_pointer as project;
+
 use core::mem::{
     align_of,
     size_of, //
diff --git a/rust/kernel/ptr/projection.rs b/rust/kernel/ptr/projection.rs
new file mode 100644
index 000000000000..140ea8e21617
--- /dev/null
+++ b/rust/kernel/ptr/projection.rs
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Infrastructure for handling projections.
+
+use core::{
+    mem::MaybeUninit,
+    ops::Deref, //
+};
+
+use crate::prelude::*;
+
+/// Error raised when a projection is attempted on an array or slice out of bounds.
+pub struct OutOfBound;
+
+impl From<OutOfBound> for Error {
+    #[inline(always)]
+    fn from(_: OutOfBound) -> Self {
+        ERANGE
+    }
+}
+
+/// A helper trait to perform index projection.
+///
+/// This is similar to [`core::slice::SliceIndex`], but operates on raw pointers safely and
+/// fallibly.
+///
+/// # Safety
+///
+/// The implementation of `index` and `get` (if [`Some`] is returned) must ensure that, if provided
+/// input pointer `slice` and returned pointer `output`, then:
+/// - `output` has the same provenance as `slice`;
+/// - `output.byte_offset_from(slice)` is between 0 to
+///   `KnownSize::size(slice) - KnownSize::size(output)`.
+///
+/// This means that if the input pointer is valid, then pointer returned by `get` or `index` is
+/// also valid.
+#[diagnostic::on_unimplemented(message = "`{Self}` cannot be used to index `{T}`")]
+#[doc(hidden)]
+pub unsafe trait ProjectIndex<T: ?Sized>: Sized {
+    type Output: ?Sized;
+
+    /// Returns an index-projected pointer, if in bounds.
+    fn get(self, slice: *mut T) -> Option<*mut Self::Output>;
+
+    /// Returns an index-projected pointer; fail the build if it cannot be proved to be in bounds.
+    #[inline(always)]
+    fn index(self, slice: *mut T) -> *mut Self::Output {
+        Self::get(self, slice).unwrap_or_else(|| build_error!())
+    }
+}
+
+// Forward array impl to slice impl.
+//
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T, I, const N: usize> ProjectIndex<[T; N]> for I
+where
+    I: ProjectIndex<[T]>,
+{
+    type Output = <I as ProjectIndex<[T]>>::Output;
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T; N]) -> Option<*mut Self::Output> {
+        <I as ProjectIndex<[T]>>::get(self, slice)
+    }
+
+    #[inline(always)]
+    fn index(self, slice: *mut [T; N]) -> *mut Self::Output {
+        <I as ProjectIndex<[T]>>::index(self, slice)
+    }
+}
+
+// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to
+// not exceed the required bound.
+unsafe impl<T> ProjectIndex<[T]> for usize {
+    type Output = T;
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut T> {
+        if self >= slice.len() {
+            None
+        } else {
+            Some(slice.cast::<T>().wrapping_add(self))
+        }
+    }
+}
+
+// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to
+// not exceed the required bound.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::Range<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        let new_len = self.end.checked_sub(self.start)?;
+        if self.end > slice.len() {
+            return None;
+        }
+        Some(core::ptr::slice_from_raw_parts_mut(
+            slice.cast::<T>().wrapping_add(self.start),
+            new_len,
+        ))
+    }
+}
+
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeTo<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        (0..self.end).get(slice)
+    }
+}
+
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFrom<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        (self.start..slice.len()).get(slice)
+    }
+}
+
+// SAFETY: `get` returned the pointer as is, so it always has the same provenance and offset of 0.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFull {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        Some(slice)
+    }
+}
+
+/// A helper trait to perform field projection.
+///
+/// This trait has a `DEREF` generic parameter so it can be implemented twice for types that
+/// implement [`Deref`]. This will cause an ambiguity error and thus block [`Deref`] types being
+/// used as base of projection, as they can inject unsoundness. Users therefore must not specify
+/// `DEREF` and should always leave it to be inferred.
+///
+/// # Safety
+///
+/// `proj` may only invoke `f` with a valid allocation, as the documentation of [`Self::proj`]
+/// describes.
+#[doc(hidden)]
+pub unsafe trait ProjectField<const DEREF: bool> {
+    /// Project a pointer to a type to a pointer of a field.
+    ///
+    /// `f` may only be invoked with a valid allocation so it can safely obtain raw pointers to
+    /// fields using `&raw mut`.
+    ///
+    /// This is needed because `base` might not point to a valid allocation, while `&raw mut`
+    /// requires pointers to be in bounds of a valid allocation.
+    ///
+    /// # Safety
+    ///
+    /// `f` must return a pointer in bounds of the provided pointer.
+    unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F;
+}
+
+// NOTE: in theory, this API should work for `T: ?Sized` and `F: ?Sized`, too. However, we cannot
+// currently support that as we need to obtain a valid allocation that `&raw const` can operate on.
+//
+// SAFETY: `proj` invokes `f` with valid allocation.
+unsafe impl<T> ProjectField<false> for T {
+    #[inline(always)]
+    unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F {
+        // Create a valid allocation to start projection, as `base` is not necessarily so. The
+        // memory is never actually used so it will be optimized out, so it should work even for
+        // very large `T` (`memoffset` crate also relies on this). To be extra certain, we also
+        // annotate `f` closure with `#[inline(always)]` in the macro.
+        let mut place = MaybeUninit::uninit();
+        let place_base = place.as_mut_ptr();
+        let field = f(place_base);
+        // SAFETY: `field` is in bounds from `base` per safety requirement.
+        let offset = unsafe { field.byte_offset_from(place_base) };
+        // Use `wrapping_byte_offset` as `base` does not need to be of valid allocation.
+        base.wrapping_byte_offset(offset).cast()
+    }
+}
+
+// SAFETY: Vacuously satisfied.
+unsafe impl<T: Deref> ProjectField<true> for T {
+    #[inline(always)]
+    unsafe fn proj<F>(_: *mut Self, _: impl FnOnce(*mut Self) -> *mut F) -> *mut F {
+        build_error!("this function is a guard against `Deref` impl and is never invoked");
+    }
+}
+
+/// Create a projection from a raw pointer.
+///
+/// The projected pointer is within the memory region marked by the input pointer. There is no
+/// requirement that the input raw pointer needs to be valid, so this macro may be used for
+/// projecting pointers outside normal address space, e.g. I/O pointers. However, if the input
+/// pointer is valid, the projected pointer is also valid.
+///
+/// Supported projections include field projections and index projections.
+/// It is not allowed to project into types that implement custom [`Deref`] or
+/// [`Index`](core::ops::Index).
+///
+/// The macro has basic syntax of `kernel::ptr::project!(ptr, projection)`, where `ptr` is an
+/// expression that evaluates to a raw pointer which serves as the base of projection. `projection`
+/// can be a projection expression of form `.field` (normally identifier, or numeral in case of
+/// tuple structs) or of form `[index]`.
+///
+/// If a mutable pointer is needed, the macro input can be prefixed with the `mut` keyword, i.e.
+/// `kernel::ptr::project!(mut ptr, projection)`. By default, a const pointer is created.
+///
+/// `ptr::project!` macro can perform both fallible indexing and build-time checked indexing.
+/// `[index]` form performs build-time bounds checking; if compiler fails to prove `[index]` is in
+/// bounds, compilation will fail. `[index]?` can be used to perform runtime bounds checking;
+/// `OutOfBound` error is raised via `?` if the index is out of bounds.
+///
+/// # Examples
+///
+/// Field projections are performed with `.field_name`:
+///
+/// ```
+/// struct MyStruct { field: u32, }
+/// let ptr: *const MyStruct = core::ptr::dangling();
+/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .field);
+///
+/// struct MyTupleStruct(u32, u32);
+///
+/// fn proj(ptr: *const MyTupleStruct) {
+///     let field_ptr: *const u32 = kernel::ptr::project!(ptr, .1);
+/// }
+/// ```
+///
+/// Index projections are performed with `[index]`:
+///
+/// ```
+/// fn proj(ptr: *const [u8; 32]) -> Result {
+///     let field_ptr: *const u8 = kernel::ptr::project!(ptr, [1]);
+///     // The following invocation, if uncommented, would fail the build.
+///     //
+///     // kernel::ptr::project!(ptr, [128]);
+///
+///     // This will raise an `OutOfBound` error (which is convertible to `ERANGE`).
+///     kernel::ptr::project!(ptr, [128]?);
+///     Ok(())
+/// }
+/// ```
+///
+/// If you need to match on the error instead of propagate, put the invocation inside a closure:
+///
+/// ```
+/// let ptr: *const [u8; 32] = core::ptr::dangling();
+/// let field_ptr: Result<*const u8> = (|| -> Result<_> {
+///     Ok(kernel::ptr::project!(ptr, [128]?))
+/// })();
+/// assert!(field_ptr.is_err());
+/// ```
+///
+/// For mutable pointers, put `mut` as the first token in macro invocation.
+///
+/// ```
+/// let ptr: *mut [(u8, u16); 32] = core::ptr::dangling_mut();
+/// let field_ptr: *mut u16 = kernel::ptr::project!(mut ptr, [1].1);
+/// ```
+#[macro_export]
+macro_rules! project_pointer {
+    (@gen $ptr:ident, ) => {};
+    // Field projection. `$field` needs to be `tt` to support tuple index like `.0`.
+    (@gen $ptr:ident, .$field:tt $($rest:tt)*) => {
+        // SAFETY: The provided closure always returns an in-bounds pointer.
+        let $ptr = unsafe {
+            $crate::ptr::projection::ProjectField::proj($ptr, #[inline(always)] |ptr| {
+                // Check unaligned field. Not all users (e.g. DMA) can handle unaligned
+                // projections.
+                if false {
+                    let _ = &(*ptr).$field;
+                }
+                // SAFETY: `$field` is in bounds, and no implicit `Deref` is possible (if the
+                // type implements `Deref`, Rust cannot infer the generic parameter `DEREF`).
+                &raw mut (*ptr).$field
+            })
+        };
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    // Fallible index projection.
+    (@gen $ptr:ident, [$index:expr]? $($rest:tt)*) => {
+        let $ptr = $crate::ptr::projection::ProjectIndex::get($index, $ptr)
+            .ok_or($crate::ptr::projection::OutOfBound)?;
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    // Build-time checked index projection.
+    (@gen $ptr:ident, [$index:expr] $($rest:tt)*) => {
+        let $ptr = $crate::ptr::projection::ProjectIndex::index($index, $ptr);
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    (mut $ptr:expr, $($proj:tt)*) => {{
+        let ptr: *mut _ = $ptr;
+        $crate::ptr::project!(@gen ptr, $($proj)*);
+        ptr
+    }};
+    ($ptr:expr, $($proj:tt)*) => {{
+        let ptr = <*const _>::cast_mut($ptr);
+        // We currently always project using mutable pointer, as it is not decided whether `&raw
+        // const` allows the resulting pointer to be mutated (see documentation of `addr_of!`).
+        $crate::ptr::project!(@gen ptr, $($proj)*);
+        ptr.cast_const()
+    }};
+}
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 32e209bc7985..3652b85be545 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -310,16 +310,18 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 
 # The features in this list are the ones allowed for non-`rust/` code.
 #
+#   - Stable since Rust 1.79.0: `feature(slice_ptr_len)`.
 #   - Stable since Rust 1.81.0: `feature(lint_reasons)`.
 #   - Stable since Rust 1.82.0: `feature(asm_const)`,
 #     `feature(offset_of_nested)`, `feature(raw_ref_op)`.
+#   - Stable since Rust 1.84.0: `feature(strict_provenance)`.
 #   - Stable since Rust 1.87.0: `feature(asm_goto)`.
 #   - Expected to become stable: `feature(arbitrary_self_types)`.
 #   - To be determined: `feature(used_with_arg)`.
 #
 # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on
 # the unstable features in use.
-rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg
+rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree

From 4da879a0d3fd170a70994b73baa554c6913918b5 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:36 +0000
Subject: [PATCH 1049/1303] rust: dma: use pointer projection infra for
 `dma_{read,write}` macro

Current `dma_read!`, `dma_write!` macros also use a custom
`addr_of!()`-based implementation for projecting pointers, which has
soundness issue as it relies on absence of `Deref` implementation on types.
It also has a soundness issue where it does not protect against unaligned
fields (when `#[repr(packed)]` is used) so it can generate misaligned
accesses.

This commit migrates them to use the general pointer projection
infrastructure, which handles these cases correctly.

As part of migration, the macro is updated to have an improved surface
syntax. The current macro have

    dma_read!(a.b.c[d].e.f)

to mean `a.b.c` is a DMA coherent allocation and it should project into it
with `[d].e.f` and do a read, which is confusing as it makes the indexing
operator integral to the macro (so it will break if you have an array of
`CoherentAllocation`, for example).

This also is problematic as we would like to generalize
`CoherentAllocation` from just slices to arbitrary types.

Make the macro expects `dma_read!(path.to.dma, .path.inside.dma)` as the
canonical syntax. The index operator is no longer special and is just one
type of projection (in additional to field projection). Similarly, make
`dma_write!(path.to.dma, .path.inside.dma, value)` become the canonical
syntax for writing.

Another issue of the current macro is that it is always fallible. This
makes sense with existing design of `CoherentAllocation`, but once we
support fixed size arrays with `CoherentAllocation`, it is desirable to
have the ability to perform infallible indexing as well, e.g. doing a `[0]`
index of `[Foo; 2]` is okay and can be checked at build-time, so forcing
falliblity is non-ideal. To capture this, the macro is changed to use
`[idx]` as infallible projection and `[idx]?` as fallible index projection
(those syntax are part of the general projection infra). A benefit of this
is that while individual indexing operation may fail, the overall
read/write operation is not fallible.

Fixes: ad2907b4e308 ("rust: add dma coherent allocator abstraction")
Reviewed-by: Benno Lossin <lossin@kernel.org>
Signed-off-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260302164239.284084-4-gary@kernel.org
[ Capitalize safety comments; slightly improve wording in doc-comments.
  - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp.rs      |  14 ++--
 drivers/gpu/nova-core/gsp/boot.rs |   2 +-
 drivers/gpu/nova-core/gsp/cmdq.rs |  10 ++-
 rust/kernel/dma.rs                | 114 +++++++++++++-----------------
 samples/rust/rust_dma.rs          |  30 ++++----
 5 files changed, 81 insertions(+), 89 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 174feaca0a6b..25cd48514c77 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -143,14 +143,14 @@ pub(crate) fn new(pdev: &pci::Device<device::Bound>) -> impl PinInit<Self, Error
                     // _kgspInitLibosLoggingStructures (allocates memory for buffers)
                     // kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array)
                     dma_write!(
-                        libos[0] = LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0)
-                    )?;
+                        libos, [0]?, LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0)
+                    );
                     dma_write!(
-                        libos[1] = LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0)
-                    )?;
-                    dma_write!(libos[2] = LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0))?;
-                    dma_write!(rmargs[0].inner = fw::GspArgumentsCached::new(cmdq))?;
-                    dma_write!(libos[3] = LibosMemoryRegionInitArgument::new("RMARGS", rmargs))?;
+                        libos, [1]?, LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0)
+                    );
+                    dma_write!(libos, [2]?, LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0));
+                    dma_write!(rmargs, [0]?.inner, fw::GspArgumentsCached::new(cmdq));
+                    dma_write!(libos, [3]?, LibosMemoryRegionInitArgument::new("RMARGS", rmargs));
                 },
             }))
         })
diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs
index be427fe26a58..94833f7996e8 100644
--- a/drivers/gpu/nova-core/gsp/boot.rs
+++ b/drivers/gpu/nova-core/gsp/boot.rs
@@ -157,7 +157,7 @@ pub(crate) fn boot(
 
         let wpr_meta =
             CoherentAllocation::<GspFwWprMeta>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(wpr_meta[0] = GspFwWprMeta::new(&gsp_fw, &fb_layout))?;
+        dma_write!(wpr_meta, [0]?, GspFwWprMeta::new(&gsp_fw, &fb_layout));
 
         self.cmdq
             .send_command(bar, commands::SetSystemInfo::new(pdev))?;
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 46819a82a51a..ae54708c38eb 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -201,9 +201,13 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {
 
         let gsp_mem =
             CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(gsp_mem[0].ptes = PteArray::new(gsp_mem.dma_handle())?)?;
-        dma_write!(gsp_mem[0].cpuq.tx = MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES))?;
-        dma_write!(gsp_mem[0].cpuq.rx = MsgqRxHeader::new())?;
+        dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?);
+        dma_write!(
+            gsp_mem,
+            [0]?.cpuq.tx,
+            MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES)
+        );
+        dma_write!(gsp_mem, [0]?.cpuq.rx, MsgqRxHeader::new());
 
         Ok(Self(gsp_mem))
     }
diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs
index 909d56fd5118..a396f8435739 100644
--- a/rust/kernel/dma.rs
+++ b/rust/kernel/dma.rs
@@ -461,6 +461,19 @@ pub fn size(&self) -> usize {
         self.count * core::mem::size_of::<T>()
     }
 
+    /// Returns the raw pointer to the allocated region in the CPU's virtual address space.
+    #[inline]
+    pub fn as_ptr(&self) -> *const [T] {
+        core::ptr::slice_from_raw_parts(self.cpu_addr.as_ptr(), self.count)
+    }
+
+    /// Returns the raw pointer to the allocated region in the CPU's virtual address space as
+    /// a mutable pointer.
+    #[inline]
+    pub fn as_mut_ptr(&self) -> *mut [T] {
+        core::ptr::slice_from_raw_parts_mut(self.cpu_addr.as_ptr(), self.count)
+    }
+
     /// Returns the base address to the allocated region in the CPU's virtual address space.
     pub fn start_ptr(&self) -> *const T {
         self.cpu_addr.as_ptr()
@@ -581,23 +594,6 @@ pub unsafe fn write(&mut self, src: &[T], offset: usize) -> Result {
         Ok(())
     }
 
-    /// Returns a pointer to an element from the region with bounds checking. `offset` is in
-    /// units of `T`, not the number of bytes.
-    ///
-    /// Public but hidden since it should only be used from [`dma_read`] and [`dma_write`] macros.
-    #[doc(hidden)]
-    pub fn item_from_index(&self, offset: usize) -> Result<*mut T> {
-        if offset >= self.count {
-            return Err(EINVAL);
-        }
-        // SAFETY:
-        // - The pointer is valid due to type invariant on `CoherentAllocation`
-        // and we've just checked that the range and index is within bounds.
-        // - `offset` can't overflow since it is smaller than `self.count` and we've checked
-        // that `self.count` won't overflow early in the constructor.
-        Ok(unsafe { self.cpu_addr.as_ptr().add(offset) })
-    }
-
     /// Reads the value of `field` and ensures that its type is [`FromBytes`].
     ///
     /// # Safety
@@ -670,6 +666,9 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {}
 
 /// Reads a field of an item from an allocated region of structs.
 ///
+/// The syntax is of the form `kernel::dma_read!(dma, proj)` where `dma` is an expression evaluating
+/// to a [`CoherentAllocation`] and `proj` is a [projection specification](kernel::ptr::project!).
+///
 /// # Examples
 ///
 /// ```
@@ -684,36 +683,29 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {}
 /// unsafe impl kernel::transmute::AsBytes for MyStruct{};
 ///
 /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result {
-/// let whole = kernel::dma_read!(alloc[2]);
-/// let field = kernel::dma_read!(alloc[1].field);
+/// let whole = kernel::dma_read!(alloc, [2]?);
+/// let field = kernel::dma_read!(alloc, [1]?.field);
 /// # Ok::<(), Error>(()) }
 /// ```
 #[macro_export]
 macro_rules! dma_read {
-    ($dma:expr, $idx: expr, $($field:tt)*) => {{
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be
-            // dereferenced. The compiler also further validates the expression on whether `field`
-            // is a member of `item` when expanded by the macro.
-            unsafe {
-                let ptr_field = ::core::ptr::addr_of!((*item) $($field)*);
-                ::core::result::Result::Ok(
-                    $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field)
-                )
-            }
-        })()
+    ($dma:expr, $($proj:tt)*) => {{
+        let dma = &$dma;
+        let ptr = $crate::ptr::project!(
+            $crate::dma::CoherentAllocation::as_ptr(dma), $($proj)*
+        );
+        // SAFETY: The pointer created by the projection is within the DMA region.
+        unsafe { $crate::dma::CoherentAllocation::field_read(dma, ptr) }
     }};
-    ($dma:ident [ $idx:expr ] $($field:tt)* ) => {
-        $crate::dma_read!($dma, $idx, $($field)*)
-    };
-    ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {
-        $crate::dma_read!($($dma).*, $idx, $($field)*)
-    };
 }
 
 /// Writes to a field of an item from an allocated region of structs.
 ///
+/// The syntax is of the form `kernel::dma_write!(dma, proj, val)` where `dma` is an expression
+/// evaluating to a [`CoherentAllocation`], `proj` is a
+/// [projection specification](kernel::ptr::project!), and `val` is the value to be written to the
+/// projected location.
+///
 /// # Examples
 ///
 /// ```
@@ -728,37 +720,31 @@ macro_rules! dma_read {
 /// unsafe impl kernel::transmute::AsBytes for MyStruct{};
 ///
 /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result {
-/// kernel::dma_write!(alloc[2].member = 0xf);
-/// kernel::dma_write!(alloc[1] = MyStruct { member: 0xf });
+/// kernel::dma_write!(alloc, [2]?.member, 0xf);
+/// kernel::dma_write!(alloc, [1]?, MyStruct { member: 0xf });
 /// # Ok::<(), Error>(()) }
 /// ```
 #[macro_export]
 macro_rules! dma_write {
-    ($dma:ident [ $idx:expr ] $($field:tt)*) => {{
-        $crate::dma_write!($dma, $idx, $($field)*)
+    (@parse [$dma:expr] [$($proj:tt)*] [, $val:expr]) => {{
+        let dma = &$dma;
+        let ptr = $crate::ptr::project!(
+            mut $crate::dma::CoherentAllocation::as_mut_ptr(dma), $($proj)*
+        );
+        let val = $val;
+        // SAFETY: The pointer created by the projection is within the DMA region.
+        unsafe { $crate::dma::CoherentAllocation::field_write(dma, ptr, val) }
     }};
-    ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {{
-        $crate::dma_write!($($dma).*, $idx, $($field)*)
-    }};
-    ($dma:expr, $idx: expr, = $val:expr) => {
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid item.
-            unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) }
-            ::core::result::Result::Ok(())
-        })()
+    (@parse [$dma:expr] [$($proj:tt)*] [.$field:tt $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* .$field] [$($rest)*])
     };
-    ($dma:expr, $idx: expr, $(.$field:ident)* = $val:expr) => {
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be
-            // dereferenced. The compiler also further validates the expression on whether `field`
-            // is a member of `item` when expanded by the macro.
-            unsafe {
-                let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*);
-                $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val)
-            }
-            ::core::result::Result::Ok(())
-        })()
+    (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr]? $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* [$index]?] [$($rest)*])
+    };
+    (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr] $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* [$index]] [$($rest)*])
+    };
+    ($dma:expr, $($rest:tt)*) => {
+        $crate::dma_write!(@parse [$dma] [] [$($rest)*])
     };
 }
diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs
index 9c45851c876e..ce39b5545097 100644
--- a/samples/rust/rust_dma.rs
+++ b/samples/rust/rust_dma.rs
@@ -68,7 +68,7 @@ fn probe(pdev: &pci::Device<Core>, _info: &Self::IdInfo) -> impl PinInit<Self, E
                 CoherentAllocation::alloc_coherent(pdev.as_ref(), TEST_VALUES.len(), GFP_KERNEL)?;
 
             for (i, value) in TEST_VALUES.into_iter().enumerate() {
-                kernel::dma_write!(ca[i] = MyStruct::new(value.0, value.1))?;
+                kernel::dma_write!(ca, [i]?, MyStruct::new(value.0, value.1));
             }
 
             let size = 4 * page::PAGE_SIZE;
@@ -85,24 +85,26 @@ fn probe(pdev: &pci::Device<Core>, _info: &Self::IdInfo) -> impl PinInit<Self, E
     }
 }
 
+impl DmaSampleDriver {
+    fn check_dma(&self) -> Result {
+        for (i, value) in TEST_VALUES.into_iter().enumerate() {
+            let val0 = kernel::dma_read!(self.ca, [i]?.h);
+            let val1 = kernel::dma_read!(self.ca, [i]?.b);
+
+            assert_eq!(val0, value.0);
+            assert_eq!(val1, value.1);
+        }
+
+        Ok(())
+    }
+}
+
 #[pinned_drop]
 impl PinnedDrop for DmaSampleDriver {
     fn drop(self: Pin<&mut Self>) {
         dev_info!(self.pdev, "Unload DMA test driver.\n");
 
-        for (i, value) in TEST_VALUES.into_iter().enumerate() {
-            let val0 = kernel::dma_read!(self.ca[i].h);
-            let val1 = kernel::dma_read!(self.ca[i].b);
-            assert!(val0.is_ok());
-            assert!(val1.is_ok());
-
-            if let Ok(val0) = val0 {
-                assert_eq!(val0, value.0);
-            }
-            if let Ok(val1) = val1 {
-                assert_eq!(val1, value.1);
-            }
-        }
+        assert!(self.check_dma().is_ok());
 
         for (i, entry) in self.sgt.iter().enumerate() {
             dev_info!(

From 1954c4f012206147c34acda8da04f827aa7d3ee3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2026 20:07:15 +0000
Subject: [PATCH 1050/1303] eventpoll: Convert epoll_put_uevent() to scoped
 user access

Saves two function calls, and one stac/clac pair.

stac/clac is rather expensive on older cpus like Zen 2.

A synthetic network stress test gives a ~1.5% increase of pps
on AMD Zen 2.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/eventpoll.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index ccb478eb174b..ea9ca0e4172a 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -82,11 +82,14 @@ static inline struct epoll_event __user *
 epoll_put_uevent(__poll_t revents, __u64 data,
 		 struct epoll_event __user *uevent)
 {
-	if (__put_user(revents, &uevent->events) ||
-	    __put_user(data, &uevent->data))
-		return NULL;
-
+	scoped_user_write_access_size(uevent, sizeof(*uevent), efault) {
+		unsafe_put_user(revents, &uevent->events, efault);
+		unsafe_put_user(data, &uevent->data, efault);
+	}
 	return uevent+1;
+
+efault:
+	return NULL;
 }
 #endif
 

From 46d8a07b4ae262e2fec6ce2aa454e06243661265 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 28 Feb 2026 22:30:30 -0600
Subject: [PATCH 1051/1303] drm/sitronix/st7586: fix bad pixel data due to byte
 swap

Correctly set dbi->write_memory_bpw for the ST7586 driver. This driver
is for a monochrome display that has an unusual data format, so the
default value set in mipi_dbi_spi_init() is not correct simply because
this controller is non-standard.

Previously, we were using dbi->swap_bytes to make the same sort of
workaround, but it was removed in the same commit that added
dbi->write_memory_bpw, so we need to use the latter now to have the
correct behavior.

This fixes every 3 columns of pixels being swapped on the display. There
are 3 pixels per byte, so the byte swap caused this effect.

Fixes: df3fb27a74a4 ("drm/mipi-dbi: Make bits per word configurable for pixel transfers")
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20260228-drm-mipi-dbi-fix-st7586-byte-swap-v1-1-e78f6c24cd28@baylibre.com
---
 drivers/gpu/drm/sitronix/st7586.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/sitronix/st7586.c b/drivers/gpu/drm/sitronix/st7586.c
index b57ebf37a664..16b6b4e368af 100644
--- a/drivers/gpu/drm/sitronix/st7586.c
+++ b/drivers/gpu/drm/sitronix/st7586.c
@@ -347,6 +347,12 @@ static int st7586_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
+	/*
+	 * Override value set by mipi_dbi_spi_init(). This driver is a bit
+	 * non-standard, so best to set it explicitly here.
+	 */
+	dbi->write_memory_bpw = 8;
+
 	/* Cannot read from this controller via SPI */
 	dbi->read_commands = NULL;
 
@@ -356,15 +362,6 @@ static int st7586_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	/*
-	 * we are using 8-bit data, so we are not actually swapping anything,
-	 * but setting mipi->swap_bytes makes mipi_dbi_typec3_command() do the
-	 * right thing and not use 16-bit transfers (which results in swapped
-	 * bytes on little-endian systems and causes out of order data to be
-	 * sent to the display).
-	 */
-	dbi->swap_bytes = true;
-
 	drm_mode_config_reset(drm);
 
 	ret = drm_dev_register(drm, 0);

From 7149be786da012afc6bae293d38f8c1fff1fb90d Mon Sep 17 00:00:00 2001
From: Shenghao Yang <me@shenghaoyang.info>
Date: Sun, 22 Feb 2026 13:45:51 +0800
Subject: [PATCH 1052/1303] drm/gud: fix NULL crtc dereference on display
 disable

gud_plane_atomic_update() currently handles both crtc state and
framebuffer updates - the complexity has led to a few accidental
NULL pointer dereferences.

Commit dc2d5ddb193e ("drm/gud: fix NULL fb and crtc dereferences
on USB disconnect") [1] fixed an earlier dereference but planes
can also be disabled in non-hotplug paths (e.g. display disables
via the desktop environment). The drm_dev_enter() call would not
cause an early return in those and subsequently oops on
dereferencing crtc:

BUG: kernel NULL pointer dereference, address: 00000000000005c8
CPU: 6 UID: 1000 PID: 3473 Comm: kwin_wayland Not tainted 6.18.2-200.vanilla.gud.fc42.x86_64 #1 PREEMPT(lazy)
RIP: 0010:gud_plane_atomic_update+0x148/0x470 [gud]
 <TASK>
 drm_atomic_helper_commit_planes+0x28e/0x310
 drm_atomic_helper_commit_tail+0x2a/0x70
 commit_tail+0xf1/0x150
 drm_atomic_helper_commit+0x13c/0x180
 drm_atomic_commit+0xb1/0xe0
info ? __pfx___drm_printfn_info+0x10/0x10
 drm_mode_atomic_ioctl+0x70f/0x7c0
 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10
 drm_ioctl_kernel+0xae/0x100
 drm_ioctl+0x2a8/0x550
 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10
 __x64_sys_ioctl+0x97/0xe0
 do_syscall_64+0x7e/0x7f0
 ? __ct_user_enter+0x56/0xd0
 ? do_syscall_64+0x158/0x7f0
 ? __ct_user_enter+0x56/0xd0
 ? do_syscall_64+0x158/0x7f0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Split out crtc handling from gud_plane_atomic_update() into
atomic_enable() and atomic_disable() functions to delegate
crtc state transitioning work to the DRM helpers.

To preserve the gud state commit sequence [2], switch to
the runtime PM version of drm_atomic_helper_commit_tail() which
ensures that crtcs are enabled (hence sending the
GUD_REQ_SET_CONTROLLER_ENABLE and GUD_REQ_SET_DISPLAY_ENABLE
requests) before a framebuffer update is sent.

[1] https://lore.kernel.org/all/20251231055039.44266-1-me@shenghaoyang.info/
[2] https://github.com/notro/gud/wiki/GUD-Protocol#display-state

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202601142159.0v8ilfVs-lkp@intel.com/
Fixes: 73cfd166e045 ("drm/gud: Replace simple display pipe with DRM atomic helpers")
Cc: <stable@vger.kernel.org> # 6.19.x
Cc: <stable@vger.kernel.org> # 6.18.x
Signed-off-by: Shenghao Yang <me@shenghaoyang.info>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Ruben Wauters <rubenru09@aol.com>
Signed-off-by: Ruben Wauters <rubenru09@aol.com>
Link: https://patch.msgid.link/20260222054551.80864-1-me@shenghaoyang.info
---
 drivers/gpu/drm/gud/gud_drv.c      |  9 ++++-
 drivers/gpu/drm/gud/gud_internal.h |  4 +++
 drivers/gpu/drm/gud/gud_pipe.c     | 54 ++++++++++++++++++++----------
 3 files changed, 48 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c
index d0122d477610..17c2dead2c13 100644
--- a/drivers/gpu/drm/gud/gud_drv.c
+++ b/drivers/gpu/drm/gud/gud_drv.c
@@ -339,7 +339,9 @@ static int gud_stats_debugfs(struct seq_file *m, void *data)
 }
 
 static const struct drm_crtc_helper_funcs gud_crtc_helper_funcs = {
-	.atomic_check = drm_crtc_helper_atomic_check
+	.atomic_check = drm_crtc_helper_atomic_check,
+	.atomic_enable = gud_crtc_atomic_enable,
+	.atomic_disable = gud_crtc_atomic_disable,
 };
 
 static const struct drm_crtc_funcs gud_crtc_funcs = {
@@ -364,6 +366,10 @@ static const struct drm_plane_funcs gud_plane_funcs = {
 	DRM_GEM_SHADOW_PLANE_FUNCS,
 };
 
+static const struct drm_mode_config_helper_funcs gud_mode_config_helpers = {
+	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
+};
+
 static const struct drm_mode_config_funcs gud_mode_config_funcs = {
 	.fb_create = drm_gem_fb_create_with_dirty,
 	.atomic_check = drm_atomic_helper_check,
@@ -499,6 +505,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	drm->mode_config.min_height = le32_to_cpu(desc.min_height);
 	drm->mode_config.max_height = le32_to_cpu(desc.max_height);
 	drm->mode_config.funcs = &gud_mode_config_funcs;
+	drm->mode_config.helper_private = &gud_mode_config_helpers;
 
 	/* Format init */
 	formats_dev = devm_kmalloc(dev, GUD_FORMATS_MAX_NUM, GFP_KERNEL);
diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h
index d27c31648341..8eec8335f5f9 100644
--- a/drivers/gpu/drm/gud/gud_internal.h
+++ b/drivers/gpu/drm/gud/gud_internal.h
@@ -62,6 +62,10 @@ int gud_usb_set_u8(struct gud_device *gdrm, u8 request, u8 val);
 
 void gud_clear_damage(struct gud_device *gdrm);
 void gud_flush_work(struct work_struct *work);
+void gud_crtc_atomic_enable(struct drm_crtc *crtc,
+			    struct drm_atomic_state *state);
+void gud_crtc_atomic_disable(struct drm_crtc *crtc,
+			     struct drm_atomic_state *state);
 int gud_plane_atomic_check(struct drm_plane *plane,
 			   struct drm_atomic_state *state);
 void gud_plane_atomic_update(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c
index 4b77be94348d..b355bf4d3389 100644
--- a/drivers/gpu/drm/gud/gud_pipe.c
+++ b/drivers/gpu/drm/gud/gud_pipe.c
@@ -580,6 +580,39 @@ int gud_plane_atomic_check(struct drm_plane *plane,
 	return ret;
 }
 
+void gud_crtc_atomic_enable(struct drm_crtc *crtc,
+			    struct drm_atomic_state *state)
+{
+	struct drm_device *drm = crtc->dev;
+	struct gud_device *gdrm = to_gud_device(drm);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
+	gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1);
+	gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0);
+	gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 1);
+
+	drm_dev_exit(idx);
+}
+
+void gud_crtc_atomic_disable(struct drm_crtc *crtc,
+			     struct drm_atomic_state *state)
+{
+	struct drm_device *drm = crtc->dev;
+	struct gud_device *gdrm = to_gud_device(drm);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
+	gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 0);
+	gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0);
+
+	drm_dev_exit(idx);
+}
+
 void gud_plane_atomic_update(struct drm_plane *plane,
 			     struct drm_atomic_state *atomic_state)
 {
@@ -607,24 +640,12 @@ void gud_plane_atomic_update(struct drm_plane *plane,
 		mutex_unlock(&gdrm->damage_lock);
 	}
 
-	if (!drm_dev_enter(drm, &idx))
+	if (!crtc || !drm_dev_enter(drm, &idx))
 		return;
 
-	if (!old_state->fb)
-		gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1);
-
-	if (fb && (crtc->state->mode_changed || crtc->state->connectors_changed))
-		gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0);
-
-	if (crtc->state->active_changed)
-		gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, crtc->state->active);
-
-	if (!fb)
-		goto ctrl_disable;
-
 	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
 	if (ret)
-		goto ctrl_disable;
+		goto out;
 
 	drm_atomic_helper_damage_iter_init(&iter, old_state, new_state);
 	drm_atomic_for_each_plane_damage(&iter, &damage)
@@ -632,9 +653,6 @@ void gud_plane_atomic_update(struct drm_plane *plane,
 
 	drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
 
-ctrl_disable:
-	if (!crtc->state->enable)
-		gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0);
-
+out:
 	drm_dev_exit(idx);
 }

From 1f318b96cc84d7c2ab792fcc0bfd42a7ca890681 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 8 Mar 2026 16:56:54 -0700
Subject: [PATCH 1053/1303] Linux 7.0-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 4b54a5c74332..2b15f0b4a0cb 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From d6db827b430bdcca3976cebca7bd69cca03cde2c Mon Sep 17 00:00:00 2001
From: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Date: Fri, 27 Feb 2026 20:15:34 +0530
Subject: [PATCH 1054/1303] ASoC: qcom: qdsp6: Fix q6apm remove ordering during
 ADSP stop and start

During ADSP stop and start, the kernel crashes due to the order in which
ASoC components are removed.

On ADSP stop, the q6apm-audio .remove callback unloads topology and removes
PCM runtimes during ASoC teardown. This deletes the RTDs that contain the
q6apm DAI components before their removal pass runs, leaving those
components still linked to the card and causing crashes on the next rebind.

Fix this by ensuring that all dependent (child) components are removed
first, and the q6apm component is removed last.

[   48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0
[   48.114763] Mem abort info:
[   48.117650]   ESR = 0x0000000096000004
[   48.121526]   EC = 0x25: DABT (current EL), IL = 32 bits
[   48.127010]   SET = 0, FnV = 0
[   48.130172]   EA = 0, S1PTW = 0
[   48.133415]   FSC = 0x04: level 0 translation fault
[   48.138446] Data abort info:
[   48.141422]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[   48.147079]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[   48.152354]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000
[   48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000
[   48.171530] Internal error: Oops: 0000000096000004 [#1]  SMP
[   48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core
[   48.177444]  coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6
[   48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT
[   48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT)
[   48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface]
[   48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   48.330825] pc : mutex_lock+0xc/0x54
[   48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core]
[   48.340794] sp : ffff800084ddb7b0
[   48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00
[   48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098
[   48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0
[   48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff
[   48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f
[   48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673
[   48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001
[   48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000
[   48.402854] x5 : 0000000000000000 x4 : 0000000000000028 x3 : ffff000ef397a698
[   48.410180] x2 : ffff00009a2aadc0 x1 : 0000000000000000 x0 : 00000000000000d0
[   48.417506] Call trace:
[   48.420025]  mutex_lock+0xc/0x54 (P)
[   48.423712]  snd_soc_dapm_shutdown+0x44/0xbc [snd_soc_core]
[   48.429447]  soc_cleanup_card_resources+0x30/0x2c0 [snd_soc_core]
[   48.435719]  snd_soc_bind_card+0x4dc/0xcc0 [snd_soc_core]
[   48.441278]  snd_soc_add_component+0x27c/0x2c8 [snd_soc_core]
[   48.447192]  snd_soc_register_component+0x9c/0xf4 [snd_soc_core]
[   48.453371]  devm_snd_soc_register_component+0x64/0xc4 [snd_soc_core]
[   48.459994]  apm_probe+0xb4/0x110 [snd_q6apm]
[   48.464479]  apr_device_probe+0x24/0x40 [apr]
[   48.468964]  really_probe+0xbc/0x298
[   48.472651]  __driver_probe_device+0x78/0x12c
[   48.477132]  driver_probe_device+0x40/0x160
[   48.481435]  __device_attach_driver+0xb8/0x134
[   48.486011]  bus_for_each_drv+0x80/0xdc
[   48.489964]  __device_attach+0xa8/0x1b0
[   48.493916]  device_initial_probe+0x50/0x54
[   48.498219]  bus_probe_device+0x38/0xa0
[   48.502170]  device_add+0x590/0x760
[   48.505761]  device_register+0x20/0x30
[   48.509623]  of_register_apr_devices+0x1d8/0x318 [apr]
[   48.514905]  apr_pd_status+0x2c/0x54 [apr]
[   48.519114]  pdr_notifier_work+0x8c/0xe0 [pdr_interface]
[   48.524570]  process_one_work+0x150/0x294
[   48.528692]  worker_thread+0x2d8/0x3d8
[   48.532551]  kthread+0x130/0x204
[   48.535874]  ret_from_fork+0x10/0x20
[   48.539559] Code: d65f03c0 d5384102 d503201f d2800001 (c8e17c02)
[   48.545823] ---[ end trace 0000000000000000 ]---

Fixes: 5477518b8a0e ("ASoC: qdsp6: audioreach: add q6apm support")
Cc: stable@vger.kernel.org
Signed-off-by: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Link: https://patch.msgid.link/20260227144534.278568-1-ravi.hothi@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6apm-dai.c        | 1 +
 sound/soc/qcom/qdsp6/q6apm-lpass-dais.c | 1 +
 sound/soc/qcom/qdsp6/q6apm.c            | 1 +
 3 files changed, 3 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c
index de3bdac3e791..168c166c960d 100644
--- a/sound/soc/qcom/qdsp6/q6apm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6apm-dai.c
@@ -838,6 +838,7 @@ static const struct snd_soc_component_driver q6apm_fe_dai_component = {
 	.ack		= q6apm_dai_ack,
 	.compress_ops	= &q6apm_dai_compress_ops,
 	.use_dai_pcm_id = true,
+	.remove_order   = SND_SOC_COMP_ORDER_EARLY,
 };
 
 static int q6apm_dai_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
index 528756f1332b..5be37eeea329 100644
--- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
+++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
@@ -278,6 +278,7 @@ static const struct snd_soc_component_driver q6apm_lpass_dai_component = {
 	.of_xlate_dai_name = q6dsp_audio_ports_of_xlate_dai_name,
 	.be_pcm_base = AUDIOREACH_BE_PCM_BASE,
 	.use_dai_pcm_id = true,
+	.remove_order   = SND_SOC_COMP_ORDER_FIRST,
 };
 
 static int q6apm_lpass_dai_dev_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c
index 44841fde3856..970b08c89bb3 100644
--- a/sound/soc/qcom/qdsp6/q6apm.c
+++ b/sound/soc/qcom/qdsp6/q6apm.c
@@ -715,6 +715,7 @@ static const struct snd_soc_component_driver q6apm_audio_component = {
 	.name		= APM_AUDIO_DRV_NAME,
 	.probe		= q6apm_audio_probe,
 	.remove		= q6apm_audio_remove,
+	.remove_order   = SND_SOC_COMP_ORDER_LAST,
 };
 
 static int apm_probe(gpr_device_t *gdev)

From facfdef64d11c08e6f1e69d02a0b87cb74cee0f5 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 4 Mar 2026 14:12:50 +0000
Subject: [PATCH 1055/1303] firmware: cs_dsp: Fix fragmentation regression in
 firmware download

Use vmalloc() instead of kmalloc(..., GFP_DMA) to alloc the temporary
buffer for firmware download blobs. This avoids the problem that a
heavily fragmented system cannot allocate enough physically-contiguous
memory for a large blob.

The redundant alloc buffer mechanism was removed in commit 900baa6e7bb0
("firmware: cs_dsp: Remove redundant download buffer allocator").
While doing that I was overly focused on the possibility of the
underlying bus requiring DMA-safe memory. So I used GFP_DMA kmalloc()s.
I failed to notice that the code I was removing used vmalloc().
This creates a regression.

Way back in 2014 the problem of fragmentation with kmalloc()s was fixed
by commit cdcd7f728753 ("ASoC: wm_adsp: Use vmalloc to allocate firmware
download buffer").

Although we don't need physically-contiguous memory, we don't know if the
bus needs some particular alignment of the buffers. Since the change in
2014, the firmware download has always used whatever alignment vmalloc()
returns. To avoid introducing a new problem, the temporary buffer is still
used, to keep the same alignment of pointers passed to regmap_raw_write().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 900baa6e7bb0 ("firmware: cs_dsp: Remove redundant download buffer allocator")
Link: https://patch.msgid.link/20260304141250.1578597-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/cirrus/cs_dsp.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index b4f1c01e3b5b..5d8be0ac7c5e 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1610,11 +1610,17 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 			   region_name);
 
 		if (reg) {
+			/*
+			 * Although we expect the underlying bus does not require
+			 * physically-contiguous buffers, we pessimistically use
+			 * a temporary buffer instead of trusting that the
+			 * alignment of region->data is ok.
+			 */
 			region_len = le32_to_cpu(region->len);
 			if (region_len > buf_len) {
 				buf_len = round_up(region_len, PAGE_SIZE);
-				kfree(buf);
-				buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA);
+				vfree(buf);
+				buf = vmalloc(buf_len);
 				if (!buf) {
 					ret = -ENOMEM;
 					goto out_fw;
@@ -1643,7 +1649,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 
 	ret = 0;
 out_fw:
-	kfree(buf);
+	vfree(buf);
 
 	if (ret == -EOVERFLOW)
 		cs_dsp_err(dsp, "%s: file content overflows file data\n", file);
@@ -2331,11 +2337,17 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 		}
 
 		if (reg) {
+			/*
+			 * Although we expect the underlying bus does not require
+			 * physically-contiguous buffers, we pessimistically use
+			 * a temporary buffer instead of trusting that the
+			 * alignment of blk->data is ok.
+			 */
 			region_len = le32_to_cpu(blk->len);
 			if (region_len > buf_len) {
 				buf_len = round_up(region_len, PAGE_SIZE);
-				kfree(buf);
-				buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA);
+				vfree(buf);
+				buf = vmalloc(buf_len);
 				if (!buf) {
 					ret = -ENOMEM;
 					goto out_fw;
@@ -2366,7 +2378,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 
 	ret = 0;
 out_fw:
-	kfree(buf);
+	vfree(buf);
 
 	if (ret == -EOVERFLOW)
 		cs_dsp_err(dsp, "%s: file content overflows file data\n", file);

From c15e7c62feb3751cbdd458555819df1d70374890 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 26 Feb 2026 21:54:21 -0800
Subject: [PATCH 1056/1303] smb/server: Fix another refcount leak in
 smb2_open()

If ksmbd_override_fsids() fails, we jump to err_out2. At that point, fp is
NULL because it hasn't been assigned dh_info.fp yet, so ksmbd_fd_put(work,
fp) will not be called. However, dh_info.fp was already inserted into the
session file table by ksmbd_reopen_durable_fd(), so it will leak in the
session file table until the session is closed.

Move fp = dh_info.fp; ahead of the ksmbd_override_fsids() check to fix the
problem.

Found by an experimental AI code review agent at Google.

Fixes: c8efcc786146a ("ksmbd: add support for durable handles v1/v2")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 743c629fe7ec..48836b97951b 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -3012,13 +3012,14 @@ int smb2_open(struct ksmbd_work *work)
 				goto err_out2;
 			}
 
+			fp = dh_info.fp;
+
 			if (ksmbd_override_fsids(work)) {
 				rc = -ENOMEM;
 				ksmbd_put_durable_fd(dh_info.fp);
 				goto err_out2;
 			}
 
-			fp = dh_info.fp;
 			file_info = FILE_OPENED;
 
 			rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat);

From 40955015fae4908157ac6c959ea696d05e6e9b31 Mon Sep 17 00:00:00 2001
From: Ali Khaledi <ali.khaledi1989@gmail.com>
Date: Mon, 2 Mar 2026 10:15:48 +0900
Subject: [PATCH 1057/1303] ksmbd: fix use-after-free in proc_show_files due to
 early rcu_read_unlock

The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window. A concurrent opinfo_put() can free the opinfo between the
unlock and the subsequent access to opinfo->is_lease,
opinfo->o_lease->state, and opinfo->level.

Fix this by deferring rcu_read_unlock() until after all opinfo
field accesses are complete. The values needed (const_names, count,
level) are copied into local variables under the RCU read lock,
and the potentially-sleeping seq_printf calls happen after the
lock is released.

Found by AI-assisted code review (Claude Opus 4.6, Anthropic)
in collaboration with Ali Khaledi.

Cc: stable@vger.kernel.org
Fixes: b38f99c1217a ("ksmbd: add procfs interface for runtime monitoring and statistics")
Signed-off-by: Ali Khaledi <ali.khaledi1989@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/vfs_cache.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index ff4ea412d900..168f2dd7e200 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -87,11 +87,7 @@ static int proc_show_files(struct seq_file *m, void *v)
 
 		rcu_read_lock();
 		opinfo = rcu_dereference(fp->f_opinfo);
-		rcu_read_unlock();
-
-		if (!opinfo) {
-			seq_printf(m, " %-15s", " ");
-		} else {
+		if (opinfo) {
 			const struct ksmbd_const_name *const_names;
 			int count;
 			unsigned int level;
@@ -105,8 +101,12 @@ static int proc_show_files(struct seq_file *m, void *v)
 				count = ARRAY_SIZE(ksmbd_oplock_const_names);
 				level = opinfo->level;
 			}
+			rcu_read_unlock();
 			ksmbd_proc_show_const_name(m, " %-15s",
 						   const_names, count, level);
+		} else {
+			rcu_read_unlock();
+			seq_printf(m, " %-15s", " ");
 		}
 
 		seq_printf(m, " %#010x %#010x %s\n",

From 1dfd062caa165ec9d7ee0823087930f3ab8a6294 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 7 Mar 2026 11:32:31 +0900
Subject: [PATCH 1058/1303] ksmbd: fix use-after-free by using call_rcu() for
 oplock_info

ksmbd currently frees oplock_info immediately using kfree(), even
though it is accessed under RCU read-side critical sections in places
like opinfo_get() and proc_show_files().

Since there is no RCU grace period delay between nullifying the pointer
and freeing the memory, a reader can still access oplock_info
structure after it has been freed. This can leads to a use-after-free
especially in opinfo_get() where atomic_inc_not_zero() is called on
already freed memory.

Fix this by switching to deferred freeing using call_rcu().

Fixes: 18b4fac5ef17 ("ksmbd: fix use-after-free in smb_break_all_levII_oplock()")
Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 29 +++++++++++++++++++++--------
 fs/smb/server/oplock.h |  5 +++--
 2 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 09d9878db9cb..8c9aa17384f3 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -120,7 +120,7 @@ static void free_lease(struct oplock_info *opinfo)
 	kfree(lease);
 }
 
-static void free_opinfo(struct oplock_info *opinfo)
+static void __free_opinfo(struct oplock_info *opinfo)
 {
 	if (opinfo->is_lease)
 		free_lease(opinfo);
@@ -129,6 +129,18 @@ static void free_opinfo(struct oplock_info *opinfo)
 	kfree(opinfo);
 }
 
+static void free_opinfo_rcu(struct rcu_head *rcu)
+{
+	struct oplock_info *opinfo = container_of(rcu, struct oplock_info, rcu);
+
+	__free_opinfo(opinfo);
+}
+
+static void free_opinfo(struct oplock_info *opinfo)
+{
+	call_rcu(&opinfo->rcu, free_opinfo_rcu);
+}
+
 struct oplock_info *opinfo_get(struct ksmbd_file *fp)
 {
 	struct oplock_info *opinfo;
@@ -176,9 +188,9 @@ void opinfo_put(struct oplock_info *opinfo)
 	free_opinfo(opinfo);
 }
 
-static void opinfo_add(struct oplock_info *opinfo)
+static void opinfo_add(struct oplock_info *opinfo, struct ksmbd_file *fp)
 {
-	struct ksmbd_inode *ci = opinfo->o_fp->f_ci;
+	struct ksmbd_inode *ci = fp->f_ci;
 
 	down_write(&ci->m_lock);
 	list_add(&opinfo->op_entry, &ci->m_op_list);
@@ -1277,20 +1289,21 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	set_oplock_level(opinfo, req_op_level, lctx);
 
 out:
-	rcu_assign_pointer(fp->f_opinfo, opinfo);
-	opinfo->o_fp = fp;
-
 	opinfo_count_inc(fp);
-	opinfo_add(opinfo);
+	opinfo_add(opinfo, fp);
+
 	if (opinfo->is_lease) {
 		err = add_lease_global_list(opinfo);
 		if (err)
 			goto err_out;
 	}
 
+	rcu_assign_pointer(fp->f_opinfo, opinfo);
+	opinfo->o_fp = fp;
+
 	return 0;
 err_out:
-	free_opinfo(opinfo);
+	__free_opinfo(opinfo);
 	return err;
 }
 
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 9a56eaadd0dd..921e3199e4df 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -69,8 +69,9 @@ struct oplock_info {
 	struct lease		*o_lease;
 	struct list_head        op_entry;
 	struct list_head        lease_entry;
-	wait_queue_head_t oplock_q; /* Other server threads */
-	wait_queue_head_t oplock_brk; /* oplock breaking wait */
+	wait_queue_head_t	oplock_q; /* Other server threads */
+	wait_queue_head_t	oplock_brk; /* oplock breaking wait */
+	struct rcu_head		rcu;
 };
 
 struct lease_break_info {

From eac3361e3d5dd8067b3258c69615888eb45e9f25 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Mon, 2 Mar 2026 12:55:02 +0900
Subject: [PATCH 1059/1303] ksmbd: fix use-after-free in
 smb_lazy_parent_lease_break_close()

opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is being
accessed after rcu_read_unlock() has been called. This creates a
race condition where the memory could be freed by a concurrent
writer between the unlock and the subsequent pointer dereferences
(opinfo->is_lease, etc.), leading to a use-after-free.

Fixes: 5fb282ba4fef ("ksmbd: fix possible null-deref in smb_lazy_parent_lease_break_close")
Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 8c9aa17384f3..393a4ae47cc1 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1135,10 +1135,12 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
 
 	rcu_read_lock();
 	opinfo = rcu_dereference(fp->f_opinfo);
-	rcu_read_unlock();
 
-	if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2)
+	if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2) {
+		rcu_read_unlock();
 		return;
+	}
+	rcu_read_unlock();
 
 	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
 	if (!p_ci)

From 1e689a56173827669a35da7cb2a3c78ed5c53680 Mon Sep 17 00:00:00 2001
From: Marios Makassikis <mmakassikis@freebox.fr>
Date: Tue, 3 Mar 2026 11:14:32 +0100
Subject: [PATCH 1060/1303] smb: server: fix use-after-free in smb2_open()

The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window.

Cc: stable@vger.kernel.org
Signed-off-by: Marios Makassikis <mmakassikis@freebox.fr>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 48836b97951b..9f7ff7491e9a 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -3617,10 +3617,8 @@ int smb2_open(struct ksmbd_work *work)
 
 reconnected_fp:
 	rsp->StructureSize = cpu_to_le16(89);
-	rcu_read_lock();
-	opinfo = rcu_dereference(fp->f_opinfo);
+	opinfo = opinfo_get(fp);
 	rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0;
-	rcu_read_unlock();
 	rsp->Flags = 0;
 	rsp->CreateAction = cpu_to_le32(file_info);
 	rsp->CreationTime = cpu_to_le64(fp->create_time);
@@ -3661,6 +3659,7 @@ int smb2_open(struct ksmbd_work *work)
 		next_ptr = &lease_ccontext->Next;
 		next_off = conn->vals->create_lease_size;
 	}
+	opinfo_put(opinfo);
 
 	if (maximal_access_ctxt) {
 		struct create_context *mxac_ccontext;

From 441336115df26b966575de56daf7107ed474faed Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 14:25:53 +0100
Subject: [PATCH 1061/1303] ksmbd: Don't log keys in SMB3 signing and
 encryption key generation

When KSMBD_DEBUG_AUTH logging is enabled, generate_smb3signingkey() and
generate_smb3encryptionkey() log the session, signing, encryption, and
decryption key bytes. Remove the logs to avoid exposing credentials.

Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/auth.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 5fe8c667c6b1..af5f40304331 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -589,12 +589,8 @@ static int generate_smb3signingkey(struct ksmbd_session *sess,
 	if (!(conn->dialect >= SMB30_PROT_ID && signing->binding))
 		memcpy(chann->smb3signingkey, key, SMB3_SIGN_KEY_SIZE);
 
-	ksmbd_debug(AUTH, "dumping generated AES signing keys\n");
+	ksmbd_debug(AUTH, "generated SMB3 signing key\n");
 	ksmbd_debug(AUTH, "Session Id    %llu\n", sess->id);
-	ksmbd_debug(AUTH, "Session Key   %*ph\n",
-		    SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key);
-	ksmbd_debug(AUTH, "Signing Key   %*ph\n",
-		    SMB3_SIGN_KEY_SIZE, key);
 	return 0;
 }
 
@@ -652,23 +648,9 @@ static void generate_smb3encryptionkey(struct ksmbd_conn *conn,
 		     ptwin->decryption.context,
 		     sess->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE);
 
-	ksmbd_debug(AUTH, "dumping generated AES encryption keys\n");
+	ksmbd_debug(AUTH, "generated SMB3 encryption/decryption keys\n");
 	ksmbd_debug(AUTH, "Cipher type   %d\n", conn->cipher_type);
 	ksmbd_debug(AUTH, "Session Id    %llu\n", sess->id);
-	ksmbd_debug(AUTH, "Session Key   %*ph\n",
-		    SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key);
-	if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM ||
-	    conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) {
-		ksmbd_debug(AUTH, "ServerIn Key  %*ph\n",
-			    SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3encryptionkey);
-		ksmbd_debug(AUTH, "ServerOut Key %*ph\n",
-			    SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3decryptionkey);
-	} else {
-		ksmbd_debug(AUTH, "ServerIn Key  %*ph\n",
-			    SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3encryptionkey);
-		ksmbd_debug(AUTH, "ServerOut Key %*ph\n",
-			    SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3decryptionkey);
-	}
 }
 
 void ksmbd_gen_smb30_encryptionkey(struct ksmbd_conn *conn,

From 56fbbe096a89ff4b52af78a21a4afd9d94bdcc80 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Thu, 5 Mar 2026 10:35:59 +0800
Subject: [PATCH 1062/1303] ALSA: hda/realtek: Add quirk for Gigabyte
 Technology to fix headphone

The BIOS of this machine has set 0x19 to mic, which needs to be set
to headphone pin in order to work properly.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220814
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/b55f6ebe-7449-49f7-ae85-00d2ba1e7af0@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc662.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c
index 5073165d1f3c..3a943adf9087 100644
--- a/sound/hda/codecs/realtek/alc662.c
+++ b/sound/hda/codecs/realtek/alc662.c
@@ -313,6 +313,7 @@ enum {
 	ALC897_FIXUP_HEADSET_MIC_PIN2,
 	ALC897_FIXUP_UNIS_H3C_X500S,
 	ALC897_FIXUP_HEADSET_MIC_PIN3,
+	ALC897_FIXUP_H610M_HP_PIN,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -766,6 +767,13 @@ static const struct hda_fixup alc662_fixups[] = {
 			{ }
 		},
 	},
+	[ALC897_FIXUP_H610M_HP_PIN] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x0321403f }, /* HP out */
+			{ }
+		},
+	},
 };
 
 static const struct hda_quirk alc662_fixup_tbl[] = {
@@ -815,6 +823,7 @@ static const struct hda_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
 	SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2),
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
+	SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN),
 	SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS),
 	SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN),

From 9b1dbd69ba6f8f8c69bc7b77c2ce3b9c6ed05ba6 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Thu, 5 Mar 2026 14:35:07 -0500
Subject: [PATCH 1063/1303] ALSA: pcm: fix use-after-free on linked stream
 runtime in snd_pcm_drain()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the drain loop, the local variable 'runtime' is reassigned to a
linked stream's runtime (runtime = s->runtime at line 2157).  After
releasing the stream lock at line 2169, the code accesses
runtime->no_period_wakeup, runtime->rate, and runtime->buffer_size
(lines 2170-2178) — all referencing the linked stream's runtime without
any lock or refcount protecting its lifetime.

A concurrent close() on the linked stream's fd triggers
snd_pcm_release_substream() → snd_pcm_drop() → pcm_release_private()
→ snd_pcm_unlink() → snd_pcm_detach_substream() → kfree(runtime).
No synchronization prevents kfree(runtime) from completing while the
drain path dereferences the stale pointer.

Fix by caching the needed runtime fields (no_period_wakeup, rate,
buffer_size) into local variables while still holding the stream lock,
and using the cached values after the lock is released.

Fixes: f2b3614cefb6 ("ALSA: PCM - Don't check DMA time-out too shortly")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Link: https://patch.msgid.link/20260305193508.311096-1-mehulrao@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm_native.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 67cf6a0e17ba..5a64453da728 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -2144,6 +2144,10 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 	for (;;) {
 		long tout;
 		struct snd_pcm_runtime *to_check;
+		unsigned int drain_rate;
+		snd_pcm_uframes_t drain_bufsz;
+		bool drain_no_period_wakeup;
+
 		if (signal_pending(current)) {
 			result = -ERESTARTSYS;
 			break;
@@ -2163,16 +2167,25 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 		snd_pcm_group_unref(group, substream);
 		if (!to_check)
 			break; /* all drained */
+		/*
+		 * Cache the runtime fields needed after unlock.
+		 * A concurrent close() on the linked stream may free
+		 * its runtime via snd_pcm_detach_substream() once we
+		 * release the stream lock below.
+		 */
+		drain_no_period_wakeup = to_check->no_period_wakeup;
+		drain_rate = to_check->rate;
+		drain_bufsz = to_check->buffer_size;
 		init_waitqueue_entry(&wait, current);
 		set_current_state(TASK_INTERRUPTIBLE);
 		add_wait_queue(&to_check->sleep, &wait);
 		snd_pcm_stream_unlock_irq(substream);
-		if (runtime->no_period_wakeup)
+		if (drain_no_period_wakeup)
 			tout = MAX_SCHEDULE_TIMEOUT;
 		else {
 			tout = 100;
-			if (runtime->rate) {
-				long t = runtime->buffer_size * 1100 / runtime->rate;
+			if (drain_rate) {
+				long t = drain_bufsz * 1100 / drain_rate;
 				tout = max(t, tout);
 			}
 			tout = msecs_to_jiffies(tout);

From 0d3429f12133c2ca47aa82ddab2342bc360c47d3 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 6 Mar 2026 20:33:17 +0800
Subject: [PATCH 1064/1303] ALSA: hda/realtek: add quirk for ASUS UM6702RC

The sound card of this machine cannot adjust the volume, it can only
be 0 or 100%. The reason is that the DAC with pin 0x17 is connected
to 0x06. Testing found that connecting 0x02 can fix this problem.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220356
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260306123317.575346-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 4c49f1195e1b..dc4a10aaef60 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7273,6 +7273,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2),
+	HDA_CODEC_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1),
 	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),

From 178dd118c0f07fd63a9ed74cfbd8c31ae50e33af Mon Sep 17 00:00:00 2001
From: Liucheng Lu <luliucheng100@outlook.com>
Date: Sat, 7 Mar 2026 11:27:27 +0800
Subject: [PATCH 1065/1303] ALSA: hda/realtek: add HP Laptop 14s-dr5xxx mute
 LED quirk

HP Laptop 14s-dr5xxx with ALC236 codec does not handle the toggling of
the mute LED.
This patch adds a quirk entry for subsystem ID 0x8a1f using
ALC236_FIXUP_HP_MUTE_LED_COEFBIT2 fixup, enabling correct mute LED
behavior.

Signed-off-by: Liucheng Lu <luliucheng100@outlook.com>
Link: https://patch.msgid.link/PAVPR03MB9774F3FCE9CCD181C585281AE37BA@PAVPR03MB9774.eurprd03.prod.outlook.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index dc4a10aaef60..4cfbb7922eeb 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6940,6 +6940,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x89da, "HP Spectre x360 14t-ea100", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
 	SND_PCI_QUIRK(0x103c, 0x89e7, "HP Elite x2 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8a1f, "HP Laptop 14s-dr5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a26, "HP Victus 16-d1xxx (MB 8A26)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),

From 542127f6528ca7cc3cf61e1651d6ccb58495f953 Mon Sep 17 00:00:00 2001
From: Uzair Mughal <contact@uzair.is-a.dev>
Date: Sat, 7 Mar 2026 06:29:06 +0500
Subject: [PATCH 1066/1303] ALSA: hda/realtek: Add headset jack quirk for
 Thinkpad X390

The Lenovo ThinkPad X390 (ALC257 codec, subsystem ID 0x17aa2288)
does not report headset button press events. Headphone insertion is
detected (SW_HEADPHONE_INSERT), but pressing the inline microphone
button on a headset produces no input events.

Add a SND_PCI_QUIRK entry that maps this subsystem ID to
ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, which enables
headset jack button detection through alc_fixup_headset_jack()
and ThinkPad ACPI integration. This is the same fixup used by
similar ThinkPad models (P1 Gen 3, X1 Extreme Gen 3).

Signed-off-by: Uzair Mughal <contact@uzair.is-a.dev>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260307012906.20093-1-contact@uzair.is-a.dev
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 4cfbb7922eeb..ab4b22fcb72e 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7495,6 +7495,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2288, "Thinkpad X390", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),

From ce0123cbb4a40a2f1bbb815f292b26e96088639f Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Fri, 5 Sep 2025 23:15:30 +0200
Subject: [PATCH 1067/1303] ceph: fix i_nlink underrun during async unlink

During async unlink, we drop the `i_nlink` counter before we receive
the completion (that will eventually update the `i_nlink`) because "we
assume that the unlink will succeed".  That is not a bad idea, but it
races against deletions by other clients (or against the completion of
our own unlink) and can lead to an underrun which emits a WARNING like
this one:

 WARNING: CPU: 85 PID: 25093 at fs/inode.c:407 drop_nlink+0x50/0x68
 Modules linked in:
 CPU: 85 UID: 3221252029 PID: 25093 Comm: php-cgi8.1 Not tainted 6.14.11-cm4all1-ampere #655
 Hardware name: Supermicro ARS-110M-NR/R12SPD-A, BIOS 1.1b 10/17/2023
 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : drop_nlink+0x50/0x68
 lr : ceph_unlink+0x6c4/0x720
 sp : ffff80012173bc90
 x29: ffff80012173bc90 x28: ffff086d0a45aaf8 x27: ffff0871d0eb5680
 x26: ffff087f2a64a718 x25: 0000020000000180 x24: 0000000061c88647
 x23: 0000000000000002 x22: ffff07ff9236d800 x21: 0000000000001203
 x20: ffff07ff9237b000 x19: ffff088b8296afc0 x18: 00000000f3c93365
 x17: 0000000000070000 x16: ffff08faffcbdfe8 x15: ffff08faffcbdfec
 x14: 0000000000000000 x13: 45445f65645f3037 x12: 34385f6369706f74
 x11: 0000a2653104bb20 x10: ffffd85f26d73290 x9 : ffffd85f25664f94
 x8 : 00000000000000c0 x7 : 0000000000000000 x6 : 0000000000000002
 x5 : 0000000000000081 x4 : 0000000000000481 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff08727d3f91e8
 Call trace:
  drop_nlink+0x50/0x68 (P)
  vfs_unlink+0xb0/0x2e8
  do_unlinkat+0x204/0x288
  __arm64_sys_unlinkat+0x3c/0x80
  invoke_syscall.constprop.0+0x54/0xe8
  do_el0_svc+0xa4/0xc8
  el0_svc+0x18/0x58
  el0t_64_sync_handler+0x104/0x130
  el0t_64_sync+0x154/0x158

In ceph_unlink(), a call to ceph_mdsc_submit_request() submits the
CEPH_MDS_OP_UNLINK to the MDS, but does not wait for completion.

Meanwhile, between this call and the following drop_nlink() call, a
worker thread may process a CEPH_CAP_OP_IMPORT, CEPH_CAP_OP_GRANT or
just a CEPH_MSG_CLIENT_REPLY (the latter of which could be our own
completion).  These will lead to a set_nlink() call, updating the
`i_nlink` counter to the value received from the MDS.  If that new
`i_nlink` value happens to be zero, it is illegal to decrement it
further.  But that is exactly what ceph_unlink() will do then.

The WARNING can be reproduced this way:

1. Force async unlink; only the async code path is affected.  Having
   no real clue about Ceph internals, I was unable to find out why the
   MDS wouldn't give me the "Fxr" capabilities, so I patched
   get_caps_for_async_unlink() to always succeed.

   (Note that the WARNING dump above was found on an unpatched kernel,
   without this kludge - this is not a theoretical bug.)

2. Add a sleep call after ceph_mdsc_submit_request() so the unlink
   completion gets handled by a worker thread before drop_nlink() is
   called.  This guarantees that the `i_nlink` is already zero before
   drop_nlink() runs.

The solution is to skip the counter decrement when it is already zero,
but doing so without a lock is still racy (TOCTOU).  Since
ceph_fill_inode() and handle_cap_grant() both hold the
`ceph_inode_info.i_ceph_lock` spinlock while set_nlink() runs, this
seems like the proper lock to protect the `i_nlink` updates.

I found prior art in NFS and SMB (using `inode.i_lock`) and AFS (using
`afs_vnode.cb_lock`).  All three have the zero check as well.

Cc: stable@vger.kernel.org
Fixes: 2ccb45462aea ("ceph: perform asynchronous unlink if we have sufficient caps")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 86d7aa594ea9..415db39a56d8 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1339,6 +1339,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = d_inode(dentry);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
 	struct dentry *dn;
@@ -1424,7 +1425,19 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 			 * We have enough caps, so we assume that the unlink
 			 * will succeed. Fix up the target inode and dcache.
 			 */
-			drop_nlink(inode);
+
+			/*
+			 * Protect the i_nlink update with i_ceph_lock
+			 * to precent racing against ceph_fill_inode()
+			 * handling our completion on a worker thread
+			 * and don't decrement if i_nlink has already
+			 * been updated to zero by this completion.
+			 */
+			spin_lock(&ci->i_ceph_lock);
+			if (inode->i_nlink > 0)
+				drop_nlink(inode);
+			spin_unlock(&ci->i_ceph_lock);
+
 			d_delete(dentry);
 		} else {
 			spin_lock(&fsc->async_unlink_conflict_lock);

From 43323a5934b660afae687e8e4e95ac328615a5c4 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Tue, 24 Feb 2026 14:10:29 +0100
Subject: [PATCH 1068/1303] ceph: add a bunch of missing ceph_path_info
 initializers

ceph_mdsc_build_path() must be called with a zero-initialized
ceph_path_info parameter, or else the following
ceph_mdsc_free_path_info() may crash.

Example crash (on Linux 6.18.12):

  virt_to_cache: Object is not a Slab page!
  WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6732 kmem_cache_free+0x316/0x400
  [...]
  Call Trace:
   [...]
   ceph_open+0x13d/0x3e0
   do_dentry_open+0x134/0x480
   vfs_open+0x2a/0xe0
   path_openat+0x9a3/0x1160
  [...]
  cache_from_obj: Wrong slab cache. names_cache but object is from ceph_inode_info
  WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6746 kmem_cache_free+0x2dd/0x400
  [...]
  kernel BUG at mm/slub.c:634!
  Oops: invalid opcode: 0000 [#1] SMP NOPTI
  RIP: 0010:__slab_free+0x1a4/0x350

Some of the ceph_mdsc_build_path() callers had initializers, but
others had not, even though they were all added by commit 15f519e9f883
("ceph: fix race condition validating r_parent before applying state").
The ones without initializer are suspectible to random crashes.  (I can
imagine it could even be possible to exploit this bug to elevate
privileges.)

Unfortunately, these Ceph functions are undocumented and its semantics
can only be derived from the code.  I see that ceph_mdsc_build_path()
initializes the structure only on success, but not on error.

Calling ceph_mdsc_free_path_info() after a failed
ceph_mdsc_build_path() call does not even make sense, but that's what
all callers do, and for it to be safe, the structure must be
zero-initialized.  The least intrusive approach to fix this is
therefore to add initializers everywhere.

Cc: stable@vger.kernel.org
Fixes: 15f519e9f883 ("ceph: fix race condition validating r_parent before applying state")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/debugfs.c | 4 ++--
 fs/ceph/dir.c     | 2 +-
 fs/ceph/file.c    | 4 ++--
 fs/ceph/inode.c   | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f3fe786b4143..7dc307790240 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -79,7 +79,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		if (req->r_inode) {
 			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
 		} else if (req->r_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
@@ -98,7 +98,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		}
 
 		if (req->r_old_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 415db39a56d8..bac9cfb6b982 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1364,7 +1364,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 66bbf6d517a9..5e7c73a29aa3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -397,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
@@ -807,7 +807,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d76f9a79dc0c..d99e12d1100b 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2551,7 +2551,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;

From 040d159a45ded7f33201421a81df0aa2a86e5a0b Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Tue, 24 Feb 2026 14:26:57 +0100
Subject: [PATCH 1069/1303] ceph: fix memory leaks in ceph_mdsc_build_path()

Add __putname() calls to error code paths that did not free the "path"
pointer obtained by __getname().  If ownership of this pointer is not
passed to the caller via path_info.path, the function must free it
before returning.

Cc: stable@vger.kernel.org
Fixes: 3fd945a79e14 ("ceph: encode encrypted name in ceph_mdsc_build_path and dentry release")
Fixes: 550f7ca98ee0 ("ceph: give up on paths longer than PATH_MAX")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 23b6d00643c9..b1746273f186 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2768,6 +2768,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 			if (ret < 0) {
 				dput(parent);
 				dput(cur);
+				__putname(path);
 				return ERR_PTR(ret);
 			}
 
@@ -2777,6 +2778,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 				if (len < 0) {
 					dput(parent);
 					dput(cur);
+					__putname(path);
 					return ERR_PTR(len);
 				}
 			}
@@ -2813,6 +2815,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
 		 * cannot ever succeed.  Creating paths that long is
 		 * possible with Ceph, but Linux cannot use them.
 		 */
+		__putname(path);
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 

From 081a0b78ef30f5746cda3e92e28b4d4ae92901d1 Mon Sep 17 00:00:00 2001
From: Hristo Venev <hristo@venev.name>
Date: Wed, 25 Feb 2026 19:07:56 +0200
Subject: [PATCH 1070/1303] ceph: do not skip the first folio of the next
 object in writeback

When `ceph_process_folio_batch` encounters a folio past the end of the
current object, it should leave it in the batch so that it is picked up
in the next iteration.

Removing the folio from the batch means that it does not get written
back and remains dirty instead. This makes `fsync()` silently skip some
of the data, delays capability release, and breaks coherence with
`O_DIRECT`.

The link below contains instructions for reproducing the bug.

Cc: stable@vger.kernel.org
Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method")
Link: https://tracker.ceph.com/issues/75156
Signed-off-by: Hristo Venev <hristo@venev.name>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e87b3bb94ee8..2090fc78529c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1326,7 +1326,6 @@ void ceph_process_folio_batch(struct address_space *mapping,
 			continue;
 		} else if (rc == -E2BIG) {
 			folio_unlock(folio);
-			ceph_wbc->fbatch.folios[i] = NULL;
 			break;
 		}
 

From d800d0bb2009a73630a096d7c7a80a2e64c1e41e Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 25 Feb 2026 13:51:09 +0100
Subject: [PATCH 1071/1303] dt-bindings: i2c: dw: Update maintainer

Jarkko does now work for Intel anymore and since I'm currently
maintaining this driver, update my contact information here to make sure
patches get Cc'd to me as well.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> (internally)
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
index 914200188809..082fdc2e69ea 100644
--- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Synopsys DesignWare APB I2C Controller
 
 maintainers:
-  - Jarkko Nikula <jarkko.nikula@linux.intel.com>
+  - Mika Westerberg <mika.westerberg@linux.intel.com>
 
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#

From b20b437666e1cb26a7c499d1664e8f2a0ac67000 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Fri, 6 Mar 2026 01:24:32 +0800
Subject: [PATCH 1072/1303] spi: amlogic: spifc-a4: Fix DMA mapping error
 handling

Fix three bugs in aml_sfc_dma_buffer_setup() error paths:
1. Unnecessary goto: When the first DMA mapping (sfc->daddr) fails,
   nothing needs cleanup. Use direct return instead of goto.
2. Double-unmap bug: When info DMA mapping failed, the code would
   unmap sfc->daddr inline, then fall through to out_map_data which
   would unmap it again, causing a double-unmap.
3. Wrong unmap size: The out_map_info label used datalen instead of
   infolen when unmapping sfc->iaddr, which could lead to incorrect
   DMA sync behavior.

Fixes: 4670db6f32e9 ("spi: amlogic: add driver for Amlogic SPI Flash Controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260306-spifc-a4-v1-1-f22c9965f64a@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-amlogic-spifc-a4.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c
index 2aef528cfc1b..3956869cfec1 100644
--- a/drivers/spi/spi-amlogic-spifc-a4.c
+++ b/drivers/spi/spi-amlogic-spifc-a4.c
@@ -411,7 +411,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 	ret = dma_mapping_error(sfc->dev, sfc->daddr);
 	if (ret) {
 		dev_err(sfc->dev, "DMA mapping error\n");
-		goto out_map_data;
+		return ret;
 	}
 
 	cmd = CMD_DATA_ADDRL(sfc->daddr);
@@ -429,7 +429,6 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 		ret = dma_mapping_error(sfc->dev, sfc->iaddr);
 		if (ret) {
 			dev_err(sfc->dev, "DMA mapping error\n");
-			dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir);
 			goto out_map_data;
 		}
 
@@ -448,7 +447,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 	return 0;
 
 out_map_info:
-	dma_unmap_single(sfc->dev, sfc->iaddr, datalen, dir);
+	dma_unmap_single(sfc->dev, sfc->iaddr, infolen, dir);
 out_map_data:
 	dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir);
 

From ad0e9ac2d5f5ab7a773c2c07ecf06ee59db9259f Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 5 Mar 2026 20:22:38 +0800
Subject: [PATCH 1073/1303] spi: atcspi200: Fix double-free in
 atcspi_configure_dma()

The driver uses devm_dma_request_chan() which registers automatic cleanup
via devm_add_action_or_reset(). Calling dma_release_channel() manually on
the RX channel when TX channel request fails causes a double-free when
the devm cleanup runs.

Remove the unnecessary manual cleanup and simplify the error handling
since devm will properly release channels on probe failure or driver
detach.

Fixes: 34e3815ea459 ("spi: atcspi200: Add ATCSPI200 SPI controller driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260305-atcspi2000-v1-1-eafe08dcca60@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-atcspi200.c | 28 +++++++---------------------
 1 file changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c
index 60a37ff5c6f5..fef6954d27e1 100644
--- a/drivers/spi/spi-atcspi200.c
+++ b/drivers/spi/spi-atcspi200.c
@@ -497,31 +497,17 @@ static int atcspi_init_resources(struct platform_device *pdev,
 
 static int atcspi_configure_dma(struct atcspi_dev *spi)
 {
-	struct dma_chan *dma_chan;
-	int ret = 0;
+	spi->host->dma_rx = devm_dma_request_chan(spi->dev, "rx");
+	if (IS_ERR(spi->host->dma_rx))
+		return PTR_ERR(spi->host->dma_rx);
 
-	dma_chan = devm_dma_request_chan(spi->dev, "rx");
-	if (IS_ERR(dma_chan)) {
-		ret = PTR_ERR(dma_chan);
-		goto err_exit;
-	}
-	spi->host->dma_rx = dma_chan;
+	spi->host->dma_tx = devm_dma_request_chan(spi->dev, "tx");
+	if (IS_ERR(spi->host->dma_tx))
+		return PTR_ERR(spi->host->dma_tx);
 
-	dma_chan = devm_dma_request_chan(spi->dev, "tx");
-	if (IS_ERR(dma_chan)) {
-		ret = PTR_ERR(dma_chan);
-		goto free_rx;
-	}
-	spi->host->dma_tx = dma_chan;
 	init_completion(&spi->dma_completion);
 
-	return ret;
-
-free_rx:
-	dma_release_channel(spi->host->dma_rx);
-	spi->host->dma_rx = NULL;
-err_exit:
-	return ret;
+	return 0;
 }
 
 static int atcspi_enable_clk(struct atcspi_dev *spi)

From 155a3bedccaf57c69aa0b590ba3fb579debf3a4d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 8 Mar 2026 22:39:02 +0800
Subject: [PATCH 1074/1303] ublk: don't clear GD_SUPPRESS_PART_SCAN for
 unprivileged daemons

When UBLK_F_NO_AUTO_PART_SCAN is set, GD_SUPPRESS_PART_SCAN is cleared
unconditionally, including for unprivileged daemons. Keep it consistent
with the code block for setting GD_SUPPRESS_PART_SCAN by not clearing
it for unprivileged daemons.

In reality this isn't a problem because ioctl(BLKRRPART) requires
CAP_SYS_ADMIN, but it is more reliable to not clear the bit.

Cc: Alexander Atanasov <alex@zazolabs.com>
Fixes: 8443e2087e70 ("ublk: add UBLK_F_NO_AUTO_PART_SCAN feature flag")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 03edabdf8977..9f6e9109d310 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -4440,7 +4440,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 
 	/* Skip partition scan if disabled by user */
 	if (ub->dev_info.flags & UBLK_F_NO_AUTO_PART_SCAN) {
-		clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
+		/* Not clear for unprivileged daemons, see comment above */
+		if (!ub->unprivileged_daemons)
+			clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 	} else {
 		/* Schedule async partition scan for trusted daemons */
 		if (!ub->unprivileged_daemons)

From 1bc17c67194716f53037685b7059a22cc1a911b2 Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Tue, 3 Mar 2026 15:32:49 +0530
Subject: [PATCH 1075/1303] ASoC: tegra: Add support for Tegra238 soundcard

Tegra238 platforms use different clock rates for plla and
plla_out0 clocks. Add Tegra238 support in the Tegra
sound card driver to apply specific clock configurations.

Signed-off-by: Aditya Bavanari <abavanari@nvidia.com>
Signed-off-by: Sheetal <sheetal@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Link: https://patch.msgid.link/20260303100249.3214529-3-sheetal@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra_audio_graph_card.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c
index 94b5ab77649b..ea10e6e8a9fe 100644
--- a/sound/soc/tegra/tegra_audio_graph_card.c
+++ b/sound/soc/tegra/tegra_audio_graph_card.c
@@ -231,6 +231,15 @@ static const struct tegra_audio_cdata tegra186_data = {
 	.plla_out0_rates[x11_RATE] = 45158400,
 };
 
+static const struct tegra_audio_cdata tegra238_data = {
+	/* PLLA */
+	.plla_rates[x8_RATE] = 1277952000,
+	.plla_rates[x11_RATE] = 1264435200,
+	/* PLLA_OUT0 */
+	.plla_out0_rates[x8_RATE] = 49152000,
+	.plla_out0_rates[x11_RATE] = 45158400,
+};
+
 static const struct tegra_audio_cdata tegra264_data = {
 	/* PLLA1 */
 	.plla_rates[x8_RATE] = 983040000,
@@ -245,6 +254,8 @@ static const struct of_device_id graph_of_tegra_match[] = {
 	  .data = &tegra210_data },
 	{ .compatible = "nvidia,tegra186-audio-graph-card",
 	  .data = &tegra186_data },
+	{ .compatible = "nvidia,tegra238-audio-graph-card",
+	  .data = &tegra238_data },
 	{ .compatible = "nvidia,tegra264-audio-graph-card",
 	  .data = &tegra264_data },
 	{},

From 3306a589e598b50a5bbdfe837371670b507043c0 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Mon, 9 Mar 2026 15:34:41 +0100
Subject: [PATCH 1076/1303] io_uring/register: fix comment about
 task_no_new_privs

The actual code is right, but the comment is the wrong way around.

Fixes: ed82f35b926b ("io_uring: allow registration of per-task restrictions")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/register.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/register.c b/io_uring/register.c
index 594b1f2ce875..a839b22fd392 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -202,7 +202,7 @@ static int io_register_restrictions_task(void __user *arg, unsigned int nr_args)
 		return -EPERM;
 	/*
 	 * Similar to seccomp, disallow setting a filter if task_no_new_privs
-	 * is true and we're not CAP_SYS_ADMIN.
+	 * is false and we're not CAP_SYS_ADMIN.
 	 */
 	if (!task_no_new_privs(current) &&
 	    !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
@@ -238,7 +238,7 @@ static int io_register_bpf_filter_task(void __user *arg, unsigned int nr_args)
 
 	/*
 	 * Similar to seccomp, disallow setting a filter if task_no_new_privs
-	 * is true and we're not CAP_SYS_ADMIN.
+	 * is false and we're not CAP_SYS_ADMIN.
 	 */
 	if (!task_no_new_privs(current) &&
 	    !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))

From 7fdaa640c810cb42090a182c33f905bcc47a616a Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Fri, 6 Mar 2026 09:35:06 -0800
Subject: [PATCH 1077/1303] objtool: Handle Clang RSP musical chairs

For no apparent reason (possibly related to CONFIG_KMSAN), Clang can
randomly pass the value of RSP to other registers and then back again to
RSP.  Handle that accordingly.

Fixes the following warnings:

  drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: undefined stack state
  drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: unknown CFA base reg -1

Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com
Link: https://patch.msgid.link/240e6a172cc73292499334a3724d02ccb3247fc7.1772818491.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/arch/x86/decode.c | 68 +++++++++++++--------------------
 tools/objtool/check.c           | 14 +++++++
 2 files changed, 40 insertions(+), 42 deletions(-)

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 73bfea220d1b..c5817829cdfa 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -395,52 +395,36 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 		if (!rex_w)
 			break;
 
-		if (modrm_reg == CFI_SP) {
-
-			if (mod_is_reg()) {
-				/* mov %rsp, reg */
-				ADD_OP(op) {
-					op->src.type = OP_SRC_REG;
-					op->src.reg = CFI_SP;
-					op->dest.type = OP_DEST_REG;
-					op->dest.reg = modrm_rm;
-				}
-				break;
-
-			} else {
-				/* skip RIP relative displacement */
-				if (is_RIP())
-					break;
-
-				/* skip nontrivial SIB */
-				if (have_SIB()) {
-					modrm_rm = sib_base;
-					if (sib_index != CFI_SP)
-						break;
-				}
-
-				/* mov %rsp, disp(%reg) */
-				ADD_OP(op) {
-					op->src.type = OP_SRC_REG;
-					op->src.reg = CFI_SP;
-					op->dest.type = OP_DEST_REG_INDIRECT;
-					op->dest.reg = modrm_rm;
-					op->dest.offset = ins.displacement.value;
-				}
-				break;
-			}
-
-			break;
-		}
-
-		if (rm_is_reg(CFI_SP)) {
-
-			/* mov reg, %rsp */
+		if (mod_is_reg()) {
+			/* mov reg, reg */
 			ADD_OP(op) {
 				op->src.type = OP_SRC_REG;
 				op->src.reg = modrm_reg;
 				op->dest.type = OP_DEST_REG;
-				op->dest.reg = CFI_SP;
+				op->dest.reg = modrm_rm;
+			}
+			break;
+		}
+
+		/* skip RIP relative displacement */
+		if (is_RIP())
+			break;
+
+		/* skip nontrivial SIB */
+		if (have_SIB()) {
+			modrm_rm = sib_base;
+			if (sib_index != CFI_SP)
+				break;
+		}
+
+		/* mov %rsp, disp(%reg) */
+		if (modrm_reg == CFI_SP) {
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = CFI_SP;
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = modrm_rm;
+				op->dest.offset = ins.displacement.value;
 			}
 			break;
 		}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index a30379e4ff97..786b2f2adbab 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3000,6 +3000,20 @@ static int update_cfi_state(struct instruction *insn,
 				cfi->stack_size += 8;
 			}
 
+			else if (cfi->vals[op->src.reg].base == CFI_CFA) {
+				/*
+				 * Clang RSP musical chairs:
+				 *
+				 *   mov %rsp, %rdx [handled above]
+				 *   ...
+				 *   mov %rdx, %rbx [handled here]
+				 *   ...
+				 *   mov %rbx, %rsp [handled above]
+				 */
+				cfi->vals[op->dest.reg].base = CFI_CFA;
+				cfi->vals[op->dest.reg].offset = cfi->vals[op->src.reg].offset;
+			}
+
 
 			break;
 

From 9a73f085dc91980ab7fcc5e9716f4449424b3b59 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Fri, 6 Mar 2026 10:28:14 -0800
Subject: [PATCH 1078/1303] objtool: Fix another stack overflow in
 validate_branch()

The insn state is getting saved on the stack twice for each recursive
iteration.  No need for that, once is enough.

Fixes the following reported stack overflow:

  drivers/scsi/qla2xxx/qla_dbg.o: error: SIGSEGV: objtool stack overflow!
  Segmentation fault

Fixes: 70589843b36f ("objtool: Add option to trace function validation")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com
Link: https://patch.msgid.link/8b97f62d083457f3b0a29a424275f7957dd3372f.1772821683.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/check.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 786b2f2adbab..91b3ff4803cf 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3748,7 +3748,7 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func,
 static int validate_branch(struct objtool_file *file, struct symbol *func,
 			   struct instruction *insn, struct insn_state state);
 static int do_validate_branch(struct objtool_file *file, struct symbol *func,
-			      struct instruction *insn, struct insn_state state);
+			      struct instruction *insn, struct insn_state *state);
 
 static int validate_insn(struct objtool_file *file, struct symbol *func,
 			 struct instruction *insn, struct insn_state *statep,
@@ -4013,7 +4013,7 @@ static int validate_insn(struct objtool_file *file, struct symbol *func,
  * tools/objtool/Documentation/objtool.txt.
  */
 static int do_validate_branch(struct objtool_file *file, struct symbol *func,
-			      struct instruction *insn, struct insn_state state)
+			      struct instruction *insn, struct insn_state *state)
 {
 	struct instruction *next_insn, *prev_insn = NULL;
 	bool dead_end;
@@ -4044,7 +4044,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func,
 			return 1;
 		}
 
-		ret = validate_insn(file, func, insn, &state, prev_insn, next_insn,
+		ret = validate_insn(file, func, insn, state, prev_insn, next_insn,
 				    &dead_end);
 
 		if (!insn->trace) {
@@ -4055,7 +4055,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func,
 		}
 
 		if (!dead_end && !next_insn) {
-			if (state.cfi.cfa.base == CFI_UNDEFINED)
+			if (state->cfi.cfa.base == CFI_UNDEFINED)
 				return 0;
 			if (file->ignore_unreachables)
 				return 0;
@@ -4080,7 +4080,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 	int ret;
 
 	trace_depth_inc();
-	ret = do_validate_branch(file, func, insn, state);
+	ret = do_validate_branch(file, func, insn, &state);
 	trace_depth_dec();
 
 	return ret;

From 2fcfe5951eb2e8440fc5e1dd6ea977336ff83a1d Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 9 Mar 2026 10:46:12 +0800
Subject: [PATCH 1079/1303] sched_ext: Use WRITE_ONCE() for the write side of
 scx_enable helper pointer

scx_enable() uses double-checked locking to lazily initialize a static
kthread_worker pointer. The fast path reads helper locklessly:

    if (!READ_ONCE(helper)) {          // lockless read -- no helper_mutex

The write side initializes helper under helper_mutex, but previously
used a plain assignment:

        helper = kthread_run_worker(0, "scx_enable_helper");
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                 plain write -- KCSAN data race with READ_ONCE() above

Since READ_ONCE() on the fast path and the plain write on the
initialization path access the same variable without a common lock,
they constitute a data race. KCSAN requires that all sides of a
lock-free access use READ_ONCE()/WRITE_ONCE() consistently.

Use a temporary variable to stage the result of kthread_run_worker(),
and only WRITE_ONCE() into helper after confirming the pointer is
valid. This avoids a window where a concurrent caller on the fast path
could observe an ERR pointer via READ_ONCE(helper) before the error
check completes.

Fixes: b06ccbabe250 ("sched_ext: Fix starvation of scx_enable() under fair-class saturation")
Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 174e3650d7fe..26a6ac2f8826 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5258,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	if (!READ_ONCE(helper)) {
 		mutex_lock(&helper_mutex);
 		if (!helper) {
-			helper = kthread_run_worker(0, "scx_enable_helper");
-			if (IS_ERR_OR_NULL(helper)) {
-				helper = NULL;
+			struct kthread_worker *w =
+				kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(w)) {
 				mutex_unlock(&helper_mutex);
 				return -ENOMEM;
 			}
-			sched_set_fifo(helper->task);
+			sched_set_fifo(w->task);
+			WRITE_ONCE(helper, w);
 		}
 		mutex_unlock(&helper_mutex);
 	}

From 111e2863372c322e836e0c896f6dd9cf4ee08c71 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 10 Mar 2026 02:01:34 +0800
Subject: [PATCH 1080/1303] spi: rockchip-sfc: Fix double-free in remove()
 callback

The driver uses devm_spi_register_controller() for registration, which
automatically unregisters the controller via devm cleanup when the
device is removed. The manual call to spi_unregister_controller() in
the remove() callback can lead to a double-free.

And to make sure controller is unregistered before DMA buffer is
unmapped, switch to use spi_register_controller() in probe().

Fixes: 8011709906d0 ("spi: rockchip-sfc: Support pm ops")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260310-sfc-v2-1-67fab04b097f@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-rockchip-sfc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c
index 2990bf85ee47..174995042f53 100644
--- a/drivers/spi/spi-rockchip-sfc.c
+++ b/drivers/spi/spi-rockchip-sfc.c
@@ -711,7 +711,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev)
 		}
 	}
 
-	ret = devm_spi_register_controller(dev, host);
+	ret = spi_register_controller(host);
 	if (ret)
 		goto err_register;
 

From 785d4625d3e05bb0ac536ff4fd74d096cfe51714 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:20:14 -0600
Subject: [PATCH 1081/1303] io_uring/bpf_filter: use bpf_prog_run_pin_on_cpu()
 to prevent migration

Since the caller, __io_uring_run_bpf_filters(), doesn't prevent
migration, it should use the migration disabling variant for running
the BPF program.

Fixes: d42eb05e60fe ("io_uring: add support for BPF filtering for opcode restrictions")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/bpf_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/bpf_filter.c b/io_uring/bpf_filter.c
index 28a23e92ee81..9cc44764e0ac 100644
--- a/io_uring/bpf_filter.c
+++ b/io_uring/bpf_filter.c
@@ -85,7 +85,7 @@ int __io_uring_run_bpf_filters(struct io_bpf_filter __rcu **filters,
 	do {
 		if (filter == &dummy_filter)
 			return -EACCES;
-		ret = bpf_prog_run(filter->prog, &bpf_ctx);
+		ret = bpf_prog_run_pin_on_cpu(filter->prog, &bpf_ctx);
 		if (!ret)
 			return -EACCES;
 		filter = filter->next;

From 2f22702dc0fee06a240404e0f7ead5b789b253d8 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Thu, 26 Feb 2026 17:16:44 +0100
Subject: [PATCH 1082/1303] drm/bridge: ti-sn65dsi83: fix CHA_DSI_CLK_RANGE
 rounding

The DSI frequency must be in the range:

  (CHA_DSI_CLK_RANGE * 5 MHz) <= DSI freq < ((CHA_DSI_CLK_RANGE + 1) * 5 MHz)

So the register value should point to the lower range value, but
DIV_ROUND_UP() rounds the division to the higher range value, resulting in
an excess of 1 (unless the frequency is an exact multiple of 5 MHz).

For example for a 437100000 MHz clock CHA_DSI_CLK_RANGE should be 87 (0x57):

  (87 * 5 = 435) <= 437.1 < (88 * 5 = 440)

but current code returns 88 (0x58).

Fix the computation by removing the DIV_ROUND_UP().

Fixes: ceb515ba29ba ("drm/bridge: ti-sn65dsi83: Add TI SN65DSI83 and SN65DSI84 driver")
Cc: stable@vger.kernel.org
Reviewed-by: Marek Vasut <marek.vasut@mailbox.org>
Link: https://patch.msgid.link/20260226-ti-sn65dsi83-dual-lvds-fixes-and-test-pattern-v1-1-2e15f5a9a6a0@bootlin.com
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/bridge/ti-sn65dsi83.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
index f6736b4457bb..d2a81175d279 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
@@ -351,9 +351,9 @@ static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx,
 	 *  DSI_CLK = mode clock * bpp / dsi_data_lanes / 2
 	 * the 2 is there because the bus is DDR.
 	 */
-	return DIV_ROUND_UP(clamp((unsigned int)mode->clock *
-			    mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) /
-			    ctx->dsi->lanes / 2, 40000U, 500000U), 5000U);
+	return clamp((unsigned int)mode->clock *
+		     mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) /
+		     ctx->dsi->lanes / 2, 40000U, 500000U) / 5000U;
 }
 
 static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx)

From d0d727746944096a6681dc6adb5f123fc5aa018d Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Thu, 26 Feb 2026 17:16:45 +0100
Subject: [PATCH 1083/1303] drm/bridge: ti-sn65dsi83: halve horizontal syncs
 for dual LVDS output

Dual LVDS output (available on the SN65DSI84) requires HSYNC_PULSE_WIDTH
and HORIZONTAL_BACK_PORCH to be divided by two with respect to the values
used for single LVDS output.

While not clearly stated in the datasheet, this is needed according to the
DSI Tuner [0] output. It also makes sense intuitively because in dual LVDS
output two pixels at a time are output and so the output clock is half of
the pixel clock.

Some dual-LVDS panels refuse to show any picture without this fix.

Divide by two HORIZONTAL_FRONT_PORCH too, even though this register is used
only for test pattern generation which is not currently implemented by this
driver.

[0] https://www.ti.com/tool/DSI-TUNER

Fixes: ceb515ba29ba ("drm/bridge: ti-sn65dsi83: Add TI SN65DSI83 and SN65DSI84 driver")
Cc: stable@vger.kernel.org
Reviewed-by: Marek Vasut <marek.vasut@mailbox.org>
Link: https://patch.msgid.link/20260226-ti-sn65dsi83-dual-lvds-fixes-and-test-pattern-v1-2-2e15f5a9a6a0@bootlin.com
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
---
 drivers/gpu/drm/bridge/ti-sn65dsi83.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
index d2a81175d279..17a885244e1e 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
@@ -517,6 +517,7 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge,
 					struct drm_atomic_state *state)
 {
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
+	const unsigned int dual_factor = ctx->lvds_dual_link ? 2 : 1;
 	const struct drm_bridge_state *bridge_state;
 	const struct drm_crtc_state *crtc_state;
 	const struct drm_display_mode *mode;
@@ -653,18 +654,18 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge,
 	/* 32 + 1 pixel clock to ensure proper operation */
 	le16val = cpu_to_le16(32 + 1);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &le16val, 2);
-	le16val = cpu_to_le16(mode->hsync_end - mode->hsync_start);
+	le16val = cpu_to_le16((mode->hsync_end - mode->hsync_start) / dual_factor);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW,
 			  &le16val, 2);
 	le16val = cpu_to_le16(mode->vsync_end - mode->vsync_start);
 	regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW,
 			  &le16val, 2);
 	regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH,
-		     mode->htotal - mode->hsync_end);
+		     (mode->htotal - mode->hsync_end) / dual_factor);
 	regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH,
 		     mode->vtotal - mode->vsync_end);
 	regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH,
-		     mode->hsync_start - mode->hdisplay);
+		     (mode->hsync_start - mode->hdisplay) / dual_factor);
 	regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH,
 		     mode->vsync_start - mode->vdisplay);
 	regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00);

From 3c99c9f0ed60582c1c9852b685d78d5d3a50de63 Mon Sep 17 00:00:00 2001
From: "matteo.cotifava" <cotifavamatteo@gmail.com>
Date: Mon, 9 Mar 2026 22:54:11 +0100
Subject: [PATCH 1084/1303] ASoC: soc-core: drop delayed_work_pending() check
 before flush

The delayed_work_pending() check before flush_delayed_work() in
soc_free_pcm_runtime() is unnecessary and racy. flush_delayed_work()
is safe to call unconditionally - it is a no-op when no work is
pending. Remove the check.

The original check was added by commit 9c9b65203492 ("ASoC: core:
only flush inited work during free") but delayed_work_pending()
followed by flush_delayed_work() has a time-of-check/time-of-use
window where work can become pending between the two calls.

Fixes: 9c9b65203492 ("ASoC: core: only flush inited work during free")
Signed-off-by: Matteo Cotifava <cotifavamatteo@gmail.com>
Link: https://patch.msgid.link/20260309215412.545628-2-cotifavamatteo@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d0fffef65daf..e5ac8ae1665d 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -462,8 +462,7 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd)
 
 	list_del(&rtd->list);
 
-	if (delayed_work_pending(&rtd->delayed_work))
-		flush_delayed_work(&rtd->delayed_work);
+	flush_delayed_work(&rtd->delayed_work);
 	snd_soc_pcm_component_free(rtd);
 
 	/*

From 95bc5c225513fc3c4ce169563fb5e3929fbb938b Mon Sep 17 00:00:00 2001
From: "matteo.cotifava" <cotifavamatteo@gmail.com>
Date: Mon, 9 Mar 2026 22:54:12 +0100
Subject: [PATCH 1085/1303] ASoC: soc-core: flush delayed work before removing
 DAIs and widgets

When a sound card is unbound while a PCM stream is open, a
use-after-free can occur in snd_soc_dapm_stream_event(), called from
the close_delayed_work workqueue handler.

During unbind, snd_soc_unbind_card() flushes delayed work and then
calls soc_cleanup_card_resources(). Inside cleanup,
snd_card_disconnect_sync() releases all PCM file descriptors, and
the resulting PCM close path can call snd_soc_dapm_stream_stop()
which schedules new delayed work with a pmdown_time timer delay.
Since this happens after the flush in snd_soc_unbind_card(), the
new work is not caught. soc_remove_link_components() then frees
DAPM widgets before this work fires, leading to the use-after-free.

The existing flush in soc_free_pcm_runtime() also cannot help as it
runs after soc_remove_link_components() has already freed the widgets.

Add a flush in soc_cleanup_card_resources() after
snd_card_disconnect_sync() (after which no new PCM closes can
schedule further delayed work) and before soc_remove_link_dais()
and soc_remove_link_components() (which tear down the structures the
delayed work accesses).

Fixes: e894efef9ac7 ("ASoC: core: add support to card rebind")
Signed-off-by: Matteo Cotifava <cotifavamatteo@gmail.com>
Link: https://patch.msgid.link/20260309215412.545628-3-cotifavamatteo@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index e5ac8ae1665d..cf826c2a8b59 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2121,6 +2121,9 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card)
 	for_each_card_rtds(card, rtd)
 		if (rtd->initialized)
 			snd_soc_link_exit(rtd);
+	/* flush delayed work before removing DAIs and DAPM widgets */
+	snd_soc_flush_all_delayed_work(card);
+
 	/* remove and free each DAI */
 	soc_remove_link_dais(card);
 	soc_remove_link_components(card);

From 9063d7e2615f4a7ab321de6b520e23d370e58816 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 15 Jan 2026 15:30:50 +0100
Subject: [PATCH 1086/1303] apparmor: validate DFA start states are in bounds
 in unpack_pdb

Start states are read from untrusted data and used as indexes into the
DFA state tables. The aa_dfa_next() function call in unpack_pdb() will
access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds
the number of states in the DFA, this results in an out-of-bound read.

==================================================================
 BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360
 Read of size 4 at addr ffff88811956fb90 by task su/1097
 ...

Reject policies with out-of-bounds start states during unpacking
to prevent the issue.

Fixes: ad5ff3db53c6 ("AppArmor: Add ability to load extended policy")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 1769417a9962..ba5d40dbeb24 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -1010,7 +1010,17 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy,
 		if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
 			/* default start state for xmatch and file dfa */
 			pdb->start[AA_CLASS_FILE] = DFA_START;
-		}	/* setup class index */
+		}
+
+		size_t state_count = pdb->dfa->tables[YYTD_ID_BASE]->td_lolen;
+
+		if (pdb->start[0] >= state_count ||
+		    pdb->start[AA_CLASS_FILE] >= state_count) {
+			*info = "invalid dfa start state";
+			goto fail;
+		}
+
+		/* setup class index */
 		for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
 			pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
 						    i);

From e38c55d9f834e5b848bfed0f5c586aaf45acb825 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Tue, 20 Jan 2026 15:24:04 +0100
Subject: [PATCH 1087/1303] apparmor: fix memory leak in verify_header

The function sets `*ns = NULL` on every call, leaking the namespace
string allocated in previous iterations when multiple profiles are
unpacked. This also breaks namespace consistency checking since *ns
is always NULL when the comparison is made.

Remove the incorrect assignment.
The caller (aa_unpack) initializes *ns to NULL once before the loop,
which is sufficient.

Fixes: dd51c8485763 ("apparmor: provide base for multiple profiles to be replaced at once")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index ba5d40dbeb24..5d90ea55de82 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -1419,7 +1419,6 @@ static int verify_header(struct aa_ext *e, int required, const char **ns)
 {
 	int error = -EPROTONOSUPPORT;
 	const char *name = NULL;
-	*ns = NULL;
 
 	/* get the interface version */
 	if (!aa_unpack_u32(e, &e->version, "version")) {

From ab09264660f9de5d05d1ef4e225aa447c63a8747 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Tue, 13 Jan 2026 09:09:43 +0100
Subject: [PATCH 1088/1303] apparmor: replace recursive profile removal with
 iterative approach

The profile removal code uses recursion when removing nested profiles,
which can lead to kernel stack exhaustion and system crashes.

Reproducer:
  $ pf='a'; for ((i=0; i<1024; i++)); do
      echo -e "profile $pf { \n }" | apparmor_parser -K -a;
      pf="$pf//x";
  done
  $ echo -n a > /sys/kernel/security/apparmor/.remove

Replace the recursive __aa_profile_list_release() approach with an
iterative approach in __remove_profile(). The function repeatedly
finds and removes leaf profiles until the entire subtree is removed,
maintaining the same removal semantic without recursion.

Fixes: c88d4c7b049e ("AppArmor: core policy routines")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy.c | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 9108d74c6b46..566821852592 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -191,19 +191,43 @@ static void __list_remove_profile(struct aa_profile *profile)
 }
 
 /**
- * __remove_profile - remove old profile, and children
- * @profile: profile to be replaced  (NOT NULL)
+ * __remove_profile - remove profile, and children
+ * @profile: profile to be removed  (NOT NULL)
  *
  * Requires: namespace list lock be held, or list not be shared
  */
 static void __remove_profile(struct aa_profile *profile)
 {
+	struct aa_profile *curr, *to_remove;
+
 	AA_BUG(!profile);
 	AA_BUG(!profile->ns);
 	AA_BUG(!mutex_is_locked(&profile->ns->lock));
 
 	/* release any children lists first */
-	__aa_profile_list_release(&profile->base.profiles);
+	if (!list_empty(&profile->base.profiles)) {
+		curr = list_first_entry(&profile->base.profiles, struct aa_profile, base.list);
+
+		while (curr != profile) {
+
+			while (!list_empty(&curr->base.profiles))
+				curr = list_first_entry(&curr->base.profiles,
+							struct aa_profile, base.list);
+
+			to_remove = curr;
+			if (!list_is_last(&to_remove->base.list,
+					  &aa_deref_parent(curr)->base.profiles))
+				curr = list_next_entry(to_remove, base.list);
+			else
+				curr = aa_deref_parent(curr);
+
+			/* released by free_profile */
+			aa_label_remove(&to_remove->label);
+			__aafs_profile_rmdir(to_remove);
+			__list_remove_profile(to_remove);
+		}
+	}
+
 	/* released by free_profile */
 	aa_label_remove(&profile->label);
 	__aafs_profile_rmdir(profile);

From 306039414932c80f8420695a24d4fe10c84ccfb2 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 3 Mar 2026 11:08:02 -0800
Subject: [PATCH 1089/1303] apparmor: fix: limit the number of levels of policy
 namespaces

Currently the number of policy namespaces is not bounded relying on
the user namespace limit. However policy namespaces aren't strictly
tied to user namespaces and it is possible to create them and nest
them arbitrarily deep which can be used to exhaust system resource.

Hard cap policy namespaces to the same depth as user namespaces.

Fixes: c88d4c7b049e8 ("AppArmor: core policy routines")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Ryan Lee <ryan.lee@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/include/policy_ns.h | 2 ++
 security/apparmor/policy_ns.c         | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/security/apparmor/include/policy_ns.h b/security/apparmor/include/policy_ns.h
index d646070fd966..cc6e84151812 100644
--- a/security/apparmor/include/policy_ns.h
+++ b/security/apparmor/include/policy_ns.h
@@ -18,6 +18,8 @@
 #include "label.h"
 #include "policy.h"
 
+/* Match max depth of user namespaces */
+#define MAX_NS_DEPTH 32
 
 /* struct aa_ns_acct - accounting of profiles in namespace
  * @max_size: maximum space allowed for all profiles in namespace
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
index 01b653a3609b..5a907a875d8f 100644
--- a/security/apparmor/policy_ns.c
+++ b/security/apparmor/policy_ns.c
@@ -223,6 +223,8 @@ static struct aa_ns *__aa_create_ns(struct aa_ns *parent, const char *name,
 	AA_BUG(!name);
 	AA_BUG(!mutex_is_locked(&parent->lock));
 
+	if (parent->level > MAX_NS_DEPTH)
+		return ERR_PTR(-ENOSPC);
 	ns = alloc_ns(parent->base.hname, name);
 	if (!ns)
 		return ERR_PTR(-ENOMEM);

From 8756b68edae37ff546c02091989a4ceab3f20abd Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 29 Jan 2026 17:08:25 +0100
Subject: [PATCH 1090/1303] apparmor: fix side-effect bug in match_char() macro
 usage

The match_char() macro evaluates its character parameter multiple
times when traversing differential encoding chains. When invoked
with *str++, the string pointer advances on each iteration of the
inner do-while loop, causing the DFA to check different characters
at each iteration and therefore skip input characters.
This results in out-of-bounds reads when the pointer advances past
the input buffer boundary.

[   94.984676] ==================================================================
[   94.985301] BUG: KASAN: slab-out-of-bounds in aa_dfa_match+0x5ae/0x760
[   94.985655] Read of size 1 at addr ffff888100342000 by task file/976

[   94.986319] CPU: 7 UID: 1000 PID: 976 Comm: file Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy)
[   94.986322] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   94.986329] Call Trace:
[   94.986341]  <TASK>
[   94.986347]  dump_stack_lvl+0x5e/0x80
[   94.986374]  print_report+0xc8/0x270
[   94.986384]  ? aa_dfa_match+0x5ae/0x760
[   94.986388]  kasan_report+0x118/0x150
[   94.986401]  ? aa_dfa_match+0x5ae/0x760
[   94.986405]  aa_dfa_match+0x5ae/0x760
[   94.986408]  __aa_path_perm+0x131/0x400
[   94.986418]  aa_path_perm+0x219/0x2f0
[   94.986424]  apparmor_file_open+0x345/0x570
[   94.986431]  security_file_open+0x5c/0x140
[   94.986442]  do_dentry_open+0x2f6/0x1120
[   94.986450]  vfs_open+0x38/0x2b0
[   94.986453]  ? may_open+0x1e2/0x2b0
[   94.986466]  path_openat+0x231b/0x2b30
[   94.986469]  ? __x64_sys_openat+0xf8/0x130
[   94.986477]  do_file_open+0x19d/0x360
[   94.986487]  do_sys_openat2+0x98/0x100
[   94.986491]  __x64_sys_openat+0xf8/0x130
[   94.986499]  do_syscall_64+0x8e/0x660
[   94.986515]  ? count_memcg_events+0x15f/0x3c0
[   94.986526]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986540]  ? handle_mm_fault+0x1639/0x1ef0
[   94.986551]  ? vma_start_read+0xf0/0x320
[   94.986558]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986561]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986563]  ? fpregs_assert_state_consistent+0x50/0xe0
[   94.986572]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986574]  ? arch_exit_to_user_mode_prepare+0x9/0xb0
[   94.986587]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986588]  ? irqentry_exit+0x3c/0x590
[   94.986595]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   94.986597] RIP: 0033:0x7fda4a79c3ea

Fix by extracting the character value before invoking match_char,
ensuring single evaluation per outer loop.

Fixes: 074c1cd798cb ("apparmor: dfa move character match into a macro")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/match.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 8fa0a1494acd..30c46b119869 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -463,13 +463,18 @@ aa_state_t aa_dfa_match_len(struct aa_dfa *dfa, aa_state_t start,
 	if (dfa->tables[YYTD_ID_EC]) {
 		/* Equivalence class table defined */
 		u8 *equiv = EQUIV_TABLE(dfa);
-		for (; len; len--)
-			match_char(state, def, base, next, check,
-				   equiv[(u8) *str++]);
+		for (; len; len--) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
 	} else {
 		/* default is direct to next state */
-		for (; len; len--)
-			match_char(state, def, base, next, check, (u8) *str++);
+		for (; len; len--) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
 	}
 
 	return state;
@@ -503,13 +508,18 @@ aa_state_t aa_dfa_match(struct aa_dfa *dfa, aa_state_t start, const char *str)
 		/* Equivalence class table defined */
 		u8 *equiv = EQUIV_TABLE(dfa);
 		/* default is direct to next state */
-		while (*str)
-			match_char(state, def, base, next, check,
-				   equiv[(u8) *str++]);
+		while (*str) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
 	} else {
 		/* default is direct to next state */
-		while (*str)
-			match_char(state, def, base, next, check, (u8) *str++);
+		while (*str) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
 	}
 
 	return state;

From d352873bbefa7eb39995239d0b44ccdf8aaa79a4 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 29 Jan 2026 16:51:11 +0100
Subject: [PATCH 1091/1303] apparmor: fix missing bounds check on DEFAULT table
 in verify_dfa()

The verify_dfa() function only checks DEFAULT_TABLE bounds when the state
is not differentially encoded.

When the verification loop traverses the differential encoding chain,
it reads k = DEFAULT_TABLE[j] and uses k as an array index without
validation. A malformed DFA with DEFAULT_TABLE[j] >= state_count,
therefore, causes both out-of-bounds reads and writes.

[   57.179855] ==================================================================
[   57.180549] BUG: KASAN: slab-out-of-bounds in verify_dfa+0x59a/0x660
[   57.180904] Read of size 4 at addr ffff888100eadec4 by task su/993

[   57.181554] CPU: 1 UID: 0 PID: 993 Comm: su Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy)
[   57.181558] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   57.181563] Call Trace:
[   57.181572]  <TASK>
[   57.181577]  dump_stack_lvl+0x5e/0x80
[   57.181596]  print_report+0xc8/0x270
[   57.181605]  ? verify_dfa+0x59a/0x660
[   57.181608]  kasan_report+0x118/0x150
[   57.181620]  ? verify_dfa+0x59a/0x660
[   57.181623]  verify_dfa+0x59a/0x660
[   57.181627]  aa_dfa_unpack+0x1610/0x1740
[   57.181629]  ? __kmalloc_cache_noprof+0x1d0/0x470
[   57.181640]  unpack_pdb+0x86d/0x46b0
[   57.181647]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181653]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181656]  ? aa_unpack_nameX+0x1a8/0x300
[   57.181659]  aa_unpack+0x20b0/0x4c30
[   57.181662]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181664]  ? stack_depot_save_flags+0x33/0x700
[   57.181681]  ? kasan_save_track+0x4f/0x80
[   57.181683]  ? kasan_save_track+0x3e/0x80
[   57.181686]  ? __kasan_kmalloc+0x93/0xb0
[   57.181688]  ? __kvmalloc_node_noprof+0x44a/0x780
[   57.181693]  ? aa_simple_write_to_buffer+0x54/0x130
[   57.181697]  ? policy_update+0x154/0x330
[   57.181704]  aa_replace_profiles+0x15a/0x1dd0
[   57.181707]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181710]  ? __kvmalloc_node_noprof+0x44a/0x780
[   57.181712]  ? aa_loaddata_alloc+0x77/0x140
[   57.181715]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181717]  ? _copy_from_user+0x2a/0x70
[   57.181730]  policy_update+0x17a/0x330
[   57.181733]  profile_replace+0x153/0x1a0
[   57.181735]  ? rw_verify_area+0x93/0x2d0
[   57.181740]  vfs_write+0x235/0xab0
[   57.181745]  ksys_write+0xb0/0x170
[   57.181748]  do_syscall_64+0x8e/0x660
[   57.181762]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   57.181765] RIP: 0033:0x7f6192792eb2

Remove the MATCH_FLAG_DIFF_ENCODE condition to validate all DEFAULT_TABLE
entries unconditionally.

Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/match.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 30c46b119869..2aad2cbed565 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -160,9 +160,10 @@ static int verify_dfa(struct aa_dfa *dfa)
 	if (state_count == 0)
 		goto out;
 	for (i = 0; i < state_count; i++) {
-		if (!(BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE) &&
-		    (DEFAULT_TABLE(dfa)[i] >= state_count))
+		if (DEFAULT_TABLE(dfa)[i] >= state_count) {
+			pr_err("AppArmor DFA default state out of bounds");
 			goto out;
+		}
 		if (BASE_TABLE(dfa)[i] & MATCH_FLAGS_INVALID) {
 			pr_err("AppArmor DFA state with invalid match flags");
 			goto out;

From 5df0c44e8f5f619d3beb871207aded7c78414502 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Wed, 10 Sep 2025 06:22:17 -0700
Subject: [PATCH 1092/1303] apparmor: Fix double free of ns_name in
 aa_replace_profiles()

if ns_name is NULL after
1071         error = aa_unpack(udata, &lh, &ns_name);

and if ent->ns_name contains an ns_name in
1089                 } else if (ent->ns_name) {

then ns_name is assigned the ent->ns_name
1095                         ns_name = ent->ns_name;

however ent->ns_name is freed at
1262                 aa_load_ent_free(ent);

and then again when freeing ns_name at
1270         kfree(ns_name);

Fix this by NULLing out ent->ns_name after it is transferred to ns_name

Fixes: 145a0ef21c8e9 ("apparmor: fix blob compression when ns is forced on a policy load
")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 566821852592..4476515d97b1 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -1166,6 +1166,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 				goto fail;
 			}
 			ns_name = ent->ns_name;
+			ent->ns_name = NULL;
 		} else
 			count++;
 	}

From 6601e13e82841879406bf9f369032656f441a425 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Fri, 7 Nov 2025 08:36:04 -0800
Subject: [PATCH 1093/1303] apparmor: fix unprivileged local user can do
 privileged policy management

An unprivileged local user can load, replace, and remove profiles by
opening the apparmorfs interfaces, via a confused deputy attack, by
passing the opened fd to a privileged process, and getting the
privileged process to write to the interface.

This does require a privileged target that can be manipulated to do
the write for the unprivileged process, but once such access is
achieved full policy management is possible and all the possible
implications that implies: removing confinement, DoS of system or
target applications by denying all execution, by-passing the
unprivileged user namespace restriction, to exploiting kernel bugs for
a local privilege escalation.

The policy management interface can not have its permissions simply
changed from 0666 to 0600 because non-root processes need to be able
to load policy to different policy namespaces.

Instead ensure the task writing the interface has privileges that
are a subset of the task that opened the interface. This is already
done via policy for confined processes, but unconfined can delegate
access to the opened fd, by-passing the usual policy check.

Fixes: b7fd2c0340eac ("apparmor: add per policy ns .load, .replace, .remove interface files")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c     | 16 ++++++++------
 security/apparmor/include/policy.h |  2 +-
 security/apparmor/policy.c         | 34 +++++++++++++++++++++++++++++-
 3 files changed, 43 insertions(+), 9 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 2f84bd23edb6..81e57666a56e 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -417,7 +417,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 }
 
 static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
-			     loff_t *pos, struct aa_ns *ns)
+			     loff_t *pos, struct aa_ns *ns,
+			     const struct cred *ocred)
 {
 	struct aa_loaddata *data;
 	struct aa_label *label;
@@ -428,7 +429,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	/* high level check about policy management - fine grained in
 	 * below after unpack
 	 */
-	error = aa_may_manage_policy(current_cred(), label, ns, mask);
+	error = aa_may_manage_policy(current_cred(), label, ns, ocred, mask);
 	if (error)
 		goto end_section;
 
@@ -449,7 +450,8 @@ static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
 			    loff_t *pos)
 {
 	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
-	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns);
+	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns,
+				  f->f_cred);
 
 	aa_put_ns(ns);
 
@@ -467,7 +469,7 @@ static ssize_t profile_replace(struct file *f, const char __user *buf,
 {
 	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY,
-				  buf, size, pos, ns);
+				  buf, size, pos, ns, f->f_cred);
 	aa_put_ns(ns);
 
 	return error;
@@ -492,7 +494,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	 * below after unpack
 	 */
 	error = aa_may_manage_policy(current_cred(), label, ns,
-				     AA_MAY_REMOVE_POLICY);
+				     f->f_cred, AA_MAY_REMOVE_POLICY);
 	if (error)
 		goto out;
 
@@ -1830,7 +1832,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir,
 	int error;
 
 	label = begin_current_label_crit_section();
-	error = aa_may_manage_policy(current_cred(), label, NULL,
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
 				     AA_MAY_LOAD_POLICY);
 	end_current_label_crit_section(label);
 	if (error)
@@ -1880,7 +1882,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry)
 	int error;
 
 	label = begin_current_label_crit_section();
-	error = aa_may_manage_policy(current_cred(), label, NULL,
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
 				     AA_MAY_LOAD_POLICY);
 	end_current_label_crit_section(label);
 	if (error)
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index 5115ebae2661..fda9e75b8879 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -443,7 +443,7 @@ bool aa_policy_admin_capable(const struct cred *subj_cred,
 			     struct aa_label *label, struct aa_ns *ns);
 int aa_may_manage_policy(const struct cred *subj_cred,
 			 struct aa_label *label, struct aa_ns *ns,
-			 u32 mask);
+			 const struct cred *ocred, u32 mask);
 bool aa_current_policy_view_capable(struct aa_ns *ns);
 bool aa_current_policy_admin_capable(struct aa_ns *ns);
 
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 4476515d97b1..e2bebf14a4d0 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -942,17 +942,44 @@ bool aa_current_policy_admin_capable(struct aa_ns *ns)
 	return res;
 }
 
+static bool is_subset_of_obj_privilege(const struct cred *cred,
+				       struct aa_label *label,
+				       const struct cred *ocred)
+{
+	if (cred == ocred)
+		return true;
+
+	if (!aa_label_is_subset(label, cred_label(ocred)))
+		return false;
+	/* don't allow crossing userns for now */
+	if (cred->user_ns != ocred->user_ns)
+		return false;
+	if (!cap_issubset(cred->cap_inheritable, ocred->cap_inheritable))
+		return false;
+	if (!cap_issubset(cred->cap_permitted, ocred->cap_permitted))
+		return false;
+	if (!cap_issubset(cred->cap_effective, ocred->cap_effective))
+		return false;
+	if (!cap_issubset(cred->cap_bset, ocred->cap_bset))
+		return false;
+	if (!cap_issubset(cred->cap_ambient, ocred->cap_ambient))
+		return false;
+	return true;
+}
+
+
 /**
  * aa_may_manage_policy - can the current task manage policy
  * @subj_cred: subjects cred
  * @label: label to check if it can manage policy
  * @ns: namespace being managed by @label (may be NULL if @label's ns)
+ * @ocred: object cred if request is coming from an open object
  * @mask: contains the policy manipulation operation being done
  *
  * Returns: 0 if the task is allowed to manipulate policy else error
  */
 int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label,
-			 struct aa_ns *ns, u32 mask)
+			 struct aa_ns *ns, const struct cred *ocred, u32 mask)
 {
 	const char *op;
 
@@ -968,6 +995,11 @@ int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label,
 		return audit_policy(label, op, NULL, NULL, "policy_locked",
 				    -EACCES);
 
+	if (ocred && !is_subset_of_obj_privilege(subj_cred, label, ocred))
+		return audit_policy(label, op, NULL, NULL,
+				    "not privileged for target profile",
+				    -EACCES);
+
 	if (!aa_policy_admin_capable(subj_cred, label, ns))
 		return audit_policy(label, op, NULL, NULL, "not policy admin",
 				    -EACCES);

From 39440b137546a3aa383cfdabc605fb73811b6093 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Fri, 17 Oct 2025 01:53:00 -0700
Subject: [PATCH 1094/1303] apparmor: fix differential encoding verification

Differential encoding allows loops to be created if it is abused. To
prevent this the unpack should verify that a diff-encode chain
terminates.

Unfortunately the differential encode verification had two bugs.

1. it conflated states that had gone through check and already been
   marked, with states that were currently being checked and marked.
   This means that loops in the current chain being verified are treated
   as a chain that has already been verified.

2. the order bailout on already checked states compared current chain
   check iterators j,k instead of using the outer loop iterator i.
   Meaning a step backwards in states in the current chain verification
   was being mistaken for moving to an already verified state.

Move to a double mark scheme where already verified states get a
different mark, than the current chain being kept. This enables us
to also drop the backwards verification check that was the cause of
the second error as any already verified state is already marked.

Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/include/match.h |  1 +
 security/apparmor/match.c         | 23 +++++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h
index 0dde8eda3d1a..7accb1c39849 100644
--- a/security/apparmor/include/match.h
+++ b/security/apparmor/include/match.h
@@ -185,6 +185,7 @@ static inline void aa_put_dfa(struct aa_dfa *dfa)
 #define MATCH_FLAG_DIFF_ENCODE 0x80000000
 #define MARK_DIFF_ENCODE 0x40000000
 #define MATCH_FLAG_OOB_TRANSITION 0x20000000
+#define MARK_DIFF_ENCODE_VERIFIED 0x10000000
 #define MATCH_FLAGS_MASK 0xff000000
 #define MATCH_FLAGS_VALID (MATCH_FLAG_DIFF_ENCODE | MATCH_FLAG_OOB_TRANSITION)
 #define MATCH_FLAGS_INVALID (MATCH_FLAGS_MASK & ~MATCH_FLAGS_VALID)
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 2aad2cbed565..e9fac67e5178 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -202,16 +202,31 @@ static int verify_dfa(struct aa_dfa *dfa)
 		size_t j, k;
 
 		for (j = i;
-		     (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) &&
-		     !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE);
+		     ((BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) &&
+		      !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE_VERIFIED));
 		     j = k) {
+			if (BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE)
+				/* loop in current chain */
+				goto out;
 			k = DEFAULT_TABLE(dfa)[j];
 			if (j == k)
+				/* self loop */
 				goto out;
-			if (k < j)
-				break;		/* already verified */
 			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE;
 		}
+		/* move mark to verified */
+		for (j = i;
+		     (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE);
+		     j = k) {
+			k = DEFAULT_TABLE(dfa)[j];
+			if (j < i)
+				/* jumps to state/chain that has been
+				 * verified
+				 */
+				break;
+			BASE_TABLE(dfa)[j] &= ~MARK_DIFF_ENCODE;
+			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE_VERIFIED;
+		}
 	}
 	error = 0;
 

From a0b7091c4de45a7325c8780e6934a894f92ac86b Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 24 Feb 2026 10:20:02 -0800
Subject: [PATCH 1095/1303] apparmor: fix race on rawdata dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a race condition that leads to a use-after-free situation:
because the rawdata inodes are not refcounted, an attacker can start
open()ing one of the rawdata files, and at the same time remove the
last reference to this rawdata (by removing the corresponding profile,
for example), which frees its struct aa_loaddata; as a result, when
seq_rawdata_open() is reached, i_private is a dangling pointer and
freed memory is accessed.

The rawdata inodes weren't refcounted to avoid a circular refcount and
were supposed to be held by the profile rawdata reference.  However
during profile removal there is a window where the vfs and profile
destruction race, resulting in the use after free.

Fix this by moving to a double refcount scheme. Where the profile
refcount on rawdata is used to break the circular dependency. Allowing
for freeing of the rawdata once all inode references to the rawdata
are put.

Fixes: 5d5182cae401 ("apparmor: move to per loaddata files, instead of replicating in profiles")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Maxime Bélair <maxime.belair@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c            | 35 ++++++----
 security/apparmor/include/policy_unpack.h | 79 ++++++++++++++---------
 security/apparmor/policy.c                | 12 ++--
 security/apparmor/policy_unpack.c         | 46 ++++++++-----
 4 files changed, 104 insertions(+), 68 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 81e57666a56e..7a6ca7c5500d 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -79,7 +79,7 @@ static void rawdata_f_data_free(struct rawdata_f_data *private)
 	if (!private)
 		return;
 
-	aa_put_loaddata(private->loaddata);
+	aa_put_i_loaddata(private->loaddata);
 	kvfree(private);
 }
 
@@ -409,7 +409,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 
 	data->size = copy_size;
 	if (copy_from_user(data->data, userbuf, copy_size)) {
-		aa_put_loaddata(data);
+		/* trigger free - don't need to put pcount */
+		aa_put_i_loaddata(data);
 		return ERR_PTR(-EFAULT);
 	}
 
@@ -437,7 +438,10 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	error = PTR_ERR(data);
 	if (!IS_ERR(data)) {
 		error = aa_replace_profiles(ns, label, mask, data);
-		aa_put_loaddata(data);
+		/* put pcount, which will put count and free if no
+		 * profiles referencing it.
+		 */
+		aa_put_profile_loaddata(data);
 	}
 end_section:
 	end_current_label_crit_section(label);
@@ -508,7 +512,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	if (!IS_ERR(data)) {
 		data->data[size] = 0;
 		error = aa_remove_profiles(ns, label, data->data, size);
-		aa_put_loaddata(data);
+		aa_put_profile_loaddata(data);
 	}
  out:
 	end_current_label_crit_section(label);
@@ -1255,18 +1259,17 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = {	      \
 static int seq_rawdata_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_loaddata *data = __aa_get_loaddata(inode->i_private);
+	struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private);
 	int error;
 
 	if (!data)
-		/* lost race this ent is being reaped */
 		return -ENOENT;
 
 	error = single_open(file, show, data);
 	if (error) {
 		AA_BUG(file->private_data &&
 		       ((struct seq_file *)file->private_data)->private);
-		aa_put_loaddata(data);
+		aa_put_i_loaddata(data);
 	}
 
 	return error;
@@ -1277,7 +1280,7 @@ static int seq_rawdata_release(struct inode *inode, struct file *file)
 	struct seq_file *seq = (struct seq_file *) file->private_data;
 
 	if (seq)
-		aa_put_loaddata(seq->private);
+		aa_put_i_loaddata(seq->private);
 
 	return single_release(inode, file);
 }
@@ -1389,9 +1392,8 @@ static int rawdata_open(struct inode *inode, struct file *file)
 	if (!aa_current_policy_view_capable(NULL))
 		return -EACCES;
 
-	loaddata = __aa_get_loaddata(inode->i_private);
+	loaddata = aa_get_i_loaddata(inode->i_private);
 	if (!loaddata)
-		/* lost race: this entry is being reaped */
 		return -ENOENT;
 
 	private = rawdata_f_data_alloc(loaddata->size);
@@ -1416,7 +1418,7 @@ static int rawdata_open(struct inode *inode, struct file *file)
 	return error;
 
 fail_private_alloc:
-	aa_put_loaddata(loaddata);
+	aa_put_i_loaddata(loaddata);
 	return error;
 }
 
@@ -1433,9 +1435,9 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata)
 
 	for (i = 0; i < AAFS_LOADDATA_NDENTS; i++) {
 		if (!IS_ERR_OR_NULL(rawdata->dents[i])) {
-			/* no refcounts on i_private */
 			aafs_remove(rawdata->dents[i]);
 			rawdata->dents[i] = NULL;
+			aa_put_i_loaddata(rawdata);
 		}
 	}
 }
@@ -1474,18 +1476,21 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	if (IS_ERR(dir))
 		/* ->name freed when rawdata freed */
 		return PTR_ERR(dir);
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DIR] = dir;
 
 	dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata,
 				      &seq_rawdata_abi_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_ABI] = dent;
 
 	dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata,
 				      &seq_rawdata_revision_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
@@ -1493,6 +1498,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 					      rawdata, &seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
+		aa_get_i_loaddata(rawdata);
 		rawdata->dents[AAFS_LOADDATA_HASH] = dent;
 	}
 
@@ -1501,24 +1507,25 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 				&seq_rawdata_compressed_size_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent;
 
 	dent = aafs_create_file("raw_data", S_IFREG | 0444,
 				      dir, rawdata, &rawdata_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DATA] = dent;
 	d_inode(dent)->i_size = rawdata->size;
 
 	rawdata->ns = aa_get_ns(ns);
 	list_add(&rawdata->list, &ns->rawdata_list);
-	/* no refcount on inode rawdata */
 
 	return 0;
 
 fail:
 	remove_rawdata_dents(rawdata);
-
+	aa_put_i_loaddata(rawdata);
 	return PTR_ERR(dent);
 }
 #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
index a6f4611ee50c..4f800fbb805a 100644
--- a/security/apparmor/include/policy_unpack.h
+++ b/security/apparmor/include/policy_unpack.h
@@ -87,17 +87,29 @@ struct aa_ext {
 	u32 version;
 };
 
-/*
- * struct aa_loaddata - buffer of policy raw_data set
+/* struct aa_loaddata - buffer of policy raw_data set
+ * @count: inode/filesystem refcount - use aa_get_i_loaddata()
+ * @pcount: profile refcount - use aa_get_profile_loaddata()
+ * @list: list the loaddata is on
+ * @work: used to do a delayed cleanup
+ * @dents: refs to dents created in aafs
+ * @ns: the namespace this loaddata was loaded into
+ * @name:
+ * @size: the size of the data that was loaded
+ * @compressed_size: the size of the data when it is compressed
+ * @revision: unique revision count that this data was loaded as
+ * @abi: the abi number the loaddata uses
+ * @hash: a hash of the loaddata, used to help dedup data
  *
- * there is no loaddata ref for being on ns list, nor a ref from
- * d_inode(@dentry) when grab a ref from these, @ns->lock must be held
- * && __aa_get_loaddata() needs to be used, and the return value
- * checked, if NULL the loaddata is already being reaped and should be
- * considered dead.
+ * There is no loaddata ref for being on ns->rawdata_list, so
+ * @ns->lock must be held when walking the list. Dentries and
+ * inode opens hold refs on @count; profiles hold refs on @pcount.
+ * When the last @pcount drops, do_ploaddata_rmfs() removes the
+ * fs entries and drops the associated @count ref.
  */
 struct aa_loaddata {
 	struct kref count;
+	struct kref pcount;
 	struct list_head list;
 	struct work_struct work;
 	struct dentry *dents[AAFS_LOADDATA_NDENTS];
@@ -118,53 +130,56 @@ struct aa_loaddata {
 
 int aa_unpack(struct aa_loaddata *udata, struct list_head *lh, const char **ns);
 
-/**
- * __aa_get_loaddata - get a reference count to uncounted data reference
- * @data: reference to get a count on
- *
- * Returns: pointer to reference OR NULL if race is lost and reference is
- *          being repeated.
- * Requires: @data->ns->lock held, and the return code MUST be checked
- *
- * Use only from inode->i_private and @data->list found references
- */
-static inline struct aa_loaddata *
-__aa_get_loaddata(struct aa_loaddata *data)
-{
-	if (data && kref_get_unless_zero(&(data->count)))
-		return data;
-
-	return NULL;
-}
-
 /**
  * aa_get_loaddata - get a reference count from a counted data reference
  * @data: reference to get a count on
  *
- * Returns: point to reference
+ * Returns: pointer to reference
  * Requires: @data to have a valid reference count on it. It is a bug
  *           if the race to reap can be encountered when it is used.
  */
 static inline struct aa_loaddata *
-aa_get_loaddata(struct aa_loaddata *data)
+aa_get_i_loaddata(struct aa_loaddata *data)
 {
-	struct aa_loaddata *tmp = __aa_get_loaddata(data);
 
-	AA_BUG(data && !tmp);
+	if (data)
+		kref_get(&(data->count));
+	return data;
+}
 
-	return tmp;
+
+/**
+ * aa_get_profile_loaddata - get a profile reference count on loaddata
+ * @data: reference to get a count on
+ *
+ * Returns: pointer to reference
+ * Requires: @data to have a valid reference count on it.
+ */
+static inline struct aa_loaddata *
+aa_get_profile_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_get(&(data->pcount));
+	return data;
 }
 
 void __aa_loaddata_update(struct aa_loaddata *data, long revision);
 bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r);
 void aa_loaddata_kref(struct kref *kref);
+void aa_ploaddata_kref(struct kref *kref);
 struct aa_loaddata *aa_loaddata_alloc(size_t size);
-static inline void aa_put_loaddata(struct aa_loaddata *data)
+static inline void aa_put_i_loaddata(struct aa_loaddata *data)
 {
 	if (data)
 		kref_put(&data->count, aa_loaddata_kref);
 }
 
+static inline void aa_put_profile_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_put(&data->pcount, aa_ploaddata_kref);
+}
+
 #if IS_ENABLED(CONFIG_KUNIT)
 bool aa_inbounds(struct aa_ext *e, size_t size);
 size_t aa_unpack_u16_chunk(struct aa_ext *e, char **chunk);
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index e2bebf14a4d0..b6a5eb4021db 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -350,7 +350,7 @@ void aa_free_profile(struct aa_profile *profile)
 	}
 
 	kfree_sensitive(profile->hash);
-	aa_put_loaddata(profile->rawdata);
+	aa_put_profile_loaddata(profile->rawdata);
 	aa_label_destroy(&profile->label);
 
 	kfree_sensitive(profile);
@@ -1171,7 +1171,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 	LIST_HEAD(lh);
 
 	op = mask & AA_MAY_REPLACE_POLICY ? OP_PROF_REPL : OP_PROF_LOAD;
-	aa_get_loaddata(udata);
+	aa_get_profile_loaddata(udata);
 	/* released below */
 	error = aa_unpack(udata, &lh, &ns_name);
 	if (error)
@@ -1223,10 +1223,10 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 			if (aa_rawdata_eq(rawdata_ent, udata)) {
 				struct aa_loaddata *tmp;
 
-				tmp = __aa_get_loaddata(rawdata_ent);
+				tmp = aa_get_profile_loaddata(rawdata_ent);
 				/* check we didn't fail the race */
 				if (tmp) {
-					aa_put_loaddata(udata);
+					aa_put_profile_loaddata(udata);
 					udata = tmp;
 					break;
 				}
@@ -1239,7 +1239,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 		struct aa_profile *p;
 
 		if (aa_g_export_binary)
-			ent->new->rawdata = aa_get_loaddata(udata);
+			ent->new->rawdata = aa_get_profile_loaddata(udata);
 		error = __lookup_replace(ns, ent->new->base.hname,
 					 !(mask & AA_MAY_REPLACE_POLICY),
 					 &ent->old, &info);
@@ -1372,7 +1372,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 
 out:
 	aa_put_ns(ns);
-	aa_put_loaddata(udata);
+	aa_put_profile_loaddata(udata);
 	kfree(ns_name);
 
 	if (error)
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 5d90ea55de82..69a040194e36 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -109,22 +109,8 @@ bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r)
 	return memcmp(l->data, r->data, r->compressed_size ?: r->size) == 0;
 }
 
-/*
- * need to take the ns mutex lock which is NOT safe most places that
- * put_loaddata is called, so we have to delay freeing it
- */
-static void do_loaddata_free(struct work_struct *work)
+static void do_loaddata_free(struct aa_loaddata *d)
 {
-	struct aa_loaddata *d = container_of(work, struct aa_loaddata, work);
-	struct aa_ns *ns = aa_get_ns(d->ns);
-
-	if (ns) {
-		mutex_lock_nested(&ns->lock, ns->level);
-		__aa_fs_remove_rawdata(d);
-		mutex_unlock(&ns->lock);
-		aa_put_ns(ns);
-	}
-
 	kfree_sensitive(d->hash);
 	kfree_sensitive(d->name);
 	kvfree(d->data);
@@ -135,8 +121,35 @@ void aa_loaddata_kref(struct kref *kref)
 {
 	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count);
 
+	do_loaddata_free(d);
+}
+
+/*
+ * need to take the ns mutex lock which is NOT safe most places that
+ * put_loaddata is called, so we have to delay freeing it
+ */
+static void do_ploaddata_rmfs(struct work_struct *work)
+{
+	struct aa_loaddata *d = container_of(work, struct aa_loaddata, work);
+	struct aa_ns *ns = aa_get_ns(d->ns);
+
+	if (ns) {
+		mutex_lock_nested(&ns->lock, ns->level);
+		/* remove fs ref to loaddata */
+		__aa_fs_remove_rawdata(d);
+		mutex_unlock(&ns->lock);
+		aa_put_ns(ns);
+	}
+	/* called by dropping last pcount, so drop its associated icount */
+	aa_put_i_loaddata(d);
+}
+
+void aa_ploaddata_kref(struct kref *kref)
+{
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, pcount);
+
 	if (d) {
-		INIT_WORK(&d->work, do_loaddata_free);
+		INIT_WORK(&d->work, do_ploaddata_rmfs);
 		schedule_work(&d->work);
 	}
 }
@@ -154,6 +167,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size)
 		return ERR_PTR(-ENOMEM);
 	}
 	kref_init(&d->count);
+	kref_init(&d->pcount);
 	INIT_LIST_HEAD(&d->list);
 
 	return d;

From 8e135b8aee5a06c52a4347a5a6d51223c6f36ba3 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Sun, 1 Mar 2026 16:10:51 -0800
Subject: [PATCH 1096/1303] apparmor: fix race between freeing data and fs
 accessing it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AppArmor was putting the reference to i_private data on its end after
removing the original entry from the file system. However the inode
can aand does live beyond that point and it is possible that some of
the fs call back functions will be invoked after the reference has
been put, which results in a race between freeing the data and
accessing it through the fs.

While the rawdata/loaddata is the most likely candidate to fail the
race, as it has the fewest references. If properly crafted it might be
possible to trigger a race for the other types stored in i_private.

Fix this by moving the put of i_private referenced data to the correct
place which is during inode eviction.

Fixes: c961ee5f21b20 ("apparmor: convert from securityfs to apparmorfs for policy ns files")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Maxime Bélair <maxime.belair@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c            | 194 +++++++++++++---------
 security/apparmor/include/label.h         |  16 +-
 security/apparmor/include/lib.h           |  12 ++
 security/apparmor/include/policy.h        |   8 +-
 security/apparmor/include/policy_unpack.h |   6 +-
 security/apparmor/label.c                 |  12 +-
 security/apparmor/policy_unpack.c         |   6 +-
 7 files changed, 153 insertions(+), 101 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 7a6ca7c5500d..242c71b3fb6e 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -32,6 +32,7 @@
 #include "include/crypto.h"
 #include "include/ipc.h"
 #include "include/label.h"
+#include "include/lib.h"
 #include "include/policy.h"
 #include "include/policy_ns.h"
 #include "include/resource.h"
@@ -62,6 +63,7 @@
  * securityfs and apparmorfs filesystems.
  */
 
+#define IREF_POISON 101
 
 /*
  * support fns
@@ -153,6 +155,71 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
 	return 0;
 }
 
+static struct aa_ns *get_ns_common_ref(struct aa_common_ref *ref)
+{
+	if (ref) {
+		struct aa_label *reflabel = container_of(ref, struct aa_label,
+							 count);
+		return aa_get_ns(labels_ns(reflabel));
+	}
+
+	return NULL;
+}
+
+static struct aa_proxy *get_proxy_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_proxy(container_of(ref, struct aa_proxy, count));
+
+	return NULL;
+}
+
+static struct aa_loaddata *get_loaddata_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_i_loaddata(container_of(ref, struct aa_loaddata,
+						      count));
+	return NULL;
+}
+
+static void aa_put_common_ref(struct aa_common_ref *ref)
+{
+	if (!ref)
+		return;
+
+	switch (ref->reftype) {
+	case REF_RAWDATA:
+		aa_put_i_loaddata(container_of(ref, struct aa_loaddata,
+					       count));
+		break;
+	case REF_PROXY:
+		aa_put_proxy(container_of(ref, struct aa_proxy,
+					  count));
+		break;
+	case REF_NS:
+		/* ns count is held on its unconfined label */
+		aa_put_ns(labels_ns(container_of(ref, struct aa_label, count)));
+		break;
+	default:
+		AA_BUG(true, "unknown refcount type");
+		break;
+	}
+}
+
+static void aa_get_common_ref(struct aa_common_ref *ref)
+{
+	kref_get(&ref->count);
+}
+
+static void aafs_evict(struct inode *inode)
+{
+	struct aa_common_ref *ref = inode->i_private;
+
+	clear_inode(inode);
+	aa_put_common_ref(ref);
+	inode->i_private = (void *) IREF_POISON;
+}
+
 static void aafs_free_inode(struct inode *inode)
 {
 	if (S_ISLNK(inode->i_mode))
@@ -162,6 +229,7 @@ static void aafs_free_inode(struct inode *inode)
 
 static const struct super_operations aafs_super_ops = {
 	.statfs = simple_statfs,
+	.evict_inode = aafs_evict,
 	.free_inode = aafs_free_inode,
 	.show_path = aafs_show_path,
 };
@@ -262,7 +330,8 @@ static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry,
  * aafs_remove(). Will return ERR_PTR on failure.
  */
 static struct dentry *aafs_create(const char *name, umode_t mode,
-				  struct dentry *parent, void *data, void *link,
+				  struct dentry *parent,
+				  struct aa_common_ref *data, void *link,
 				  const struct file_operations *fops,
 				  const struct inode_operations *iops)
 {
@@ -299,6 +368,9 @@ static struct dentry *aafs_create(const char *name, umode_t mode,
 		goto fail_dentry;
 	inode_unlock(dir);
 
+	if (data)
+		aa_get_common_ref(data);
+
 	return dentry;
 
 fail_dentry:
@@ -323,7 +395,8 @@ static struct dentry *aafs_create(const char *name, umode_t mode,
  * see aafs_create
  */
 static struct dentry *aafs_create_file(const char *name, umode_t mode,
-				       struct dentry *parent, void *data,
+				       struct dentry *parent,
+				       struct aa_common_ref *data,
 				       const struct file_operations *fops)
 {
 	return aafs_create(name, mode, parent, data, NULL, fops, NULL);
@@ -453,7 +526,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
 			    loff_t *pos)
 {
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns,
 				  f->f_cred);
 
@@ -471,7 +544,7 @@ static const struct file_operations aa_fs_profile_load = {
 static ssize_t profile_replace(struct file *f, const char __user *buf,
 			       size_t size, loff_t *pos)
 {
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY,
 				  buf, size, pos, ns, f->f_cred);
 	aa_put_ns(ns);
@@ -491,7 +564,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	struct aa_loaddata *data;
 	struct aa_label *label;
 	ssize_t error;
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 
 	label = begin_current_label_crit_section();
 	/* high level check about policy management - fine grained in
@@ -581,7 +654,7 @@ static int ns_revision_open(struct inode *inode, struct file *file)
 	if (!rev)
 		return -ENOMEM;
 
-	rev->ns = aa_get_ns(inode->i_private);
+	rev->ns = get_ns_common_ref(inode->i_private);
 	if (!rev->ns)
 		rev->ns = aa_get_current_ns();
 	file->private_data = rev;
@@ -1067,7 +1140,7 @@ static const struct file_operations seq_profile_ ##NAME ##_fops = {	      \
 static int seq_profile_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_proxy *proxy = aa_get_proxy(inode->i_private);
+	struct aa_proxy *proxy = get_proxy_common_ref(inode->i_private);
 	int error = single_open(file, show, proxy);
 
 	if (error) {
@@ -1259,7 +1332,7 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = {	      \
 static int seq_rawdata_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private);
+	struct aa_loaddata *data = get_loaddata_common_ref(inode->i_private);
 	int error;
 
 	if (!data)
@@ -1392,7 +1465,7 @@ static int rawdata_open(struct inode *inode, struct file *file)
 	if (!aa_current_policy_view_capable(NULL))
 		return -EACCES;
 
-	loaddata = aa_get_i_loaddata(inode->i_private);
+	loaddata = get_loaddata_common_ref(inode->i_private);
 	if (!loaddata)
 		return -ENOENT;
 
@@ -1437,7 +1510,6 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata)
 		if (!IS_ERR_OR_NULL(rawdata->dents[i])) {
 			aafs_remove(rawdata->dents[i]);
 			rawdata->dents[i] = NULL;
-			aa_put_i_loaddata(rawdata);
 		}
 	}
 }
@@ -1476,45 +1548,41 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	if (IS_ERR(dir))
 		/* ->name freed when rawdata freed */
 		return PTR_ERR(dir);
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DIR] = dir;
 
-	dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata,
+	dent = aafs_create_file("abi", S_IFREG | 0444, dir, &rawdata->count,
 				      &seq_rawdata_abi_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_ABI] = dent;
 
-	dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata,
-				      &seq_rawdata_revision_fops);
+	dent = aafs_create_file("revision", S_IFREG | 0444, dir,
+				&rawdata->count,
+				&seq_rawdata_revision_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
 		dent = aafs_create_file("sha256", S_IFREG | 0444, dir,
-					      rawdata, &seq_rawdata_hash_fops);
+					&rawdata->count,
+					&seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_i_loaddata(rawdata);
 		rawdata->dents[AAFS_LOADDATA_HASH] = dent;
 	}
 
 	dent = aafs_create_file("compressed_size", S_IFREG | 0444, dir,
-				rawdata,
+				&rawdata->count,
 				&seq_rawdata_compressed_size_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent;
 
-	dent = aafs_create_file("raw_data", S_IFREG | 0444,
-				      dir, rawdata, &rawdata_fops);
+	dent = aafs_create_file("raw_data", S_IFREG | 0444, dir,
+				&rawdata->count, &rawdata_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DATA] = dent;
 	d_inode(dent)->i_size = rawdata->size;
 
@@ -1525,7 +1593,6 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 
 fail:
 	remove_rawdata_dents(rawdata);
-	aa_put_i_loaddata(rawdata);
 	return PTR_ERR(dent);
 }
 #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
@@ -1549,13 +1616,10 @@ void __aafs_profile_rmdir(struct aa_profile *profile)
 		__aafs_profile_rmdir(child);
 
 	for (i = AAFS_PROF_SIZEOF - 1; i >= 0; --i) {
-		struct aa_proxy *proxy;
 		if (!profile->dents[i])
 			continue;
 
-		proxy = d_inode(profile->dents[i])->i_private;
 		aafs_remove(profile->dents[i]);
-		aa_put_proxy(proxy);
 		profile->dents[i] = NULL;
 	}
 }
@@ -1589,14 +1653,7 @@ static struct dentry *create_profile_file(struct dentry *dir, const char *name,
 					  struct aa_profile *profile,
 					  const struct file_operations *fops)
 {
-	struct aa_proxy *proxy = aa_get_proxy(profile->label.proxy);
-	struct dentry *dent;
-
-	dent = aafs_create_file(name, S_IFREG | 0444, dir, proxy, fops);
-	if (IS_ERR(dent))
-		aa_put_proxy(proxy);
-
-	return dent;
+	return aafs_create_file(name, S_IFREG | 0444, dir, &profile->label.proxy->count, fops);
 }
 
 #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
@@ -1646,7 +1703,8 @@ static const char *rawdata_get_link_base(struct dentry *dentry,
 					 struct delayed_call *done,
 					 const char *name)
 {
-	struct aa_proxy *proxy = inode->i_private;
+	struct aa_common_ref *ref = inode->i_private;
+	struct aa_proxy *proxy = container_of(ref, struct aa_proxy, count);
 	struct aa_label *label;
 	struct aa_profile *profile;
 	char *target;
@@ -1788,27 +1846,24 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 	if (profile->rawdata) {
 		if (aa_g_hash_policy) {
 			dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir,
-					   profile->label.proxy, NULL, NULL,
-					   &rawdata_link_sha256_iops);
+					   &profile->label.proxy->count, NULL,
+					   NULL, &rawdata_link_sha256_iops);
 			if (IS_ERR(dent))
 				goto fail;
-			aa_get_proxy(profile->label.proxy);
 			profile->dents[AAFS_PROF_RAW_HASH] = dent;
 		}
 		dent = aafs_create("raw_abi", S_IFLNK | 0444, dir,
-				   profile->label.proxy, NULL, NULL,
+				   &profile->label.proxy->count, NULL, NULL,
 				   &rawdata_link_abi_iops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_proxy(profile->label.proxy);
 		profile->dents[AAFS_PROF_RAW_ABI] = dent;
 
 		dent = aafs_create("raw_data", S_IFLNK | 0444, dir,
-				   profile->label.proxy, NULL, NULL,
+				   &profile->label.proxy->count, NULL, NULL,
 				   &rawdata_link_data_iops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_proxy(profile->label.proxy);
 		profile->dents[AAFS_PROF_RAW_DATA] = dent;
 	}
 #endif /*CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
@@ -1845,7 +1900,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return ERR_PTR(error);
 
-	parent = aa_get_ns(dir->i_private);
+	parent = get_ns_common_ref(dir->i_private);
 	AA_BUG(d_inode(ns_subns_dir(parent)) != dir);
 
 	/* we have to unlock and then relock to get locking order right
@@ -1895,7 +1950,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry)
 	if (error)
 		return error;
 
-	parent = aa_get_ns(dir->i_private);
+	parent = get_ns_common_ref(dir->i_private);
 	/* rmdir calls the generic securityfs functions to remove files
 	 * from the apparmor dir. It is up to the apparmor ns locking
 	 * to avoid races.
@@ -1965,27 +2020,6 @@ void __aafs_ns_rmdir(struct aa_ns *ns)
 
 	__aa_fs_list_remove_rawdata(ns);
 
-	if (ns_subns_dir(ns)) {
-		sub = d_inode(ns_subns_dir(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subload(ns)) {
-		sub = d_inode(ns_subload(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subreplace(ns)) {
-		sub = d_inode(ns_subreplace(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subremove(ns)) {
-		sub = d_inode(ns_subremove(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subrevision(ns)) {
-		sub = d_inode(ns_subrevision(ns))->i_private;
-		aa_put_ns(sub);
-	}
-
 	for (i = AAFS_NS_SIZEOF - 1; i >= 0; --i) {
 		aafs_remove(ns->dents[i]);
 		ns->dents[i] = NULL;
@@ -2010,40 +2044,40 @@ static int __aafs_ns_mkdir_entries(struct aa_ns *ns, struct dentry *dir)
 		return PTR_ERR(dent);
 	ns_subdata_dir(ns) = dent;
 
-	dent = aafs_create_file("revision", 0444, dir, ns,
+	dent = aafs_create_file("revision", 0444, dir,
+				&ns->unconfined->label.count,
 				&aa_fs_ns_revision_fops);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subrevision(ns) = dent;
 
-	dent = aafs_create_file(".load", 0640, dir, ns,
-				      &aa_fs_profile_load);
+	dent = aafs_create_file(".load", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_load);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subload(ns) = dent;
 
-	dent = aafs_create_file(".replace", 0640, dir, ns,
-				      &aa_fs_profile_replace);
+	dent = aafs_create_file(".replace", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_replace);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subreplace(ns) = dent;
 
-	dent = aafs_create_file(".remove", 0640, dir, ns,
-				      &aa_fs_profile_remove);
+	dent = aafs_create_file(".remove", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_remove);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subremove(ns) = dent;
 
 	  /* use create_dentry so we can supply private data */
-	dent = aafs_create("namespaces", S_IFDIR | 0755, dir, ns, NULL, NULL,
-			   &ns_dir_inode_operations);
+	dent = aafs_create("namespaces", S_IFDIR | 0755, dir,
+			   &ns->unconfined->label.count,
+			   NULL, NULL, &ns_dir_inode_operations);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subns_dir(ns) = dent;
 
 	return 0;
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
index c0812dbc1b5b..335f21930702 100644
--- a/security/apparmor/include/label.h
+++ b/security/apparmor/include/label.h
@@ -102,7 +102,7 @@ enum label_flags {
 
 struct aa_label;
 struct aa_proxy {
-	struct kref count;
+	struct aa_common_ref count;
 	struct aa_label __rcu *label;
 };
 
@@ -125,7 +125,7 @@ struct label_it {
  * vec: vector of profiles comprising the compound label
  */
 struct aa_label {
-	struct kref count;
+	struct aa_common_ref count;
 	struct rb_node node;
 	struct rcu_head rcu;
 	struct aa_proxy *proxy;
@@ -357,7 +357,7 @@ int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules,
  */
 static inline struct aa_label *__aa_get_label(struct aa_label *l)
 {
-	if (l && kref_get_unless_zero(&l->count))
+	if (l && kref_get_unless_zero(&l->count.count))
 		return l;
 
 	return NULL;
@@ -366,7 +366,7 @@ static inline struct aa_label *__aa_get_label(struct aa_label *l)
 static inline struct aa_label *aa_get_label(struct aa_label *l)
 {
 	if (l)
-		kref_get(&(l->count));
+		kref_get(&(l->count.count));
 
 	return l;
 }
@@ -386,7 +386,7 @@ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l)
 	rcu_read_lock();
 	do {
 		c = rcu_dereference(*l);
-	} while (c && !kref_get_unless_zero(&c->count));
+	} while (c && !kref_get_unless_zero(&c->count.count));
 	rcu_read_unlock();
 
 	return c;
@@ -426,7 +426,7 @@ static inline struct aa_label *aa_get_newest_label(struct aa_label *l)
 static inline void aa_put_label(struct aa_label *l)
 {
 	if (l)
-		kref_put(&l->count, aa_label_kref);
+		kref_put(&l->count.count, aa_label_kref);
 }
 
 /* wrapper fn to indicate semantics of the check */
@@ -443,7 +443,7 @@ void aa_proxy_kref(struct kref *kref);
 static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy)
 {
 	if (proxy)
-		kref_get(&(proxy->count));
+		kref_get(&(proxy->count.count));
 
 	return proxy;
 }
@@ -451,7 +451,7 @@ static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy)
 static inline void aa_put_proxy(struct aa_proxy *proxy)
 {
 	if (proxy)
-		kref_put(&proxy->count, aa_proxy_kref);
+		kref_put(&proxy->count.count, aa_proxy_kref);
 }
 
 void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new);
diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h
index 1c5d1f60f6a7..8c6ce8484552 100644
--- a/security/apparmor/include/lib.h
+++ b/security/apparmor/include/lib.h
@@ -102,6 +102,18 @@ void aa_info_message(const char *str);
 /* Security blob offsets */
 extern struct lsm_blob_sizes apparmor_blob_sizes;
 
+enum reftype {
+	REF_NS,
+	REF_PROXY,
+	REF_RAWDATA,
+};
+
+/* common reference count used by data the shows up in aafs */
+struct aa_common_ref {
+	struct kref count;
+	enum reftype reftype;
+};
+
 /**
  * aa_strneq - compare null terminated @str to a non null terminated substring
  * @str: a null terminated string
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index fda9e75b8879..3895f8774a3f 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -379,7 +379,7 @@ static inline bool profile_mediates_safe(struct aa_profile *profile,
 static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
 {
 	if (p)
-		kref_get(&(p->label.count));
+		kref_get(&(p->label.count.count));
 
 	return p;
 }
@@ -393,7 +393,7 @@ static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
  */
 static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p)
 {
-	if (p && kref_get_unless_zero(&p->label.count))
+	if (p && kref_get_unless_zero(&p->label.count.count))
 		return p;
 
 	return NULL;
@@ -413,7 +413,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
 	rcu_read_lock();
 	do {
 		c = rcu_dereference(*p);
-	} while (c && !kref_get_unless_zero(&c->label.count));
+	} while (c && !kref_get_unless_zero(&c->label.count.count));
 	rcu_read_unlock();
 
 	return c;
@@ -426,7 +426,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
 static inline void aa_put_profile(struct aa_profile *p)
 {
 	if (p)
-		kref_put(&p->label.count, aa_label_kref);
+		kref_put(&p->label.count.count, aa_label_kref);
 }
 
 static inline int AUDIT_MODE(struct aa_profile *profile)
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
index 4f800fbb805a..e5a95dc4da1f 100644
--- a/security/apparmor/include/policy_unpack.h
+++ b/security/apparmor/include/policy_unpack.h
@@ -108,7 +108,7 @@ struct aa_ext {
  * fs entries and drops the associated @count ref.
  */
 struct aa_loaddata {
-	struct kref count;
+	struct aa_common_ref count;
 	struct kref pcount;
 	struct list_head list;
 	struct work_struct work;
@@ -143,7 +143,7 @@ aa_get_i_loaddata(struct aa_loaddata *data)
 {
 
 	if (data)
-		kref_get(&(data->count));
+		kref_get(&(data->count.count));
 	return data;
 }
 
@@ -171,7 +171,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size);
 static inline void aa_put_i_loaddata(struct aa_loaddata *data)
 {
 	if (data)
-		kref_put(&data->count, aa_loaddata_kref);
+		kref_put(&data->count.count, aa_loaddata_kref);
 }
 
 static inline void aa_put_profile_loaddata(struct aa_loaddata *data)
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index e478283bc514..3a721fdf1833 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -52,7 +52,8 @@ static void free_proxy(struct aa_proxy *proxy)
 
 void aa_proxy_kref(struct kref *kref)
 {
-	struct aa_proxy *proxy = container_of(kref, struct aa_proxy, count);
+	struct aa_proxy *proxy = container_of(kref, struct aa_proxy,
+					      count.count);
 
 	free_proxy(proxy);
 }
@@ -63,7 +64,8 @@ struct aa_proxy *aa_alloc_proxy(struct aa_label *label, gfp_t gfp)
 
 	new = kzalloc_obj(struct aa_proxy, gfp);
 	if (new) {
-		kref_init(&new->count);
+		kref_init(&new->count.count);
+		new->count.reftype = REF_PROXY;
 		rcu_assign_pointer(new->label, aa_get_label(label));
 	}
 	return new;
@@ -375,7 +377,8 @@ static void label_free_rcu(struct rcu_head *head)
 
 void aa_label_kref(struct kref *kref)
 {
-	struct aa_label *label = container_of(kref, struct aa_label, count);
+	struct aa_label *label = container_of(kref, struct aa_label,
+					      count.count);
 	struct aa_ns *ns = labels_ns(label);
 
 	if (!ns) {
@@ -412,7 +415,8 @@ bool aa_label_init(struct aa_label *label, int size, gfp_t gfp)
 
 	label->size = size;			/* doesn't include null */
 	label->vec[size] = NULL;		/* null terminate */
-	kref_init(&label->count);
+	kref_init(&label->count.count);
+	label->count.reftype = REF_NS;		/* for aafs purposes */
 	RB_CLEAR_NODE(&label->node);
 
 	return true;
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 69a040194e36..076d3ff14da6 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -119,7 +119,8 @@ static void do_loaddata_free(struct aa_loaddata *d)
 
 void aa_loaddata_kref(struct kref *kref)
 {
-	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count);
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata,
+					     count.count);
 
 	do_loaddata_free(d);
 }
@@ -166,7 +167,8 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size)
 		kfree(d);
 		return ERR_PTR(-ENOMEM);
 	}
-	kref_init(&d->count);
+	kref_init(&d->count.count);
+	d->count.reftype = REF_RAWDATA;
 	kref_init(&d->pcount);
 	INIT_LIST_HEAD(&d->list);
 

From 4185b95f8a42d92d68c49289b4644546b51e252b Mon Sep 17 00:00:00 2001
From: Sen Wang <sen@ti.com>
Date: Sun, 8 Mar 2026 23:21:09 -0500
Subject: [PATCH 1097/1303] ASoC: simple-card-utils: fix graph_util_is_ports0()
 for DT overlays

graph_util_is_ports0() identifies DPCM front-end (ports@0) vs back-end
(ports@1) by calling of_get_child_by_name() to find the first "ports"
child and comparing pointers. This relies on child iteration order
matching DTS source order.

When the DPCM topology comes from a DT overlay, __of_attach_node()
inserts new children at the head of the sibling list, reversing the
order. of_get_child_by_name() then returns ports@1 instead of ports@0,
causing all front-end links to be classified as back-ends. The card
registers with no PCM devices.

Fix this by matching the unit address directly from the node name
instead of relying on sibling order.

Fixes: 92939252458f ("ASoC: simple-card-utils: add asoc_graph_is_ports0()")
Signed-off-by: Sen Wang <sen@ti.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/20260309042109.2576612-1-sen@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-card-utils.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index bdc02e85b089..9e5be0eaa77f 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1038,11 +1038,15 @@ int graph_util_is_ports0(struct device_node *np)
 	else
 		port = np;
 
-	struct device_node *ports  __free(device_node) = of_get_parent(port);
-	struct device_node *top    __free(device_node) = of_get_parent(ports);
-	struct device_node *ports0 __free(device_node) = of_get_child_by_name(top, "ports");
+	struct device_node *ports __free(device_node) = of_get_parent(port);
+	const char *at = strchr(kbasename(ports->full_name), '@');
 
-	return ports0 == ports;
+	/*
+	 * Since child iteration order may differ
+	 * between a base DT and DT overlays,
+	 * string match "ports" or "ports@0" in the node name instead.
+	 */
+	return !at || !strcmp(at, "@0");
 }
 EXPORT_SYMBOL_GPL(graph_util_is_ports0);
 

From 87d126852158467ab87d5cbc36ccfd3f15464a6c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= <noltari@gmail.com>
Date: Fri, 6 Mar 2026 13:29:55 +0100
Subject: [PATCH 1098/1303] net: sfp: improve Huawei MA5671a fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the current sfp_fixup_ignore_tx_fault() fixup we ignore the TX_FAULT
signal, but we also need to apply sfp_fixup_ignore_los() in order to be
able to communicate with the module even if the fiber isn't connected for
configuration purposes.
This is needed for all the MA5671a firmwares, excluding the FS modded
firmware.

Fixes: 2069624dac19 ("net: sfp: Add tx-fault workaround for Huawei MA5671A SFP ONT")
Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260306125139.213637-1-noltari@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index f4bf53da3d4f..5db841377199 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -367,6 +367,12 @@ static void sfp_fixup_ignore_tx_fault(struct sfp *sfp)
 	sfp->state_ignore_mask |= SFP_F_TX_FAULT;
 }
 
+static void sfp_fixup_ignore_tx_fault_and_los(struct sfp *sfp)
+{
+	sfp_fixup_ignore_tx_fault(sfp);
+	sfp_fixup_ignore_los(sfp);
+}
+
 static void sfp_fixup_ignore_hw(struct sfp *sfp, unsigned int mask)
 {
 	sfp->state_hw_mask &= ~mask;
@@ -530,7 +536,7 @@ static const struct sfp_quirk sfp_quirks[] = {
 	// Huawei MA5671A can operate at 2500base-X, but report 1.2GBd NRZ in
 	// their EEPROM
 	SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex,
-		  sfp_fixup_ignore_tx_fault),
+		  sfp_fixup_ignore_tx_fault_and_los),
 
 	// Lantech 8330-262D-E and 8330-265D can operate at 2500base-X, but
 	// incorrectly report 2500MBd NRZ in their EEPROM.

From 288598d80a068a0e9281de35bcb4ce495f189e2a Mon Sep 17 00:00:00 2001
From: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
Date: Thu, 5 Mar 2026 22:40:06 -0500
Subject: [PATCH 1099/1303] serial: caif: hold tty->link reference in
 ldisc_open and ser_release

A reproducer triggers a KASAN slab-use-after-free in pty_write_room()
when caif_serial's TX path calls tty_write_room(). The faulting access
is on tty->link->port.

Hold an extra kref on tty->link for the lifetime of the caif_serial line
discipline: get it in ldisc_open() and drop it in ser_release(), and
also drop it on the ldisc_open() error path.

With this change applied, the reproducer no longer triggers the UAF in
my testing.

Link: https://gist.github.com/shuangpengbai/c898debad6bdf170a84be7e6b3d8707f
Link: https://lore.kernel.org/netdev/20260301220525.1546355-1-shuangpeng.kernel@gmail.com
Fixes: e31d5a05948e ("caif: tty's are kref objects so take a reference")
Signed-off-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://patch.msgid.link/20260306034006.3395740-1-shuangpeng.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/caif/caif_serial.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index b90890030751..1873d8287bb9 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -297,6 +297,7 @@ static void ser_release(struct work_struct *work)
 			dev_close(ser->dev);
 			unregister_netdevice(ser->dev);
 			debugfs_deinit(ser);
+			tty_kref_put(tty->link);
 			tty_kref_put(tty);
 		}
 		rtnl_unlock();
@@ -331,6 +332,7 @@ static int ldisc_open(struct tty_struct *tty)
 
 	ser = netdev_priv(dev);
 	ser->tty = tty_kref_get(tty);
+	tty_kref_get(tty->link);
 	ser->dev = dev;
 	debugfs_init(ser, tty);
 	tty->receive_room = 4096;
@@ -339,6 +341,7 @@ static int ldisc_open(struct tty_struct *tty)
 	rtnl_lock();
 	result = register_netdevice(dev);
 	if (result) {
+		tty_kref_put(tty->link);
 		tty_kref_put(tty);
 		rtnl_unlock();
 		free_netdev(dev);

From b2662e7593e94ae09b1cf7ee5f09160a3612bcb2 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Fri, 6 Mar 2026 18:38:20 -0500
Subject: [PATCH 1100/1303] net: nexthop: fix percpu use-after-free in
 remove_nh_grp_entry

When removing a nexthop from a group, remove_nh_grp_entry() publishes
the new group via rcu_assign_pointer() then immediately frees the
removed entry's percpu stats with free_percpu(). However, the
synchronize_net() grace period in the caller remove_nexthop_from_groups()
runs after the free. RCU readers that entered before the publish still
see the old group and can dereference the freed stats via
nh_grp_entry_stats_inc() -> get_cpu_ptr(nhge->stats), causing a
use-after-free on percpu memory.

Fix by deferring the free_percpu() until after synchronize_net() in the
caller. Removed entries are chained via nh_list onto a local deferred
free list. After the grace period completes and all RCU readers have
finished, the percpu stats are safely freed.

Fixes: f4676ea74b85 ("net: nexthop: Add nexthop group entry stats")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260306233821.196789-1-mehulrao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 1aa2b05ee8de..c942f1282236 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg)
 }
 
 static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
-				struct nl_info *nlinfo)
+				struct nl_info *nlinfo,
+				struct list_head *deferred_free)
 {
 	struct nh_grp_entry *nhges, *new_nhges;
 	struct nexthop *nhp = nhge->nh_parent;
@@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 	rcu_assign_pointer(nhp->nh_grp, newg);
 
 	list_del(&nhge->nh_list);
-	free_percpu(nhge->stats);
 	nexthop_put(nhge->nh);
+	list_add(&nhge->nh_list, deferred_free);
 
 	/* Removal of a NH from a resilient group is notified through
 	 * bucket notifications.
@@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 				       struct nl_info *nlinfo)
 {
 	struct nh_grp_entry *nhge, *tmp;
+	LIST_HEAD(deferred_free);
 
 	/* If there is nothing to do, let's avoid the costly call to
 	 * synchronize_net()
@@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 		return;
 
 	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
-		remove_nh_grp_entry(net, nhge, nlinfo);
+		remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free);
 
 	/* make sure all see the newly published array before releasing rtnl */
 	synchronize_net();
+
+	/* Now safe to free percpu stats — all RCU readers have finished */
+	list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) {
+		list_del(&nhge->nh_list);
+		free_percpu(nhge->stats);
+	}
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)

From 7a85d370bbd0d55791ec57ea8ba13032410e8b9d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2026 12:06:07 +0000
Subject: [PATCH 1101/1303] MAINTAINERS: include/net/tc_wrapper.h belongs to TC
 subsystem

include/net/tc_wrapper.h changes should be reviewed by TC maintainers.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260307120607.3504191-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4f8e772808c7..07474a56821a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -25750,6 +25750,7 @@ F:	include/net/pkt_cls.h
 F:	include/net/pkt_sched.h
 F:	include/net/sch_priv.h
 F:	include/net/tc_act/
+F:	include/net/tc_wrapper.h
 F:	include/uapi/linux/pkt_cls.h
 F:	include/uapi/linux/pkt_sched.h
 F:	include/uapi/linux/tc_act/

From e4f774a0cc955ce762aec91c66915a6e15087ab7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:26 +0100
Subject: [PATCH 1102/1303] net: usb: lan78xx: fix silent drop of packets with
 checksum errors

Do not drop packets with checksum errors at the USB driver level;
pass them to the network stack.

Previously, the driver dropped all packets where the 'Receive Error
Detected' (RED) bit was set, regardless of the specific error type. This
caused packets with only IP or TCP/UDP checksum errors to be dropped
before reaching the kernel, preventing the network stack from accounting
for them or performing software fallback.

Add a mask for hard hardware errors to safely drop genuinely corrupt
frames, while allowing checksum-errored frames to pass with their
ip_summed field explicitly set to CHECKSUM_NONE.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 4 +++-
 drivers/net/usb/lan78xx.h | 3 +++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a0021df12fde..1c8f69190378 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3829,6 +3829,7 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 	 */
 	if (!(dev->net->features & NETIF_F_RXCSUM) ||
 	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+	    unlikely(rx_cmd_a & RX_CMD_A_CSE_MASK_) ||
 	    ((rx_cmd_a & RX_CMD_A_FVTG_) &&
 	     !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
 		skb->ip_summed = CHECKSUM_NONE;
@@ -3901,7 +3902,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb,
 			return 0;
 		}
 
-		if (unlikely(rx_cmd_a & RX_CMD_A_RED_)) {
+		if (unlikely(rx_cmd_a & RX_CMD_A_RED_) &&
+		    (rx_cmd_a & RX_CMD_A_RX_HARD_ERRS_MASK_)) {
 			netif_dbg(dev, rx_err, dev->net,
 				  "Error rx_cmd_a=0x%08x", rx_cmd_a);
 		} else {
diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h
index 968e5e5faee0..17a934acff3d 100644
--- a/drivers/net/usb/lan78xx.h
+++ b/drivers/net/usb/lan78xx.h
@@ -74,6 +74,9 @@
 #define RX_CMD_A_ICSM_			(0x00004000)
 #define RX_CMD_A_LEN_MASK_		(0x00003FFF)
 
+#define RX_CMD_A_RX_HARD_ERRS_MASK_ \
+	(RX_CMD_A_RX_ERRS_MASK_ & ~RX_CMD_A_CSE_MASK_)
+
 /* Rx Command B */
 #define RX_CMD_B_CSUM_SHIFT_		(16)
 #define RX_CMD_B_CSUM_MASK_		(0xFFFF0000)

From 50988747c30df47b73b787f234f746027cb7ec6c Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:27 +0100
Subject: [PATCH 1103/1303] net: usb: lan78xx: fix TX byte statistics for small
 packets

Account for hardware auto-padding in TX byte counters to reflect actual
wire traffic.

The LAN7850 hardware automatically pads undersized frames to the minimum
Ethernet frame length (ETH_ZLEN, 60 bytes). However, the driver tracks
the network statistics based on the unpadded socket buffer length. This
results in the tx_bytes counter under-reporting the actual physical
bytes placed on the Ethernet wire for small packets (like short ARP or
ICMP requests).

Use max_t() to ensure the transmission statistics accurately account for
the hardware-generated padding.

Fixes: d383216a7efe ("lan78xx: Introduce Tx URB processing improvements")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 1c8f69190378..507dbcf3b7b0 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4178,7 +4178,7 @@ static struct skb_data *lan78xx_tx_buf_fill(struct lan78xx_net *dev,
 		}
 
 		tx_data += len;
-		entry->length += len;
+		entry->length += max_t(unsigned int, len, ETH_ZLEN);
 		entry->num_of_packet += skb_shinfo(skb)->gso_segs ?: 1;
 
 		dev_kfree_skb_any(skb);

From d9cc0e440f0664f6f3e2c26e39ab9dd5f3badba7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:28 +0100
Subject: [PATCH 1104/1303] net: usb: lan78xx: skip LTM configuration for
 LAN7850

Do not configure Latency Tolerance Messaging (LTM) on USB 2.0 hardware.

The LAN7850 is a High-Speed (USB 2.0) only device and does not support
SuperSpeed features like LTM. Currently, the driver unconditionally
attempts to configure LTM registers during initialization. On the
LAN7850, these registers do not exist, resulting in writes to invalid
or undocumented memory space.

This issue was identified during a port to the regmap API with strict
register validation enabled. While no functional issues or crashes have
been observed from these invalid writes, bypassing LTM initialization
on the LAN7850 ensures the driver strictly adheres to the hardware's
valid register map.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 507dbcf3b7b0..f8558b87eaec 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3119,6 +3119,10 @@ static int lan78xx_init_ltm(struct lan78xx_net *dev)
 	int ret;
 	u32 buf;
 
+	/* LAN7850 is USB 2.0 and does not support LTM */
+	if (dev->chipid == ID_REV_CHIP_ID_7850_)
+		return 0;
+
 	ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
 	if (ret < 0)
 		goto init_ltm_failed;

From 312c816c6bc30342bc30dca0d6db617ab4d3ae4e Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:29 +0100
Subject: [PATCH 1105/1303] net: usb: lan78xx: fix WARN in
 __netif_napi_del_locked on disconnect

Remove redundant netif_napi_del() call from disconnect path.

A WARN may be triggered in __netif_napi_del_locked() during USB device
disconnect:

  WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350

This happens because netif_napi_del() is called in the disconnect path while
NAPI is still enabled. However, it is not necessary to call netif_napi_del()
explicitly, since unregister_netdev() will handle NAPI teardown automatically
and safely. Removing the redundant call avoids triggering the warning.

Full trace:
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x000000c4. ret = -ENODEV
 lan78xx 1-1:1.0 enu1: Failed to set MAC down with error -ENODEV
 lan78xx 1-1:1.0 enu1: Link is Down
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x00000120. ret = -ENODEV
 ------------[ cut here ]------------
 WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350
 Modules linked in: flexcan can_dev fuse
 CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.0-rc2-00624-ge926949dab03 #9 PREEMPT
 Hardware name: SKOV IMX8MP CPU revC - bd500 (DT)
 Workqueue: usb_hub_wq hub_event
 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : __netif_napi_del_locked+0x2b4/0x350
 lr : __netif_napi_del_locked+0x7c/0x350
 sp : ffffffc085b673c0
 x29: ffffffc085b673c0 x28: ffffff800b7f2000 x27: ffffff800b7f20d8
 x26: ffffff80110bcf58 x25: ffffff80110bd978 x24: 1ffffff0022179eb
 x23: ffffff80110bc000 x22: ffffff800b7f5000 x21: ffffff80110bc000
 x20: ffffff80110bcf38 x19: ffffff80110bcf28 x18: dfffffc000000000
 x17: ffffffc081578940 x16: ffffffc08284cee0 x15: 0000000000000028
 x14: 0000000000000006 x13: 0000000000040000 x12: ffffffb0022179e8
 x11: 1ffffff0022179e7 x10: ffffffb0022179e7 x9 : dfffffc000000000
 x8 : 0000004ffdde8619 x7 : ffffff80110bcf3f x6 : 0000000000000001
 x5 : ffffff80110bcf38 x4 : ffffff80110bcf38 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 1ffffff0022179e7 x0 : 0000000000000000
 Call trace:
  __netif_napi_del_locked+0x2b4/0x350 (P)
  lan78xx_disconnect+0xf4/0x360
  usb_unbind_interface+0x158/0x718
  device_remove+0x100/0x150
  device_release_driver_internal+0x308/0x478
  device_release_driver+0x1c/0x30
  bus_remove_device+0x1a8/0x368
  device_del+0x2e0/0x7b0
  usb_disable_device+0x244/0x540
  usb_disconnect+0x220/0x758
  hub_event+0x105c/0x35e0
  process_one_work+0x760/0x17b0
  worker_thread+0x768/0xce8
  kthread+0x3bc/0x690
  ret_from_fork+0x10/0x20
 irq event stamp: 211604
 hardirqs last  enabled at (211603): [<ffffffc0828cc9ec>] _raw_spin_unlock_irqrestore+0x84/0x98
 hardirqs last disabled at (211604): [<ffffffc0828a9a84>] el1_dbg+0x24/0x80
 softirqs last  enabled at (211296): [<ffffffc080095f10>] handle_softirqs+0x820/0xbc8
 softirqs last disabled at (210993): [<ffffffc080010288>] __do_softirq+0x18/0x20
 ---[ end trace 0000000000000000 ]---
 lan78xx 1-1:1.0 enu1: failed to kill vid 0081/0

Fixes: e110bc825897 ("net: usb: lan78xx: Convert to PHYLINK for improved PHY and MAC management")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-5-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f8558b87eaec..19cdf69fa589 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4552,8 +4552,6 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	phylink_disconnect_phy(dev->phylink);
 	rtnl_unlock();
 
-	netif_napi_del(&dev->napi);
-
 	unregister_netdev(net);
 
 	timer_shutdown_sync(&dev->stat_monitor);

From 0d9a60a0618d255530ca56072c5f39eb58e1ed4a Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Fri, 6 Mar 2026 14:58:54 -0800
Subject: [PATCH 1106/1303] bnxt_en: Fix RSS table size check when changing
 ethtool channels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When changing channels, the current check in bnxt_set_channels()
is not checking for non-default RSS contexts when the RSS table size
changes. The current check for IFF_RXFH_CONFIGURED is only sufficient
for the default RSS context. Expand the check to include the presence
of any non-default RSS contexts.

Allowing such change will result in incorrect configuration of the
context's RSS table when the table size changes.

Fixes: b3d0083caf9a ("bnxt_en: Support RSS contexts in ethtool .{get|set}_rxfh()")
Reported-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/netdev/20260303181535.2671734-1-bjorn@kernel.org/
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260306225854.3575672-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ba47e8294fff..28d0ece2e7b1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -979,8 +979,8 @@ static int bnxt_set_channels(struct net_device *dev,
 
 	if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) !=
 	    bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) &&
-	    netif_is_rxfh_configured(dev)) {
-		netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n");
+	    (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) {
+		netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n");
 		return -EINVAL;
 	}
 

From 237aab549676288d9255bb8dcc284738e56eaa31 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 3 Mar 2026 11:54:14 +0200
Subject: [PATCH 1107/1303] drm/i915/vrr: Configure VRR timings after enabling
 TRANS_DDI_FUNC_CTL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apparently ICL may hang with an MCE if we write TRANS_VRR_VMAX/FLIPLINE
before enabling TRANS_DDI_FUNC_CTL.

Personally I was only able to reproduce a hang (on an Dell XPS 7390
2-in-1) with an external display connected via a dock using a dodgy
type-C cable that made the link training fail. After the failed
link training the machine would hang. TGL seemed immune to the
problem for whatever reason.

BSpec does tell us to configure VRR after enabling TRANS_DDI_FUNC_CTL
as well. The DMC firmware also does the VRR restore in two stages:
- first stage seems to be unconditional and includes TRANS_VRR_CTL
  and a few other VRR registers, among other things
- second stage is conditional on the DDI being enabled,
  and includes TRANS_DDI_FUNC_CTL and TRANS_VRR_VMAX/VMIN/FLIPLINE,
  among other things

So let's reorder the steps to match to avoid the hang, and
toss in an extra WARN to make sure we don't screw this up later.

BSpec: 22243
Cc: stable@vger.kernel.org
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reported-by: Benjamin Tissoires <bentiss@kernel.org>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15777
Tested-by: Benjamin Tissoires <bentiss@kernel.org>
Fixes: dda7dcd9da73 ("drm/i915/vrr: Use fixed timings for platforms that support VRR")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260303095414.4331-1-ville.syrjala@linux.intel.com
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
(cherry picked from commit 93f3a267c3dd4d811b224bb9e179a10d81456a74)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_display.c |  1 -
 drivers/gpu/drm/i915/display/intel_vrr.c     | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3b8ba8ab76a1..c4246481fc2f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -1614,7 +1614,6 @@ static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_sta
 	}
 
 	intel_set_transcoder_timings(crtc_state);
-	intel_vrr_set_transcoder_timings(crtc_state);
 
 	if (cpu_transcoder != TRANSCODER_EDP)
 		intel_de_write(display, TRANS_MULT(display, cpu_transcoder),
diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c
index db74744ddb31..bea005752327 100644
--- a/drivers/gpu/drm/i915/display/intel_vrr.c
+++ b/drivers/gpu/drm/i915/display/intel_vrr.c
@@ -597,6 +597,18 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state)
 	if (!HAS_VRR(display))
 		return;
 
+	/*
+	 * Bspec says:
+	 * "(note: VRR needs to be programmed after
+	 *  TRANS_DDI_FUNC_CTL and before TRANS_CONF)."
+	 *
+	 * In practice it turns out that ICL can hang if
+	 * TRANS_VRR_VMAX/FLIPLINE are written before
+	 * enabling TRANS_DDI_FUNC_CTL.
+	 */
+	drm_WARN_ON(display->drm,
+		    !(intel_de_read(display, TRANS_DDI_FUNC_CTL(display, cpu_transcoder)) & TRANS_DDI_FUNC_ENABLE));
+
 	/*
 	 * This bit seems to have two meanings depending on the platform:
 	 * TGL: generate VRR "safe window" for DSB vblank waits
@@ -939,6 +951,8 @@ void intel_vrr_transcoder_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(crtc_state);
 
+	intel_vrr_set_transcoder_timings(crtc_state);
+
 	if (!intel_vrr_possible(crtc_state))
 		return;
 

From 029ae067431ab9d0fca479bdabe780fa436706ea Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Date: Tue, 24 Feb 2026 10:49:06 +0100
Subject: [PATCH 1108/1303] drm/i915: Fix potential overflow of shmem
 scatterlist length

When a scatterlists table of a GEM shmem object of size 4 GB or more is
populated with pages allocated from a folio, unsigned int .length
attribute of a scatterlist may get overflowed if total byte length of
pages allocated to that single scatterlist happens to reach or cross the
4GB limit.  As a consequence, users of the object may suffer from hitting
unexpected, premature end of the object's backing pages.

[278.780187] ------------[ cut here ]------------
[278.780377] WARNING: CPU: 1 PID: 2326 at drivers/gpu/drm/i915/i915_mm.c:55 remap_sg+0x199/0x1d0 [i915]
...
[278.780654] CPU: 1 UID: 0 PID: 2326 Comm: gem_mmap_offset Tainted: G S   U              6.17.0-rc1-CI_DRM_16981-ged823aaa0607+ #1 PREEMPT(voluntary)
[278.780656] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER
[278.780658] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024
[278.780659] RIP: 0010:remap_sg+0x199/0x1d0 [i915]
...
[278.780786] Call Trace:
[278.780787]  <TASK>
[278.780788]  ? __apply_to_page_range+0x3e6/0x910
[278.780795]  ? __pfx_remap_sg+0x10/0x10 [i915]
[278.780906]  apply_to_page_range+0x14/0x30
[278.780908]  remap_io_sg+0x14d/0x260 [i915]
[278.781013]  vm_fault_cpu+0xd2/0x330 [i915]
[278.781137]  __do_fault+0x3a/0x1b0
[278.781140]  do_fault+0x322/0x640
[278.781143]  __handle_mm_fault+0x938/0xfd0
[278.781150]  handle_mm_fault+0x12c/0x300
[278.781152]  ? lock_mm_and_find_vma+0x4b/0x760
[278.781155]  do_user_addr_fault+0x2d6/0x8e0
[278.781160]  exc_page_fault+0x96/0x2c0
[278.781165]  asm_exc_page_fault+0x27/0x30
...

That issue was apprehended by the author of a change that introduced it,
and potential risk even annotated with a comment, but then never addressed.

When adding folio pages to a scatterlist table, take care of byte length
of any single scatterlist not exceeding max_segment.

Fixes: 0b62af28f249b ("i915: convert shmem_sg_free_table() to use a folio_batch")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14809
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org # v6.5+
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20260224094944.2447913-2-janusz.krzysztofik@linux.intel.com
(cherry picked from commit 06249b4e691a75694c014a61708c007fb5755f60)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index c6c64ba29bc4..720a9ad39aa2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -153,8 +153,12 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 			}
 		} while (1);
 
-		nr_pages = min_t(unsigned long,
-				folio_nr_pages(folio), page_count - i);
+		nr_pages = min_array(((unsigned long[]) {
+					folio_nr_pages(folio),
+					page_count - i,
+					max_segment / PAGE_SIZE,
+				      }), 3);
+
 		if (!i ||
 		    sg->length >= max_segment ||
 		    folio_pfn(folio) != next_pfn) {
@@ -164,7 +168,9 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 			st->nents++;
 			sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0);
 		} else {
-			/* XXX: could overflow? */
+			nr_pages = min_t(unsigned long, nr_pages,
+					 (max_segment - sg->length) / PAGE_SIZE);
+
 			sg->length += nr_pages * PAGE_SIZE;
 		}
 		next_pfn = folio_pfn(folio) + nr_pages;

From 1be2fca84f520105413d0d89ed04bb0ff742ab16 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:08 +0200
Subject: [PATCH 1109/1303] drm/i915/psr: Repeat Selective Update area
 alignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are aligning Selective Update area to cover cursor fully if
needed only once. It may happen that cursor is in Selective Update area
after pipe alignment and after that covering cursor plane only
partially. Fix this by looping alignment as long as alignment isn't needed
anymore.

v2:
  - do not unecessarily loop if cursor was already fully covered
  - rename aligned as su_area_changed

Fixes: 1bff93b8bc27 ("drm/i915/psr: Extend SU area to cover cursor fully if needed")
Cc: <stable@vger.kernel.org> # v6.9+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-2-jouni.hogander@intel.com
(cherry picked from commit 681e12440d8b110350a5709101169f319e10ccbb)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 50 ++++++++++++++++++------
 1 file changed, 38 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 4ce1173a2e91..3848cd4fba0e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2689,11 +2689,12 @@ static void clip_area_update(struct drm_rect *overlap_damage_area,
 		overlap_damage_area->y2 = damage_area->y2;
 }
 
-static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state)
+static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(crtc_state);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	u16 y_alignment;
+	bool su_area_changed = false;
 
 	/* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */
 	if (crtc_state->dsc.compression_enable &&
@@ -2702,10 +2703,18 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st
 	else
 		y_alignment = crtc_state->su_y_granularity;
 
-	crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment;
-	if (crtc_state->psr2_su_area.y2 % y_alignment)
+	if (crtc_state->psr2_su_area.y1 % y_alignment) {
+		crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment;
+		su_area_changed = true;
+	}
+
+	if (crtc_state->psr2_su_area.y2 % y_alignment) {
 		crtc_state->psr2_su_area.y2 = ((crtc_state->psr2_su_area.y2 /
 						y_alignment) + 1) * y_alignment;
+		su_area_changed = true;
+	}
+
+	return su_area_changed;
 }
 
 /*
@@ -2839,7 +2848,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_plane_state *new_plane_state, *old_plane_state;
 	struct intel_plane *plane;
-	bool full_update = false, cursor_in_su_area = false;
+	bool full_update = false, su_area_changed;
 	int i, ret;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
@@ -2946,15 +2955,32 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	if (ret)
 		return ret;
 
-	/*
-	 * Adjust su area to cover cursor fully as necessary (early
-	 * transport). This needs to be done after
-	 * drm_atomic_add_affected_planes to ensure visible cursor is added into
-	 * affected planes even when cursor is not updated by itself.
-	 */
-	intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area);
+	do {
+		bool cursor_in_su_area;
 
-	intel_psr2_sel_fetch_pipe_alignment(crtc_state);
+		/*
+		 * Adjust su area to cover cursor fully as necessary
+		 * (early transport). This needs to be done after
+		 * drm_atomic_add_affected_planes to ensure visible
+		 * cursor is added into affected planes even when
+		 * cursor is not updated by itself.
+		 */
+		intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area);
+
+		su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state);
+
+		/*
+		 * If the cursor was outside the SU area before
+		 * alignment, the alignment step (which only expands
+		 * SU) may pull the cursor partially inside, so we
+		 * must run ET alignment again to fully cover it. But
+		 * if the cursor was already fully inside before
+		 * alignment, expanding the SU area won't change that,
+		 * so no further work is needed.
+		 */
+		if (cursor_in_su_area)
+			break;
+	} while (su_area_changed);
 
 	/*
 	 * Now that we have the pipe damaged area check if it intersect with

From c2c79c6d5b939ae8a42ddb884f576bddae685672 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:09 +0200
Subject: [PATCH 1110/1303] drm/i915/dsc: Add Selective Update register
 definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add definitions for DSC_SU_PARAMETER_SET_0_DSC0 and
DSC_SU_PARAMETER_SET_0_DSC1 registers. These are for Selective Update Early
Transport configuration.

Bspec: 71709
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-3-jouni.hogander@intel.com
(cherry picked from commit 24f96d903daf3dcf8fafe84d3d22b80ef47ba493)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_vdsc_regs.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 2d478a84b07c..2b2e3c1b8138 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -196,6 +196,18 @@
 #define   DSC_PPS18_NSL_BPG_OFFSET(offset)	REG_FIELD_PREP(DSC_PPS18_NSL_BPG_OFFSET_MASK, offset)
 #define   DSC_PPS18_SL_OFFSET_ADJ(offset)	REG_FIELD_PREP(DSC_PPS18_SL_OFFSET_ADJ_MASK, offset)
 
+#define _LNL_DSC0_SU_PARAMETER_SET_0_PA		0x78064
+#define _LNL_DSC1_SU_PARAMETER_SET_0_PA		0x78164
+#define _LNL_DSC0_SU_PARAMETER_SET_0_PB		0x78264
+#define _LNL_DSC1_SU_PARAMETER_SET_0_PB		0x78364
+#define LNL_DSC0_SU_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe), _LNL_DSC0_SU_PARAMETER_SET_0_PA, _LNL_DSC0_SU_PARAMETER_SET_0_PB)
+#define LNL_DSC1_SU_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe), _LNL_DSC1_SU_PARAMETER_SET_0_PA, _LNL_DSC1_SU_PARAMETER_SET_0_PB)
+
+#define   DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK		REG_GENMASK(31, 20)
+#define   DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(rows)	REG_FIELD_PREP(DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK, (rows))
+#define   DSC_SUPS0_SU_PIC_HEIGHT_MASK			REG_GENMASK(15, 0)
+#define   DSC_SUPS0_SU_PIC_HEIGHT(h)			REG_FIELD_PREP(DSC_SUPS0_SU_PIC_HEIGHT_MASK, (h))
+
 /* Icelake Rate Control Buffer Threshold Registers */
 #define DSCA_RC_BUF_THRESH_0			_MMIO(0x6B230)
 #define DSCA_RC_BUF_THRESH_0_UDW		_MMIO(0x6B230 + 4)

From bb5f1cd10101c2567bff4d0e760b74aee7c42f44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:10 +0200
Subject: [PATCH 1111/1303] drm/i915/dsc: Add helper for writing DSC Selective
 Update ET parameters
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are slice row per frame and pic height configuration in DSC Selective
Update Parameter Set 1 register. Add helper for configuring these.

v2:
  - Add WARN_ON_ONCE if vdsc instances per pipe > 2
  - instead of checking vdsc instances per pipe being > 1 check == 2

Bspec: 71709
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-4-jouni.hogander@intel.com
(cherry picked from commit c8698d61aeb3f70fe33761ee9d3d0e131b5bc2eb)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
[tursulin: fixup forward declaration conflict]
---
 drivers/gpu/drm/i915/display/intel_vdsc.c | 23 +++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_vdsc.h |  3 +++
 2 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 5493082f30a7..2065dac1e3fd 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -767,6 +767,29 @@ void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
 				  sizeof(dp_dsc_pps_sdp));
 }
 
+void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state, int su_lines)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	enum pipe pipe = crtc->pipe;
+	int vdsc_instances_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state);
+	int slice_row_per_frame = su_lines / vdsc_cfg->slice_height;
+	u32 val;
+
+	drm_WARN_ON_ONCE(display->drm, su_lines % vdsc_cfg->slice_height);
+	drm_WARN_ON_ONCE(display->drm, vdsc_instances_per_pipe > 2);
+
+	val = DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(slice_row_per_frame);
+	val |= DSC_SUPS0_SU_PIC_HEIGHT(su_lines);
+
+	intel_de_write_dsb(display, dsb, LNL_DSC0_SU_PARAMETER_SET_0(pipe), val);
+
+	if (vdsc_instances_per_pipe == 2)
+		intel_de_write_dsb(display, dsb, LNL_DSC1_SU_PARAMETER_SET_0(pipe), val);
+}
+
 static i915_reg_t dss_ctl1_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder)
 {
 	return is_pipe_dsc(crtc, cpu_transcoder) ?
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h
index 99f64ac54b27..99bb9042592a 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.h
@@ -13,6 +13,7 @@ struct drm_printer;
 enum transcoder;
 struct intel_crtc;
 struct intel_crtc_state;
+struct intel_dsb;
 struct intel_encoder;
 
 bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state);
@@ -31,6 +32,8 @@ void intel_dsc_dsi_pps_write(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state);
 void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state);
+void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state, int su_lines);
 void intel_vdsc_state_dump(struct drm_printer *p, int indent,
 			   const struct intel_crtc_state *crtc_state);
 int intel_vdsc_min_cdclk(const struct intel_crtc_state *crtc_state);

From 5923a6e0459fdd3edac4ad5abccb24d777d8f1b6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:11 +0200
Subject: [PATCH 1112/1303] drm/i915/psr: Write DSC parameters on Selective
 Update in ET mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are slice row per frame and pic height parameters in DSC that needs
to be configured on every Selective Update in Early Transport mode. Use
helper provided by DSC code to configure these on Selective Update when in
Early Transport mode. Also fill crtc_state->psr2_su_area with full frame
area on full frame update for DSC calculation.

v2: move psr2_su_area under skip_sel_fetch_set_loop label

Bspec: 68927, 71709
Fixes: 467e4e061c44 ("drm/i915/psr: Enable psr2 early transport as possible")
Cc: <stable@vger.kernel.org> # v6.9+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-5-jouni.hogander@intel.com
(cherry picked from commit 3140af2fab505a4cd47d516284529bf1585628be)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 3848cd4fba0e..b7302a32ded4 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2619,6 +2619,12 @@ void intel_psr2_program_trans_man_trk_ctl(struct intel_dsb *dsb,
 
 	intel_de_write_dsb(display, dsb, PIPE_SRCSZ_ERLY_TPT(crtc->pipe),
 			   crtc_state->pipe_srcsz_early_tpt);
+
+	if (!crtc_state->dsc.compression_enable)
+		return;
+
+	intel_dsc_su_et_parameters_configure(dsb, encoder, crtc_state,
+					     drm_rect_height(&crtc_state->psr2_su_area));
 }
 
 static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
@@ -3040,6 +3046,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	}
 
 skip_sel_fetch_set_loop:
+	if (full_update)
+		clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src,
+				 &crtc_state->pipe_src);
+
 	psr2_man_trk_ctl_calc(crtc_state, full_update);
 	crtc_state->pipe_srcsz_early_tpt =
 		psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update);

From 335b237d902c7362cb7228802e68374406b24acf Mon Sep 17 00:00:00 2001
From: Arun R Murthy <arun.r.murthy@intel.com>
Date: Wed, 4 Mar 2026 12:51:57 +0530
Subject: [PATCH 1113/1303] drm/i915/dp: Read ALPM caps after DPCD init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For eDP read the ALPM DPCD caps after DPCD initalization and just before
the PSR init.

v2: Move intel_alpm_init to intel_edp_init_dpcd (Jouni)
v3: Add Fixes with commit-id (Jouni)
v4: Separated the alpm dpcd read caps from alpm_init and moved to
intel_edp_init_dpcd.
v5: Read alpm_caps always for eDP irrespective of the eDP version (Jouni)
v6: replace drm_dp_dpcd_readb with drm_dp_dpcd_read_byte (Jouni)

Fixes: 15438b325987 ("drm/i915/alpm: Add compute config for lobf")
Signed-off-by: Arun R Murthy <arun.r.murthy@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Link: https://patch.msgid.link/20260304072157.1123283-1-arun.r.murthy@intel.com
(cherry picked from commit 88442ba208dd5d3405de3f5000cf5b2c86876ae3)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 6 ------
 drivers/gpu/drm/i915/display/intel_dp.c   | 7 +++++++
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index 07ffee38974b..f4f1b68f7543 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -43,12 +43,6 @@ bool intel_alpm_is_alpm_aux_less(struct intel_dp *intel_dp,
 
 void intel_alpm_init(struct intel_dp *intel_dp)
 {
-	u8 dpcd;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, &dpcd) < 0)
-		return;
-
-	intel_dp->alpm_dpcd = dpcd;
 	mutex_init(&intel_dp->alpm.lock);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 559cf3bb23fd..696edf40b243 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4577,6 +4577,7 @@ static bool
 intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
+	int ret;
 
 	/* this function is meant to be called only once */
 	drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0);
@@ -4616,6 +4617,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector
 	 */
 	intel_dp_init_source_oui(intel_dp);
 
+	/* Read the ALPM DPCD caps */
+	ret = drm_dp_dpcd_read_byte(&intel_dp->aux, DP_RECEIVER_ALPM_CAP,
+				    &intel_dp->alpm_dpcd);
+	if (ret < 0)
+		return false;
+
 	/*
 	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
 	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]

From df1d8abf36ca3681c21a6809eaa9a1e01ef897a6 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 9 Mar 2026 11:46:27 +0100
Subject: [PATCH 1114/1303] ALSA: usb-audio: Check endpoint numbers at parsing
 Scarlett2 mixer interfaces

The Scarlett2 mixer quirk in USB-audio driver may hit a NULL
dereference when a malformed USB descriptor is passed, since it
assumes the presence of an endpoint in the parsed interface in
scarlett2_find_fc_interface(), as reported by fuzzer.

For avoiding the NULL dereference, just add the sanity check of
bNumEndpoints and skip the invalid interface.

Reported-by: syzbot+8f29539ef9a1c8334f42@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/69acbbe1.050a0220.310d8.0001.GAE@google.com
Reported-by: syzbot+ae893a8901067fde2741@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/69acf72a.050a0220.310d8.0004.GAE@google.com
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20260309104632.141895-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_scarlett2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index ef3150581eab..fd1fb668929a 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -8251,6 +8251,8 @@ static int scarlett2_find_fc_interface(struct usb_device *dev,
 
 		if (desc->bInterfaceClass != 255)
 			continue;
+		if (desc->bNumEndpoints < 1)
+			continue;
 
 		epd = get_endpoint(intf->altsetting, 0);
 		private->bInterfaceNumber = desc->bInterfaceNumber;

From f1d77b863b414586ee45e10d9837c9ab27d8692d Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Thu, 5 Mar 2026 16:49:21 +0800
Subject: [PATCH 1115/1303] xfs: remove redundant set null for ip->i_itemp

ip->i_itemp has been set null in xfs_inode_item_destroy(), so there is
no need set it null again in xfs_inode_free_callback().

Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_icache.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a7a09e7eec81..2040a9292ee6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -159,7 +159,6 @@ xfs_inode_free_callback(
 		ASSERT(!test_bit(XFS_LI_IN_AIL,
 				 &ip->i_itemp->ili_item.li_flags));
 		xfs_inode_item_destroy(ip);
-		ip->i_itemp = NULL;
 	}
 
 	kmem_cache_free(xfs_inode_cache, ip);

From 186ac39b8a7d3ec7ce9c5dd45e5c2730177f375c Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Thu, 5 Mar 2026 16:49:22 +0800
Subject: [PATCH 1116/1303] xfs: ensure dquot item is deleted from AIL only
 after log shutdown

In xfs_qm_dqflush(), when a dquot flush fails due to corruption
(the out_abort error path), the original code removed the dquot log
item from the AIL before calling xfs_force_shutdown(). This ordering
introduces a subtle race condition that can lead to data loss after
a crash.

The AIL tracks the oldest dirty metadata in the journal. The position
of the tail item in the AIL determines the log tail LSN, which is the
oldest LSN that must be preserved for crash recovery. When an item is
removed from the AIL, the log tail can advance past the LSN of that item.

The race window is as follows: if the dquot item happens to be at
the tail of the log, removing it from the AIL allows the log tail
to advance. If a concurrent log write is sampling the tail LSN at
the same time and subsequently writes a complete checkpoint (i.e.,
one containing a commit record) to disk before the shutdown takes
effect, the journal will no longer protect the dquot's last
modification. On the next mount, log recovery will not replay the
dquot changes, even though they were never written back to disk,
resulting in silent data loss.

Fix this by calling xfs_force_shutdown() before xfs_trans_ail_delete()
in the out_abort path. Once the log is shut down, no new log writes
can complete with an updated tail LSN, making it safe to remove the
dquot item from the AIL.

Cc: stable@vger.kernel.org
Fixes: b707fffda6a3 ("xfs: abort consistently on dquot flush failure")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_dquot.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 2b208e2c5264..69e9bc588c8b 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1439,9 +1439,15 @@ xfs_qm_dqflush(
 	return 0;
 
 out_abort:
+	/*
+	 * Shut down the log before removing the dquot item from the AIL.
+	 * Otherwise, the log tail may advance past this item's LSN while
+	 * log writes are still in progress, making these unflushed changes
+	 * unrecoverable on the next mount.
+	 */
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	dqp->q_flags &= ~XFS_DQFLAG_DIRTY;
 	xfs_trans_ail_delete(lip, 0);
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	xfs_dqfunlock(dqp);
 	return error;
 }

From 246953f33e8cf95621d6c00332e2780ce1594082 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 5 Mar 2026 11:12:10 +0800
Subject: [PATCH 1117/1303] net: enetc: fix incorrect fallback PHY address
 handling

The current netc_get_phy_addr() implementation falls back to PHY address
0 when the "mdio" node or the PHY child node is missing. On i.MX95, this
causes failures when a real PHY is actually assigned address 0 and is
managed through the EMDIO interface. Because the bit 0 of phy_mask will
be set, leading imx95_enetc_mdio_phyaddr_config() to return an error, and
the netc_blk_ctrl driver probe subsequently fails. Fix this by returning
-ENODEV when neither an "mdio" node nor any PHY node is present, it means
that ENETC port MDIO is not used to manage the PHY, so there is no need
to configure LaBCR[MDIO_PHYAD_PRTAD].

Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Closes: https://lore.kernel.org/all/7825188.GXAFRqVoOG@steina-w
Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage")
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260305031211.904812-2-wei.fang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
index 7fd39f895290..f0e103615e88 100644
--- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
+++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
@@ -333,11 +333,13 @@ static int netc_get_phy_addr(struct device_node *np)
 
 	mdio_node = of_get_child_by_name(np, "mdio");
 	if (!mdio_node)
-		return 0;
+		return -ENODEV;
 
 	phy_node = of_get_next_child(mdio_node, NULL);
-	if (!phy_node)
+	if (!phy_node) {
+		err = -ENODEV;
 		goto of_put_mdio_node;
+	}
 
 	err = of_property_read_u32(phy_node, "reg", &addr);
 	if (err)
@@ -423,6 +425,9 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 
 			addr = netc_get_phy_addr(gchild);
 			if (addr < 0) {
+				if (addr == -ENODEV)
+					continue;
+
 				dev_err(dev, "Failed to get PHY address\n");
 				return addr;
 			}
@@ -578,6 +583,9 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
 
 	addr = netc_get_phy_addr(np);
 	if (addr < 0) {
+		if (addr == -ENODEV)
+			return 0;
+
 		dev_err(dev, "Failed to get PHY address\n");
 		return addr;
 	}

From dbe17e7783cb5d6451ff1217d0464865857e97e1 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 5 Mar 2026 11:12:11 +0800
Subject: [PATCH 1118/1303] net: enetc: do not skip setting
 LaBCR[MDIO_PHYAD_PRTAD] for addr 0

Given that some platforms may use PHY address 0 (I suppose the PHY may
not treat address 0 as a broadcast address or default response address).
It is possible for some boards to connect multiple PHYs to the same
ENETC MAC, for example:

  - a PHY with a non-zero address connects to ENETC MAC through SGMII
    interface (selected via DTS_A)
  - a PHY with address 0 connects to ENETC MAC through RGMII interface
    (selected via DTS_B)

For the case where the ENETC port MDIO is used to manage the PHY, when
switching from DTS_A to DTS_B via soft reboot, LaBCR[MDIO_PHYAD_PRTAD]
must be updated to 0 because the NETCMIX block is not reset during soft
reboot. However, the current driver explicitly skips configuring address
0, causing LaBCR[MDIO_PHYAD_PRTAD] to retain its old value.

Therefore, remove the special-case skip of PHY address 0 so that valid
configurations using address 0 are properly supported.

Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage")
Fixes: 50bfd9c06f0f ("net: enetc: set external PHY address in IERB for i.MX94 ENETC")
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260305031211.904812-3-wei.fang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
index f0e103615e88..92a0f824dae7 100644
--- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
+++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
@@ -438,12 +438,6 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 				return -EINVAL;
 			}
 
-			/* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is
-			 * 0, so no need to set the register.
-			 */
-			if (!addr)
-				continue;
-
 			switch (bus_devfn) {
 			case IMX95_ENETC0_BUS_DEVFN:
 				netc_reg_write(priv->ierb, IERB_LBCR(0),
@@ -590,12 +584,6 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
 		return addr;
 	}
 
-	/* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0,
-	 * so no need to set the register.
-	 */
-	if (!addr)
-		return 0;
-
 	if (phy_mask & BIT(addr)) {
 		dev_err(dev,
 			"Find same PHY address in EMDIO and ENETC node\n");

From a79f7b4aeb8e7562cd6dbf9c223e2c2a04b1a85f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 10 Mar 2026 08:54:33 +0000
Subject: [PATCH 1119/1303] KVM: arm64: pkvm: Don't reprobe for ICH_VTR_EL2.TDS
 on CPU hotplug

Hotplugging a CPU off and back on fails with pKVM, as we try to
probe for ICH_VTR_EL2.TDS. In a non-VHE setup, this is achieved
by using an EL2 stub helper. However, the stubs are out of reach
once pKVM has deprivileged the kernel. The CPU never boots.

Since pKVM doesn't allow late onlining of CPUs, we can detect
that protected mode is enforced early on, and return the current
state of the capability.

Fixes: 2a28810cbb8b2 ("KVM: arm64: GICv3: Detect and work around the lack of ICV_DIR_EL1 trapping")
Reported-by: Vincent Donnefort <vdonnefort@google.com>
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://patch.msgid.link/20260310085433.3936742-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/kernel/cpufeature.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c31f8e17732a..32c2dbcc0c64 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry,
 	    !is_midr_in_range_list(has_vgic_v3))
 		return false;
 
+	/*
+	 * pKVM prevents late onlining of CPUs. This means that whatever
+	 * state the capability is in after deprivilege cannot be affected
+	 * by a new CPU booting -- this is garanteed to be a CPU we have
+	 * already seen, and the cap is therefore unchanged.
+	 */
+	if (system_capabilities_finalized() && is_protected_kvm_enabled())
+		return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR);
+
 	if (is_kernel_in_hyp_mode())
 		res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2);
 	else

From 8dafa9f5900c4855a65dbfee51e3bd00636deee1 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 9 Mar 2026 16:22:19 +0900
Subject: [PATCH 1120/1303] mm/slab: fix an incorrect check in
 obj_exts_alloc_size()

obj_exts_alloc_size() prevents recursive allocation of slabobj_ext
array from the same cache, to avoid creating slabs that are never freed.

There is one mistake that returns the original size when memory
allocation profiling is disabled. The assumption was that
memcg-triggered slabobj_ext allocation is always served from
KMALLOC_CGROUP type. But this is wrong [1]: when the caller specifies
both __GFP_RECLAIMABLE and __GFP_ACCOUNT with SLUB_TINY enabled, the
allocation is served from normal kmalloc. This is because kmalloc_type()
prioritizes __GFP_RECLAIMABLE over __GFP_ACCOUNT, and SLUB_TINY aliases
KMALLOC_RECLAIM with KMALLOC_NORMAL.

As a result, the recursion guard is bypassed and the problematic slabs
can be created. Fix this by removing the mem_alloc_profiling_enabled()
check entirely. The remaining is_kmalloc_normal() check is still
sufficient to detect whether the cache is of KMALLOC_NORMAL type and
avoid bumping the size if it's not.

Without SLUB_TINY, no functional change intended.
With SLUB_TINY, allocations with __GFP_ACCOUNT|__GFP_RECLAIMABLE
now allocate a larger array if the sizes equal.

Reported-by: Zw Tang <shicenci@gmail.com>
Fixes: 280ea9c3154b ("mm/slab: avoid allocating slabobj_ext array from its own slab")
Closes: https://lore.kernel.org/linux-mm/CAPHJ_VKuMKSke8b11AZQw1PTSFN4n2C0gFxC6xGOG0ZLHgPmnA@mail.gmail.com [1]
Cc: stable@vger.kernel.org
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260309072219.22653-1-harry.yoo@oracle.com
Tested-by: Zw Tang <shicenci@gmail.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 20cb4f3b636d..6371838d2352 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2119,13 +2119,6 @@ static inline size_t obj_exts_alloc_size(struct kmem_cache *s,
 	size_t sz = sizeof(struct slabobj_ext) * slab->objects;
 	struct kmem_cache *obj_exts_cache;
 
-	/*
-	 * slabobj_ext array for KMALLOC_CGROUP allocations
-	 * are served from KMALLOC_NORMAL caches.
-	 */
-	if (!mem_alloc_profiling_enabled())
-		return sz;
-
 	if (sz > KMALLOC_MAX_CACHE_SIZE)
 		return sz;
 

From e3f5e0f22cfc2371e7471c9fd5b4da78f9df7c69 Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Thu, 5 Mar 2026 22:32:34 +0800
Subject: [PATCH 1121/1303] mctp: i2c: fix skb memory leak in receive path

When 'midev->allow_rx' is false, the newly allocated skb isn't consumed
by netif_rx(), it needs to free the skb directly.

Fixes: f5b8abf9fc3d ("mctp i2c: MCTP I2C binding driver")
Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Link: https://patch.msgid.link/20260305143240.97592-1-haiyuewa@163.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mctp/mctp-i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c
index de6bc1736734..15fe4d1163c1 100644
--- a/drivers/net/mctp/mctp-i2c.c
+++ b/drivers/net/mctp/mctp-i2c.c
@@ -343,6 +343,7 @@ static int mctp_i2c_recv(struct mctp_i2c_dev *midev)
 	} else {
 		status = NET_RX_DROP;
 		spin_unlock_irqrestore(&midev->lock, flags);
+		kfree_skb(skb);
 	}
 
 	if (status == NET_RX_SUCCESS) {

From 1eea46908c57abb7109b1fce024f366ae6c69c4f Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Fri, 6 Mar 2026 17:04:48 +0800
Subject: [PATCH 1122/1303] can: dev: keep the max bitrate error at 5%

Commit b360a13d44db ("can: dev: print bitrate error with two decimal
digits") changed calculation of the bit rate error from on-tenth of a
percent to on-hundredth of a percent, but forgot to adjust the scale of the
CAN_CALC_MAX_ERROR constant.

Keeping the existing logic unchanged: Only when the bitrate error exceeds
5% should an error be returned. Otherwise, simply output a warning log.

Fixes: b360a13d44db ("can: dev: print bitrate error with two decimal digits")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Link: https://patch.msgid.link/20260306-can-fix-v1-1-ac526cec6777@nxp.com
Cc: stable@kernel.org
[mkl: improve commit message]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/calc_bittiming.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c
index cc4022241553..42498e9d3f38 100644
--- a/drivers/net/can/dev/calc_bittiming.c
+++ b/drivers/net/can/dev/calc_bittiming.c
@@ -8,7 +8,7 @@
 #include <linux/units.h>
 #include <linux/can/dev.h>
 
-#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
+#define CAN_CALC_MAX_ERROR 500 /* max error 5% */
 
 /* CiA recommended sample points for Non Return to Zero encoding. */
 static int can_calc_sample_point_nrz(const struct can_bittiming *bt)

From 47bba09b14fa21712398febf36cb14fd4fc3bded Mon Sep 17 00:00:00 2001
From: Wenyuan Li <2063309626@qq.com>
Date: Tue, 10 Mar 2026 13:08:44 +0800
Subject: [PATCH 1123/1303] can: hi311x: hi3110_open(): add check for
 hi3110_power_enable() return value

In hi3110_open(), the return value of hi3110_power_enable() is not checked.
If power enable fails, the device may not function correctly, while the
driver still returns success.

Add a check for the return value and propagate the error accordingly.

Signed-off-by: Wenyuan Li <2063309626@qq.com>
Link: https://patch.msgid.link/tencent_B5E2E7528BB28AA8A2A56E16C49BD58B8B07@qq.com
Fixes: 57e83fb9b746 ("can: hi311x: Add Holt HI-311x CAN driver")
[mkl: adjust subject, commit message and jump label]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/hi311x.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index e00d3dbc4cf4..91b1fa970f8f 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -755,7 +755,9 @@ static int hi3110_open(struct net_device *net)
 		return ret;
 
 	mutex_lock(&priv->hi3110_lock);
-	hi3110_power_enable(priv->transceiver, 1);
+	ret = hi3110_power_enable(priv->transceiver, 1);
+	if (ret)
+		goto out_close_candev;
 
 	priv->force_quit = 0;
 	priv->tx_skb = NULL;
@@ -790,6 +792,7 @@ static int hi3110_open(struct net_device *net)
 	hi3110_hw_sleep(spi);
  out_close:
 	hi3110_power_enable(priv->transceiver, 0);
+ out_close_candev:
 	close_candev(net);
 	mutex_unlock(&priv->hi3110_lock);
 	return ret;

From 950803f7254721c1c15858fbbfae3deaaeeecb11 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Fri, 6 Mar 2026 10:15:07 +0800
Subject: [PATCH 1124/1303] bonding: fix type confusion in
 bond_setup_by_slave()

kernel BUG at net/core/skbuff.c:2306!
Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
RIP: 0010:pskb_expand_head+0xa08/0xfe0 net/core/skbuff.c:2306
RSP: 0018:ffffc90004aff760 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff88807e3c8780 RCX: ffffffff89593e0e
RDX: ffff88807b7c4900 RSI: ffffffff89594747 RDI: ffff88807b7c4900
RBP: 0000000000000820 R08: 0000000000000005 R09: 0000000000000000
R10: 00000000961a63e0 R11: 0000000000000000 R12: ffff88807e3c8780
R13: 00000000961a6560 R14: dffffc0000000000 R15: 00000000961a63e0
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe1a0ed8df0 CR3: 000000002d816000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 ipgre_header+0xdd/0x540 net/ipv4/ip_gre.c:900
 dev_hard_header include/linux/netdevice.h:3439 [inline]
 packet_snd net/packet/af_packet.c:3028 [inline]
 packet_sendmsg+0x3ae5/0x53c0 net/packet/af_packet.c:3108
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg net/socket.c:742 [inline]
 ____sys_sendmsg+0xa54/0xc30 net/socket.c:2592
 ___sys_sendmsg+0x190/0x1e0 net/socket.c:2646
 __sys_sendmsg+0x170/0x220 net/socket.c:2678
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fe1a0e6c1a9

When a non-Ethernet device (e.g. GRE tunnel) is enslaved to a bond,
bond_setup_by_slave() directly copies the slave's header_ops to the
bond device:

    bond_dev->header_ops = slave_dev->header_ops;

This causes a type confusion when dev_hard_header() is later called
on the bond device. Functions like ipgre_header(), ip6gre_header(),all use
netdev_priv(dev) to access their device-specific private data. When
called with the bond device, netdev_priv() returns the bond's private
data (struct bonding) instead of the expected type (e.g. struct
ip_tunnel), leading to garbage values being read and kernel crashes.

Fix this by introducing bond_header_ops with wrapper functions that
delegate to the active slave's header_ops using the slave's own
device. This ensures netdev_priv() in the slave's header functions
always receives the correct device.

The fix is placed in the bonding driver rather than individual device
drivers, as the root cause is bond blindly inheriting header_ops from
the slave without considering that these callbacks expect a specific
netdev_priv() layout.

The type confusion can be observed by adding a printk in
ipgre_header() and running the following commands:

    ip link add dummy0 type dummy
    ip addr add 10.0.0.1/24 dev dummy0
    ip link set dummy0 up
    ip link add gre1 type gre local 10.0.0.1
    ip link add bond1 type bond mode active-backup
    ip link set gre1 master bond1
    ip link set gre1 up
    ip link set bond1 up
    ip addr add fe80::1/64 dev bond1

Fixes: 1284cd3a2b74 ("bonding: two small fixes for IPoIB support")
Suggested-by: Jay Vosburgh <jv@jvosburgh.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260306021508.222062-1-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 47 ++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 444519078da3..c1fb92602e46 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1509,6 +1509,50 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	return features;
 }
 
+static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned int len)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->create)
+			ret = slave_ops->create(skb, slave->dev,
+						type, daddr, saddr, len);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	struct bonding *bond = netdev_priv(skb->dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->parse)
+			ret = slave_ops->parse(skb, haddr);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static const struct header_ops bond_header_ops = {
+	.create	= bond_header_create,
+	.parse	= bond_header_parse,
+};
+
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
@@ -1516,7 +1560,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 
 	dev_close(bond_dev);
 
-	bond_dev->header_ops	    = slave_dev->header_ops;
+	bond_dev->header_ops	    = slave_dev->header_ops ?
+				      &bond_header_ops : NULL;
 
 	bond_dev->type		    = slave_dev->type;
 	bond_dev->hard_header_len   = slave_dev->hard_header_len;

From 7d86aa41c073c4e7eb75fd2e674f1fd8f289728a Mon Sep 17 00:00:00 2001
From: Chengfeng Ye <dg573847474@gmail.com>
Date: Fri, 6 Mar 2026 03:14:02 +0000
Subject: [PATCH 1125/1303] mctp: route: hold key->lock in
 mctp_flow_prepare_output()

mctp_flow_prepare_output() checks key->dev and may call
mctp_dev_set_key(), but it does not hold key->lock while doing so.

mctp_dev_set_key() and mctp_dev_release_key() are annotated with
__must_hold(&key->lock), so key->dev access is intended to be
serialized by key->lock. The mctp_sendmsg() transmit path reaches
mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output()
without holding key->lock, so the check-and-set sequence is racy.

Example interleaving:

  CPU0                                  CPU1
  ----                                  ----
  mctp_flow_prepare_output(key, devA)
    if (!key->dev)  // sees NULL
                                        mctp_flow_prepare_output(
                                            key, devB)
                                          if (!key->dev)  // still NULL
                                          mctp_dev_set_key(devB, key)
                                            mctp_dev_hold(devB)
                                            key->dev = devB
    mctp_dev_set_key(devA, key)
      mctp_dev_hold(devA)
      key->dev = devA   // overwrites devB

Now both devA and devB references were acquired, but only the final
key->dev value is tracked for release. One reference can be lost,
causing a resource leak as mctp_dev_release_key() would only decrease
the reference on one dev.

Fix by taking key->lock around the key->dev check and
mctp_dev_set_key() call.

Fixes: 67737c457281 ("mctp: Pass flow data & flow release events to drivers")
Signed-off-by: Chengfeng Ye <dg573847474@gmail.com>
Link: https://patch.msgid.link/20260306031402.857224-1-dg573847474@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mctp/route.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/mctp/route.c b/net/mctp/route.c
index 0381377ab760..59ad60b88563 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -359,6 +359,7 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
 {
 	struct mctp_sk_key *key;
 	struct mctp_flow *flow;
+	unsigned long flags;
 
 	flow = skb_ext_find(skb, SKB_EXT_MCTP);
 	if (!flow)
@@ -366,12 +367,14 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
 
 	key = flow->key;
 
-	if (key->dev) {
-		WARN_ON(key->dev != dev);
-		return;
-	}
+	spin_lock_irqsave(&key->lock, flags);
 
-	mctp_dev_set_key(dev, key);
+	if (!key->dev)
+		mctp_dev_set_key(dev, key);
+	else
+		WARN_ON(key->dev != dev);
+
+	spin_unlock_irqrestore(&key->lock, flags);
 }
 #else
 static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {}

From 8cc7dd77a1466f0ec58c03478b2e735a5b289b96 Mon Sep 17 00:00:00 2001
From: Shashank Balaji <shashank.mahadasyam@sony.com>
Date: Fri, 6 Mar 2026 14:46:28 +0900
Subject: [PATCH 1126/1303] x86/apic: Disable x2apic on resume if the kernel
 expects so

When resuming from s2ram, firmware may re-enable x2apic mode, which may have
been disabled by the kernel during boot either because it doesn't support IRQ
remapping or for other reasons. This causes the kernel to continue using the
xapic interface, while the hardware is in x2apic mode, which causes hangs.
This happens on defconfig + bare metal + s2ram.

Fix this in lapic_resume() by disabling x2apic if the kernel expects it to be
disabled, i.e. when x2apic_mode = 0.

The ACPI v6.6 spec, Section 16.3 [1] says firmware restores either the
pre-sleep configuration or initial boot configuration for each CPU, including
MSR state:

  When executing from the power-on reset vector as a result of waking from an
  S2 or S3 sleep state, the platform firmware performs only the hardware
  initialization required to restore the system to either the state the
  platform was in prior to the initial operating system boot, or to the
  pre-sleep configuration state. In multiprocessor systems, non-boot
  processors should be placed in the same state as prior to the initial
  operating system boot.

  (further ahead)

  If this is an S2 or S3 wake, then the platform runtime firmware restores
  minimum context of the system before jumping to the waking vector. This
  includes:

	CPU configuration. Platform runtime firmware restores the pre-sleep
	configuration or initial boot configuration of each CPU (MSR, MTRR,
	firmware update, SMBase, and so on). Interrupts must be disabled (for
	IA-32 processors, disabled by CLI instruction).

	(and other things)

So at least as per the spec, re-enablement of x2apic by the firmware is
allowed if "x2apic on" is a part of the initial boot configuration.

  [1] https://uefi.org/specs/ACPI/6.6/16_Waking_and_Sleeping.html#initialization

  [ bp: Massage. ]

Fixes: 6e1cb38a2aef ("x64, x2apic/intr-remap: add x2apic support, including enabling interrupt-remapping")
Co-developed-by: Rahul Bukte <rahul.bukte@sony.com>
Signed-off-by: Rahul Bukte <rahul.bukte@sony.com>
Signed-off-by: Shashank Balaji <shashank.mahadasyam@sony.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260306-x2apic-fix-v2-1-bee99c12efa3@sony.com
---
 arch/x86/kernel/apic/apic.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d93f87f29d03..961714e6adae 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1894,6 +1894,7 @@ void __init check_x2apic(void)
 
 static inline void try_to_enable_x2apic(int remap_mode) { }
 static inline void __x2apic_enable(void) { }
+static inline void __x2apic_disable(void) { }
 #endif /* !CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
@@ -2456,6 +2457,11 @@ static void lapic_resume(void *data)
 	if (x2apic_mode) {
 		__x2apic_enable();
 	} else {
+		if (x2apic_enabled()) {
+			pr_warn_once("x2apic: re-enabled by firmware during resume. Disabling\n");
+			__x2apic_disable();
+		}
+
 		/*
 		 * Make sure the APICBASE points to the right address
 		 *

From 6485cb96be5cd0f4bf39554737ba11322cc9b053 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:27 +0530
Subject: [PATCH 1127/1303] amd-xgbe: fix link status handling in
 xgbe_rx_adaptation

The link status bit is latched low to allow detection of momentary
link drops. If the status indicates that the link is already down,
read it again to obtain the current state.

Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-2-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index c63ddb12237e..13c556dc0d67 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -1942,7 +1942,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata,
 static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
+	int reg;
 
 	/* step 2: force PCS to send RX_ADAPT Req to PHY */
 	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4,
@@ -1964,11 +1964,20 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 
 	/* Step 4: Check for Block lock */
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		goto set_mode;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
 	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			goto set_mode;
+	}
+
 	if (reg & MDIO_STAT1_LSTATUS) {
 		/* If the block lock is found, update the helpers
 		 * and declare the link up

From 27a4dd0c702b3b2b9cf2c045d100cc2fe8720b81 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:28 +0530
Subject: [PATCH 1128/1303] amd-xgbe: prevent CRC errors during RX adaptation
 with AN disabled

When operating in 10GBASE-KR mode with auto-negotiation disabled and RX
adaptation enabled, CRC errors can occur during the RX adaptation
process. This happens because the driver continues transmitting and
receiving packets while adaptation is in progress.

Fix this by stopping TX/RX immediately when the link goes down and RX
adaptation needs to be re-triggered, and only re-enabling TX/RX after
adaptation completes and the link is confirmed up. Introduce a flag to
track whether TX/RX was disabled for adaptation so it can be restored
correctly.

This prevents packets from being transmitted or received during the RX
adaptation window and avoids CRC errors from corrupted frames.

The flag tracking the data path state is synchronized with hardware
state in xgbe_start() to prevent stale state after device restarts.
This ensures that after a restart cycle (where xgbe_stop disables
TX/RX and xgbe_start re-enables them), the flag correctly reflects
that the data path is active.

Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-3-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c    |  4 ++
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 63 ++++++++++++++++++++-
 drivers/net/ethernet/amd/xgbe/xgbe.h        |  4 ++
 3 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 8b79d88480db..39da2f811858 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1277,6 +1277,10 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	hw_if->enable_tx(pdata);
 	hw_if->enable_rx(pdata);
+	/* Synchronize flag with hardware state after enabling TX/RX.
+	 * This prevents stale state after device restart cycles.
+	 */
+	pdata->data_path_stopped = false;
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 13c556dc0d67..b8cf6ccfe641 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -2017,6 +2017,48 @@ static void xgbe_phy_rx_adaptation(struct xgbe_prv_data *pdata)
 	xgbe_rx_adaptation(pdata);
 }
 
+/*
+ * xgbe_phy_stop_data_path - Stop TX/RX to prevent packet corruption
+ * @pdata: driver private data
+ *
+ * This function stops the data path (TX and RX) to prevent packet
+ * corruption during critical PHY operations like RX adaptation.
+ * Must be called before initiating RX adaptation when link goes down.
+ */
+static void xgbe_phy_stop_data_path(struct xgbe_prv_data *pdata)
+{
+	if (pdata->data_path_stopped)
+		return;
+
+	/* Stop TX/RX to prevent packet corruption during RX adaptation */
+	pdata->hw_if.disable_tx(pdata);
+	pdata->hw_if.disable_rx(pdata);
+	pdata->data_path_stopped = true;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "stopping data path for RX adaptation\n");
+}
+
+/*
+ * xgbe_phy_start_data_path - Re-enable TX/RX after RX adaptation
+ * @pdata: driver private data
+ *
+ * This function re-enables the data path (TX and RX) after RX adaptation
+ * has completed successfully. Only called when link is confirmed up.
+ */
+static void xgbe_phy_start_data_path(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->data_path_stopped)
+		return;
+
+	pdata->hw_if.enable_rx(pdata);
+	pdata->hw_if.enable_tx(pdata);
+	pdata->data_path_stopped = false;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "restarting data path after RX adaptation\n");
+}
+
 static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata)
 {
 	int reg;
@@ -2810,13 +2852,27 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
 		 * declare link up
+		 *
+		 * Note: When link is up and adaptation is done, we can
+		 * safely re-enable the data path if it was stopped
+		 * for adaptation.
 		 */
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) {
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 		/* If either link is not available or adaptation is not done,
 		 * retrigger the adaptation logic. (if the mode is not set,
 		 * then issue mailbox command first)
 		 */
+
+		/* CRITICAL: Stop data path BEFORE triggering RX adaptation
+		 * to prevent CRC errors from packets corrupted during
+		 * the adaptation process. This is especially important
+		 * when AN is OFF in 10G KR mode.
+		 */
+		xgbe_phy_stop_data_path(pdata);
+
 		if (pdata->mode_set) {
 			xgbe_phy_rx_adaptation(pdata);
 		} else {
@@ -2824,8 +2880,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		if (pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done) {
+			/* Adaptation complete, safe to re-enable data path */
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index e1d7d7150e16..438033a71523 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1243,6 +1243,10 @@ struct xgbe_prv_data {
 	bool en_rx_adap;
 	int rx_adapt_retries;
 	bool rx_adapt_done;
+	/* Flag to track if data path (TX/RX) was stopped for RX adaptation.
+	 * This prevents packet corruption during the adaptation window.
+	 */
+	bool data_path_stopped;
 	bool mode_set;
 	bool sph;
 };

From a8ba129af46856112981c124850ec6a85a1c1ab6 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:29 +0530
Subject: [PATCH 1129/1303] amd-xgbe: reset PHY settings before starting PHY

commit f93505f35745 ("amd-xgbe: let the MAC manage PHY PM") moved
xgbe_phy_reset() from xgbe_open() to xgbe_start(), placing it after
phy_start(). As a result, the PHY settings were being reset after the
PHY had already started.

Reorder the calls so that the PHY settings are reset before
phy_start() is invoked.

Fixes: f93505f35745 ("amd-xgbe: let the MAC manage PHY PM")
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-4-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 39da2f811858..23beea48ae26 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1271,6 +1271,12 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 	if (ret)
 		goto err_napi;
 
+	/* Reset the phy settings */
+	ret = xgbe_phy_reset(pdata);
+	if (ret)
+		goto err_irqs;
+
+	/* Start the phy */
 	ret = phy_if->phy_start(pdata);
 	if (ret)
 		goto err_irqs;
@@ -1284,11 +1290,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
-	/* Reset the phy settings */
-	ret = xgbe_phy_reset(pdata);
-	if (ret)
-		goto err_txrx;
-
 	netif_tx_start_all_queues(netdev);
 
 	xgbe_start_timers(pdata);
@@ -1298,10 +1299,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	return 0;
 
-err_txrx:
-	hw_if->disable_rx(pdata);
-	hw_if->disable_tx(pdata);
-
 err_irqs:
 	xgbe_free_irqs(pdata);
 

From 69fb5d91bba44ecf7eb80530b85fa4fb028921d5 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 17:38:00 +0100
Subject: [PATCH 1130/1303] libceph: prevent potential out-of-bounds reads in
 process_message_header()

If the message frame is (maliciously) corrupted in a way that the
length of the control segment ends up being less than the size of the
message header or a different frame is made to look like a message
frame, out-of-bounds reads may ensue in process_message_header().

Perform an explicit bounds check before decoding the message header.

Cc: stable@vger.kernel.org
Reported-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
---
 net/ceph/messenger_v2.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 5ec3272cd2dd..ed618435d33a 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -2833,12 +2833,15 @@ static int process_message_header(struct ceph_connection *con,
 				  void *p, void *end)
 {
 	struct ceph_frame_desc *desc = &con->v2.in_desc;
-	struct ceph_msg_header2 *hdr2 = p;
+	struct ceph_msg_header2 *hdr2;
 	struct ceph_msg_header hdr;
 	int skip;
 	int ret;
 	u64 seq;
 
+	ceph_decode_need(&p, end, sizeof(*hdr2), bad);
+	hdr2 = p;
+
 	/* verify seq# */
 	seq = le64_to_cpu(hdr2->seq);
 	if ((s64)seq - (s64)con->in_seq < 1) {
@@ -2869,6 +2872,10 @@ static int process_message_header(struct ceph_connection *con,
 	WARN_ON(!con->in_msg);
 	WARN_ON(con->in_msg->con != con);
 	return 1;
+
+bad:
+	pr_err("failed to decode message header\n");
+	return -EINVAL;
 }
 
 static int process_message(struct ceph_connection *con)

From a5a373705081d7cc6363e16990e2361b0b362314 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 17:57:23 +0100
Subject: [PATCH 1131/1303] libceph: admit message frames only in
 CEPH_CON_S_OPEN state

Similar checks are performed for all control frames, but an early check
for message frames was missing.  process_message() is already set up to
terminate the loop in case the state changes while con->ops->dispatch()
handler is being executed.

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
---
 net/ceph/messenger_v2.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index ed618435d33a..c4ddf7911f7d 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -2905,6 +2905,11 @@ static int __handle_control(struct ceph_connection *con, void *p)
 	if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE)
 		return process_control(con, p, end);
 
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected message";
+		return -EINVAL;
+	}
+
 	ret = process_message_header(con, p, end);
 	if (ret < 0)
 		return ret;

From c4c22b846eceff05b1129b8844a80310e55a7f87 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 20:01:27 +0100
Subject: [PATCH 1132/1303] libceph: reject preamble if control segment is
 empty

While head_onwire_len() has a branch to handle ctrl_len == 0 case,
prepare_read_control() always sets up a kvec for the CRC meaning that
a non-empty control segment is effectively assumed.  All frames that
clients deal with meet that assumption, so let's make it official and
treat the preamble with an empty control segment as malformed.

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
---
 net/ceph/messenger_v2.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c4ddf7911f7d..50f65820f623 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 	int head_len;
 	int rem_len;
 
-	BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
+	BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
 
 	if (secure) {
 		head_len = CEPH_PREAMBLE_SECURE_LEN;
@@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 			head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN;
 		}
 	} else {
-		head_len = CEPH_PREAMBLE_PLAIN_LEN;
-		if (ctrl_len)
-			head_len += ctrl_len + CEPH_CRC_LEN;
+		head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN;
 	}
 	return head_len;
 }
@@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		desc->fd_aligns[i] = ceph_decode_16(&p);
 	}
 
-	if (desc->fd_lens[0] < 0 ||
+	/*
+	 * This would fire for FRAME_TAG_WAIT (it has one empty
+	 * segment), but we should never get it as client.
+	 */
+	if (desc->fd_lens[0] < 1 ||
 	    desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) {
 		pr_err("bad control segment length %d\n", desc->fd_lens[0]);
 		return -EINVAL;
 	}
+
 	if (desc->fd_lens[1] < 0 ||
 	    desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) {
 		pr_err("bad front segment length %d\n", desc->fd_lens[1]);
@@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		return -EINVAL;
 	}
 
-	/*
-	 * This would fire for FRAME_TAG_WAIT (it has one empty
-	 * segment), but we should never get it as client.
-	 */
 	if (!desc->fd_lens[desc->fd_seg_cnt - 1]) {
 		pr_err("last segment empty, segment count %d\n",
 		       desc->fd_seg_cnt);

From a5f930eebde6f27c1e404f566c09332f42f349fb Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <dongsheng.yang@linux.dev>
Date: Tue, 10 Mar 2026 07:05:14 +0000
Subject: [PATCH 1133/1303] MAINTAINERS: update email address of Dongsheng Yang

My easystack email will be unreachable soon, update my email address to
linux.dev one.

Signed-off-by: Dongsheng Yang <dongsheng.yang@linux.dev>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 77fdfcb55f06..8a9d35b29dbe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21938,7 +21938,7 @@ F:	drivers/media/radio/radio-tea5777.c
 
 RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
-R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
+R:	Dongsheng Yang <dongsheng.yang@linux.dev>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/

From 6f1a9140ecda3baba3d945b9a6155af4268aafc4 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Sat, 7 Mar 2026 00:01:34 +0800
Subject: [PATCH 1134/1303] net: add xmit recursion limit to tunnel xmit
 functions

Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own
recursion limit. When a bond device in broadcast mode has GRE tap
interfaces as slaves, and those GRE tunnels route back through the
bond, multicast/broadcast traffic triggers infinite recursion between
bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing
kernel stack overflow.

The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not
sufficient because tunnel recursion involves route lookups and full IP
output, consuming much more stack per level. Use a lower limit of 4
(IP_TUNNEL_RECURSION_LIMIT) to prevent overflow.

Add recursion detection using dev_xmit_recursion helpers directly in
iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel
paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.).

Move dev_xmit_recursion helpers from net/core/dev.h to public header
include/linux/netdevice.h so they can be used by tunnel code.

 BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160
 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11
 Workqueue: mld mld_ifc_work
 Call Trace:
  <TASK>
  __build_flow_key.constprop.0 (net/ipv4/route.c:515)
  ip_rt_update_pmtu (net/ipv4/route.c:1073)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84)
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  ip_output (net/ipv4/ip_output.c:438)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  ip_output (net/ipv4/ip_output.c:438)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86)
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  mld_sendpack
  mld_ifc_work
  process_one_work
  worker_thread
  </TASK>

Fixes: 745e20f1b626 ("net: add a recursion limit in xmit path")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260306160133.3852900-2-bestswngs@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++++
 include/net/ip6_tunnel.h  | 12 ++++++++++++
 include/net/ip_tunnels.h  |  7 +++++++
 net/core/dev.h            | 35 -----------------------------------
 net/ipv4/ip_tunnel_core.c | 13 +++++++++++++
 5 files changed, 64 insertions(+), 35 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67e25f6d15a4..ae269a2e7f4d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3576,17 +3576,49 @@ struct page_pool_bh {
 };
 DECLARE_PER_CPU(struct page_pool_bh, system_page_pool);
 
+#define XMIT_RECURSION_LIMIT	8
+
 #ifndef CONFIG_PREEMPT_RT
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
+
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
+			XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	__this_cpu_inc(softnet_data.xmit.recursion);
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	__this_cpu_dec(softnet_data.xmit.recursion);
+}
 #else
 static inline int dev_recursion_level(void)
 {
 	return current->net_xmit.recursion;
 }
 
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	current->net_xmit.recursion++;
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	current->net_xmit.recursion--;
+}
 #endif
 
 void __netif_schedule(struct Qdisc *q);
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 120db2865811..1253cbb4b0a4 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -156,6 +156,16 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 {
 	int pkt_len, err;
 
+	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
+		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+				     dev->name);
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return;
+	}
+
+	dev_xmit_recursion_inc();
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	IP6CB(skb)->flags = ip6cb_flags;
 	pkt_len = skb->len - skb_inner_network_offset(skb);
@@ -166,6 +176,8 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 			pkt_len = -1;
 		iptunnel_xmit_stats(dev, pkt_len);
 	}
+
+	dev_xmit_recursion_dec();
 }
 #endif
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 4021e6a73e32..80662f812080 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -27,6 +27,13 @@
 #include <net/ip6_route.h>
 #endif
 
+/* Recursion limit for tunnel xmit to detect routing loops.
+ * Unlike XMIT_RECURSION_LIMIT (8) used in the no-qdisc path, tunnel
+ * recursion involves route lookups and full IP output, consuming much
+ * more stack per level, so a lower limit is needed.
+ */
+#define IP_TUNNEL_RECURSION_LIMIT	4
+
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
 
diff --git a/net/core/dev.h b/net/core/dev.h
index 98793a738f43..781619e76b3e 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -366,41 +366,6 @@ static inline void napi_assert_will_not_race(const struct napi_struct *napi)
 
 void kick_defer_list_purge(unsigned int cpu);
 
-#define XMIT_RECURSION_LIMIT	8
-
-#ifndef CONFIG_PREEMPT_RT
-static inline bool dev_xmit_recursion(void)
-{
-	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-			XMIT_RECURSION_LIMIT);
-}
-
-static inline void dev_xmit_recursion_inc(void)
-{
-	__this_cpu_inc(softnet_data.xmit.recursion);
-}
-
-static inline void dev_xmit_recursion_dec(void)
-{
-	__this_cpu_dec(softnet_data.xmit.recursion);
-}
-#else
-static inline bool dev_xmit_recursion(void)
-{
-	return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT);
-}
-
-static inline void dev_xmit_recursion_inc(void)
-{
-	current->net_xmit.recursion++;
-}
-
-static inline void dev_xmit_recursion_dec(void)
-{
-	current->net_xmit.recursion--;
-}
-#endif
-
 int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct kernel_hwtstamp_config *cfg,
 			    struct netlink_ext_ack *extack);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 2e61ac137128..b1b6bf949f65 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -58,6 +58,17 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	struct iphdr *iph;
 	int err;
 
+	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
+		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+				     dev->name);
+		DEV_STATS_INC(dev, tx_errors);
+		ip_rt_put(rt);
+		kfree_skb(skb);
+		return;
+	}
+
+	dev_xmit_recursion_inc();
+
 	skb_scrub_packet(skb, xnet);
 
 	skb_clear_hash_if_not_l4(skb);
@@ -88,6 +99,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 			pkt_len = 0;
 		iptunnel_xmit_stats(dev, pkt_len);
 	}
+
+	dev_xmit_recursion_dec();
 }
 EXPORT_SYMBOL_GPL(iptunnel_xmit);
 

From 59bdbabccaa470ed94aae7d94a1229c7b0ff4681 Mon Sep 17 00:00:00 2001
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Date: Thu, 5 Mar 2026 15:22:26 +0100
Subject: [PATCH 1135/1303] accel/ivpu: Remove boot params address setting via
 MMIO register

The NPU 60XX uses the default boot params location specified
in the firmware image header, consistent with earlier generations.
Remove the unnecessary MMIO register write, freeing the AON register
for future use.

Fixes: 44e4c88951fa ("accel/ivpu: Implement warm boot flow for NPU6 and unify boot handling")
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Link: https://patch.msgid.link/20260305142226.194995-1-andrzej.kacprowski@linux.intel.com
(cherry picked from commit 81e62e7bf8b9309bf0febdf00940818f98bc23d8)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
 drivers/accel/ivpu/ivpu_hw_40xx_reg.h | 6 ------
 drivers/accel/ivpu/ivpu_hw_ip.c       | 1 -
 2 files changed, 7 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
index 421242acb184..fc0ee8d637f9 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
@@ -121,12 +121,6 @@
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY			0x0003006cu
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK	GENMASK(7, 0)
 
-#define VPU_40XX_HOST_SS_AON_RETENTION0                                 0x0003000cu
-#define VPU_40XX_HOST_SS_AON_RETENTION1                                 0x00030010u
-#define VPU_40XX_HOST_SS_AON_RETENTION2                                 0x00030014u
-#define VPU_40XX_HOST_SS_AON_RETENTION3                                 0x00030018u
-#define VPU_40XX_HOST_SS_AON_RETENTION4                                 0x0003001cu
-
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN					0x00030200u
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN_EN_MASK				BIT_MASK(0)
 #define VPU_40XX_HOST_SS_AON_IDLE_GEN_HW_PG_EN_MASK			BIT_MASK(1)
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c
index 959984c54341..37f95a0551ed 100644
--- a/drivers/accel/ivpu/ivpu_hw_ip.c
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -931,7 +931,6 @@ static int soc_cpu_boot_40xx(struct ivpu_device *vdev)
 
 static int soc_cpu_boot_60xx(struct ivpu_device *vdev)
 {
-	REGV_WR64(VPU_40XX_HOST_SS_AON_RETENTION1, vdev->fw->mem_bp->vpu_addr);
 	soc_cpu_set_entry_point_40xx(vdev, vdev->fw->cold_boot_entry_point);
 
 	return 0;

From 3c3b41e5911db7668e3938eae8df7ed80c76c153 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 6 Mar 2026 14:08:34 +0000
Subject: [PATCH 1136/1303] perf cs-etm: Finish removal of ETM_OPT_*

These #defines have been removed from the kernel headers in favour of
the string based PMU format attributes. Usages were previously removed
from the recording side of cs-etm in Perf. Finish the removal by
removing usages from the decode side too.

It's a straight replacement of the old #defines with the new register
bit definitions. Except cs_etm__setup_timeless_decoding() which wasn't
looking at the saved metadata and was instead hard coding an access to
'attr.config'. This was vulnerable to the same issue of .config being
moved to .config2 etc that the original removal of ETM_OPT_* tried to
fix. So fix that too.

Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/cs-etm.c             | 14 --------
 .../perf/util/cs-etm-decoder/cs-etm-decoder.c |  2 +-
 tools/perf/util/cs-etm.c                      | 36 +++++++------------
 tools/perf/util/cs-etm.h                      | 15 ++++++++
 4 files changed, 29 insertions(+), 38 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index dc3f4e86b075..4418d21708d6 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -68,20 +68,6 @@ static const char * const metadata_ete_ro[] = {
 
 enum cs_etm_version { CS_NOT_PRESENT, CS_ETMV3, CS_ETMV4, CS_ETE };
 
-/* ETMv4 CONFIGR register bits */
-#define TRCCONFIGR_BB		BIT(3)
-#define TRCCONFIGR_CCI		BIT(4)
-#define TRCCONFIGR_CID		BIT(6)
-#define TRCCONFIGR_VMID		BIT(7)
-#define TRCCONFIGR_TS		BIT(11)
-#define TRCCONFIGR_RS		BIT(12)
-#define TRCCONFIGR_VMIDOPT	BIT(15)
-
-/* ETMv3 ETMCR register bits */
-#define ETMCR_CYC_ACC		BIT(12)
-#define ETMCR_TIMESTAMP_EN	BIT(28)
-#define ETMCR_RETURN_STACK	BIT(29)
-
 static bool cs_etm_is_ete(struct perf_pmu *cs_etm_pmu, struct perf_cpu cpu);
 static int cs_etm_get_ro(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path, __u64 *val);
 static bool cs_etm_pmu_path_exists(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path);
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 3050fe212666..212f17a3dc72 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -549,7 +549,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 	/*
 	 * Process the PE_CONTEXT packets if we have a valid contextID or VMID.
 	 * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2
-	 * as VMID, Bit ETM_OPT_CTXTID2 is set in this case.
+	 * as VMID, Format attribute 'contextid2' is set in this case.
 	 */
 	switch (cs_etm__get_pid_fmt(etmq)) {
 	case CS_ETM_PIDFMT_CTXTID:
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 95f439c96180..8a639d2e51a4 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -194,7 +194,7 @@ int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu)
  *   CS_ETM_PIDFMT_CTXTID2: CONTEXTIDR_EL2 is traced.
  *   CS_ETM_PIDFMT_NONE: No context IDs
  *
- * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2
+ * It's possible that the two format attributes 'contextid1' and 'contextid2'
  * are enabled at the same time when the session runs on an EL2 kernel.
  * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be
  * recorded in the trace data, the tool will selectively use
@@ -210,15 +210,15 @@ static enum cs_etm_pid_fmt cs_etm__init_pid_fmt(u64 *metadata)
 	if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
 		val = metadata[CS_ETM_ETMCR];
 		/* CONTEXTIDR is traced */
-		if (val & BIT(ETM_OPT_CTXTID))
+		if (val & ETMCR_CTXTID)
 			return CS_ETM_PIDFMT_CTXTID;
 	} else {
 		val = metadata[CS_ETMV4_TRCCONFIGR];
 		/* CONTEXTIDR_EL2 is traced */
-		if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT)))
+		if (val & (TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT))
 			return CS_ETM_PIDFMT_CTXTID2;
 		/* CONTEXTIDR_EL1 is traced */
-		else if (val & BIT(ETM4_CFG_BIT_CTXTID))
+		else if (val & TRCCONFIGR_CID)
 			return CS_ETM_PIDFMT_CTXTID;
 	}
 
@@ -2914,29 +2914,21 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
 	return 0;
 }
 
-static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm)
+static void cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm)
 {
-	struct evsel *evsel;
-	struct evlist *evlist = etm->session->evlist;
+	/* Take first ETM as all options will be the same for all ETMs */
+	u64 *metadata = etm->metadata[0];
 
 	/* Override timeless mode with user input from --itrace=Z */
 	if (etm->synth_opts.timeless_decoding) {
 		etm->timeless_decoding = true;
-		return 0;
+		return;
 	}
 
-	/*
-	 * Find the cs_etm evsel and look at what its timestamp setting was
-	 */
-	evlist__for_each_entry(evlist, evsel)
-		if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) {
-			etm->timeless_decoding =
-				!(evsel->core.attr.config & BIT(ETM_OPT_TS));
-			return 0;
-		}
-
-	pr_err("CS ETM: Couldn't find ETM evsel\n");
-	return -EINVAL;
+	if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic)
+		etm->timeless_decoding = !(metadata[CS_ETM_ETMCR] & ETMCR_TIMESTAMP_EN);
+	else
+		etm->timeless_decoding = !(metadata[CS_ETMV4_TRCCONFIGR] & TRCCONFIGR_TS);
 }
 
 /*
@@ -3499,9 +3491,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace;
 	session->auxtrace = &etm->auxtrace;
 
-	err = cs_etm__setup_timeless_decoding(etm);
-	if (err)
-		return err;
+	cs_etm__setup_timeless_decoding(etm);
 
 	etm->tc.time_shift = tc->time_shift;
 	etm->tc.time_mult = tc->time_mult;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index a8caeea720aa..aa9bb4a32eca 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -230,6 +230,21 @@ struct cs_etm_packet_queue {
 /* CoreSight trace ID is currently the bottom 7 bits of the value */
 #define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
 
+/* ETMv4 CONFIGR register bits */
+#define TRCCONFIGR_BB		BIT(3)
+#define TRCCONFIGR_CCI		BIT(4)
+#define TRCCONFIGR_CID		BIT(6)
+#define TRCCONFIGR_VMID		BIT(7)
+#define TRCCONFIGR_TS		BIT(11)
+#define TRCCONFIGR_RS		BIT(12)
+#define TRCCONFIGR_VMIDOPT	BIT(15)
+
+/* ETMv3 ETMCR register bits */
+#define ETMCR_CYC_ACC		BIT(12)
+#define ETMCR_CTXTID		BIT(14)
+#define ETMCR_TIMESTAMP_EN	BIT(28)
+#define ETMCR_RETURN_STACK	BIT(29)
+
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
 void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr);

From e3741935a341983885aba1b09c6dfbc9e6ff5466 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 6 Mar 2026 14:08:35 +0000
Subject: [PATCH 1137/1303] perf cs-etm: Sync coresight-pmu.h header with the
 kernel sources

Update the header to pull in the changes from commit 3285c471d0c0b991
("coresight: Remove misleading definitions").

Signed-off-by: James Clark <james.clark@linaro.org>
Requested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/557db631-aef8-43b1-9f45-fae75910ccb4@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/coresight-pmu.h | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index 89b0ac0014b0..2e179abe472a 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -21,30 +21,6 @@
  */
 #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu)  (0x10 + (cpu * 2))
 
-/*
- * Below are the definition of bit offsets for perf option, and works as
- * arbitrary values for all ETM versions.
- *
- * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
- * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
- * directly use below macros as config bits.
- */
-#define ETM_OPT_BRANCH_BROADCAST 8
-#define ETM_OPT_CYCACC		12
-#define ETM_OPT_CTXTID		14
-#define ETM_OPT_CTXTID2		15
-#define ETM_OPT_TS		28
-#define ETM_OPT_RETSTK		29
-
-/* ETMv4 CONFIGR programming bits for the ETM OPTs */
-#define ETM4_CFG_BIT_BB         3
-#define ETM4_CFG_BIT_CYCACC	4
-#define ETM4_CFG_BIT_CTXTID	6
-#define ETM4_CFG_BIT_VMID	7
-#define ETM4_CFG_BIT_TS		11
-#define ETM4_CFG_BIT_RETSTK	12
-#define ETM4_CFG_BIT_VMID_OPT	15
-
 /*
  * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
  * Used to associate a CPU with the CoreSight Trace ID.

From b7cdc5a97d02c943f4bdde4d5767ad0c13cad92b Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 5 Mar 2026 13:01:44 +0100
Subject: [PATCH 1138/1303] netfilter: nf_tables: Fix for duplicate device in
 netdev hooks

When handling NETDEV_REGISTER notification, duplicate device
registration must be avoided since the device may have been added by
nft_netdev_hook_alloc() already when creating the hook.

Suggested-by: Florian Westphal <fw@strlen.de>
Reported-by: syzbot+bb9127e278fa198e110c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=bb9127e278fa198e110c
Fixes: a331b78a5525 ("netfilter: nf_tables: Respect NETDEV_REGISTER events")
Tested-by: Helen Koike <koike@igalia.com>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c    | 2 +-
 net/netfilter/nft_chain_filter.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1862bd7fe804..710f0ee21a34 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9688,7 +9688,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev,
 			break;
 		case NETDEV_REGISTER:
 			/* NOP if not matching or already registered */
-			if (!match || (changename && ops))
+			if (!match || ops)
 				continue;
 
 			ops = kzalloc_obj(struct nf_hook_ops,
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index b16185e9a6dd..041426e3bdbf 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -344,7 +344,7 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev,
 			break;
 		case NETDEV_REGISTER:
 			/* NOP if not matching or already registered */
-			if (!match || (changename && ops))
+			if (!match || ops)
 				continue;
 
 			ops = kmemdup(&basechain->ops,

From 7cb9a23d7ae40a702577d3d8bacb7026f04ac2a9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 5 Mar 2026 21:32:00 +0100
Subject: [PATCH 1139/1303] netfilter: nf_tables: always walk all pending
 catchall elements

During transaction processing we might have more than one catchall element:
1 live catchall element and 1 pending element that is coming as part of the
new batch.

If the map holding the catchall elements is also going away, its
required to toggle all catchall elements and not just the first viable
candidate.

Otherwise, we get:
 WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404
 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables]
 [..]
 __nft_set_elem_destroy+0x106/0x380 [nf_tables]
 nf_tables_abort_release+0x348/0x8d0 [nf_tables]
 nf_tables_abort+0xcf2/0x3ac0 [nf_tables]
 nfnetlink_rcv_batch+0x9c9/0x20e0 [..]

Fixes: 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 710f0ee21a34..dacec5f8a11c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -829,7 +829,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 
 		nft_set_elem_change_active(ctx->net, set, ext);
 		nft_setelem_data_deactivate(ctx->net, set, catchall->elem);
-		break;
 	}
 }
 
@@ -5873,7 +5872,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx,
 
 		nft_clear(ctx->net, ext);
 		nft_setelem_data_activate(ctx->net, set, catchall->elem);
-		break;
 	}
 }
 

From d6d8cd2db236a9dd13dbc2d05843b3445cc964b5 Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Fri, 6 Mar 2026 19:12:38 +0000
Subject: [PATCH 1140/1303] netfilter: nft_set_pipapo: fix stack out-of-bounds
 read in pipapo_drop()

pipapo_drop() passes rulemap[i + 1].n to pipapo_unmap() as the
to_offset argument on every iteration, including the last one where
i == m->field_count - 1. This reads one element past the end of the
stack-allocated rulemap array (declared as rulemap[NFT_PIPAPO_MAX_FIELDS]
with NFT_PIPAPO_MAX_FIELDS == 16).

Although pipapo_unmap() returns early when is_last is true without
using the to_offset value, the argument is evaluated at the call site
before the function body executes, making this a genuine out-of-bounds
stack read confirmed by KASAN:

  BUG: KASAN: stack-out-of-bounds in pipapo_drop+0x50c/0x57c [nf_tables]
  Read of size 4 at addr ffff8000810e71a4

  This frame has 1 object:
   [32, 160) 'rulemap'

  The buggy address is at offset 164 -- exactly 4 bytes past the end
  of the rulemap array.

Pass 0 instead of rulemap[i + 1].n on the last iteration to avoid
the out-of-bounds read.

Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_pipapo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index a34632ae6048..7fd24e0cc428 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1640,6 +1640,7 @@ static void pipapo_drop(struct nft_pipapo_match *m,
 	int i;
 
 	nft_pipapo_for_each_field(f, i, m) {
+		bool last = i == m->field_count - 1;
 		int g;
 
 		for (g = 0; g < f->groups; g++) {
@@ -1659,7 +1660,7 @@ static void pipapo_drop(struct nft_pipapo_match *m,
 		}
 
 		pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n,
-			     rulemap[i + 1].n, i == m->field_count - 1);
+			     last ? 0 : rulemap[i + 1].n, last);
 		if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) {
 			/* We can ignore this, a failure to shrink tables down
 			 * doesn't make tables invalid.

From cfe770220ac2dbd3e104c6b45094037455da81d4 Mon Sep 17 00:00:00 2001
From: David Dull <monderasdor@gmail.com>
Date: Sat, 7 Mar 2026 20:26:21 +0200
Subject: [PATCH 1141/1303] netfilter: x_tables: guard option walkers against
 1-byte tail reads

When the last byte of options is a non-single-byte option kind, walkers
that advance with i += op[i + 1] ? : 1 can read op[i + 1] past the end
of the option area.

Add an explicit i == optlen - 1 check before dereferencing op[i + 1]
in xt_tcpudp and xt_dccp option walkers.

Fixes: 2e4e6a17af35 ("[NETFILTER] x_tables: Abstraction layer for {ip,ip6,arp}_tables")
Signed-off-by: David Dull <monderasdor@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_dccp.c   | 4 ++--
 net/netfilter/xt_tcpudp.c | 6 ++++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c
index e5a13ecbe67a..037ab93e25d0 100644
--- a/net/netfilter/xt_dccp.c
+++ b/net/netfilter/xt_dccp.c
@@ -62,10 +62,10 @@ dccp_find_option(u_int8_t option,
 			return true;
 		}
 
-		if (op[i] < 2)
+		if (op[i] < 2 || i == optlen - 1)
 			i++;
 		else
-			i += op[i+1]?:1;
+			i += op[i + 1] ? : 1;
 	}
 
 	spin_unlock_bh(&dccp_buflock);
diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c
index e8991130a3de..f76cf18f1a24 100644
--- a/net/netfilter/xt_tcpudp.c
+++ b/net/netfilter/xt_tcpudp.c
@@ -59,8 +59,10 @@ tcp_find_option(u_int8_t option,
 
 	for (i = 0; i < optlen; ) {
 		if (op[i] == option) return !invert;
-		if (op[i] < 2) i++;
-		else i += op[i+1]?:1;
+		if (op[i] < 2 || i == optlen - 1)
+			i++;
+		else
+			i += op[i + 1] ? : 1;
 	}
 
 	return invert;

From f1ba83755d81c6fc66ac7acd723d238f974091e9 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Sun, 8 Mar 2026 02:24:06 +0900
Subject: [PATCH 1142/1303] netfilter: nfnetlink_queue: fix entry leak in
 bridge verdict error path

nfqnl_recv_verdict() calls find_dequeue_entry() to remove the queue
entry from the queue data structures, taking ownership of the entry.
For PF_BRIDGE packets, it then calls nfqa_parse_bridge() to parse VLAN
attributes.  If nfqa_parse_bridge() returns an error (e.g. NFQA_VLAN
present but NFQA_VLAN_TCI missing), the function returns immediately
without freeing the dequeued entry or its sk_buff.

This leaks the nf_queue_entry, its associated sk_buff, and all held
references (net_device refcounts, struct net refcount).  Repeated
triggering exhausts kernel memory.

Fix this by dropping the entry via nfqnl_reinject() with NF_DROP verdict
on the error path, consistent with other error handling in this file.

Fixes: 8d45ff22f1b4 ("netfilter: bridge: nf queue verdict to use NFQA_VLAN and NFQA_L2HDR")
Reviewed-by: David Dull <monderasdor@gmail.com>
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_queue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 7f5248b5f1ee..47f7f62906e2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1546,8 +1546,10 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 
 	if (entry->state.pf == PF_BRIDGE) {
 		err = nfqa_parse_bridge(entry, nfqa);
-		if (err < 0)
+		if (err < 0) {
+			nfqnl_reinject(entry, NF_DROP);
 			return err;
+		}
 	}
 
 	if (nfqa[NFQA_PAYLOAD]) {

From 6dcee8496d53165b2d8a5909b3050b62ae71fe89 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Sun, 8 Mar 2026 02:23:34 +0900
Subject: [PATCH 1143/1303] netfilter: nfnetlink_cthelper: fix OOB read in
 nfnl_cthelper_dump_table()

nfnl_cthelper_dump_table() has a 'goto restart' that jumps to a label
inside the for loop body.  When the "last" helper saved in cb->args[1]
is deleted between dump rounds, every entry fails the (cur != last)
check, so cb->args[1] is never cleared.  The for loop finishes with
cb->args[0] == nf_ct_helper_hsize, and the 'goto restart' jumps back
into the loop body bypassing the bounds check, causing an 8-byte
out-of-bounds read on nf_ct_helper_hash[nf_ct_helper_hsize].

The 'goto restart' block was meant to re-traverse the current bucket
when "last" is no longer found, but it was placed after the for loop
instead of inside it.  Move the block into the for loop body so that
the restart only occurs while cb->args[0] is still within bounds.

 BUG: KASAN: slab-out-of-bounds in nfnl_cthelper_dump_table+0x9f/0x1b0
 Read of size 8 at addr ffff888104ca3000 by task poc_cthelper/131
 Call Trace:
  nfnl_cthelper_dump_table+0x9f/0x1b0
  netlink_dump+0x333/0x880
  netlink_recvmsg+0x3e2/0x4b0
  sock_recvmsg+0xde/0xf0
  __sys_recvfrom+0x150/0x200
  __x64_sys_recvfrom+0x76/0x90
  do_syscall_64+0xc3/0x6e0

 Allocated by task 1:
  __kvmalloc_node_noprof+0x21b/0x700
  nf_ct_alloc_hashtable+0x65/0xd0
  nf_conntrack_helper_init+0x21/0x60
  nf_conntrack_init_start+0x18d/0x300
  nf_conntrack_standalone_init+0x12/0xc0

Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_cthelper.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index d658b1478fa0..d545fa459455 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -601,10 +601,10 @@ nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 				goto out;
 			}
 		}
-	}
-	if (cb->args[1]) {
-		cb->args[1] = 0;
-		goto restart;
+		if (cb->args[1]) {
+			cb->args[1] = 0;
+			goto restart;
+		}
 	}
 out:
 	rcu_read_unlock();

From 329f0b9b48ee6ab59d1ab72fef55fe8c6463a6cf Mon Sep 17 00:00:00 2001
From: Yuan Tan <tanyuan98@outlook.com>
Date: Mon, 9 Mar 2026 03:41:46 -0700
Subject: [PATCH 1144/1303] netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM
 timer labels

IDLETIMER revision 0 rules reuse existing timers by label and always call
mod_timer() on timer->timer.

If the label was created first by revision 1 with XT_IDLETIMER_ALARM,
the object uses alarm timer semantics and timer->timer is never initialized.
Reusing that object from revision 0 causes mod_timer() on an uninitialized
timer_list, triggering debugobjects warnings and possible panic when
panic_on_warn=1.

Fix this by rejecting revision 0 rule insertion when an existing timer with
the same label is of ALARM type.

Fixes: 68983a354a65 ("netfilter: xtables: Add snapshot of hardidletimer target")
Co-developed-by: Yifan Wu <yifanwucs@gmail.com>
Signed-off-by: Yifan Wu <yifanwucs@gmail.com>
Co-developed-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Xin Liu <dstsmallbird@foxmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_IDLETIMER.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 5d93e225d0f8..517106165ad2 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -318,6 +318,12 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 
 	info->timer = __idletimer_tg_find_by_label(info->label);
 	if (info->timer) {
+		if (info->timer->timer_type & XT_IDLETIMER_ALARM) {
+			pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n");
+			mutex_unlock(&list_mutex);
+			return -EINVAL;
+		}
+
 		info->timer->refcnt++;
 		mod_timer(&info->timer->timer,
 			  secs_to_jiffies(info->timeout) + jiffies);

From bf29cb3641b80bac759c3332b02e0b270e16bf94 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Fri, 6 Mar 2026 11:56:48 +0800
Subject: [PATCH 1145/1303] perf annotate: Fix hashmap__new() error checking

The hashmap__new() function never returns NULL, it returns error
pointers. Fix the error checking to match.

Additionally, set src->samples to NULL to prevent any later code from
accidentally using the error pointer.

Fixes: d3e7cad6f36d9e80 ("perf annotate: Add a hashmap for symbol histogram")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2e3522905046..63f0ee9d4c03 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -44,6 +44,7 @@
 #include "strbuf.h"
 #include <regex.h>
 #include <linux/bitops.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
@@ -137,8 +138,10 @@ static int annotated_source__alloc_histograms(struct annotated_source *src,
 		return -1;
 
 	src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL);
-	if (src->samples == NULL)
+	if (IS_ERR(src->samples)) {
 		zfree(&src->histograms);
+		src->samples = NULL;
+	}
 
 	return src->histograms ? 0 : -1;
 }

From 6ab3532b4c98f4e51969f0e5f3fc919c535f3ce1 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 9 Mar 2026 21:54:17 +0100
Subject: [PATCH 1146/1303] ACPI: video: Switch over to auxiliary bus type

Commit 02c057ddefef ("ACPI: video: Convert the driver to a platform one")
switched over the ACPI video bus driver from an ACPI driver to a platform
driver, but that change introduced an unwanted and unexpected side effect.
Namely, on some systems, the ACPI device object of the ACPI video bus
device is an ACPI companion of multiple platform devices and, after
adding video_device_ids[] as an acpi_match_table to the acpi_video_bus
platform driver, all of those devices started to match that driver and
its probe callback is invoked for all of them (it fails, but it leaves
a confusing message in the log).  Moreover, the MODULE_DEVICE_TABLE()
of the ACPI video driver module matches all of the devices sharing the
ACPI companion with the ACPI video bus device.

To address this, make the core ACPI device enumeration code create an
auxiliary device for the ACPI video bus device object instead of a
platform device and switch over the ACPI video bus driver (once more)
to an auxiliary driver.

Auxiliary driver generally is a better match for ACPI video bus than
platform driver, among other things because the ACPI video bus device
does not require any resources to be allocated for it during
enumeration.  It also allows the ACPI video bus driver to stop abusing
device matching based on ACPI device IDs and it allows a special case
to be dropped from acpi_create_platform_device() because that function
need not worry about the ACPI video bus device any more.

Fixes: 02c057ddefef ("ACPI: video: Convert the driver to a platform one")
Reported-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Closes: https://lore.kernel.org/linux-acpi/007e3390-6b2b-457e-83c7-c794c5952018@amd.com/
Tested-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
[ rjw: Added AUXILIARY_BUS selection to CONFIG_ACPI to fix build issue ]
[ rjw: Fixed error path in acpi_create_video_bus_device() ]
Link: https://patch.msgid.link/5986516.DvuYhMxLoT@rafael.j.wysocki
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Kconfig         |  1 +
 drivers/acpi/acpi_platform.c |  2 +-
 drivers/acpi/acpi_video.c    | 45 ++++++++++++++++++------------------
 drivers/acpi/scan.c          | 45 ++++++++++++++++++++++++++++++++++++
 4 files changed, 69 insertions(+), 24 deletions(-)

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index df0ff0764d0d..6f4b545f7377 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -9,6 +9,7 @@ config ARCH_SUPPORTS_ACPI
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
 	depends on ARCH_SUPPORTS_ACPI
+	select AUXILIARY_BUS
 	select PNP
 	select NLS
 	select CRC32
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 64199b19ceff..a09636a4168e 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -135,7 +135,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 		}
 	}
 
-	if (adev->device_type == ACPI_BUS_TYPE_DEVICE && !adev->pnp.type.backlight) {
+	if (adev->device_type == ACPI_BUS_TYPE_DEVICE) {
 		LIST_HEAD(resource_list);
 
 		count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 3fa28f1abca3..adbaf0226c90 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -9,6 +9,7 @@
 
 #define pr_fmt(fmt) "ACPI: video: " fmt
 
+#include <linux/auxiliary_bus.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -21,7 +22,6 @@
 #include <linux/sort.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/dmi.h>
 #include <linux/suspend.h>
@@ -77,8 +77,9 @@ static int register_count;
 static DEFINE_MUTEX(register_count_mutex);
 static DEFINE_MUTEX(video_list_lock);
 static LIST_HEAD(video_bus_head);
-static int acpi_video_bus_probe(struct platform_device *pdev);
-static void acpi_video_bus_remove(struct platform_device *pdev);
+static int acpi_video_bus_probe(struct auxiliary_device *aux_dev,
+				const struct auxiliary_device_id *id);
+static void acpi_video_bus_remove(struct auxiliary_device *aux);
 static void acpi_video_bus_notify(acpi_handle handle, u32 event, void *data);
 
 /*
@@ -93,19 +94,16 @@ enum acpi_video_level_idx {
 	ACPI_VIDEO_FIRST_LEVEL,		/* actual supported levels begin here */
 };
 
-static const struct acpi_device_id video_device_ids[] = {
-	{ACPI_VIDEO_HID, 0},
-	{"", 0},
+static const struct auxiliary_device_id video_bus_auxiliary_id_table[] = {
+	{ .name = "acpi.video_bus" },
+	{},
 };
-MODULE_DEVICE_TABLE(acpi, video_device_ids);
+MODULE_DEVICE_TABLE(auxiliary, video_bus_auxiliary_id_table);
 
-static struct platform_driver acpi_video_bus = {
+static struct auxiliary_driver acpi_video_bus = {
 	.probe = acpi_video_bus_probe,
 	.remove = acpi_video_bus_remove,
-	.driver = {
-		.name = "acpi-video",
-		.acpi_match_table = video_device_ids,
-	},
+	.id_table = video_bus_auxiliary_id_table,
 };
 
 struct acpi_video_bus_flags {
@@ -1885,7 +1883,7 @@ static void acpi_video_dev_add_notify_handler(struct acpi_video_device *device)
 }
 
 static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video,
-					     struct platform_device *pdev)
+					     struct device *parent)
 {
 	struct input_dev *input;
 	struct acpi_video_device *dev;
@@ -1908,7 +1906,7 @@ static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video,
 	input->phys = video->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
-	input->dev.parent = &pdev->dev;
+	input->dev.parent = parent;
 	input->evbit[0] = BIT(EV_KEY);
 	set_bit(KEY_SWITCHVIDEOMODE, input->keybit);
 	set_bit(KEY_VIDEO_NEXT, input->keybit);
@@ -1980,9 +1978,10 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video)
 
 static int instance;
 
-static int acpi_video_bus_probe(struct platform_device *pdev)
+static int acpi_video_bus_probe(struct auxiliary_device *aux_dev,
+				const struct auxiliary_device_id *id_unused)
 {
-	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+	struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev);
 	struct acpi_video_bus *video;
 	bool auto_detect;
 	int error;
@@ -2019,7 +2018,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev)
 		instance++;
 	}
 
-	platform_set_drvdata(pdev, video);
+	auxiliary_set_drvdata(aux_dev, video);
 
 	video->device = device;
 	strscpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
@@ -2068,7 +2067,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev)
 	    !auto_detect)
 		acpi_video_bus_register_backlight(video);
 
-	error = acpi_video_bus_add_notify_handler(video, pdev);
+	error = acpi_video_bus_add_notify_handler(video, &aux_dev->dev);
 	if (error)
 		goto err_del;
 
@@ -2096,10 +2095,10 @@ static int acpi_video_bus_probe(struct platform_device *pdev)
 	return error;
 }
 
-static void acpi_video_bus_remove(struct platform_device *pdev)
+static void acpi_video_bus_remove(struct auxiliary_device *aux_dev)
 {
-	struct acpi_video_bus *video = platform_get_drvdata(pdev);
-	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+	struct acpi_video_bus *video = auxiliary_get_drvdata(aux_dev);
+	struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev);
 
 	acpi_dev_remove_notify_handler(device, ACPI_DEVICE_NOTIFY,
 				       acpi_video_bus_notify);
@@ -2163,7 +2162,7 @@ int acpi_video_register(void)
 
 	dmi_check_system(video_dmi_table);
 
-	ret = platform_driver_register(&acpi_video_bus);
+	ret = auxiliary_driver_register(&acpi_video_bus);
 	if (ret)
 		goto leave;
 
@@ -2183,7 +2182,7 @@ void acpi_video_unregister(void)
 {
 	mutex_lock(&register_count_mutex);
 	if (register_count) {
-		platform_driver_unregister(&acpi_video_bus);
+		auxiliary_driver_unregister(&acpi_video_bus);
 		register_count = 0;
 		may_report_brightness_keys = false;
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index dfdd004fb1a9..e8cdbdb46fdb 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) "ACPI: " fmt
 
 #include <linux/async.h>
+#include <linux/auxiliary_bus.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -2192,6 +2193,44 @@ static acpi_status acpi_bus_check_add_2(acpi_handle handle, u32 lvl_not_used,
 	return acpi_bus_check_add(handle, false, (struct acpi_device **)ret_p);
 }
 
+static void acpi_video_bus_device_release(struct device *dev)
+{
+	struct auxiliary_device *aux_dev = to_auxiliary_dev(dev);
+
+	kfree(aux_dev);
+}
+
+static void acpi_create_video_bus_device(struct acpi_device *adev,
+					 struct acpi_device *parent)
+{
+	struct auxiliary_device *aux_dev;
+	static unsigned int aux_dev_id;
+
+	aux_dev = kzalloc_obj(*aux_dev);
+	if (!aux_dev)
+		return;
+
+	aux_dev->id = aux_dev_id++;
+	aux_dev->name = "video_bus";
+	aux_dev->dev.parent = acpi_get_first_physical_node(parent);
+	if (!aux_dev->dev.parent)
+		goto err;
+
+	aux_dev->dev.release = acpi_video_bus_device_release;
+
+	if (auxiliary_device_init(aux_dev))
+		goto err;
+
+	ACPI_COMPANION_SET(&aux_dev->dev, adev);
+	if (__auxiliary_device_add(aux_dev, "acpi"))
+		auxiliary_device_uninit(aux_dev);
+
+	return;
+
+err:
+	kfree(aux_dev);
+}
+
 struct acpi_scan_system_dev {
 	struct list_head node;
 	struct acpi_device *adev;
@@ -2229,6 +2268,12 @@ static void acpi_default_enumeration(struct acpi_device *device)
 			sd->adev = device;
 			list_add_tail(&sd->node, &acpi_scan_system_dev_list);
 		}
+	} else if (device->pnp.type.backlight) {
+		struct acpi_device *parent;
+
+		parent = acpi_dev_parent(device);
+		if (parent)
+			acpi_create_video_bus_device(device, parent);
 	} else {
 		/* For a regular device object, create a platform device. */
 		acpi_create_platform_device(device, NULL);

From e53c0e99fd93da200c413deb57875f9f5fdb314a Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sat, 7 Mar 2026 09:50:35 +0000
Subject: [PATCH 1147/1303] spi: cadence-qspi: Fix requesting of APB and AHB
 clocks on JH7110

The move of the AHB and APB clocks from a JH7110 specific quirk to the
main clock init dropped the specification of the clock names to request
for the AHB and APB clocks, resulting in the clock framework requesting
a clock with a NULL name three times.  On most platforms where the
clocks are physically the same or some are always on this makes no
difference but the reason we had the specific quirk for JH7110 is that
it does actually have separate, controllable clocks.  Update the new
code to request the AHB and APB clocks by name to restore the original
behaviour on JH7110.

Fixes: 324ecc7788c2 ("spi: cadence-qspi: Kill cqspi_jh7110_clk_init")
Reported-by: Ron Economos <re@w6rz.net>
Closes: https://lore.kernel.org/r/a3ca5e9b-7446-497e-8df2-7ef2b42a02e9@w6rz.net
Tested-by: Ron Economos <re@w6rz.net>
Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org
---
 drivers/spi/spi-cadence-quadspi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 649ff55333f0..5fb0cb07c110 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -76,6 +76,11 @@ struct cqspi_flash_pdata {
 	u8		cs;
 };
 
+static const struct clk_bulk_data cqspi_clks[CLK_QSPI_NUM] = {
+	[CLK_QSPI_APB] = { .id = "apb" },
+	[CLK_QSPI_AHB] = { .id = "ahb" },
+};
+
 struct cqspi_st {
 	struct platform_device	*pdev;
 	struct spi_controller	*host;
@@ -1823,6 +1828,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	}
 
 	/* Obtain QSPI clocks. */
+	memcpy(&cqspi->clks, &cqspi_clks, sizeof(cqspi->clks));
 	ret = devm_clk_bulk_get_optional(dev, CLK_QSPI_NUM, cqspi->clks);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to get clocks\n");

From 5d0efaf47ee90ac60efae790acee3a3ed99ebf80 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Tue, 10 Mar 2026 12:25:52 +0800
Subject: [PATCH 1148/1303] regulator: pca9450: Correct interrupt type

Kernel warning on i.MX8MP-EVK when doing module test:
irq: type mismatch, failed to map hwirq-3 for gpio@30200000!

Per PCA945[X] specification: The IRQ_B pin is pulled low when any unmasked
interrupt bit status is changed and it is released high once application
processor read INT1 register.

So the interrupt should be configured as IRQF_TRIGGER_LOW, not
IRQF_TRIGGER_FALLING.

Fixes: 0935ff5f1f0a4 ("regulator: pca9450: add pca9450 pmic driver")
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20260310-pca9450-irq-v1-1-36adf52c2c55@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 5fa868264250..2205f6de37e7 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -1369,7 +1369,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	if (pca9450->irq) {
 		ret = devm_request_threaded_irq(pca9450->dev, pca9450->irq, NULL,
 						pca9450_irq_handler,
-						(IRQF_TRIGGER_FALLING | IRQF_ONESHOT),
+						(IRQF_TRIGGER_LOW | IRQF_ONESHOT),
 						"pca9450-irq", pca9450);
 		if (ret != 0)
 			return dev_err_probe(pca9450->dev, ret, "Failed to request IRQ: %d\n",

From 21b3fb7dc19caa488d285e3c47999f7f1a179334 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Tue, 10 Mar 2026 12:25:53 +0800
Subject: [PATCH 1149/1303] regulator: pca9450: Correct probed name for PCA9452

An incorrect device name was logged for PCA9452 because the dev_info()
ternary omitted PCA9452 and fell through to "pca9450bc". Introduce a
type_name and set it per device type so the probed message matches the
actual PMIC. While here, make the PCA9451A case explicit.

No functional changes.

Fixes: 017b76fb8e5b6 ("regulator: pca9450: Add PMIC pca9452 support")
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20260310-pca9450-irq-v1-2-36adf52c2c55@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 2205f6de37e7..45d7dc44c2cd 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -1293,6 +1293,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	struct regulator_dev *ldo5;
 	struct pca9450 *pca9450;
 	unsigned int device_id, i;
+	const char *type_name;
 	int ret;
 
 	pca9450 = devm_kzalloc(&i2c->dev, sizeof(struct pca9450), GFP_KERNEL);
@@ -1303,15 +1304,22 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	case PCA9450_TYPE_PCA9450A:
 		regulator_desc = pca9450a_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9450a_regulators);
+		type_name = "pca9450a";
 		break;
 	case PCA9450_TYPE_PCA9450BC:
 		regulator_desc = pca9450bc_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators);
+		type_name = "pca9450bc";
 		break;
 	case PCA9450_TYPE_PCA9451A:
+		regulator_desc = pca9451a_regulators;
+		pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators);
+		type_name = "pca9451a";
+		break;
 	case PCA9450_TYPE_PCA9452:
 		regulator_desc = pca9451a_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators);
+		type_name = "pca9452";
 		break;
 	default:
 		dev_err(&i2c->dev, "Unknown device type");
@@ -1413,9 +1421,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 					  pca9450_i2c_restart_handler, pca9450))
 		dev_warn(&i2c->dev, "Failed to register restart handler\n");
 
-	dev_info(&i2c->dev, "%s probed.\n",
-		type == PCA9450_TYPE_PCA9450A ? "pca9450a" :
-		(type == PCA9450_TYPE_PCA9451A ? "pca9451a" : "pca9450bc"));
+	dev_info(&i2c->dev, "%s probed.\n", type_name);
 
 	return 0;
 }

From be34705aa527872e5ce83927b7bc9307ba8095ca Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Fri, 6 Mar 2026 12:10:52 +0800
Subject: [PATCH 1150/1303] perf ftrace: Fix hashmap__new() error checking

The hashmap__new() function never returns NULL, it returns error
pointers. Fix the error checking to match.

Additionally, set ftrace->profile_hash to NULL on error, and return the
exact error code from hashmap__new().

Fixes: 0f223813edd051a5 ("perf ftrace: Add 'profile' command")
Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-ftrace.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 6b6eec65f93f..4cc33452d79b 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -18,6 +18,7 @@
 #include <poll.h>
 #include <ctype.h>
 #include <linux/capability.h>
+#include <linux/err.h>
 #include <linux/string.h>
 #include <sys/stat.h>
 
@@ -1209,8 +1210,12 @@ static int prepare_func_profile(struct perf_ftrace *ftrace)
 	ftrace->graph_verbose = 0;
 
 	ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL);
-	if (ftrace->profile_hash == NULL)
-		return -ENOMEM;
+	if (IS_ERR(ftrace->profile_hash)) {
+		int err = PTR_ERR(ftrace->profile_hash);
+
+		ftrace->profile_hash = NULL;
+		return err;
+	}
 
 	return 0;
 }

From 40e9cd4ae8ec43b107ed2bff422a8fa39dcf4e4b Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Tue, 10 Mar 2026 15:23:29 +0100
Subject: [PATCH 1151/1303] s390/dasd: Move quiesce state with pprc swap

Quiesce and resume is a mechanism to suspend operations on DASD devices.
In the context of a controlled copy pair swap operation, the quiesce
operation is usually issued before the actual swap and a resume
afterwards.

During the swap operation, the underlying device is exchanged. Therefore,
the quiesce flag must be moved to the secondary device to ensure a
consistent quiesce state after the swap.

The secondary device itself cannot be suspended separately because there
is no separate block device representation for it.

Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability")
Cc: stable@vger.kernel.org #6.1
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Link: https://patch.msgid.link/20260310142330.4080106-2-sth@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index b08e900687f3..e8f0e302a625 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -6182,6 +6182,11 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 			dev_name(&secondary->cdev->dev), rc);
 	}
 
+	if (primary->stopped & DASD_STOPPED_QUIESCE) {
+		dasd_device_set_stop_bits(secondary, DASD_STOPPED_QUIESCE);
+		dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE);
+	}
+
 	/* re-enable device */
 	dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC);
 	dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC);

From 4c527c7e030672efd788d0806d7a68972a7ba3c1 Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Tue, 10 Mar 2026 15:23:30 +0100
Subject: [PATCH 1152/1303] s390/dasd: Copy detected format information to
 secondary device

During online processing for a DASD device an IO operation is started to
determine the format of the device. CDL format contains specifically
sized blocks at the beginning of the disk.

For a PPRC secondary device no real IO operation is possible therefore
this IO request can not be started and this step is skipped for online
processing of secondary devices. This is generally fine since the
secondary is a copy of the primary device.

In case of an additional partition detection that is run after a swap
operation the format information is needed to properly drive partition
detection IO.

Currently the information is not passed leading to IO errors during
partition detection and a wrongly detected partition table which in turn
might lead to data corruption on the disk with the wrong partition table.

Fix by passing the format information from primary to secondary device.

Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability")
Cc: stable@vger.kernel.org #6.1
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Acked-by: Eduard Shishkin <edward6@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Link: https://patch.msgid.link/20260310142330.4080106-3-sth@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index e8f0e302a625..c0f665a2929d 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -6135,6 +6135,7 @@ static void copy_pair_set_active(struct dasd_copy_relation *copy, char *new_busi
 static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid,
 				    char *sec_busid)
 {
+	struct dasd_eckd_private *prim_priv, *sec_priv;
 	struct dasd_device *primary, *secondary;
 	struct dasd_copy_relation *copy;
 	struct dasd_block *block;
@@ -6155,6 +6156,9 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 	if (!secondary)
 		return DASD_COPYPAIRSWAP_SECONDARY;
 
+	prim_priv = primary->private;
+	sec_priv = secondary->private;
+
 	/*
 	 * usually the device should be quiesced for swap
 	 * for paranoia stop device and requeue requests again
@@ -6187,6 +6191,13 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 		dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE);
 	}
 
+	/*
+	 * The secondary device never got through format detection, but since it
+	 * is a copy of the primary device, the format is exactly the same;
+	 * therefore, the detected layout can simply be copied.
+	 */
+	sec_priv->uses_cdl = prim_priv->uses_cdl;
+
 	/* re-enable device */
 	dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC);
 	dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC);

From d557640e4ce589a24dca5ca7ce3b9680f471325f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sat, 7 Mar 2026 17:12:05 +0100
Subject: [PATCH 1153/1303] sched: idle: Make skipping governor callbacks more
 consistent

If the cpuidle governor .select() callback is skipped because there
is only one idle state in the cpuidle driver, the .reflect() callback
should be skipped as well, at least for consistency (if not for
correctness), so do it.

Fixes: e5c9ffc6ae1b ("cpuidle: Skip governor when only one idle state is available")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Reviewed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://patch.msgid.link/12857700.O9o76ZdvQC@rafael.j.wysocki
---
 drivers/cpuidle/cpuidle.c | 10 ----------
 kernel/sched/idle.c       | 11 ++++++++++-
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 65fbb8e807b9..c7876e9e024f 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -359,16 +359,6 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		   bool *stop_tick)
 {
-	/*
-	 * If there is only a single idle state (or none), there is nothing
-	 * meaningful for the governor to choose. Skip the governor and
-	 * always use state 0 with the tick running.
-	 */
-	if (drv->state_count <= 1) {
-		*stop_tick = false;
-		return 0;
-	}
-
 	return cpuidle_curr_governor->select(drv, dev, stop_tick);
 }
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 3681b6ad9276..b95449165122 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -221,7 +221,7 @@ static void cpuidle_idle_call(void)
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
-	} else {
+	} else if (drv->state_count > 1) {
 		bool stop_tick = true;
 
 		/*
@@ -239,6 +239,15 @@ static void cpuidle_idle_call(void)
 		 * Give the governor an opportunity to reflect on the outcome
 		 */
 		cpuidle_reflect(dev, entered_state);
+	} else {
+		tick_nohz_idle_retain_tick();
+
+		/*
+		 * If there is only a single idle state (or none), there is
+		 * nothing meaningful for the governor to choose.  Skip the
+		 * governor and always use state 0.
+		 */
+		call_cpuidle(drv, dev, 0);
 	}
 
 exit_idle:

From c7c92f76f90a81dcc5c48cefa3343556501870b9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Mar 2026 10:53:06 -0800
Subject: [PATCH 1154/1303] perf annotate loongarch: Fix off-by-one bug in
 outside check

A copy-paste of a similar issue fixed by Peter Collingbourne in:
https://lore.kernel.org/linux-perf-users/20260304190613.2507582-1-pcc@google.com/

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-arch/annotate-loongarch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c
index 3aeab453a059..950f34e59e5c 100644
--- a/tools/perf/util/annotate-arch/annotate-loongarch.c
+++ b/tools/perf/util/annotate-arch/annotate-loongarch.c
@@ -93,7 +93,7 @@ static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *o
 	start = map__unmap_ip(map, sym->start);
 	end = map__unmap_ip(map, sym->end);
 
-	ops->target.outside = target.addr < start || target.addr > end;
+	ops->target.outside = target.addr < start || target.addr >= end;
 
 	if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
 	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)

From 52a8a1ba883defbfe3200baa22cf4cd21985d51a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 4 Mar 2026 20:26:20 -0800
Subject: [PATCH 1155/1303] xfs: fix undersized l_iclog_roundoff values

If the superblock doesn't list a log stripe unit, we set the incore log
roundoff value to 512.  This leads to corrupt logs and unmountable
filesystems in generic/617 on a disk with 4k physical sectors...

XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c
XFS (sda1): Torn write (CRC failure) detected at log block 0x318e. Truncating head block from 0x3197.
XFS (sda1): failed to locate log tail
XFS (sda1): log mount/recovery failed: error -74
XFS (sda1): log mount failed
XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c
XFS (sda1): Ending clean mount

...on the current xfsprogs for-next which has a broken mkfs.  xfs_info
shows this...

meta-data=/dev/sda1              isize=512    agcount=4, agsize=644992 blks
         =                       sectsz=4096  attr=2, projid32bit=1
         =                       crc=1        finobt=1, sparse=1, rmapbt=1
         =                       reflink=1    bigtime=1 inobtcount=1 nrext64=1
         =                       exchange=1   metadir=1
data     =                       bsize=4096   blocks=2579968, imaxpct=25
         =                       sunit=0      swidth=0 blks
naming   =version 2              bsize=4096   ascii-ci=0, ftype=1, parent=1
log      =internal log           bsize=4096   blocks=16384, version=2
         =                       sectsz=4096  sunit=0 blks, lazy-count=1
realtime =none                   extsz=4096   blocks=0, rtextents=0
         =                       rgcount=0    rgsize=268435456 extents
         =                       zoned=0      start=0 reserved=0

...observe that the log section has sectsz=4096 sunit=0, which means
that the roundoff factor is 512, not 4096 as you'd expect.  We should
fix mkfs not to generate broken filesystems, but anyone can fuzz the
ondisk superblock so we should be more cautious.  I think the inadequate
logic predates commit a6a65fef5ef8d0, but that's clearly going to
require a different backport.

Cc: stable@vger.kernel.org # v5.14
Fixes: a6a65fef5ef8d0 ("xfs: log stripe roundoff is a property of the log")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_log.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index b96f262ba139..f807f8f4f705 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1357,6 +1357,8 @@ xlog_alloc_log(
 
 	if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1)
 		log->l_iclog_roundoff = mp->m_sb.sb_logsunit;
+	else if (mp->m_sb.sb_logsectsize > 0)
+		log->l_iclog_roundoff = mp->m_sb.sb_logsectsize;
 	else
 		log->l_iclog_roundoff = BBSIZE;
 

From b4e78f1427c7d6859229ae9616df54e1fc05a516 Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Sun, 8 Mar 2026 14:20:59 -0400
Subject: [PATCH 1156/1303] nvme-pci: Fix slab-out-of-bounds in nvme_dbbuf_set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dev->online_queues is a count incremented in nvme_init_queue. Thus,
valid indices are 0 through dev->online_queues − 1.

This patch fixes the loop condition to ensure the index stays within the
valid range. Index 0 is excluded because it is the admin queue.

KASAN splat:

==================================================================
BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline]
BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404
Read of size 2 at addr ffff88800592a574 by task kworker/u8:5/74

CPU: 0 UID: 0 PID: 74 Comm: kworker/u8:5 Not tainted 6.19.0-dirty #10 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
Workqueue: nvme-reset-wq nvme_reset_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0xea/0x150 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xce/0x5d0 mm/kasan/report.c:482
 kasan_report+0xdc/0x110 mm/kasan/report.c:595
 __asan_report_load2_noabort+0x18/0x20 mm/kasan/report_generic.c:379
 nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline]
 nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404
 nvme_reset_work+0x36b/0x8c0 drivers/nvme/host/pci.c:3252
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246
 </TASK>

Allocated by task 34 on cpu 1 at 4.241550s:
 kasan_save_stack+0x2c/0x60 mm/kasan/common.c:57
 kasan_save_track+0x1c/0x70 mm/kasan/common.c:78
 kasan_save_alloc_info+0x3c/0x50 mm/kasan/generic.c:570
 poison_kmalloc_redzone mm/kasan/common.c:398 [inline]
 __kasan_kmalloc+0xb5/0xc0 mm/kasan/common.c:415
 kasan_kmalloc include/linux/kasan.h:263 [inline]
 __do_kmalloc_node mm/slub.c:5657 [inline]
 __kmalloc_node_noprof+0x2bf/0x8d0 mm/slub.c:5663
 kmalloc_array_node_noprof include/linux/slab.h:1075 [inline]
 nvme_pci_alloc_dev drivers/nvme/host/pci.c:3479 [inline]
 nvme_probe+0x2f1/0x1820 drivers/nvme/host/pci.c:3534
 local_pci_probe+0xef/0x1c0 drivers/pci/pci-driver.c:324
 pci_call_probe drivers/pci/pci-driver.c:392 [inline]
 __pci_device_probe drivers/pci/pci-driver.c:417 [inline]
 pci_device_probe+0x743/0x920 drivers/pci/pci-driver.c:451
 call_driver_probe drivers/base/dd.c:583 [inline]
 really_probe+0x29b/0xb70 drivers/base/dd.c:661
 __driver_probe_device+0x3b0/0x4a0 drivers/base/dd.c:803
 driver_probe_device+0x56/0x1f0 drivers/base/dd.c:833
 __driver_attach_async_helper+0x155/0x340 drivers/base/dd.c:1159
 async_run_entry_fn+0xa6/0x4b0 kernel/async.c:129
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246

The buggy address belongs to the object at ffff88800592a000
 which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 244 bytes to the right of
 allocated 1152-byte region [ffff88800592a000, ffff88800592a480)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5928
head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
anon flags: 0xfffffc0000040(head|node=0|zone=1|lastcpupid=0x1fffff)
page_type: f5(slab)
raw: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001
raw: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000
head: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001
head: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000
head: 000fffffc0000003 ffffea0000164a01 00000000ffffffff 00000000ffffffff
head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88800592a400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88800592a480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88800592a500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                                                             ^
 ffff88800592a580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88800592a600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Fixes: 0f0d2c876c96 (nvme: free sq/cq dbbuf pointers when dbbuf set fails)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9a7863e2001e..d90db12c7cd8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -544,7 +544,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev)
 		/* Free memory and continue on */
 		nvme_dbbuf_dma_free(dev);
 
-		for (i = 1; i <= dev->online_queues; i++)
+		for (i = 1; i < dev->online_queues; i++)
 			nvme_dbbuf_free(&dev->queues[i]);
 	}
 }

From 2922e3507f6d5caa7f1d07f145e186fc6f317a4e Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Wed, 25 Feb 2026 20:30:03 -0800
Subject: [PATCH 1157/1303] nvmet: move async event work off nvmet-wq

For target nvmet_ctrl_free() flushes ctrl->async_event_work.
If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue
completion for the same worker:-

A. Async event work queued on nvmet-wq (prior to disconnect):
  nvmet_execute_async_event()
     queue_work(nvmet_wq, &ctrl->async_event_work)

  nvmet_add_async_event()
     queue_work(nvmet_wq, &ctrl->async_event_work)

B. Full pre-work chain (RDMA CM path):
  nvmet_rdma_cm_handler()
     nvmet_rdma_queue_disconnect()
       __nvmet_rdma_queue_disconnect()
         queue_work(nvmet_wq, &queue->release_work)
           process_one_work()
             lock((wq_completion)nvmet-wq)  <--------- 1st
             nvmet_rdma_release_queue_work()

C. Recursive path (same worker):
  nvmet_rdma_release_queue_work()
     nvmet_rdma_free_queue()
       nvmet_sq_destroy()
         nvmet_ctrl_put()
           nvmet_ctrl_free()
             flush_work(&ctrl->async_event_work)
               __flush_work()
                 touch_wq_lockdep_map()
                 lock((wq_completion)nvmet-wq) <--------- 2nd

Lockdep splat:

  ============================================
  WARNING: possible recursive locking detected
  6.19.0-rc3nvme+ #14 Tainted: G                 N
  --------------------------------------------
  kworker/u192:42/44933 is trying to acquire lock:
  ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90

  but task is already holding lock:
  ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660

  3 locks held by kworker/u192:42/44933:
   #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660
   #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660
   #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530

  Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma]
  Call Trace:
   __flush_work+0x268/0x530
   nvmet_ctrl_free+0x140/0x310 [nvmet]
   nvmet_cq_put+0x74/0x90 [nvmet]
   nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma]
   nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma]
   process_one_work+0x206/0x660
   worker_thread+0x184/0x320
   kthread+0x10c/0x240
   ret_from_fork+0x319/0x390

Move async event work to a dedicated nvmet-aen-wq to avoid reentrant
flush on nvmet-wq.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/admin-cmd.c |  2 +-
 drivers/nvme/target/core.c      | 14 ++++++++++++--
 drivers/nvme/target/nvmet.h     |  1 +
 drivers/nvme/target/rdma.c      |  1 +
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 5e366502fb75..66fc8d2a7fe3 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1586,7 +1586,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
 	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
 	mutex_unlock(&ctrl->lock);
 
-	queue_work(nvmet_wq, &ctrl->async_event_work);
+	queue_work(nvmet_aen_wq, &ctrl->async_event_work);
 }
 
 void nvmet_execute_keep_alive(struct nvmet_req *req)
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index eab3e4fc0f74..a25ac4bf9972 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -27,6 +27,8 @@ static DEFINE_IDA(cntlid_ida);
 
 struct workqueue_struct *nvmet_wq;
 EXPORT_SYMBOL_GPL(nvmet_wq);
+struct workqueue_struct *nvmet_aen_wq;
+EXPORT_SYMBOL_GPL(nvmet_aen_wq);
 
 /*
  * This read/write semaphore is used to synchronize access to configuration
@@ -206,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	list_add_tail(&aen->entry, &ctrl->async_events);
 	mutex_unlock(&ctrl->lock);
 
-	queue_work(nvmet_wq, &ctrl->async_event_work);
+	queue_work(nvmet_aen_wq, &ctrl->async_event_work);
 }
 
 static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
@@ -1959,9 +1961,14 @@ static int __init nvmet_init(void)
 	if (!nvmet_wq)
 		goto out_free_buffered_work_queue;
 
+	nvmet_aen_wq = alloc_workqueue("nvmet-aen-wq",
+			WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+	if (!nvmet_aen_wq)
+		goto out_free_nvmet_work_queue;
+
 	error = nvmet_init_debugfs();
 	if (error)
-		goto out_free_nvmet_work_queue;
+		goto out_free_nvmet_aen_work_queue;
 
 	error = nvmet_init_discovery();
 	if (error)
@@ -1977,6 +1984,8 @@ static int __init nvmet_init(void)
 	nvmet_exit_discovery();
 out_exit_debugfs:
 	nvmet_exit_debugfs();
+out_free_nvmet_aen_work_queue:
+	destroy_workqueue(nvmet_aen_wq);
 out_free_nvmet_work_queue:
 	destroy_workqueue(nvmet_wq);
 out_free_buffered_work_queue:
@@ -1994,6 +2003,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_discovery();
 	nvmet_exit_debugfs();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(nvmet_aen_wq);
 	destroy_workqueue(nvmet_wq);
 	destroy_workqueue(buffered_io_wq);
 	destroy_workqueue(zbd_wq);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index b664b584fdc8..319d6a5e9cf0 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -501,6 +501,7 @@ extern struct kmem_cache *nvmet_bvec_cache;
 extern struct workqueue_struct *buffered_io_wq;
 extern struct workqueue_struct *zbd_wq;
 extern struct workqueue_struct *nvmet_wq;
+extern struct workqueue_struct *nvmet_aen_wq;
 
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 9c12b2361a6d..038432364967 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -2088,6 +2088,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
 	flush_workqueue(nvmet_wq);
+	flush_workqueue(nvmet_aen_wq);
 }
 
 static struct ib_client nvmet_rdma_ib_client = {

From fc71f409b22ca831a9f87a2712eaa09ef2bb4a5e Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Sat, 7 Mar 2026 14:46:36 -0500
Subject: [PATCH 1158/1303] nvme-pci: Fix race bug in nvme_poll_irqdisable()

In the following scenario, pdev can be disabled between (1) and (3) by
(2). This sets pdev->msix_enabled = 0. Then, pci_irq_vector() will
return MSI-X IRQ(>15) for (1) whereas return INTx IRQ(<=15) for (2).
This causes IRQ warning because it tries to enable INTx IRQ that has
never been disabled before.

To fix this, save IRQ number into a local variable and ensure
disable_irq() and enable_irq() operate on the same IRQ number.  Even if
pci_free_irq_vectors() frees the IRQ concurrently, disable_irq() and
enable_irq() on a stale IRQ number is still valid and safe, and the
depth accounting reamins balanced.

task 1:
nvme_poll_irqdisable()
  disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(1)
  enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector))  ...(3)

task 2:
nvme_reset_work()
  nvme_dev_disable()
    pdev->msix_enable = 0;  ...(2)

crash log:

------------[ cut here ]------------
Unbalanced enable for IRQ 10
WARNING: kernel/irq/manage.c:753 at __enable_irq+0x102/0x190 kernel/irq/manage.c:753, CPU#1: kworker/1:0H/26
Modules linked in:
CPU: 1 UID: 0 PID: 26 Comm: kworker/1:0H Not tainted 6.19.0-dirty #9 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
Workqueue: kblockd blk_mq_timeout_work
RIP: 0010:__enable_irq+0x107/0x190 kernel/irq/manage.c:753
Code: ff df 48 89 fa 48 c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 79 48 8d 3d 2e 7a 3f 05 41 8b 74 24 2c <67> 48 0f b9 3a e8 ef b9 21 00 5b 41 5c 5d e9 46 54 66 03 e8 e1 b9
RSP: 0018:ffffc900001bf550 EFLAGS: 00010046
RAX: 0000000000000007 RBX: 0000000000000000 RCX: ffffffffb20c0e90
RDX: 0000000000000000 RSI: 000000000000000a RDI: ffffffffb74b88f0
RBP: ffffc900001bf560 R08: ffff88800197cf00 R09: 0000000000000001
R10: 0000000000000003 R11: 0000000000000003 R12: ffff8880012a6000
R13: 1ffff92000037eae R14: 000000000000000a R15: 0000000000000293
FS:  0000000000000000(0000) GS:ffff8880b49f7000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000555da4a25fa8 CR3: 00000000208e8000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 enable_irq+0x121/0x1e0 kernel/irq/manage.c:797
 nvme_poll_irqdisable+0x162/0x1c0 drivers/nvme/host/pci.c:1494
 nvme_timeout+0x965/0x14b0 drivers/nvme/host/pci.c:1744
 blk_mq_rq_timed_out block/blk-mq.c:1653 [inline]
 blk_mq_handle_expired+0x227/0x2d0 block/blk-mq.c:1721
 bt_iter+0x2fc/0x3a0 block/blk-mq-tag.c:292
 __sbitmap_for_each_set include/linux/sbitmap.h:269 [inline]
 sbitmap_for_each_set include/linux/sbitmap.h:290 [inline]
 bt_for_each block/blk-mq-tag.c:324 [inline]
 blk_mq_queue_tag_busy_iter+0x969/0x1e80 block/blk-mq-tag.c:536
 blk_mq_timeout_work+0x627/0x870 block/blk-mq.c:1763
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246
 </TASK>
irq event stamp: 74478
hardirqs last  enabled at (74477): [<ffffffffb5720a9c>] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:159 [inline]
hardirqs last  enabled at (74477): [<ffffffffb5720a9c>] _raw_spin_unlock_irq+0x2c/0x60 kernel/locking/spinlock.c:202
hardirqs last disabled at (74478): [<ffffffffb57207b5>] __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (74478): [<ffffffffb57207b5>] _raw_spin_lock_irqsave+0x85/0xa0 kernel/locking/spinlock.c:162
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723
softirqs last disabled at (74287): [<ffffffffb1e9466c>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last disabled at (74287): [<ffffffffb1e9466c>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last disabled at (74287): [<ffffffffb1e9466c>] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723
---[ end trace 0000000000000000 ]---

Fixes: fa059b856a59 (nvme-pci: Simplify nvme_poll_irqdisable)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d90db12c7cd8..93eb9f1cf9c1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1625,14 +1625,16 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 {
 	struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
+	int irq;
 
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
-	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	irq = pci_irq_vector(pdev, nvmeq->cq_vector);
+	disable_irq(irq);
 	spin_lock(&nvmeq->cq_poll_lock);
 	nvme_poll_cq(nvmeq, NULL);
 	spin_unlock(&nvmeq->cq_poll_lock);
-	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	enable_irq(irq);
 }
 
 static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)

From 0375c81eb2256366cd9602441d48b8b937e79635 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 20 Feb 2026 14:30:16 +0100
Subject: [PATCH 1159/1303] nvme-core: do not pass empty queue_limits to
 blk_mq_alloc_queue()

In nvme_alloc_admin_tag_set(), an empty queue_limits struct is
currently allocated on the stack and passed by reference to
blk_mq_alloc_queue().

This is redundant because blk_mq_alloc_queue() already handles
a NULL limits pointer by internally substituting it with a default
empty queue_limits struct.
Remove the unnecessary local variable and pass a NULL value.

Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3bc0b9ea00ce..6370aa35cc06 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4834,7 +4834,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		const struct blk_mq_ops *ops, unsigned int cmd_size)
 {
-	struct queue_limits lim = {};
 	int ret;
 
 	memset(set, 0, sizeof(*set));
@@ -4861,7 +4860,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ctrl->admin_q)
 		blk_put_queue(ctrl->admin_q);
 
-	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
+	ctrl->admin_q = blk_mq_alloc_queue(set, NULL, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
 		goto out_free_tagset;

From fa655a9ca73f7df32b8ca4d14ce11742f9578288 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 22:31:01 +0100
Subject: [PATCH 1160/1303] nvme: Annotate struct nvme_dhchap_key with
 __counted_by

Add the __counted_by() compiler attribute to the flexible array member
'key' to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and
CONFIG_FORTIFY_SOURCE.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme-auth.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h
index 60e069a6757f..e75c29c51464 100644
--- a/include/linux/nvme-auth.h
+++ b/include/linux/nvme-auth.h
@@ -11,7 +11,7 @@
 struct nvme_dhchap_key {
 	size_t len;
 	u8 hash;
-	u8 key[];
+	u8 key[] __counted_by(len);
 };
 
 u32 nvme_auth_get_seqnum(void);

From bd98c6204d1195973b1760fe45860863deb6200c Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Fri, 13 Feb 2026 10:48:41 +0200
Subject: [PATCH 1161/1303] drivers: net: ice: fix devlink parameters get
 without irdma

If CONFIG_IRDMA isn't enabled but there are ice NICs in the system, the
driver will prevent full devlink dev param show dump because its rdma get
callbacks return ENODEV and stop the dump. For example:
 $ devlink dev param show
 pci/0000:82:00.0:
   name msix_vec_per_pf_max type generic
     values:
       cmode driverinit value 2
   name msix_vec_per_pf_min type generic
     values:
       cmode driverinit value 2
 kernel answers: No such device

Returning EOPNOTSUPP allows the dump to continue so we can see all devices'
devlink parameters.

Fixes: c24a65b6a27c ("iidc/ice/irdma: Update IDC to support multiple consumers")
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 6c72bd15db6d..6144cee8034d 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1360,7 +1360,7 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 
 	cdev = pf->cdev_info;
 	if (!cdev)
-		return -ENODEV;
+		return -EOPNOTSUPP;
 
 	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2);
 
@@ -1427,7 +1427,7 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 
 	cdev = pf->cdev_info;
 	if (!cdev)
-		return -ENODEV;
+		return -EOPNOTSUPP;
 
 	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP);
 

From efc54fb13d79117a825fef17364315a58682c7ec Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Thu, 29 Jan 2026 10:57:23 +0100
Subject: [PATCH 1162/1303] iavf: fix PTP use-after-free during reset

Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a
worker to cache PHC time, but failed to stop it during reset or disable.

This creates a race condition where `iavf_reset_task()` or
`iavf_disable_vf()` free adapter resources (AQ) while the worker is still
running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it
accesses freed memory/locks, leading to a crash.

Fix this by calling `iavf_ptp_release()` before tearing down the adapter.
This ensures `ptp_clock_unregister()` synchronously cancels the worker and
cleans up the chardev before the backing resources are destroyed.

Fixes: 7c01dbfc8a1c5f ("iavf: periodically cache PHC time")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 86c1964f42e1..c7abd3331e03 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3036,6 +3036,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 
 	adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 
+	iavf_ptp_release(adapter);
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.
@@ -3211,6 +3213,8 @@ static void iavf_reset_task(struct work_struct *work)
 	iavf_change_state(adapter, __IAVF_RESETTING);
 	adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
 
+	iavf_ptp_release(adapter);
+
 	/* free the Tx/Rx rings and descriptors, might be better to just
 	 * re-use them sometime in the future
 	 */

From fdadbf6e84c44df8dbb85cfdd38bc10e4431501d Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 11 Feb 2026 20:18:55 +0100
Subject: [PATCH 1163/1303] iavf: fix incorrect reset handling in callbacks

Three driver callbacks schedule a reset and wait for its completion:
ndo_change_mtu(), ethtool set_ringparam(), and ethtool set_channels().

Waiting for reset in ndo_change_mtu() and set_ringparam() was added by
commit c2ed2403f12c ("iavf: Wait for reset in callbacks which trigger
it") to fix a race condition where adding an interface to bonding
immediately after MTU or ring parameter change failed because the
interface was still in __RESETTING state. The same commit also added
waiting in iavf_set_priv_flags(), which was later removed by commit
53844673d555 ("iavf: kill "legacy-rx" for good").

Waiting in set_channels() was introduced earlier by commit 4e5e6b5d9d13
("iavf: Fix return of set the new channel count") to ensure the PF has
enough time to complete the VF reset when changing channel count, and to
return correct error codes to userspace.

Commit ef490bbb2267 ("iavf: Add net_shaper_ops support") added
net_shaper_ops to iavf, which required reset_task to use _locked NAPI
variants (napi_enable_locked, napi_disable_locked) that need the netdev
instance lock.

Later, commit 7e4d784f5810 ("net: hold netdev instance lock during
rtnetlink operations") and commit 2bcf4772e45a ("net: ethtool: try to
protect all callback with netdev instance lock") started holding the
netdev instance lock during ndo and ethtool callbacks for drivers with
net_shaper_ops.

Finally, commit 120f28a6f314 ("iavf: get rid of the crit lock")
replaced the driver's crit_lock with netdev_lock in reset_task, causing
incorrect behavior: the callback holds netdev_lock and waits for
reset_task, but reset_task needs the same lock:

  Thread 1 (callback)               Thread 2 (reset_task)
  -------------------               ---------------------
  netdev_lock()                     [blocked on workqueue]
  ndo_change_mtu() or ethtool op
    iavf_schedule_reset()
    iavf_wait_for_reset()           iavf_reset_task()
      waiting...                      netdev_lock() <- blocked

This does not strictly deadlock because iavf_wait_for_reset() uses
wait_event_interruptible_timeout() with a 5-second timeout. The wait
eventually times out, the callback returns an error to userspace, and
after the lock is released reset_task completes the reset. This leads to
incorrect behavior: userspace sees an error even though the configuration
change silently takes effect after the timeout.

Fix this by extracting the reset logic from iavf_reset_task() into a new
iavf_reset_step() function that expects netdev_lock to be already held.
The three callbacks now call iavf_reset_step() directly instead of
scheduling the work and waiting, performing the reset synchronously in
the caller's context which already holds netdev_lock. This eliminates
both the incorrect error reporting and the need for
iavf_wait_for_reset(), which is removed along with the now-unused
reset_waitqueue.

The workqueue-based iavf_reset_task() becomes a thin wrapper that
acquires netdev_lock and calls iavf_reset_step(), preserving its use
for PF-initiated resets.

The callbacks may block for several seconds while iavf_reset_step()
polls hardware registers, but this is acceptable since netdev_lock is a
per-device mutex and only serializes operations on the same interface.

v3:
- Remove netif_running() guard from iavf_set_channels(). Unlike
  set_ringparam where descriptor counts are picked up by iavf_open()
  directly, num_req_queues is only consumed during
  iavf_reinit_interrupt_scheme() in the reset path. Skipping the reset
  on a down device would silently discard the channel count change.
- Remove dead reset_waitqueue code (struct field, init, and all
  wake_up calls) since iavf_wait_for_reset() was the only consumer.

Fixes: 120f28a6f314 ("iavf: get rid of the crit lock")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h        |  3 +-
 .../net/ethernet/intel/iavf/iavf_ethtool.c    | 19 ++---
 drivers/net/ethernet/intel/iavf/iavf_main.c   | 77 ++++++-------------
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |  1 -
 4 files changed, 31 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index a87e0c6d4017..e9fb0a0919e3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -260,7 +260,6 @@ struct iavf_adapter {
 	struct work_struct adminq_task;
 	struct work_struct finish_config;
 	wait_queue_head_t down_waitqueue;
-	wait_queue_head_t reset_waitqueue;
 	wait_queue_head_t vc_waitqueue;
 	struct iavf_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -626,5 +625,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter);
 void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter);
 struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 					const u8 *macaddr);
-int iavf_wait_for_reset(struct iavf_adapter *adapter);
+void iavf_reset_step(struct iavf_adapter *adapter);
 #endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index f3a1b2fb9bf8..ab67c709d5a0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -492,7 +492,6 @@ static int iavf_set_ringparam(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 new_rx_count, new_tx_count;
-	int ret = 0;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
@@ -537,13 +536,11 @@ static int iavf_set_ringparam(struct net_device *netdev,
 	}
 
 	if (netif_running(netdev)) {
-		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
-		ret = iavf_wait_for_reset(adapter);
-		if (ret)
-			netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset");
+		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+		iavf_reset_step(adapter);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -1723,7 +1720,6 @@ static int iavf_set_channels(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 num_req = ch->combined_count;
-	int ret = 0;
 
 	if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
 	    adapter->num_tc) {
@@ -1745,13 +1741,10 @@ static int iavf_set_channels(struct net_device *netdev,
 
 	adapter->num_req_queues = num_req;
 	adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
-	iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+	adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+	iavf_reset_step(adapter);
 
-	ret = iavf_wait_for_reset(adapter);
-	if (ret)
-		netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset");
-
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c7abd3331e03..7925ee152c76 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -185,31 +185,6 @@ static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter)
 	return false;
 }
 
-/**
- * iavf_wait_for_reset - Wait for reset to finish.
- * @adapter: board private structure
- *
- * Returns 0 if reset finished successfully, negative on timeout or interrupt.
- */
-int iavf_wait_for_reset(struct iavf_adapter *adapter)
-{
-	int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue,
-					!iavf_is_reset_in_progress(adapter),
-					msecs_to_jiffies(5000));
-
-	/* If ret < 0 then it means wait was interrupted.
-	 * If ret == 0 then it means we got a timeout while waiting
-	 * for reset to finish.
-	 * If ret > 0 it means reset has finished.
-	 */
-	if (ret > 0)
-		return 0;
-	else if (ret < 0)
-		return -EINTR;
-	else
-		return -EBUSY;
-}
-
 /**
  * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code
  * @hw:   pointer to the HW structure
@@ -3113,18 +3088,16 @@ static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_reset_task - Call-back task to handle hardware reset
- * @work: pointer to work_struct
+ * iavf_reset_step - Perform the VF reset sequence
+ * @adapter: board private structure
  *
- * During reset we need to shut down and reinitialize the admin queue
- * before we can use it to communicate with the PF again. We also clear
- * and reinit the rings because that context is lost as well.
- **/
-static void iavf_reset_task(struct work_struct *work)
+ * Requests a reset from PF, polls for completion, and reconfigures
+ * the driver. Caller must hold the netdev instance lock.
+ *
+ * This can sleep for several seconds while polling HW registers.
+ */
+void iavf_reset_step(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						      struct iavf_adapter,
-						      reset_task);
 	struct virtchnl_vf_resource *vfres = adapter->vf_res;
 	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
@@ -3135,7 +3108,7 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
-	netdev_lock(netdev);
+	netdev_assert_locked(netdev);
 
 	iavf_misc_irq_disable(adapter);
 	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
@@ -3180,7 +3153,6 @@ static void iavf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		iavf_disable_vf(adapter);
-		netdev_unlock(netdev);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -3192,7 +3164,6 @@ static void iavf_reset_task(struct work_struct *work)
 		iavf_startup(adapter);
 		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
 				   msecs_to_jiffies(30));
-		netdev_unlock(netdev);
 		return;
 	}
 
@@ -3335,9 +3306,6 @@ static void iavf_reset_task(struct work_struct *work)
 
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 
-	wake_up(&adapter->reset_waitqueue);
-	netdev_unlock(netdev);
-
 	return;
 reset_err:
 	if (running) {
@@ -3346,10 +3314,21 @@ static void iavf_reset_task(struct work_struct *work)
 	}
 	iavf_disable_vf(adapter);
 
-	netdev_unlock(netdev);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
 
+static void iavf_reset_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						      struct iavf_adapter,
+						      reset_task);
+	struct net_device *netdev = adapter->netdev;
+
+	netdev_lock(netdev);
+	iavf_reset_step(adapter);
+	netdev_unlock(netdev);
+}
+
 /**
  * iavf_adminq_task - worker thread to clean the admin queue
  * @work: pointer to work_struct containing our data
@@ -4615,22 +4594,17 @@ static int iavf_close(struct net_device *netdev)
 static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
-	int ret = 0;
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
 	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev)) {
-		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
-		ret = iavf_wait_for_reset(adapter);
-		if (ret < 0)
-			netdev_warn(netdev, "MTU change interrupted waiting for reset");
-		else if (ret)
-			netdev_warn(netdev, "MTU change timed out waiting for reset");
+		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+		iavf_reset_step(adapter);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -5435,9 +5409,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating transition to down status */
 	init_waitqueue_head(&adapter->down_waitqueue);
 
-	/* Setup the wait queue for indicating transition to running state */
-	init_waitqueue_head(&adapter->reset_waitqueue);
-
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 88156082a41d..a52c100dcbc5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -2736,7 +2736,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);
-		wake_up(&adapter->reset_waitqueue);
 		adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED;
 		break;
 	case VIRTCHNL_OP_DISABLE_QUEUES:

From 22fd7f7fed2ae3702f90d1985c326354e86b9c75 Mon Sep 17 00:00:00 2001
From: Muhammad Amirul Asyraf Mohamad Jamian
 <muhammad.amirul.asyraf.mohamad.jamian@altera.com>
Date: Thu, 5 Mar 2026 01:31:51 -0800
Subject: [PATCH 1164/1303] firmware: stratix10-svc: Add Multi SVC clients
 support

In the current implementation, SVC client drivers such as socfpga-hwmon,
intel_fcs, stratix10-soc, stratix10-rsu each send an SMC command that
triggers a single thread in the stratix10-svc driver. Upon receiving a
callback, the initiating client driver sends a stratix10-svc-done signal,
terminating the thread without waiting for other pending SMC commands to
complete. This leads to a timeout issue in the firmware SVC mailbox service
when multiple client drivers send SMC commands concurrently.

To resolve this issue, a dedicated thread is now created per channel. The
stratix10-svc driver will support up to the number of channels defined by
SVC_NUM_CHANNEL. Thread synchronization is handled using a mutex to prevent
simultaneous issuance of SMC commands by multiple threads.

SVC_NUM_DATA_IN_FIFO is reduced from 32 to 8, since each channel now has
its own dedicated FIFO and the SDM processes commands one at a time.
8 entries per channel is sufficient while keeping the total aggregate
capacity the same (4 channels x 8 = 32 entries).

Additionally, a thread task is now validated before invoking kthread_stop
when the user aborts, ensuring safe termination.

Timeout values have also been adjusted to accommodate the increased load
from concurrent client driver activity.

Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver")
Cc: stable@vger.kernel.org
Signed-off-by: Ang Tien Sung <tien.sung.ang@altera.com>
Signed-off-by: Fong, Yan Kei <yankei.fong@altera.com>
Signed-off-by: Muhammad Amirul Asyraf Mohamad Jamian <muhammad.amirul.asyraf.mohamad.jamian@altera.com>
Link: https://lore.kernel.org/all/20260305093151.2678-1-muhammad.amirul.asyraf.mohamad.jamian@altera.com
Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
---
 drivers/firmware/stratix10-svc.c              | 228 ++++++++++--------
 .../firmware/intel/stratix10-svc-client.h     |   8 +-
 2 files changed, 130 insertions(+), 106 deletions(-)

diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 6f5c298582ab..e9e35d67ef96 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -37,15 +37,14 @@
  * service layer will return error to FPGA manager when timeout occurs,
  * timeout is set to 30 seconds (30 * 1000) at Intel Stratix10 SoC.
  */
-#define SVC_NUM_DATA_IN_FIFO			32
+#define SVC_NUM_DATA_IN_FIFO			8
 #define SVC_NUM_CHANNEL				4
-#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS	200
+#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS	2000
 #define FPGA_CONFIG_STATUS_TIMEOUT_SEC		30
 #define BYTE_TO_WORD_SIZE              4
 
 /* stratix10 service layer clients */
 #define STRATIX10_RSU				"stratix10-rsu"
-#define INTEL_FCS				"intel-fcs"
 
 /* Maximum number of SDM client IDs. */
 #define MAX_SDM_CLIENT_IDS			16
@@ -105,11 +104,9 @@ struct stratix10_svc_chan;
 /**
  * struct stratix10_svc - svc private data
  * @stratix10_svc_rsu: pointer to stratix10 RSU device
- * @intel_svc_fcs: pointer to the FCS device
  */
 struct stratix10_svc {
 	struct platform_device *stratix10_svc_rsu;
-	struct platform_device *intel_svc_fcs;
 };
 
 /**
@@ -251,12 +248,10 @@ struct stratix10_async_ctrl {
  * @num_active_client: number of active service client
  * @node: list management
  * @genpool: memory pool pointing to the memory region
- * @task: pointer to the thread task which handles SMC or HVC call
- * @svc_fifo: a queue for storing service message data
  * @complete_status: state for completion
- * @svc_fifo_lock: protect access to service message data queue
  * @invoke_fn: function to issue secure monitor call or hypervisor call
  * @svc: manages the list of client svc drivers
+ * @sdm_lock: only allows a single command single response to SDM
  * @actrl: async control structure
  *
  * This struct is used to create communication channels for service clients, to
@@ -269,12 +264,10 @@ struct stratix10_svc_controller {
 	int num_active_client;
 	struct list_head node;
 	struct gen_pool *genpool;
-	struct task_struct *task;
-	struct kfifo svc_fifo;
 	struct completion complete_status;
-	spinlock_t svc_fifo_lock;
 	svc_invoke_fn *invoke_fn;
 	struct stratix10_svc *svc;
+	struct mutex sdm_lock;
 	struct stratix10_async_ctrl actrl;
 };
 
@@ -283,6 +276,9 @@ struct stratix10_svc_controller {
  * @ctrl: pointer to service controller which is the provider of this channel
  * @scl: pointer to service client which owns the channel
  * @name: service client name associated with the channel
+ * @task: pointer to the thread task which handles SMC or HVC call
+ * @svc_fifo: a queue for storing service message data (separate fifo for every channel)
+ * @svc_fifo_lock: protect access to service message data queue (locking pending fifo)
  * @lock: protect access to the channel
  * @async_chan: reference to asynchronous channel object for this channel
  *
@@ -293,6 +289,9 @@ struct stratix10_svc_chan {
 	struct stratix10_svc_controller *ctrl;
 	struct stratix10_svc_client *scl;
 	char *name;
+	struct task_struct *task;
+	struct kfifo svc_fifo;
+	spinlock_t svc_fifo_lock;
 	spinlock_t lock;
 	struct stratix10_async_chan *async_chan;
 };
@@ -527,10 +526,10 @@ static void svc_thread_recv_status_ok(struct stratix10_svc_data *p_data,
  */
 static int svc_normal_to_secure_thread(void *data)
 {
-	struct stratix10_svc_controller
-			*ctrl = (struct stratix10_svc_controller *)data;
-	struct stratix10_svc_data *pdata;
-	struct stratix10_svc_cb_data *cbdata;
+	struct stratix10_svc_chan *chan = (struct stratix10_svc_chan *)data;
+	struct stratix10_svc_controller *ctrl = chan->ctrl;
+	struct stratix10_svc_data *pdata = NULL;
+	struct stratix10_svc_cb_data *cbdata = NULL;
 	struct arm_smccc_res res;
 	unsigned long a0, a1, a2, a3, a4, a5, a6, a7;
 	int ret_fifo = 0;
@@ -555,12 +554,12 @@ static int svc_normal_to_secure_thread(void *data)
 	a6 = 0;
 	a7 = 0;
 
-	pr_debug("smc_hvc_shm_thread is running\n");
+	pr_debug("%s: %s: Thread is running!\n", __func__, chan->name);
 
 	while (!kthread_should_stop()) {
-		ret_fifo = kfifo_out_spinlocked(&ctrl->svc_fifo,
+		ret_fifo = kfifo_out_spinlocked(&chan->svc_fifo,
 						pdata, sizeof(*pdata),
-						&ctrl->svc_fifo_lock);
+						&chan->svc_fifo_lock);
 
 		if (!ret_fifo)
 			continue;
@@ -569,9 +568,25 @@ static int svc_normal_to_secure_thread(void *data)
 			 (unsigned int)pdata->paddr, pdata->command,
 			 (unsigned int)pdata->size);
 
+		/* SDM can only process one command at a time */
+		pr_debug("%s: %s: Thread is waiting for mutex!\n",
+			 __func__, chan->name);
+		if (mutex_lock_interruptible(&ctrl->sdm_lock)) {
+			/* item already dequeued; notify client to unblock it */
+			cbdata->status = BIT(SVC_STATUS_ERROR);
+			cbdata->kaddr1 = NULL;
+			cbdata->kaddr2 = NULL;
+			cbdata->kaddr3 = NULL;
+			if (pdata->chan->scl)
+				pdata->chan->scl->receive_cb(pdata->chan->scl,
+							     cbdata);
+			break;
+		}
+
 		switch (pdata->command) {
 		case COMMAND_RECONFIG_DATA_CLAIM:
 			svc_thread_cmd_data_claim(ctrl, pdata, cbdata);
+			mutex_unlock(&ctrl->sdm_lock);
 			continue;
 		case COMMAND_RECONFIG:
 			a0 = INTEL_SIP_SMC_FPGA_CONFIG_START;
@@ -700,10 +715,11 @@ static int svc_normal_to_secure_thread(void *data)
 			break;
 		default:
 			pr_warn("it shouldn't happen\n");
-			break;
+			mutex_unlock(&ctrl->sdm_lock);
+			continue;
 		}
-		pr_debug("%s: before SMC call -- a0=0x%016x a1=0x%016x",
-			 __func__,
+		pr_debug("%s: %s: before SMC call -- a0=0x%016x a1=0x%016x",
+			 __func__, chan->name,
 			 (unsigned int)a0,
 			 (unsigned int)a1);
 		pr_debug(" a2=0x%016x\n", (unsigned int)a2);
@@ -712,8 +728,8 @@ static int svc_normal_to_secure_thread(void *data)
 		pr_debug(" a5=0x%016x\n", (unsigned int)a5);
 		ctrl->invoke_fn(a0, a1, a2, a3, a4, a5, a6, a7, &res);
 
-		pr_debug("%s: after SMC call -- res.a0=0x%016x",
-			 __func__, (unsigned int)res.a0);
+		pr_debug("%s: %s: after SMC call -- res.a0=0x%016x",
+			 __func__, chan->name, (unsigned int)res.a0);
 		pr_debug(" res.a1=0x%016x, res.a2=0x%016x",
 			 (unsigned int)res.a1, (unsigned int)res.a2);
 		pr_debug(" res.a3=0x%016x\n", (unsigned int)res.a3);
@@ -728,6 +744,7 @@ static int svc_normal_to_secure_thread(void *data)
 			cbdata->kaddr2 = NULL;
 			cbdata->kaddr3 = NULL;
 			pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata);
+			mutex_unlock(&ctrl->sdm_lock);
 			continue;
 		}
 
@@ -801,6 +818,8 @@ static int svc_normal_to_secure_thread(void *data)
 			break;
 
 		}
+
+		mutex_unlock(&ctrl->sdm_lock);
 	}
 
 	kfree(cbdata);
@@ -1696,22 +1715,33 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg)
 	if (!p_data)
 		return -ENOMEM;
 
-	/* first client will create kernel thread */
-	if (!chan->ctrl->task) {
-		chan->ctrl->task =
-			kthread_run_on_cpu(svc_normal_to_secure_thread,
-					   (void *)chan->ctrl,
-					   cpu, "svc_smc_hvc_thread");
-		if (IS_ERR(chan->ctrl->task)) {
+	/* first caller creates the per-channel kthread */
+	if (!chan->task) {
+		struct task_struct *task;
+
+		task = kthread_run_on_cpu(svc_normal_to_secure_thread,
+					  (void *)chan,
+					  cpu, "svc_smc_hvc_thread");
+		if (IS_ERR(task)) {
 			dev_err(chan->ctrl->dev,
 				"failed to create svc_smc_hvc_thread\n");
 			kfree(p_data);
 			return -EINVAL;
 		}
+
+		spin_lock(&chan->lock);
+		if (chan->task) {
+			/* another caller won the race; discard our thread */
+			spin_unlock(&chan->lock);
+			kthread_stop(task);
+		} else {
+			chan->task = task;
+			spin_unlock(&chan->lock);
+		}
 	}
 
-	pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__,
-		 p_msg->payload, p_msg->command,
+	pr_debug("%s: %s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__,
+		 chan->name, p_msg->payload, p_msg->command,
 		 (unsigned int)p_msg->payload_length);
 
 	if (list_empty(&svc_data_mem)) {
@@ -1747,12 +1777,16 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg)
 	p_data->arg[2] = p_msg->arg[2];
 	p_data->size = p_msg->payload_length;
 	p_data->chan = chan;
-	pr_debug("%s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", __func__,
-	       (unsigned int)p_data->paddr, p_data->command,
-	       (unsigned int)p_data->size);
-	ret = kfifo_in_spinlocked(&chan->ctrl->svc_fifo, p_data,
+	pr_debug("%s: %s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n",
+		 __func__,
+		 chan->name,
+		 (unsigned int)p_data->paddr,
+		 p_data->command,
+		 (unsigned int)p_data->size);
+
+	ret = kfifo_in_spinlocked(&chan->svc_fifo, p_data,
 				  sizeof(*p_data),
-				  &chan->ctrl->svc_fifo_lock);
+				  &chan->svc_fifo_lock);
 
 	kfree(p_data);
 
@@ -1773,11 +1807,12 @@ EXPORT_SYMBOL_GPL(stratix10_svc_send);
  */
 void stratix10_svc_done(struct stratix10_svc_chan *chan)
 {
-	/* stop thread when thread is running AND only one active client */
-	if (chan->ctrl->task && chan->ctrl->num_active_client <= 1) {
-		pr_debug("svc_smc_hvc_shm_thread is stopped\n");
-		kthread_stop(chan->ctrl->task);
-		chan->ctrl->task = NULL;
+	/* stop thread when thread is running */
+	if (chan->task) {
+		pr_debug("%s: %s: svc_smc_hvc_shm_thread is stopping\n",
+			 __func__, chan->name);
+		kthread_stop(chan->task);
+		chan->task = NULL;
 	}
 }
 EXPORT_SYMBOL_GPL(stratix10_svc_done);
@@ -1817,8 +1852,8 @@ void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan,
 	pmem->paddr = pa;
 	pmem->size = s;
 	list_add_tail(&pmem->node, &svc_data_mem);
-	pr_debug("%s: va=%p, pa=0x%016x\n", __func__,
-		 pmem->vaddr, (unsigned int)pmem->paddr);
+	pr_debug("%s: %s: va=%p, pa=0x%016x\n", __func__,
+		 chan->name, pmem->vaddr, (unsigned int)pmem->paddr);
 
 	return (void *)va;
 }
@@ -1855,6 +1890,13 @@ static const struct of_device_id stratix10_svc_drv_match[] = {
 	{},
 };
 
+static const char * const chan_names[SVC_NUM_CHANNEL] = {
+	SVC_CLIENT_FPGA,
+	SVC_CLIENT_RSU,
+	SVC_CLIENT_FCS,
+	SVC_CLIENT_HWMON
+};
+
 static int stratix10_svc_drv_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1862,11 +1904,11 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	struct stratix10_svc_chan *chans;
 	struct gen_pool *genpool;
 	struct stratix10_svc_sh_memory *sh_memory;
-	struct stratix10_svc *svc;
+	struct stratix10_svc *svc = NULL;
 
 	svc_invoke_fn *invoke_fn;
 	size_t fifo_size;
-	int ret;
+	int ret, i = 0;
 
 	/* get SMC or HVC function */
 	invoke_fn = get_invoke_func(dev);
@@ -1905,8 +1947,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	controller->num_active_client = 0;
 	controller->chans = chans;
 	controller->genpool = genpool;
-	controller->task = NULL;
 	controller->invoke_fn = invoke_fn;
+	INIT_LIST_HEAD(&controller->node);
 	init_completion(&controller->complete_status);
 
 	ret = stratix10_svc_async_init(controller);
@@ -1917,32 +1959,20 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	}
 
 	fifo_size = sizeof(struct stratix10_svc_data) * SVC_NUM_DATA_IN_FIFO;
-	ret = kfifo_alloc(&controller->svc_fifo, fifo_size, GFP_KERNEL);
-	if (ret) {
-		dev_err(dev, "failed to allocate FIFO\n");
-		goto err_async_exit;
+	mutex_init(&controller->sdm_lock);
+
+	for (i = 0; i < SVC_NUM_CHANNEL; i++) {
+		chans[i].scl = NULL;
+		chans[i].ctrl = controller;
+		chans[i].name = (char *)chan_names[i];
+		spin_lock_init(&chans[i].lock);
+		ret = kfifo_alloc(&chans[i].svc_fifo, fifo_size, GFP_KERNEL);
+		if (ret) {
+			dev_err(dev, "failed to allocate FIFO %d\n", i);
+			goto err_free_fifos;
+		}
+		spin_lock_init(&chans[i].svc_fifo_lock);
 	}
-	spin_lock_init(&controller->svc_fifo_lock);
-
-	chans[0].scl = NULL;
-	chans[0].ctrl = controller;
-	chans[0].name = SVC_CLIENT_FPGA;
-	spin_lock_init(&chans[0].lock);
-
-	chans[1].scl = NULL;
-	chans[1].ctrl = controller;
-	chans[1].name = SVC_CLIENT_RSU;
-	spin_lock_init(&chans[1].lock);
-
-	chans[2].scl = NULL;
-	chans[2].ctrl = controller;
-	chans[2].name = SVC_CLIENT_FCS;
-	spin_lock_init(&chans[2].lock);
-
-	chans[3].scl = NULL;
-	chans[3].ctrl = controller;
-	chans[3].name = SVC_CLIENT_HWMON;
-	spin_lock_init(&chans[3].lock);
 
 	list_add_tail(&controller->node, &svc_ctrl);
 	platform_set_drvdata(pdev, controller);
@@ -1951,7 +1981,7 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	svc = devm_kzalloc(dev, sizeof(*svc), GFP_KERNEL);
 	if (!svc) {
 		ret = -ENOMEM;
-		goto err_free_kfifo;
+		goto err_free_fifos;
 	}
 	controller->svc = svc;
 
@@ -1959,51 +1989,43 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	if (!svc->stratix10_svc_rsu) {
 		dev_err(dev, "failed to allocate %s device\n", STRATIX10_RSU);
 		ret = -ENOMEM;
-		goto err_free_kfifo;
+		goto err_free_fifos;
 	}
 
 	ret = platform_device_add(svc->stratix10_svc_rsu);
-	if (ret) {
-		platform_device_put(svc->stratix10_svc_rsu);
-		goto err_free_kfifo;
-	}
-
-	svc->intel_svc_fcs = platform_device_alloc(INTEL_FCS, 1);
-	if (!svc->intel_svc_fcs) {
-		dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
-		ret = -ENOMEM;
-		goto err_unregister_rsu_dev;
-	}
-
-	ret = platform_device_add(svc->intel_svc_fcs);
-	if (ret) {
-		platform_device_put(svc->intel_svc_fcs);
-		goto err_unregister_rsu_dev;
-	}
+	if (ret)
+		goto err_put_device;
 
 	ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
 	if (ret)
-		goto err_unregister_fcs_dev;
+		goto err_unregister_rsu_dev;
 
 	pr_info("Intel Service Layer Driver Initialized\n");
 
 	return 0;
 
-err_unregister_fcs_dev:
-	platform_device_unregister(svc->intel_svc_fcs);
 err_unregister_rsu_dev:
 	platform_device_unregister(svc->stratix10_svc_rsu);
-err_free_kfifo:
-	kfifo_free(&controller->svc_fifo);
-err_async_exit:
+	goto err_free_fifos;
+err_put_device:
+	platform_device_put(svc->stratix10_svc_rsu);
+err_free_fifos:
+	/* only remove from list if list_add_tail() was reached */
+	if (!list_empty(&controller->node))
+		list_del(&controller->node);
+	/* free only the FIFOs that were successfully allocated */
+	while (i--)
+		kfifo_free(&chans[i].svc_fifo);
 	stratix10_svc_async_exit(controller);
 err_destroy_pool:
 	gen_pool_destroy(genpool);
+
 	return ret;
 }
 
 static void stratix10_svc_drv_remove(struct platform_device *pdev)
 {
+	int i;
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
 	struct stratix10_svc *svc = ctrl->svc;
 
@@ -2011,14 +2033,16 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
 
 	of_platform_depopulate(ctrl->dev);
 
-	platform_device_unregister(svc->intel_svc_fcs);
 	platform_device_unregister(svc->stratix10_svc_rsu);
 
-	kfifo_free(&ctrl->svc_fifo);
-	if (ctrl->task) {
-		kthread_stop(ctrl->task);
-		ctrl->task = NULL;
+	for (i = 0; i < SVC_NUM_CHANNEL; i++) {
+		if (ctrl->chans[i].task) {
+			kthread_stop(ctrl->chans[i].task);
+			ctrl->chans[i].task = NULL;
+		}
+		kfifo_free(&ctrl->chans[i].svc_fifo);
 	}
+
 	if (ctrl->genpool)
 		gen_pool_destroy(ctrl->genpool);
 	list_del(&ctrl->node);
diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index d290060f4c73..91013161e9db 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -68,12 +68,12 @@
  * timeout value used in Stratix10 FPGA manager driver.
  * timeout value used in RSU driver
  */
-#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         300
-#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          720
-#define SVC_RSU_REQUEST_TIMEOUT_MS              300
+#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         5000
+#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          5000
+#define SVC_RSU_REQUEST_TIMEOUT_MS              2000
 #define SVC_FCS_REQUEST_TIMEOUT_MS		2000
 #define SVC_COMPLETED_TIMEOUT_MS		30000
-#define SVC_HWMON_REQUEST_TIMEOUT_MS		300
+#define SVC_HWMON_REQUEST_TIMEOUT_MS		2000
 
 struct stratix10_svc_chan;
 

From c7940c8bf215b9dc6211781c77ce80e76982a723 Mon Sep 17 00:00:00 2001
From: Tim Kovalenko <tim.kovalenko@proton.me>
Date: Mon, 9 Mar 2026 12:34:21 -0400
Subject: [PATCH 1165/1303] gpu: nova-core: fix stack overflow in GSP memory
 allocation

The `Cmdq::new` function was allocating a `PteArray` struct on the stack
and was causing a stack overflow with 8216 bytes.

Modify the `PteArray` to calculate and write the Page Table Entries
directly into the coherent DMA buffer one-by-one. This reduces the stack
usage quite a lot.

Reported-by: Gary Guo <gary@garyguo.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/509436-Nova/topic/.60Cmdq.3A.3Anew.60.20uses.20excessive.20stack.20size/near/570375549
Link: https://lore.kernel.org/rust-for-linux/CANiq72mAQxbRJZDnik3Qmd4phvFwPA01O2jwaaXRh_T+2=L-qA@mail.gmail.com/
Fixes: f38b4f105cfc ("gpu: nova-core: Create initial Gsp")
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Tim Kovalenko <tim.kovalenko@proton.me>
Link: https://patch.msgid.link/20260309-drm-rust-next-v4-4-4ef485b19a4c@proton.me
[ * Use PteArray::entry() in LogBuffer::new(),
  * Add TODO comment to use IoView projections once available,
  * Add PTE_ARRAY_SIZE constant to avoid duplication.

    - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp.rs      | 32 ++++++++++++++++---------------
 drivers/gpu/nova-core/gsp/cmdq.rs | 14 ++++++++++++--
 2 files changed, 29 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 25cd48514c77..c69adaa92bbe 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -47,16 +47,12 @@
 unsafe impl<const NUM_ENTRIES: usize> AsBytes for PteArray<NUM_ENTRIES> {}
 
 impl<const NUM_PAGES: usize> PteArray<NUM_PAGES> {
-    /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`.
-    fn new(start: DmaAddress) -> Result<Self> {
-        let mut ptes = [0u64; NUM_PAGES];
-        for (i, pte) in ptes.iter_mut().enumerate() {
-            *pte = start
-                .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT)
-                .ok_or(EOVERFLOW)?;
-        }
-
-        Ok(Self(ptes))
+    /// Returns the page table entry for `index`, for a mapping starting at `start`.
+    // TODO: Replace with `IoView` projection once available.
+    fn entry(start: DmaAddress, index: usize) -> Result<u64> {
+        start
+            .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT)
+            .ok_or(EOVERFLOW)
     }
 }
 
@@ -86,16 +82,22 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {
             NUM_PAGES * GSP_PAGE_SIZE,
             GFP_KERNEL | __GFP_ZERO,
         )?);
-        let ptes = PteArray::<NUM_PAGES>::new(obj.0.dma_handle())?;
+
+        let start_addr = obj.0.dma_handle();
 
         // SAFETY: `obj` has just been created and we are its sole user.
-        unsafe {
-            // Copy the self-mapping PTE at the expected location.
+        let pte_region = unsafe {
             obj.0
-                .as_slice_mut(size_of::<u64>(), size_of_val(&ptes))?
-                .copy_from_slice(ptes.as_bytes())
+                .as_slice_mut(size_of::<u64>(), NUM_PAGES * size_of::<u64>())?
         };
 
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for (i, chunk) in pte_region.chunks_exact_mut(size_of::<u64>()).enumerate() {
+            let pte_value = PteArray::<0>::entry(start_addr, i)?;
+
+            chunk.copy_from_slice(&pte_value.to_ne_bytes());
+        }
+
         Ok(obj)
     }
 }
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index ae54708c38eb..9c5efd2daf45 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -159,7 +159,7 @@ struct Msgq {
 #[repr(C)]
 struct GspMem {
     /// Self-mapping page table entries.
-    ptes: PteArray<{ GSP_PAGE_SIZE / size_of::<u64>() }>,
+    ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>,
     /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the
     /// write and read pointers that the CPU updates.
     ///
@@ -172,6 +172,10 @@ struct GspMem {
     gspq: Msgq,
 }
 
+impl GspMem {
+    const PTE_ARRAY_SIZE: usize = GSP_PAGE_SIZE / size_of::<u64>();
+}
+
 // SAFETY: These structs don't meet the no-padding requirements of AsBytes but
 // that is not a problem because they are not used outside the kernel.
 unsafe impl AsBytes for GspMem {}
@@ -201,7 +205,13 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {
 
         let gsp_mem =
             CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?);
+
+        let start = gsp_mem.dma_handle();
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for i in 0..GspMem::PTE_ARRAY_SIZE {
+            dma_write!(gsp_mem, [0]?.ptes.0[i], PteArray::<0>::entry(start, i)?);
+        }
+
         dma_write!(
             gsp_mem,
             [0]?.cpuq.tx,

From 620b6ded72a7f0f77be6ec44d0462bb85729ab7a Mon Sep 17 00:00:00 2001
From: Jessica Liu <liu.xuemei1@zte.com.cn>
Date: Tue, 10 Mar 2026 14:16:00 +0800
Subject: [PATCH 1166/1303] irqchip/riscv-aplic: Do not clear ACPI dependencies
 on probe failure

aplic_probe() calls acpi_dev_clear_dependencies() unconditionally at the
end, even when the preceding setup (MSI or direct mode) has failed. This is
incorrect because if the device failed to probe, it should not be
considered as active and should not clear dependencies for other devices
waiting on it.

Fix this by returning immediately when the setup fails, skipping the ACPI
dependency cleanup. Also, explicitly return 0 on success instead of relying
on the value of 'rc' to make the success path clear.

Fixes: 5122e380c23b ("irqchip/riscv-aplic: Add ACPI support")
Signed-off-by: Jessica Liu <liu.xuemei1@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260310141600411Fu8H8-GXOOgKISU48Tjgx@zte.com.cn
---
 drivers/irqchip/irq-riscv-aplic-main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 4495ca26abf5..8775f188ea4f 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -372,18 +372,21 @@ static int aplic_probe(struct platform_device *pdev)
 		rc = aplic_msi_setup(dev, regs);
 	else
 		rc = aplic_direct_setup(dev, regs);
-	if (rc)
+
+	if (rc) {
 		dev_err_probe(dev, rc, "failed to setup APLIC in %s mode\n",
 			      msi_mode ? "MSI" : "direct");
-	else
-		register_syscore(&aplic_syscore);
+		return rc;
+	}
+
+	register_syscore(&aplic_syscore);
 
 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)
 		acpi_dev_clear_dependencies(ACPI_COMPANION(dev));
 #endif
 
-	return rc;
+	return 0;
 }
 
 static const struct of_device_id aplic_match[] = {

From b330fbfd34d7624bec62b99ad88dba2614326a19 Mon Sep 17 00:00:00 2001
From: Jessica Liu <liu.xuemei1@zte.com.cn>
Date: Tue, 10 Mar 2026 14:17:31 +0800
Subject: [PATCH 1167/1303] irqchip/riscv-aplic: Register syscore operations
 only once

Since commit 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC
states across suspend/resume"), when multiple NUMA nodes exist
and AIA is not configured as "none", aplic_probe() is called
multiple times. This leads to register_syscore(&aplic_syscore)
being invoked repeatedly, causing the following Oops:

 list_add double add: new=ffffffffb91461f0, prev=ffffffffb91461f0, next=ffffffffb915c408.
 [<ffffffffb7b5c8ca>] __list_add_valid_or_report+0x60/0xc0
 [<ffffffffb7cc3236>] register_syscore+0x3e/0x70
 [<ffffffffb7b8d61c>] aplic_probe+0xc6/0x112

Fix this by registering syscore operations only once, using a static
variable aplic_syscore_registered to track registration.

[ tglx: Trim backtrace properly ]

Fixes: 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume")
Signed-off-by: Jessica Liu <liu.xuemei1@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260310141731145xMwLsyvXl9Gw-m6A4VRYj@zte.com.cn
---
 drivers/irqchip/irq-riscv-aplic-main.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 8775f188ea4f..9f53979b6962 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -116,6 +116,16 @@ static struct syscore aplic_syscore = {
 	.ops = &aplic_syscore_ops,
 };
 
+static bool aplic_syscore_registered __ro_after_init;
+
+static void aplic_syscore_init(void)
+{
+	if (!aplic_syscore_registered) {
+		register_syscore(&aplic_syscore);
+		aplic_syscore_registered = true;
+	}
+}
+
 static int aplic_pm_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct aplic_priv *priv = container_of(nb, struct aplic_priv, genpd_nb);
@@ -379,7 +389,7 @@ static int aplic_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	register_syscore(&aplic_syscore);
+	aplic_syscore_init();
 
 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)

From 6b13cb8f48a42ddf6dd98865b673a82e37ff238b Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Tue, 10 Mar 2026 11:00:58 -0700
Subject: [PATCH 1168/1303] accel/amdxdna: Fix runtime suspend deadlock when
 there is pending job

The runtime suspend callback drains the running job workqueue before
suspending the device. If a job is still executing and calls
pm_runtime_resume_and_get(), it can deadlock with the runtime suspend
path.

Fix this by moving pm_runtime_resume_and_get() from the job execution
routine to the job submission routine, ensuring the device is resumed
before the job is queued and avoiding the deadlock during runtime
suspend.

Fixes: 063db451832b ("accel/amdxdna: Enhance runtime power management")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260310180058.336348-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_ctx.c    | 14 ++------------
 drivers/accel/amdxdna/amdxdna_ctx.c | 10 ++++++++++
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index afee5e667f77..c0d348884f74 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -165,7 +165,6 @@ aie2_sched_notify(struct amdxdna_sched_job *job)
 
 	trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq);
 
-	amdxdna_pm_suspend_put(job->hwctx->client->xdna);
 	job->hwctx->priv->completed++;
 	dma_fence_signal(fence);
 
@@ -290,19 +289,11 @@ aie2_sched_job_run(struct drm_sched_job *sched_job)
 	struct dma_fence *fence;
 	int ret;
 
-	ret = amdxdna_pm_resume_get(hwctx->client->xdna);
-	if (ret)
+	if (!hwctx->priv->mbox_chann)
 		return NULL;
 
-	if (!hwctx->priv->mbox_chann) {
-		amdxdna_pm_suspend_put(hwctx->client->xdna);
-		return NULL;
-	}
-
-	if (!mmget_not_zero(job->mm)) {
-		amdxdna_pm_suspend_put(hwctx->client->xdna);
+	if (!mmget_not_zero(job->mm))
 		return ERR_PTR(-ESRCH);
-	}
 
 	kref_get(&job->refcnt);
 	fence = dma_fence_get(job->fence);
@@ -333,7 +324,6 @@ aie2_sched_job_run(struct drm_sched_job *sched_job)
 
 out:
 	if (ret) {
-		amdxdna_pm_suspend_put(hwctx->client->xdna);
 		dma_fence_put(job->fence);
 		aie2_job_put(job);
 		mmput(job->mm);
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c
index 666dfd7b2a80..838430903a3e 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -17,6 +17,7 @@
 #include "amdxdna_ctx.h"
 #include "amdxdna_gem.h"
 #include "amdxdna_pci_drv.h"
+#include "amdxdna_pm.h"
 
 #define MAX_HWCTX_ID		255
 #define MAX_ARG_COUNT		4095
@@ -445,6 +446,7 @@ amdxdna_arg_bos_lookup(struct amdxdna_client *client,
 void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job)
 {
 	trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release");
+	amdxdna_pm_suspend_put(job->hwctx->client->xdna);
 	amdxdna_arg_bos_put(job);
 	amdxdna_gem_put_obj(job->cmd_bo);
 	dma_fence_put(job->fence);
@@ -482,6 +484,12 @@ int amdxdna_cmd_submit(struct amdxdna_client *client,
 		goto cmd_put;
 	}
 
+	ret = amdxdna_pm_resume_get(xdna);
+	if (ret) {
+		XDNA_ERR(xdna, "Resume failed, ret %d", ret);
+		goto put_bos;
+	}
+
 	idx = srcu_read_lock(&client->hwctx_srcu);
 	hwctx = xa_load(&client->hwctx_xa, hwctx_hdl);
 	if (!hwctx) {
@@ -522,6 +530,8 @@ int amdxdna_cmd_submit(struct amdxdna_client *client,
 	dma_fence_put(job->fence);
 unlock_srcu:
 	srcu_read_unlock(&client->hwctx_srcu, idx);
+	amdxdna_pm_suspend_put(xdna);
+put_bos:
 	amdxdna_arg_bos_put(job);
 cmd_put:
 	amdxdna_gem_put_obj(job->cmd_bo);

From 30e4b2290cc2a8d1b9ddb9dcb9c981df1f2a7399 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 10 Mar 2026 08:53:50 +0200
Subject: [PATCH 1169/1303] ASoC: codecs: rt1011: Use component to get the dapm
 context in spk_mode_put

The correct helper to use in rt1011_recv_spk_mode_put() to retrieve the
DAPM context is snd_soc_component_to_dapm(), from kcontrol we will
receive NULL pointer.

Closes: https://github.com/thesofproject/linux/issues/5691
Fixes: 5b35bb517f27 ("ASoC: codecs: rt1011: convert to snd_soc_dapm_xxx()")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20260310065350.18921-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1011.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c
index 9f34a6a35487..03f31d9d916e 100644
--- a/sound/soc/codecs/rt1011.c
+++ b/sound/soc/codecs/rt1011.c
@@ -1047,7 +1047,7 @@ static int rt1011_recv_spk_mode_put(struct snd_kcontrol *kcontrol,
 		struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_to_dapm(kcontrol);
+	struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component);
 	struct rt1011_priv *rt1011 =
 		snd_soc_component_get_drvdata(component);
 

From e809085f492842ce7a519c9ef72d40f4bca89c13 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Mon, 10 Nov 2025 11:13:38 -0800
Subject: [PATCH 1170/1303] i40e: fix src IP mask checks and memcpy argument
 names in cloud filter

Fix following issues in the IPv4 and IPv6 cloud filter handling logic in
both the add and delete paths:

- The source-IP mask check incorrectly compares mask.src_ip[0] against
  tcf.dst_ip[0]. Update it to compare against tcf.src_ip[0]. This likely
  goes unnoticed because the check is in an "else if" path that only
  executes when dst_ip is not set, most cloud filter use cases focus on
  destination-IP matching, and the buggy condition can accidentally
  evaluate true in some cases.

- memcpy() for the IPv4 source address incorrectly uses
  ARRAY_SIZE(tcf.dst_ip) instead of ARRAY_SIZE(tcf.src_ip), although
  both arrays are the same size.

- The IPv4 memcpy operations used ARRAY_SIZE(tcf.dst_ip) and ARRAY_SIZE
  (tcf.src_ip), Update these to use sizeof(cfilter->ip.v4.dst_ip) and
  sizeof(cfilter->ip.v4.src_ip) to ensure correct and explicit copy size.

- In the IPv6 delete path, memcmp() uses sizeof(src_ip6) when comparing
  dst_ip6 fields. Replace this with sizeof(dst_ip6) to make the intent
  explicit, even though both fields are struct in6_addr.

Fixes: e284fc280473 ("i40e: Add and delete cloud filter")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index fdf40f8fb239..a26c3d47ec15 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -3833,10 +3833,10 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		cfilter.n_proto = ETH_P_IP;
 		if (mask.dst_ip[0] & tcf.dst_ip[0])
 			memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
-		else if (mask.src_ip[0] & tcf.dst_ip[0])
+			       sizeof(cfilter.ip.v4.dst_ip));
+		else if (mask.src_ip[0] & tcf.src_ip[0])
 			memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
+			       sizeof(cfilter.ip.v4.src_ip));
 		break;
 	case VIRTCHNL_TCP_V6_FLOW:
 		cfilter.n_proto = ETH_P_IPV6;
@@ -3891,7 +3891,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		/* for ipv6, mask is set for all sixteen bytes (4 words) */
 		if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3])
 			if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6,
-				   sizeof(cfilter.ip.v6.src_ip6)))
+				   sizeof(cfilter.ip.v6.dst_ip6)))
 				continue;
 		if (mask.vlan_id)
 			if (cfilter.vlan_id != cf->vlan_id)
@@ -3979,10 +3979,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		cfilter->n_proto = ETH_P_IP;
 		if (mask.dst_ip[0] & tcf.dst_ip[0])
 			memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
-		else if (mask.src_ip[0] & tcf.dst_ip[0])
+			       sizeof(cfilter->ip.v4.dst_ip));
+		else if (mask.src_ip[0] & tcf.src_ip[0])
 			memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
+			       sizeof(cfilter->ip.v4.src_ip));
 		break;
 	case VIRTCHNL_TCP_V6_FLOW:
 		cfilter->n_proto = ETH_P_IPV6;

From e94eaef11142b01f77bf8ba4d0b59720b7858109 Mon Sep 17 00:00:00 2001
From: Matt Vollrath <tactii@gmail.com>
Date: Tue, 24 Feb 2026 18:28:33 -0500
Subject: [PATCH 1171/1303] e1000/e1000e: Fix leak in DMA error cleanup

If an error is encountered while mapping TX buffers, the driver should
unmap any buffers already mapped for that skb.

Because count is incremented after a successful mapping, it will always
match the correct number of unmappings needed when dma_error is reached.
Decrementing count before the while loop in dma_error causes an
off-by-one error. If any mapping was successful before an unsuccessful
mapping, exactly one DMA mapping would leak.

In these commits, a faulty while condition caused an infinite loop in
dma_error:
Commit 03b1320dfcee ("e1000e: remove use of skb_dma_map from e1000e
driver")
Commit 602c0554d7b0 ("e1000: remove use of skb_dma_map from e1000 driver")

Commit c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of
unsigned in *_tx_map()") fixed the infinite loop, but introduced the
off-by-one error.

This issue may still exist in the igbvf driver, but I did not address it
in this patch.

Fixes: c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of unsigned in *_tx_map()")
Assisted-by: Claude:claude-4.6-opus
Signed-off-by: Matt Vollrath <tactii@gmail.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 2 --
 drivers/net/ethernet/intel/e1000e/netdev.c    | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3d7648a119e5..9b09eb144b81 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2952,8 +2952,6 @@ static int e1000_tx_map(struct e1000_adapter *adapter,
 dma_error:
 	dev_err(&pdev->dev, "TX DMA map failed\n");
 	buffer_info->dma = 0;
-	if (count)
-		count--;
 
 	while (count--) {
 		if (i == 0)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 35dab1e3132f..9befdacd6730 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5652,8 +5652,6 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb,
 dma_error:
 	dev_err(&pdev->dev, "Tx DMA map failed\n");
 	buffer_info->dma = 0;
-	if (count)
-		count--;
 
 	while (count--) {
 		if (i == 0)

From 4a7d2729dc99437dbb880a64c47828c0d191b308 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Sat, 7 Mar 2026 18:20:16 -0300
Subject: [PATCH 1172/1303] smb: client: fix atomic open with O_DIRECT & O_SYNC

When user application requests O_DIRECT|O_SYNC along with O_CREAT on
open(2), CREATE_NO_BUFFER and CREATE_WRITE_THROUGH bits were missed in
CREATE request when performing an atomic open, thus leading to
potentially data integrity issues.

Fix this by setting those missing bits in CREATE request when
O_DIRECT|O_SYNC has been specified in cifs_do_create().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Acked-by: Henrique Carvalho <henrique.carvalho@suse.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h | 11 +++++++++++
 fs/smb/client/dir.c      |  1 +
 fs/smb/client/file.c     | 18 +++---------------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 6f9b6c72962b..bb0fe4b60240 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -20,6 +20,7 @@
 #include <linux/utsname.h>
 #include <linux/sched/mm.h>
 #include <linux/netfs.h>
+#include <linux/fcntl.h>
 #include "cifs_fs_sb.h"
 #include "cifsacl.h"
 #include <crypto/internal/hash.h>
@@ -2375,4 +2376,14 @@ static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi)
 	return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN;
 }
 
+static inline int cifs_open_create_options(unsigned int oflags, int opts)
+{
+	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
+	if (oflags & O_SYNC)
+		opts |= CREATE_WRITE_THROUGH;
+	if (oflags & O_DIRECT)
+		opts |= CREATE_NO_BUFFER;
+	return opts;
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 953f1fee8cb8..4bc217e9a727 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -308,6 +308,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 		goto out;
 	}
 
+	create_options |= cifs_open_create_options(oflags, create_options);
 	/*
 	 * if we're not using unix extensions, see if we need to set
 	 * ATTR_READONLY on the create call
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index cffcf82c1b69..13dda87f7711 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -584,15 +584,8 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
  *********************************************************************/
 
 	disposition = cifs_get_disposition(f_flags);
-
 	/* BB pass O_SYNC flag through on file attributes .. BB */
-
-	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
-	if (f_flags & O_SYNC)
-		create_options |= CREATE_WRITE_THROUGH;
-
-	if (f_flags & O_DIRECT)
-		create_options |= CREATE_NO_BUFFER;
+	create_options |= cifs_open_create_options(f_flags, create_options);
 
 retry_open:
 	oparms = (struct cifs_open_parms) {
@@ -1314,13 +1307,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
 		rdwr_for_fscache = 1;
 
 	desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache);
-
-	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
-	if (cfile->f_flags & O_SYNC)
-		create_options |= CREATE_WRITE_THROUGH;
-
-	if (cfile->f_flags & O_DIRECT)
-		create_options |= CREATE_NO_BUFFER;
+	create_options |= cifs_open_create_options(cfile->f_flags,
+						   create_options);
 
 	if (server->ops->get_lease_key)
 		server->ops->get_lease_key(inode, &cfile->fid);

From fae11330dc0642065568d6c0045322293fe59bc6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Mar 2026 16:07:13 +0100
Subject: [PATCH 1173/1303] smb: client: fix sbflags initialization

The newly introduced variable is initialized in an #ifdef block
but used outside of it, leading to undefined behavior when
CONFIG_CIFS_ALLOW_INSECURE_LEGACY is disabled:

fs/smb/client/dir.c:417:9: error: variable 'sbflags' is uninitialized when used here [-Werror,-Wuninitialized]
  417 |                                 if (sbflags & CIFS_MOUNT_DYNPERM)
      |                                     ^~~~~~~

Move the initialization into the declaration, the same way as the
other similar function do it.

Fixes: 4fc3a433c139 ("smb: client: use atomic_t for mnt_cifs_flags")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/dir.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 4bc217e9a727..6d2378eeb7f6 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -187,7 +187,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct inode *newinode = NULL;
-	unsigned int sbflags;
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	int disposition;
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
@@ -368,7 +368,6 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	 * If Open reported that we actually created a file then we now have to
 	 * set the mode if possible.
 	 */
-	sbflags = cifs_sb_flags(cifs_sb);
 	if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
 		struct cifs_unix_set_info_args args = {
 				.mode	= mode,

From d78840a6a38d312dc1a51a65317bb67e46f0b929 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Mon, 9 Mar 2026 16:00:49 +0530
Subject: [PATCH 1174/1303] smb: client: fix in-place encryption corruption in
 SMB2_write()

SMB2_write() places write payload in iov[1..n] as part of rq_iov.
smb3_init_transform_rq() pointer-shares rq_iov, so crypt_message()
encrypts iov[1] in-place, replacing the original plaintext with
ciphertext. On a replayable error, the retry sends the same iov[1]
which now contains ciphertext instead of the original data,
resulting in corruption.

The corruption is most likely to be observed when connections are
unstable, as reconnects trigger write retries that re-send the
already-encrypted data.

This affects SFU mknod, MF symlinks, etc. On kernels before
6.10 (prior to the netfs conversion), sync writes also used
this path and were similarly affected. The async write path
wasn't unaffected as it uses rq_iter which gets deep-copied.

Fix by moving the write payload into rq_iter via iov_iter_kvec(),
so smb3_init_transform_rq() deep-copies it before encryption.

Cc: stable@vger.kernel.org #6.3+
Acked-by: Henrique Carvalho <henrique.carvalho@suse.com>
Acked-by: Shyam Prasad N <sprasad@microsoft.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c43ca74e8704..5188218c25be 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -5307,7 +5307,10 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = n_vec + 1;
+	/* iov[0] is the SMB header; move payload to rq_iter for encryption safety */
+	rqst.rq_nvec = 1;
+	iov_iter_kvec(&rqst.rq_iter, ITER_SOURCE, &iov[1], n_vec,
+		      io_parms->length);
 
 	if (retries) {
 		/* Back-off before retry */

From 88d37abb366be95d772ceb4c7f26772e78447252 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Tue, 10 Mar 2026 21:08:47 +0800
Subject: [PATCH 1175/1303] smb/client: only export symbol for
 'smb2maperror-test' module

Only export smb2_get_err_map_test smb2_error_map_table_test and
smb2_error_map_num symbol for 'smb2maperror-test' module.

Fixes: 7d0bf050a587 ("smb/client: make SMB2 maperror KUnit tests a separate module")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2maperror.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index f4cff44e2796..2b8782c4f684 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -109,6 +109,9 @@ int __init smb2_init_maperror(void)
 }
 
 #if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
+#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \
+	EXPORT_SYMBOL_FOR_MODULES(sym, "smb2maperror_test")
+
 /* Previous prototype for eliminating the build warning. */
 const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
 
@@ -116,11 +119,11 @@ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status)
 {
 	return smb2_get_err_map(smb2_status);
 }
-EXPORT_SYMBOL_GPL(smb2_get_err_map_test);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_get_err_map_test);
 
 const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table;
-EXPORT_SYMBOL_GPL(smb2_error_map_table_test);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_table_test);
 
 unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table);
-EXPORT_SYMBOL_GPL(smb2_error_map_num);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_num);
 #endif

From 85b731ad4bbf6eb3fedf267ab00be3596f148432 Mon Sep 17 00:00:00 2001
From: Alan Borzeszkowski <alan.borzeszkowski@linux.intel.com>
Date: Mon, 9 Mar 2026 16:37:03 +0100
Subject: [PATCH 1176/1303] spi: intel-pci: Add support for Nova Lake mobile
 SPI flash

Add Intel Nova Lake PCD-H SPI serial flash PCI ID to the list of
supported devices.

Signed-off-by: Alan Borzeszkowski <alan.borzeszkowski@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://patch.msgid.link/20260309153703.74282-1-alan.borzeszkowski@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-intel-pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index bce3d149bea1..d8ef8f89330a 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -96,6 +96,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0xd323), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xe323), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xe423), (unsigned long)&cnl_info },
 	{ },

From 881a0263d502e1a93ebc13a78254e9ad19520232 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Sat, 7 Mar 2026 15:08:54 +0800
Subject: [PATCH 1177/1303] net: macb: Shuffle the tx ring before enabling tx

Quanyang observed that when using an NFS rootfs on an AMD ZynqMp board,
the rootfs may take an extended time to recover after a suspend.
Upon investigation, it was determined that the issue originates from a
problem in the macb driver.

According to the Zynq UltraScale TRM [1], when transmit is disabled,
the transmit buffer queue pointer resets to point to the address
specified by the transmit buffer queue base address register.

In the current implementation, the code merely resets `queue->tx_head`
and `queue->tx_tail` to '0'. This approach presents several issues:

- Packets already queued in the tx ring are silently lost,
  leading to memory leaks since the associated skbs cannot be released.

- Concurrent write access to `queue->tx_head` and `queue->tx_tail` may
  occur from `macb_tx_poll()` or `macb_start_xmit()` when these values
  are reset to '0'.

- The transmission may become stuck on a packet that has already been sent
  out, with its 'TX_USED' bit set, but has not yet been processed. However,
  due to the manipulation of 'queue->tx_head' and 'queue->tx_tail',
  `macb_tx_poll()` incorrectly assumes there are no packets to handle
  because `queue->tx_head == queue->tx_tail`. This issue is only resolved
  when a new packet is placed at this position. This is the root cause of
  the prolonged recovery time observed for the NFS root filesystem.

To resolve this issue, shuffle the tx ring and tx skb array so that
the first unsent packet is positioned at the start of the tx ring.
Additionally, ensure that updates to `queue->tx_head` and
`queue->tx_tail` are properly protected with the appropriate lock.

[1] https://docs.amd.com/v/u/en-US/ug1085-zynq-ultrascale-trm

Fixes: bf9cf80cab81 ("net: macb: Fix tx/rx malfunction after phy link down and up")
Reported-by: Quanyang Wang <quanyang.wang@windriver.com>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260307-zynqmp-v2-1-6ef98a70e1d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 98 +++++++++++++++++++++++-
 1 file changed, 95 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 5bc35f651ebd..f290d608b409 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/types.h>
 #include <linux/udp.h>
+#include <linux/gcd.h>
 #include <net/pkt_sched.h>
 #include "macb.h"
 
@@ -668,6 +669,97 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode,
 	netif_tx_stop_all_queues(ndev);
 }
 
+/* Use juggling algorithm to left rotate tx ring and tx skb array */
+static void gem_shuffle_tx_one_ring(struct macb_queue *queue)
+{
+	unsigned int head, tail, count, ring_size, desc_size;
+	struct macb_tx_skb tx_skb, *skb_curr, *skb_next;
+	struct macb_dma_desc *desc_curr, *desc_next;
+	unsigned int i, cycles, shift, curr, next;
+	struct macb *bp = queue->bp;
+	unsigned char desc[24];
+	unsigned long flags;
+
+	desc_size = macb_dma_desc_get_size(bp);
+
+	if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc)))
+		return;
+
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
+	head = queue->tx_head;
+	tail = queue->tx_tail;
+	ring_size = bp->tx_ring_size;
+	count = CIRC_CNT(head, tail, ring_size);
+
+	if (!(tail % ring_size))
+		goto unlock;
+
+	if (!count) {
+		queue->tx_head = 0;
+		queue->tx_tail = 0;
+		goto unlock;
+	}
+
+	shift = tail % ring_size;
+	cycles = gcd(ring_size, shift);
+
+	for (i = 0; i < cycles; i++) {
+		memcpy(&desc, macb_tx_desc(queue, i), desc_size);
+		memcpy(&tx_skb, macb_tx_skb(queue, i),
+		       sizeof(struct macb_tx_skb));
+
+		curr = i;
+		next = (curr + shift) % ring_size;
+
+		while (next != i) {
+			desc_curr = macb_tx_desc(queue, curr);
+			desc_next = macb_tx_desc(queue, next);
+
+			memcpy(desc_curr, desc_next, desc_size);
+
+			if (next == ring_size - 1)
+				desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+			if (curr == ring_size - 1)
+				desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+
+			skb_curr = macb_tx_skb(queue, curr);
+			skb_next = macb_tx_skb(queue, next);
+			memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb));
+
+			curr = next;
+			next = (curr + shift) % ring_size;
+		}
+
+		desc_curr = macb_tx_desc(queue, curr);
+		memcpy(desc_curr, &desc, desc_size);
+		if (i == ring_size - 1)
+			desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+		if (curr == ring_size - 1)
+			desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+		memcpy(macb_tx_skb(queue, curr), &tx_skb,
+		       sizeof(struct macb_tx_skb));
+	}
+
+	queue->tx_head = count;
+	queue->tx_tail = 0;
+
+	/* Make descriptor updates visible to hardware */
+	wmb();
+
+unlock:
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
+}
+
+/* Rotate the queue so that the tail is at index 0 */
+static void gem_shuffle_tx_rings(struct macb *bp)
+{
+	struct macb_queue *queue;
+	int q;
+
+	for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++)
+		gem_shuffle_tx_one_ring(queue);
+}
+
 static void macb_mac_link_up(struct phylink_config *config,
 			     struct phy_device *phy,
 			     unsigned int mode, phy_interface_t interface,
@@ -706,8 +798,6 @@ static void macb_mac_link_up(struct phylink_config *config,
 			ctrl |= MACB_BIT(PAE);
 
 		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-			queue->tx_head = 0;
-			queue->tx_tail = 0;
 			queue_writel(queue, IER,
 				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 		}
@@ -721,8 +811,10 @@ static void macb_mac_link_up(struct phylink_config *config,
 
 	spin_unlock_irqrestore(&bp->lock, flags);
 
-	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
 		macb_set_tx_clk(bp, speed);
+		gem_shuffle_tx_rings(bp);
+	}
 
 	/* Enable Rx and Tx; Enable PTP unicast */
 	ctrl = macb_readl(bp, NCR);

From 28b225282d44e2ef40e7f46cfdbd5d1b20b8874f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 Mar 2026 17:39:07 -0700
Subject: [PATCH 1178/1303] page_pool: store detach_time as ktime_t to avoid
 false-negatives

While testing other changes in vng I noticed that
nl_netdev.page_pool_check flakes. This never happens in real CI.

Turns out vng may boot and get to that test in less than a second.
page_pool_detached() records the detach time in seconds, so if
vng is fast enough detach time is set to 0. Other code treats
0 as "not detached". detach_time is only used to report the state
to the user, so it's not a huge deal in practice but let's fix it.
Store the raw ktime_t (nanoseconds) instead. A nanosecond value
of 0 is practically impossible.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Fixes: 69cb4952b6f6 ("net: page_pool: report when page pool was destroyed")
Link: https://patch.msgid.link/20260310003907.3540019-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 2 +-
 net/core/page_pool_user.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 0d453484a585..cdd95477af7a 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -247,7 +247,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
-		u64 detach_time;
+		ktime_t detach_time;
 		u32 id;
 	} user;
 };
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index c82a95beceff..ee5060d8eec0 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -245,7 +245,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		goto err_cancel;
 	if (pool->user.detach_time &&
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME,
-			 pool->user.detach_time))
+			 ktime_divns(pool->user.detach_time, NSEC_PER_SEC)))
 		goto err_cancel;
 
 	if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL))
@@ -337,7 +337,7 @@ int page_pool_list(struct page_pool *pool)
 void page_pool_detached(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
-	pool->user.detach_time = ktime_get_boottime_seconds();
+	pool->user.detach_time = ktime_get_boottime();
 	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
 	mutex_unlock(&page_pools_lock);
 }

From 2503d08f8a2de618e5c3a8183b250ff4a2e2d52c Mon Sep 17 00:00:00 2001
From: Fan Wu <fanwu01@zju.edu.cn>
Date: Mon, 9 Mar 2026 13:24:09 +0000
Subject: [PATCH 1179/1303] net: ethernet: arc: emac: quiesce interrupts before
 requesting IRQ

Normal RX/TX interrupts are enabled later, in arc_emac_open(), so probe
should not see interrupt delivery in the usual case. However, hardware may
still present stale or latched interrupt status left by firmware or the
bootloader.

If probe later unwinds after devm_request_irq() has installed the handler,
such a stale interrupt can still reach arc_emac_intr() during teardown and
race with release of the associated net_device.

Avoid that window by putting the device into a known quiescent state before
requesting the IRQ: disable all EMAC interrupt sources and clear any
pending EMAC interrupt status bits. This keeps the change hardware-focused
and minimal, while preventing spurious IRQ delivery from leftover state.

Fixes: e4f2379db6c6 ("ethernet/arc/arc_emac - Add new driver")
Cc: stable@vger.kernel.org
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Link: https://patch.msgid.link/20260309132409.584966-1-fanwu01@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/arc/emac_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 8283aeee35fb..dde4046cbf01 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -934,6 +934,17 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	/* Set poll rate so that it polls every 1 ms */
 	arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000);
 
+	/*
+	 * Put the device into a known quiescent state before requesting
+	 * the IRQ. Clear only EMAC interrupt status bits here; leave the
+	 * MDIO completion bit alone and avoid writing TXPL_MASK, which is
+	 * used to force TX polling rather than acknowledge interrupts.
+	 */
+	arc_reg_set(priv, R_ENABLE, 0);
+	arc_reg_set(priv, R_STATUS, RXINT_MASK | TXINT_MASK | ERR_MASK |
+		    TXCH_MASK | MSER_MASK | RXCR_MASK |
+		    RXFR_MASK | RXFL_MASK);
+
 	ndev->irq = irq;
 	dev_info(dev, "IRQ is %d\n", ndev->irq);
 

From f441b489cc66fbc44d78b6c123e74283b8077431 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 10 Mar 2026 00:41:56 +0000
Subject: [PATCH 1180/1303] net: dsa: mxl862xx: don't set user_mii_bus

The PHY addresses in the MII bus are not equal to the port addresses,
so the bus cannot be assigned as user_mii_bus. Falling back on the
user_mii_bus in case a PHY isn't declared in device tree will result in
using the wrong (in this case: off-by-+1) PHY.
Remove the wrong assignment.

Fixes: 23794bec1cb60 ("net: dsa: add basic initial driver for MxL862xx switches")
Suggested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/0f0df310fd8cab57e0e5e3d0831dd057fd05bcd5.1773103271.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mxl862xx/mxl862xx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c
index b1e2094b5816..d7ab04f5afef 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx.c
+++ b/drivers/net/dsa/mxl862xx/mxl862xx.c
@@ -149,7 +149,6 @@ static int mxl862xx_setup_mdio(struct dsa_switch *ds)
 		return -ENOMEM;
 
 	bus->priv = priv;
-	ds->user_mii_bus = bus;
 	bus->name = KBUILD_MODNAME "-mii";
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
 	bus->read_c45 = mxl862xx_phy_read_c45_mii_bus;

From 57885276cc16a2e2b76282c808a4e84cbecb3aae Mon Sep 17 00:00:00 2001
From: Paul Moses <p@1g4.org>
Date: Mon, 9 Mar 2026 17:35:10 +0000
Subject: [PATCH 1181/1303] net-shapers: don't free reply skb after
 genlmsg_reply()

genlmsg_reply() hands the reply skb to netlink, and
netlink_unicast() consumes it on all return paths, whether the
skb is queued successfully or freed on an error path.

net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit()
currently jump to free_msg after genlmsg_reply() fails and call
nlmsg_free(msg), which can hit the same skb twice.

Return the genlmsg_reply() error directly and keep free_msg
only for pre-reply failures.

Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation")
Fixes: 553ea9f1efd6 ("net: shaper: implement introspection support")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moses <p@1g4.org>
Link: https://patch.msgid.link/20260309173450.538026-2-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/shaper/shaper.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
index 005bfc766e22..3fd6629cb999 100644
--- a/net/shaper/shaper.c
+++ b/net/shaper/shaper.c
@@ -759,11 +759,7 @@ int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret)
 		goto free_msg;
 
-	ret = genlmsg_reply(msg, info);
-	if (ret)
-		goto free_msg;
-
-	return 0;
+	return genlmsg_reply(msg, info);
 
 free_msg:
 	nlmsg_free(msg);
@@ -1313,10 +1309,7 @@ int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret)
 		goto free_msg;
 
-	ret =  genlmsg_reply(msg, info);
-	if (ret)
-		goto free_msg;
-	return 0;
+	return genlmsg_reply(msg, info);
 
 free_msg:
 	nlmsg_free(msg);

From 908c344d5cfac4160f49715da9efacdf5b6a28bd Mon Sep 17 00:00:00 2001
From: Nicolai Buchwitz <nb@tipi-net.de>
Date: Tue, 10 Mar 2026 06:49:35 +0100
Subject: [PATCH 1182/1303] net: bcmgenet: fix broken EEE by converting to
 phylib-managed state

The bcmgenet EEE implementation is broken in several ways.
phy_support_eee() is never called, so the PHY never advertises EEE
and phylib never sets phydev->enable_tx_lpi.  bcmgenet_mac_config()
checks priv->eee.eee_enabled to decide whether to enable the MAC
LPI logic, but that field is never initialised to true, so the MAC
never enters Low Power Idle even when EEE is negotiated - wasting
the power savings EEE is designed to provide.  The only way to get
EEE working at all is a manual 'ethtool --set-eee eth0 eee on' after
every link-up, and even then bcmgenet_get_eee() immediately clobbers
the reported state because phy_ethtool_get_eee() overwrites
eee_enabled and tx_lpi_enabled with the uninitialised PHY eee_cfg
values.  Finally, bcmgenet_mac_config() is only called on link-up,
so EEE is never disabled in hardware on link-down.

Fix all of this by removing the MAC-side EEE state tracking
(priv->eee) and aligning with the pattern used by other non-phylink
MAC drivers such as FEC.

Call phy_support_eee() in bcmgenet_mii_probe() so the PHY advertises
EEE link modes and phylib tracks negotiation state.  Move the EEE
hardware control to bcmgenet_mii_setup(), which is called on every
link event, and drive it directly from phydev->enable_tx_lpi - the
flag phylib sets when EEE is negotiated and the user has not disabled
it.  This enables EEE automatically once the link partner agrees and
disables it cleanly on link-down.

Make bcmgenet_get_eee() and bcmgenet_set_eee() pure passthroughs to
phy_ethtool_get_eee() and phy_ethtool_set_eee(), with the MAC
hardware register read/written for tx_lpi_timer.  Drop struct
ethtool_keee eee from struct bcmgenet_priv.

Fixes: fe0d4fd9285e ("net: phy: Keep track of EEE configuration")
Link: https://lore.kernel.org/netdev/d352039f-4cbb-41e6-9aeb-0b4f3941b54c@lunn.ch/
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260310054935.1238594-1-nb@tipi-net.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 31 +++++++------------
 .../net/ethernet/broadcom/genet/bcmgenet.h    |  5 +--
 drivers/net/ethernet/broadcom/genet/bcmmii.c  | 10 +++---
 3 files changed, 18 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index a71cd729fde6..482a31e7b72b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1342,8 +1342,7 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	}
 }
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled)
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL;
@@ -1363,7 +1362,7 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 
 	/* Enable EEE and switch to a 27Mhz clock automatically */
 	reg = bcmgenet_readl(priv->base + off);
-	if (tx_lpi_enabled)
+	if (enable)
 		reg |= TBUF_EEE_EN | TBUF_PM_EN;
 	else
 		reg &= ~(TBUF_EEE_EN | TBUF_PM_EN);
@@ -1382,14 +1381,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 		priv->clk_eee_enabled = false;
 	}
 
-	priv->eee.eee_enabled = enable;
-	priv->eee.tx_lpi_enabled = tx_lpi_enabled;
 }
 
 static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
+	int ret;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1397,17 +1394,21 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	e->tx_lpi_enabled = p->tx_lpi_enabled;
+	ret = phy_ethtool_get_eee(dev->phydev, e);
+	if (ret)
+		return ret;
+
+	/* tx_lpi_timer is maintained by the MAC hardware register; the
+	 * PHY-level eee_cfg timer is not set for GENET.
+	 */
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(dev->phydev, e);
+	return 0;
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
-	bool active;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1415,15 +1416,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	p->eee_enabled = e->eee_enabled;
-
-	if (!p->eee_enabled) {
-		bcmgenet_eee_enable_set(dev, false, false);
-	} else {
-		active = phy_init_eee(dev->phydev, false) >= 0;
-		bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
-		bcmgenet_eee_enable_set(dev, active, e->tx_lpi_enabled);
-	}
+	bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
 
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 5ec3979779ec..9e4110c7fdf6 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -665,8 +665,6 @@ struct bcmgenet_priv {
 	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
-
-	struct ethtool_keee eee;
 };
 
 static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
@@ -749,7 +747,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			      enum bcmgenet_power_mode mode);
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled);
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable);
 
 #endif /* __BCMGENET_H__ */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 38f854b94a79..a4e0d5a68268 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -29,7 +29,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
-	bool active;
 
 	/* speed */
 	if (phydev->speed == SPEED_1000)
@@ -90,10 +89,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
-	active = phy_init_eee(phydev, 0) >= 0;
-	bcmgenet_eee_enable_set(dev,
-				priv->eee.eee_enabled && active,
-				priv->eee.tx_lpi_enabled);
 }
 
 /* setup netdev link state when PHY link status change and
@@ -113,6 +108,8 @@ void bcmgenet_mii_setup(struct net_device *dev)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
+	bcmgenet_eee_enable_set(dev, phydev->enable_tx_lpi);
+
 	phy_print_status(phydev);
 }
 
@@ -412,6 +409,9 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	/* Indicate that the MAC is responsible for PHY PM */
 	dev->phydev->mac_managed_pm = true;
 
+	if (!GENET_IS_V1(priv))
+		phy_support_eee(dev->phydev);
+
 	return 0;
 }
 

From 5182e5ec4355dd690307f5d5c28cbfc5b2c06a97 Mon Sep 17 00:00:00 2001
From: Lianqin Hu <hulianqin@vivo.com>
Date: Wed, 11 Mar 2026 07:22:38 +0000
Subject: [PATCH 1183/1303] ALSA: usb-audio: Add iface reset and delay quirk
 for SPACETOUCH USB Audio

Setting up the interface when suspended/resumeing fail on this card.
Adding a reset and delay quirk will eliminate this problem.

usb 1-1: New USB device found, idVendor=0666, idProduct=0880
usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
usb 1-1: Product: USB Audio
usb 1-1: Manufacturer: SPACETOUCH
usb 1-1: SerialNumber: 000000000

Signed-off-by: Lianqin Hu <hulianqin@vivo.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/TYUPR06MB6217ACC80B70BE25D87456B0D247A@TYUPR06MB6217.apcprd06.prod.outlook.com
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index d54a1a44a69b..049a94079f9e 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2243,6 +2243,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IFACE_DELAY | QUIRK_FLAG_FORCE_IFACE_RESET),
 	DEVICE_FLG(0x0661, 0x0883, /* iBasso DC04 Ultra */
 		   QUIRK_FLAG_DSD_RAW),
+	DEVICE_FLG(0x0666, 0x0880, /* SPACETOUCH USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */

From 49973e2a4156a88e46ba1c1c484b7c214199a181 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 9 Mar 2026 09:14:49 +0100
Subject: [PATCH 1184/1303] drm/loongson: Mark driver as orphaned

The maintainer's email address has been bouncing for months. Mark the
loongson DRM driver as orphaned.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Maxime Ripard <mripard@kernel.org>
Link: https://patch.msgid.link/20260309081503.67123-1-tzimmermann@suse.de
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..b35fc8e062c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8630,9 +8630,8 @@ F:	drivers/gpu/drm/lima/
 F:	include/uapi/drm/lima_drm.h
 
 DRM DRIVERS FOR LOONGSON
-M:	Sui Jingfeng <suijingfeng@loongson.cn>
 L:	dri-devel@lists.freedesktop.org
-S:	Supported
+S:	Orphan
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/loongson/
 

From 770444611f047dbfd4517ec0bc1b179d40c2f346 Mon Sep 17 00:00:00 2001
From: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Date: Thu, 26 Feb 2026 16:07:31 +0100
Subject: [PATCH 1185/1303] libceph: Use u32 for non-negative values in
 ceph_monmap_decode()

This patch fixes unnecessary implicit conversions that change signedness
of blob_len and num_mon in ceph_monmap_decode().
Currently blob_len and num_mon are (signed) int variables. They are used
to hold values that are always non-negative and get assigned in
ceph_decode_32_safe(), which is meant to assign u32 values. Both
variables are subsequently used as unsigned values, and the value of
num_mon is further assigned to monmap->num_mon, which is of type u32.
Therefore, both variables should be of type u32. This is especially
relevant for num_mon. If the value read from the incoming message is
very large, it is interpreted as a negative value, and the check for
num_mon > CEPH_MAX_MON does not catch it. This leads to the attempt to
allocate a very large chunk of memory for monmap, which will most likely
fail. In this case, an unnecessary attempt to allocate memory is
performed, and -ENOMEM is returned instead of -EINVAL.

Cc: stable@vger.kernel.org
Signed-off-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/mon_client.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 5136b3766c44..d5080530ce0c 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	struct ceph_monmap *monmap = NULL;
 	struct ceph_fsid fsid;
 	u32 struct_len;
-	int blob_len;
-	int num_mon;
+	u32 blob_len;
+	u32 num_mon;
 	u8 struct_v;
 	u32 epoch;
 	int ret;
@@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	}
 	ceph_decode_32_safe(p, end, num_mon, e_inval);
 
-	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
+	dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch,
 	     num_mon);
 	if (num_mon > CEPH_MAX_MON)
 		goto e_inval;

From b282c43ed156ae15ea76748fc15cd5c39dc9ab72 Mon Sep 17 00:00:00 2001
From: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Date: Tue, 10 Mar 2026 15:28:15 +0100
Subject: [PATCH 1186/1303] libceph: Fix potential out-of-bounds access in
 ceph_handle_auth_reply()

This patch fixes an out-of-bounds access in ceph_handle_auth_reply()
that can be triggered by a message of type CEPH_MSG_AUTH_REPLY. In
ceph_handle_auth_reply(), the value of the payload_len field of such a
message is stored in a variable of type int. A value greater than
INT_MAX leads to an integer overflow and is interpreted as a negative
value. This leads to decrementing the pointer address by this value and
subsequently accessing it because ceph_decode_need() only checks that
the memory access does not exceed the end address of the allocation.

This patch fixes the issue by changing the data type of payload_len to
u32. Additionally, the data type of result_msg_len is changed to u32,
as it is also a variable holding a non-negative length.

Also, an additional layer of sanity checks is introduced, ensuring that
directly after reading it from the message, payload_len and
result_msg_len are not greater than the overall segment length.

BUG: KASAN: slab-out-of-bounds in ceph_handle_auth_reply+0x642/0x7a0 [libceph]
Read of size 4 at addr ffff88811404df14 by task kworker/20:1/262

CPU: 20 UID: 0 PID: 262 Comm: kworker/20:1 Not tainted 6.19.2 #5 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Workqueue: ceph-msgr ceph_con_workfn [libceph]
Call Trace:
 <TASK>
 dump_stack_lvl+0x76/0xa0
 print_report+0xd1/0x620
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? kasan_complete_mode_report_info+0x72/0x210
 kasan_report+0xe7/0x130
 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 __asan_report_load_n_noabort+0xf/0x20
 ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 mon_dispatch+0x973/0x23d0 [libceph]
 ? apparmor_socket_recvmsg+0x6b/0xa0
 ? __pfx_mon_dispatch+0x10/0x10 [libceph]
 ? __kasan_check_write+0x14/0x30i
 ? mutex_unlock+0x7f/0xd0
 ? __pfx_mutex_unlock+0x10/0x10
 ? __pfx_do_recvmsg+0x10/0x10 [libceph]
 ceph_con_process_message+0x1f1/0x650 [libceph]
 process_message+0x1e/0x450 [libceph]
 ceph_con_v2_try_read+0x2e48/0x6c80 [libceph]
 ? __pfx_ceph_con_v2_try_read+0x10/0x10 [libceph]
 ? save_fpregs_to_fpstate+0xb0/0x230
 ? raw_spin_rq_unlock+0x17/0xa0
 ? finish_task_switch.isra.0+0x13b/0x760
 ? __switch_to+0x385/0xda0
 ? __kasan_check_write+0x14/0x30
 ? mutex_lock+0x8d/0xe0
 ? __pfx_mutex_lock+0x10/0x10
 ceph_con_workfn+0x248/0x10c0 [libceph]
 process_one_work+0x629/0xf80
 ? __kasan_check_write+0x14/0x30
 worker_thread+0x87f/0x1570
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? __pfx_try_to_wake_up+0x10/0x10
 ? kasan_print_address_stack_frame+0x1f7/0x280
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x396/0x830
 ? __pfx__raw_spin_lock_irq+0x10/0x10
 ? __pfx_kthread+0x10/0x10
 ? __kasan_check_write+0x14/0x30
 ? recalc_sigpending+0x180/0x210
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x3f7/0x610
 ? __pfx_ret_from_fork+0x10/0x10
 ? __switch_to+0x385/0xda0
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>

[ idryomov: replace if statements with ceph_decode_need() for
  payload_len and result_msg_len ]

Cc: stable@vger.kernel.org
Signed-off-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/auth.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index 343c841784ce..901b93530b21 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	s32 result;
 	u64 global_id;
 	void *payload, *payload_end;
-	int payload_len;
+	u32 payload_len;
 	char *result_msg;
-	int result_msg_len;
+	u32 result_msg_len;
 	int ret = -EINVAL;
 
 	mutex_lock(&ac->mutex);
@@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	result = ceph_decode_32(&p);
 	global_id = ceph_decode_64(&p);
 	payload_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, payload_len, bad);
 	payload = p;
 	p += payload_len;
 	ceph_decode_need(&p, end, sizeof(u32), bad);
 	result_msg_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, result_msg_len, bad);
 	result_msg = p;
 	p += result_msg_len;
 	if (p != end)

From 755a648e78f12574482d4698d877375793867fa1 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 6 Mar 2026 21:24:03 -0500
Subject: [PATCH 1187/1303] time/jiffies: Mark jiffies_64_to_clock_t() notrace

The trace_clock_jiffies() function that handles the "uptime" clock for
tracing calls jiffies_64_to_clock_t(). This causes the function tracer to
constantly recurse when the tracing clock is set to "uptime". Mark it
notrace to prevent unnecessary recursion when using the "uptime" clock.

Fixes: 58d4e21e50ff3 ("tracing: Fix wraparound problems in "uptime" trace clock")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260306212403.72270bb2@robin
---
 kernel/time/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/time.c b/kernel/time/time.c
index 36fd2313ae7e..0d832317d576 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -697,7 +697,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies);
  *
  * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
  */
-u64 jiffies_64_to_clock_t(u64 x)
+notrace u64 jiffies_64_to_clock_t(u64 x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ

From b2e48c429ec54715d16fefa719dd2fbded2e65be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:28:53 +0100
Subject: [PATCH 1188/1303] sched/mmcid: Prevent CID stalls due to concurrent
 forks

A newly forked task is accounted as MMCID user before the task is visible
in the process' thread list and the global task list. This creates the
following problem:

 CPU1			CPU2
 fork()
   sched_mm_cid_fork(tnew1)
     tnew1->mm.mm_cid_users++;
     tnew1->mm_cid.cid = getcid()
-> preemption
			fork()
			  sched_mm_cid_fork(tnew2)
			    tnew2->mm.mm_cid_users++;
                            // Reaches the per CPU threshold
			    mm_cid_fixup_tasks_to_cpus()
			    for_each_other(current, p)
			         ....

As tnew1 is not visible yet, this fails to fix up the already allocated CID
of tnew1. As a consequence a subsequent schedule in might fail to acquire a
(transitional) CID and the machine stalls.

Move the invocation of sched_mm_cid_fork() after the new task becomes
visible in the thread and the task list to prevent this.

This also makes it symmetrical vs. exit() where the task is removed as CID
user before the task is removed from the thread and task lists.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202525.969061974@kernel.org
---
 include/linux/sched.h |  2 --
 kernel/fork.c         |  2 --
 kernel/sched/core.c   | 22 +++++++++++++++-------
 3 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a7b4a980eb2f..5a5d3dbc9cdf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
 #ifdef CONFIG_SCHED_MM_CID
 void sched_mm_cid_before_execve(struct task_struct *t);
 void sched_mm_cid_after_execve(struct task_struct *t);
-void sched_mm_cid_fork(struct task_struct *t);
 void sched_mm_cid_exit(struct task_struct *t);
 static __always_inline int task_mm_cid(struct task_struct *t)
 {
@@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t)
 #else
 static inline void sched_mm_cid_before_execve(struct task_struct *t) { }
 static inline void sched_mm_cid_after_execve(struct task_struct *t) { }
-static inline void sched_mm_cid_fork(struct task_struct *t) { }
 static inline void sched_mm_cid_exit(struct task_struct *t) { }
 static __always_inline int task_mm_cid(struct task_struct *t)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 65113a304518..7febf4c2889e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1586,7 +1586,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk)
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
-	sched_mm_cid_fork(tsk);
 	return 0;
 }
 
@@ -2498,7 +2497,6 @@ __latent_entropy struct task_struct *copy_process(
 	exit_nsproxy_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm) {
-		sched_mm_cid_exit(p);
 		mm_clear_owner(p->mm, p);
 		mmput(p->mm);
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7f77c165a6e..d25427855b5d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4729,8 +4729,11 @@ void sched_cancel_fork(struct task_struct *p)
 	scx_cancel_fork(p);
 }
 
+static void sched_mm_cid_fork(struct task_struct *t);
+
 void sched_post_fork(struct task_struct *p)
 {
+	sched_mm_cid_fork(p);
 	uclamp_post_fork(p);
 	scx_post_fork(p);
 }
@@ -10646,12 +10649,13 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
 	 * possible switch back to per task mode happens either in the
 	 * deferred handler function or in the next fork()/exit().
 	 *
-	 * The caller has already transferred. The newly incoming task is
-	 * already accounted for, but not yet visible.
+	 * The caller has already transferred so remove it from the users
+	 * count. The incoming task is already visible and has mm_cid.active,
+	 * but has task::mm_cid::cid == UNSET. Still it needs to be accounted
+	 * for. Concurrent fork()s might add more threads, but all of them have
+	 * task::mm_cid::active = 0, so they don't affect the accounting here.
 	 */
-	users = mm->mm_cid.users - 2;
-	if (!users)
-		return;
+	users = mm->mm_cid.users - 1;
 
 	guard(rcu)();
 	for_other_threads(current, t) {
@@ -10688,12 +10692,15 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 	return mm_update_max_cids(mm);
 }
 
-void sched_mm_cid_fork(struct task_struct *t)
+static void sched_mm_cid_fork(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
 	bool percpu;
 
-	WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET);
+	if (!mm)
+		return;
+
+	WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET);
 
 	guard(mutex)(&mm->mm_cid.mutex);
 	scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) {
@@ -10885,6 +10892,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 }
 #else /* CONFIG_SCHED_MM_CID */
 static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { }
+static inline void sched_mm_cid_fork(struct task_struct *t) { }
 #endif /* !CONFIG_SCHED_MM_CID */
 
 static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);

From 28b5a1395036d6c7a6c8034d85ad3d7d365f192c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:28:58 +0100
Subject: [PATCH 1189/1303] sched/mmcid: Handle vfork()/CLONE_VM correctly

Matthieu and Jiri reported stalls where a task endlessly loops in
mm_get_cid() when scheduling in.

It turned out that the logic which handles vfork()'ed tasks is broken. It
is invoked when the number of tasks associated to a process is smaller than
the number of MMCID users. It then walks the task list to find the
vfork()'ed task, but accounts all the already processed tasks as well.

If that double processing brings the number of to be handled tasks to 0,
the walk stops and the vfork()'ed task's CID is not fixed up. As a
consequence a subsequent schedule in fails to acquire a (transitional) CID
and the machine stalls.

Cure this by removing the accounting condition and make the fixup always
walk the full task list if it could not find the exact number of users in
the process' thread list.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Closes: https://lore.kernel.org/b24ffcb3-09d5-4e48-9070-0b69bc654281@kernel.org
Reported-by: Matthieu Baerts <matttbe@kernel.org>
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.048657665@kernel.org
---
 kernel/sched/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d25427855b5d..ee59cd19b9a8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10670,10 +10670,7 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
 	for_each_process_thread(p, t) {
 		if (t == current || t->mm != mm)
 			continue;
-		if (mm_cid_fixup_task_to_cpu(t, mm)) {
-			if (--users == 0)
-				return;
-		}
+		mm_cid_fixup_task_to_cpu(t, mm);
 	}
 }
 

From 7574ac6e49789ddee1b1be9b2afb42b4a1b4b1f4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:29:04 +0100
Subject: [PATCH 1190/1303] sched/mmcid: Remove pointless preempt guard

This is a leftover from the early versions of this function where it could
be invoked without mm::mm_cid::lock held.

Remove it and add lockdep asserts instead.

Fixes: 653fda7ae73d ("sched/mmcid: Switch over to the new mechanism")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.116363613@kernel.org
---
 kernel/sched/core.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee59cd19b9a8..f56156f91d08 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10684,6 +10684,8 @@ static void mm_cid_fixup_tasks_to_cpus(void)
 
 static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 {
+	lockdep_assert_held(&mm->mm_cid.lock);
+
 	t->mm_cid.active = 1;
 	mm->mm_cid.users++;
 	return mm_update_max_cids(mm);
@@ -10736,12 +10738,12 @@ static void sched_mm_cid_fork(struct task_struct *t)
 
 static bool sched_mm_cid_remove_user(struct task_struct *t)
 {
+	lockdep_assert_held(&t->mm->mm_cid.lock);
+
 	t->mm_cid.active = 0;
-	scoped_guard(preempt) {
-		/* Clear the transition bit */
-		t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
-		mm_unset_cid_on_task(t);
-	}
+	/* Clear the transition bit */
+	t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
+	mm_unset_cid_on_task(t);
 	t->mm->mm_cid.users--;
 	return mm_update_max_cids(t->mm);
 }

From 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:29:09 +0100
Subject: [PATCH 1191/1303] sched/mmcid: Avoid full tasklist walks

Chasing vfork()'ed tasks on a CID ownership mode switch requires a full
task list walk, which is obviously expensive on large systems.

Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid
and walk this list instead. This removes the proven to be flaky counting
logic and avoids a full task list walk in the case of vfork()'ed tasks.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.183824481@kernel.org
---
 include/linux/rseq_types.h |  6 +++-
 kernel/fork.c              |  1 +
 kernel/sched/core.c        | 56 +++++++++-----------------------------
 3 files changed, 19 insertions(+), 44 deletions(-)

diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index da5fa6f40294..0b42045988db 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -133,10 +133,12 @@ struct rseq_data { };
  * @active:	MM CID is active for the task
  * @cid:	The CID associated to the task either permanently or
  *		borrowed from the CPU
+ * @node:	Queued in the per MM MMCID list
  */
 struct sched_mm_cid {
 	unsigned int		active;
 	unsigned int		cid;
+	struct hlist_node	node;
 };
 
 /**
@@ -157,6 +159,7 @@ struct mm_cid_pcpu {
  * @work:		Regular work to handle the affinity mode change case
  * @lock:		Spinlock to protect against affinity setting which can't take @mutex
  * @mutex:		Mutex to serialize forks and exits related to this mm
+ * @user_list:		List of the MM CID users of a MM
  * @nr_cpus_allowed:	The number of CPUs in the per MM allowed CPUs map. The map
  *			is growth only.
  * @users:		The number of tasks sharing this MM. Separate from mm::mm_users
@@ -177,13 +180,14 @@ struct mm_mm_cid {
 
 	raw_spinlock_t		lock;
 	struct mutex		mutex;
+	struct hlist_head	user_list;
 
 	/* Low frequency modified */
 	unsigned int		nr_cpus_allowed;
 	unsigned int		users;
 	unsigned int		pcpu_thrs;
 	unsigned int		update_deferred;
-}____cacheline_aligned_in_smp;
+} ____cacheline_aligned;
 #else /* CONFIG_SCHED_MM_CID */
 struct mm_mm_cid { };
 struct sched_mm_cid { };
diff --git a/kernel/fork.c b/kernel/fork.c
index 7febf4c2889e..bc2bf58b93b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1000,6 +1000,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_SCHED_MM_CID
 	tsk->mm_cid.cid = MM_CID_UNSET;
 	tsk->mm_cid.active = 0;
+	INIT_HLIST_NODE(&tsk->mm_cid.node);
 #endif
 	return tsk;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f56156f91d08..496dff740dca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10620,13 +10620,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc
 	}
 }
 
-static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
+static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
 {
 	/* Remote access to mm::mm_cid::pcpu requires rq_lock */
 	guard(task_rq_lock)(t);
-	/* If the task is not active it is not in the users count */
-	if (!t->mm_cid.active)
-		return false;
 	if (cid_on_task(t->mm_cid.cid)) {
 		/* If running on the CPU, put the CID in transit mode, otherwise drop it */
 		if (task_rq(t)->curr == t)
@@ -10634,51 +10631,21 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm
 		else
 			mm_unset_cid_on_task(t);
 	}
-	return true;
-}
-
-static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
-{
-	struct task_struct *p, *t;
-	unsigned int users;
-
-	/*
-	 * This can obviously race with a concurrent affinity change, which
-	 * increases the number of allowed CPUs for this mm, but that does
-	 * not affect the mode and only changes the CID constraints. A
-	 * possible switch back to per task mode happens either in the
-	 * deferred handler function or in the next fork()/exit().
-	 *
-	 * The caller has already transferred so remove it from the users
-	 * count. The incoming task is already visible and has mm_cid.active,
-	 * but has task::mm_cid::cid == UNSET. Still it needs to be accounted
-	 * for. Concurrent fork()s might add more threads, but all of them have
-	 * task::mm_cid::active = 0, so they don't affect the accounting here.
-	 */
-	users = mm->mm_cid.users - 1;
-
-	guard(rcu)();
-	for_other_threads(current, t) {
-		if (mm_cid_fixup_task_to_cpu(t, mm))
-			users--;
-	}
-
-	if (!users)
-		return;
-
-	/* Happens only for VM_CLONE processes. */
-	for_each_process_thread(p, t) {
-		if (t == current || t->mm != mm)
-			continue;
-		mm_cid_fixup_task_to_cpu(t, mm);
-	}
 }
 
 static void mm_cid_fixup_tasks_to_cpus(void)
 {
 	struct mm_struct *mm = current->mm;
+	struct task_struct *t;
+
+	lockdep_assert_held(&mm->mm_cid.mutex);
+
+	hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) {
+		/* Current has already transferred before invoking the fixup. */
+		if (t != current)
+			mm_cid_fixup_task_to_cpu(t, mm);
+	}
 
-	mm_cid_do_fixup_tasks_to_cpus(mm);
 	mm_cid_complete_transit(mm, MM_CID_ONCPU);
 }
 
@@ -10687,6 +10654,7 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 	lockdep_assert_held(&mm->mm_cid.lock);
 
 	t->mm_cid.active = 1;
+	hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list);
 	mm->mm_cid.users++;
 	return mm_update_max_cids(mm);
 }
@@ -10744,6 +10712,7 @@ static bool sched_mm_cid_remove_user(struct task_struct *t)
 	/* Clear the transition bit */
 	t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
 	mm_unset_cid_on_task(t);
+	hlist_del_init(&t->mm_cid.node);
 	t->mm->mm_cid.users--;
 	return mm_update_max_cids(t->mm);
 }
@@ -10886,6 +10855,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 	mutex_init(&mm->mm_cid.mutex);
 	mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work);
 	INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn);
+	INIT_HLIST_HEAD(&mm->mm_cid.user_list);
 	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	bitmap_zero(mm_cidmask(mm), num_possible_cpus());
 }

From 393815f57651101f1590632092986d1d5a3a41bd Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 11 Mar 2026 10:58:35 +0000
Subject: [PATCH 1192/1303] ACPI: OSL: fix __iomem type on return from
 acpi_os_map_generic_address()

The pointer returned from acpi_os_map_generic_address() is
tagged with __iomem, so make the rv it is returned to also
of void __iomem * type.

Fixes the following sparse warning:

drivers/acpi/osl.c:1686:20: warning: incorrect type in assignment (different address spaces)
drivers/acpi/osl.c:1686:20:    expected void *rv
drivers/acpi/osl.c:1686:20:    got void [noderef] __iomem *

Fixes: 6915564dc5a8 ("ACPI: OSL: Change the type of acpi_os_map_generic_address() return value")
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
[ rjw: Subject tweak, added Fixes tag ]
Link: https://patch.msgid.link/20260311105835.463030-1-ben.dooks@codethink.co.uk
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 5b777316b9ac..62b9c83d4f20 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -1681,7 +1681,7 @@ acpi_status __init acpi_os_initialize(void)
 		 * Use acpi_os_map_generic_address to pre-map the reset
 		 * register if it's in system memory.
 		 */
-		void *rv;
+		void __iomem *rv;
 
 		rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
 		pr_debug("%s: Reset register mapping %s\n", __func__,

From 743956bb9990214ff1dac66ef59e27221dc3c2d8 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@kernel.org>
Date: Mon, 2 Mar 2026 23:35:56 +0800
Subject: [PATCH 1193/1303] spi: dt-bindings: sun6i: Allow Dual SPI and Quad
 SPI for newer SoCs

Support for Dual SPI and Quad SPI was added to the Linux driver in
commit 0605d9fb411f ("spi: sun6i: add quirk for dual and quad SPI modes
support") and commit 25453d797d7a ("spi: sun6i: add dual and quad SPI
modes support for R329/D1/R528/T113s").

However the binding was never updated to allow these modes. Allow them
by adding 2 and 4 to the allowed bus widths for the newer variants.

While at it, also add 0 to the allowed bus widths. This signals that
RX or TX is not available, i.e. the MISO or MOSI pin is disconnected.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Chen-Yu Tsai <wens@kernel.org>
Link: https://patch.msgid.link/20260302153559.3199783-2-wens@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/spi/allwinner,sun6i-a31-spi.yaml | 29 +++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
index a6067030c5ed..6af4ff233158 100644
--- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
@@ -6,9 +6,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Allwinner A31 SPI Controller
 
-allOf:
-  - $ref: spi-controller.yaml
-
 maintainers:
   - Chen-Yu Tsai <wens@csie.org>
   - Maxime Ripard <mripard@kernel.org>
@@ -82,11 +79,11 @@ patternProperties:
 
       spi-rx-bus-width:
         items:
-          - const: 1
+          enum: [0, 1, 2, 4]
 
       spi-tx-bus-width:
         items:
-          - const: 1
+          enum: [0, 1, 2, 4]
 
 required:
   - compatible
@@ -95,6 +92,28 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - $ref: spi-controller.yaml
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - allwinner,sun50i-r329-spi
+                - allwinner,sun55i-a523-spi
+    then:
+      patternProperties:
+        "^.*@[0-9a-f]+":
+          properties:
+            spi-rx-bus-width:
+              items:
+                enum: [0, 1]
+
+            spi-tx-bus-width:
+              items:
+                enum: [0, 1]
+
 unevaluatedProperties: false
 
 examples:

From 362c490980867930a098b99f421268fbd7ca05fd Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 10 Mar 2026 20:32:33 +0800
Subject: [PATCH 1194/1303] xfs: fix integer overflow in bmap intent sort
 comparator

xfs_bmap_update_diff_items() sorts bmap intents by inode number using
a subtraction of two xfs_ino_t (uint64_t) values, with the result
truncated to int. This is incorrect when two inode numbers differ by
more than INT_MAX (2^31 - 1), which is entirely possible on large XFS
filesystems.

Fix this by replacing the subtraction with cmp_int().

Cc: <stable@vger.kernel.org> # v4.9
Fixes: 9f3afb57d5f1 ("xfs: implement deferred bmbt map/unmap operations")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_bmap_item.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e8775f254c89..b237a25d6045 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -245,7 +245,7 @@ xfs_bmap_update_diff_items(
 	struct xfs_bmap_intent		*ba = bi_entry(a);
 	struct xfs_bmap_intent		*bb = bi_entry(b);
 
-	return ba->bi_owner->i_ino - bb->bi_owner->i_ino;
+	return cmp_int(ba->bi_owner->i_ino, bb->bi_owner->i_ino);
 }
 
 /* Log bmap updates in the intent item. */

From 53f3a900e9a383d47af7253076e19f510c5708d0 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Tue, 10 Mar 2026 10:42:46 +0800
Subject: [PATCH 1195/1303] ASoC: amd: acp3x-rt5682-max9836: Add missing error
 check for clock acquisition

The acp3x_5682_init() function did not check the return value of
clk_get(), which could lead to dereferencing error pointers in
rt5682_clk_enable().

Fix this by:
1. Changing clk_get() to the device-managed devm_clk_get().
2. Adding proper IS_ERR() checks for both clock acquisitions.

Fixes: 6b8e4e7db3cd ("ASoC: amd: Add machine driver for Raven based platform")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Link: https://patch.msgid.link/20260310024246.2153827-1-nichen@iscas.ac.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp3x-rt5682-max9836.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c
index 4ca1978020a9..d1eb6f12a183 100644
--- a/sound/soc/amd/acp3x-rt5682-max9836.c
+++ b/sound/soc/amd/acp3x-rt5682-max9836.c
@@ -94,8 +94,13 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd)
 		return ret;
 	}
 
-	rt5682_dai_wclk = clk_get(component->dev, "rt5682-dai-wclk");
-	rt5682_dai_bclk = clk_get(component->dev, "rt5682-dai-bclk");
+	rt5682_dai_wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+	if (IS_ERR(rt5682_dai_wclk))
+		return PTR_ERR(rt5682_dai_wclk);
+
+	rt5682_dai_bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+	if (IS_ERR(rt5682_dai_bclk))
+		return PTR_ERR(rt5682_dai_bclk);
 
 	ret = snd_soc_card_jack_new_pins(card, "Headset Jack",
 					 SND_JACK_HEADSET |

From e293015ba76eb96ce4ebed7e3b2cb1a7d319f3e9 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 18 Feb 2026 21:21:07 +0100
Subject: [PATCH 1196/1303] usb: core: don't power off roothub PHYs if
 phy_set_mode() fails

Remove the error path from the usb_phy_roothub_set_mode() function.
The code is clearly wrong, because phy_set_mode() calls can't be
balanced with phy_power_off() calls.

Additionally, the usb_phy_roothub_set_mode() function is called only
from usb_add_hcd() before it powers on the PHYs, so powering off those
makes no sense anyway.

Presumably, the code is copy-pasted from the phy_power_on() function
without adjusting the error handling.

Cc: stable@vger.kernel.org # v5.1+
Fixes: b97a31348379 ("usb: core: comply to PHY framework")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://patch.msgid.link/20260218-usb-phy-poweroff-fix-v1-1-66e6831e860e@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/phy.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c
index faa20054ad5a..4bba1c275740 100644
--- a/drivers/usb/core/phy.c
+++ b/drivers/usb/core/phy.c
@@ -200,16 +200,10 @@ int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub,
 	list_for_each_entry(roothub_entry, head, list) {
 		err = phy_set_mode(roothub_entry->phy, mode);
 		if (err)
-			goto err_out;
+			return err;
 	}
 
 	return 0;
-
-err_out:
-	list_for_each_entry_continue_reverse(roothub_entry, head, list)
-		phy_power_off(roothub_entry->phy);
-
-	return err;
 }
 EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode);
 

From 416909962e7cdf29fd01ac523c953f37708df93d Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:07:47 -0500
Subject: [PATCH 1197/1303] USB: usbcore: Introduce usb_bulk_msg_killable()

The synchronous message API in usbcore (usb_control_msg(),
usb_bulk_msg(), and so on) uses uninterruptible waits.  However,
drivers may call these routines in the context of a user thread, which
means it ought to be possible to at least kill them.

For this reason, introduce a new usb_bulk_msg_killable() function
which behaves the same as usb_bulk_msg() except for using
wait_for_completion_killable_timeout() instead of
wait_for_completion_timeout().  The same can be done later for
usb_control_msg() later on, if it turns out to be needed.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Suggested-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/248628b4-cc83-4e81-a620-3ce4e0376d41@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 79 +++++++++++++++++++++++++++++++++-----
 include/linux/usb.h        |  5 ++-
 2 files changed, 72 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index ea970ddf8879..d97ec7e8c280 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -42,16 +42,17 @@ static void usb_api_blocking_completion(struct urb *urb)
 
 
 /*
- * Starts urb and waits for completion or timeout. Note that this call
- * is NOT interruptible. Many device driver i/o requests should be
- * interruptible and therefore these drivers should implement their
- * own interruptible routines.
+ * Starts urb and waits for completion or timeout.
+ * Whether or not the wait is killable depends on the flag passed in.
+ * For example, compare usb_bulk_msg() and usb_bulk_msg_killable().
  */
-static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length)
+static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
+		bool killable)
 {
 	struct api_context ctx;
 	unsigned long expire;
 	int retval;
+	long rc;
 
 	init_completion(&ctx.done);
 	urb->context = &ctx;
@@ -61,12 +62,21 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length)
 		goto out;
 
 	expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
-	if (!wait_for_completion_timeout(&ctx.done, expire)) {
+	if (killable)
+		rc = wait_for_completion_killable_timeout(&ctx.done, expire);
+	else
+		rc = wait_for_completion_timeout(&ctx.done, expire);
+	if (rc <= 0) {
 		usb_kill_urb(urb);
-		retval = (ctx.status == -ENOENT ? -ETIMEDOUT : ctx.status);
+		if (ctx.status != -ENOENT)
+			retval = ctx.status;
+		else if (rc == 0)
+			retval = -ETIMEDOUT;
+		else
+			retval = rc;
 
 		dev_dbg(&urb->dev->dev,
-			"%s timed out on ep%d%s len=%u/%u\n",
+			"%s timed out or killed on ep%d%s len=%u/%u\n",
 			current->comm,
 			usb_endpoint_num(&urb->ep->desc),
 			usb_urb_dir_in(urb) ? "in" : "out",
@@ -100,7 +110,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev,
 	usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char *)cmd, data,
 			     len, usb_api_blocking_completion, NULL);
 
-	retv = usb_start_wait_urb(urb, timeout, &length);
+	retv = usb_start_wait_urb(urb, timeout, &length, false);
 	if (retv < 0)
 		return retv;
 	else
@@ -385,10 +395,59 @@ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 		usb_fill_bulk_urb(urb, usb_dev, pipe, data, len,
 				usb_api_blocking_completion, NULL);
 
-	return usb_start_wait_urb(urb, timeout, actual_length);
+	return usb_start_wait_urb(urb, timeout, actual_length, false);
 }
 EXPORT_SYMBOL_GPL(usb_bulk_msg);
 
+/**
+ * usb_bulk_msg_killable - Builds a bulk urb, sends it off and waits for completion in a killable state
+ * @usb_dev: pointer to the usb device to send the message to
+ * @pipe: endpoint "pipe" to send the message to
+ * @data: pointer to the data to send
+ * @len: length in bytes of the data to send
+ * @actual_length: pointer to a location to put the actual length transferred
+ *	in bytes
+ * @timeout: time in msecs to wait for the message to complete before
+ *	timing out (if 0 the wait is forever)
+ *
+ * Context: task context, might sleep.
+ *
+ * This function is just like usb_blk_msg() except that it waits in a
+ * killable state.
+ *
+ * Return:
+ * If successful, 0. Otherwise a negative error number. The number of actual
+ * bytes transferred will be stored in the @actual_length parameter.
+ *
+ */
+int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe,
+		 void *data, int len, int *actual_length, int timeout)
+{
+	struct urb *urb;
+	struct usb_host_endpoint *ep;
+
+	ep = usb_pipe_endpoint(usb_dev, pipe);
+	if (!ep || len < 0)
+		return -EINVAL;
+
+	urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!urb)
+		return -ENOMEM;
+
+	if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+			USB_ENDPOINT_XFER_INT) {
+		pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30);
+		usb_fill_int_urb(urb, usb_dev, pipe, data, len,
+				usb_api_blocking_completion, NULL,
+				ep->desc.bInterval);
+	} else
+		usb_fill_bulk_urb(urb, usb_dev, pipe, data, len,
+				usb_api_blocking_completion, NULL);
+
+	return usb_start_wait_urb(urb, timeout, actual_length, true);
+}
+EXPORT_SYMBOL_GPL(usb_bulk_msg_killable);
+
 /*-------------------------------------------------------------------*/
 
 static void sg_clean(struct usb_sg_request *io)
diff --git a/include/linux/usb.h b/include/linux/usb.h
index fbfcc70b07fb..57ceeb02a7cb 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1868,8 +1868,9 @@ extern int usb_control_msg(struct usb_device *dev, unsigned int pipe,
 extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe,
 	void *data, int len, int *actual_length, int timeout);
 extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
-	void *data, int len, int *actual_length,
-	int timeout);
+	void *data, int len, int *actual_length, int timeout);
+extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe,
+	void *data, int len, int *actual_length, int timeout);
 
 /* wrappers around usb_control_msg() for the most common standard requests */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,

From 7784caa413a89487dd14dd5c41db8753483b2acb Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:09:22 -0500
Subject: [PATCH 1198/1303] USB: usbtmc: Use usb_bulk_msg_killable() with
 user-specified timeouts

The usbtmc driver accepts timeout values specified by the user in an
ioctl command, and uses these timeouts for some usb_bulk_msg() calls.
Since the user can specify arbitrarily long timeouts and
usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable()
instead to avoid the possibility of the user hanging a kernel thread
indefinitely.

Reported-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-usb/8e1c7ac5-e076-44b0-84b8-1b34b20f0ae1@suse.com/T/#t
Tested-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Fixes: 048c6d88a021 ("usb: usbtmc: Add ioctls to set/get usb timeout")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/81c6fc24-0607-40f1-8c20-5270dab2fad5@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/usbtmc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 2526a0e03cde..d39bbfd7fd18 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -727,7 +727,7 @@ static int usbtmc488_ioctl_trigger(struct usbtmc_file_data *file_data)
 	buffer[1] = data->bTag;
 	buffer[2] = ~data->bTag;
 
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_sndbulkpipe(data->usb_dev,
 					      data->bulk_out),
 			      buffer, USBTMC_HEADER_SIZE,
@@ -1347,7 +1347,7 @@ static int send_request_dev_dep_msg_in(struct usbtmc_file_data *file_data,
 	buffer[11] = 0; /* Reserved */
 
 	/* Send bulk URB */
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_sndbulkpipe(data->usb_dev,
 					      data->bulk_out),
 			      buffer, USBTMC_HEADER_SIZE,
@@ -1419,7 +1419,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 	actual = 0;
 
 	/* Send bulk URB */
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_rcvbulkpipe(data->usb_dev,
 					      data->bulk_in),
 			      buffer, bufsize, &actual,

From 1015c27a5e1a63efae2b18a9901494474b4d1dc3 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:10:32 -0500
Subject: [PATCH 1199/1303] USB: core: Limit the length of unkillable
 synchronous timeouts

The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in
usbcore allow unlimited timeout durations.  And since they use
uninterruptible waits, this leaves open the possibility of hanging a
task for an indefinitely long time, with no way to kill it short of
unplugging the target device.

To prevent this sort of problem, enforce a maximum limit on the length
of these unkillable timeouts.  The limit chosen here, somewhat
arbitrarily, is 60 seconds.  On many systems (although not all) this
is short enough to avoid triggering the kernel's hung-task detector.

In addition, clear up the ambiguity of negative timeout values by
treating them the same as 0, i.e., using the maximum allowed timeout.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/15fc9773-a007-47b0-a703-df89a8cf83dd@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 27 +++++++++++++--------------
 include/linux/usb.h        |  3 +++
 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index d97ec7e8c280..2ab120ce2fa8 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -45,6 +45,8 @@ static void usb_api_blocking_completion(struct urb *urb)
  * Starts urb and waits for completion or timeout.
  * Whether or not the wait is killable depends on the flag passed in.
  * For example, compare usb_bulk_msg() and usb_bulk_msg_killable().
+ *
+ * For non-killable waits, we enforce a maximum limit on the timeout value.
  */
 static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
 		bool killable)
@@ -61,7 +63,9 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
 	if (unlikely(retval))
 		goto out;
 
-	expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
+	if (!killable && (timeout <= 0 || timeout > USB_MAX_SYNCHRONOUS_TIMEOUT))
+		timeout = USB_MAX_SYNCHRONOUS_TIMEOUT;
+	expire = (timeout > 0) ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
 	if (killable)
 		rc = wait_for_completion_killable_timeout(&ctx.done, expire);
 	else
@@ -127,8 +131,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev,
  * @index: USB message index value
  * @data: pointer to the data to send
  * @size: length in bytes of the data to send
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -183,8 +186,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  * @index: USB message index value
  * @driver_data: pointer to the data to send
  * @size: length in bytes of the data to send
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
@@ -242,8 +244,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  * @index: USB message index value
  * @driver_data: pointer to the data to be filled in by the message
  * @size: length in bytes of the data to be received
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
@@ -314,8 +315,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_recv);
  * @len: length in bytes of the data to send
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
- * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -347,8 +347,7 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg);
  * @len: length in bytes of the data to send
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
- * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -408,12 +407,12 @@ EXPORT_SYMBOL_GPL(usb_bulk_msg);
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
  * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ *	timing out (if <= 0, the wait is as long as possible)
  *
  * Context: task context, might sleep.
  *
- * This function is just like usb_blk_msg() except that it waits in a
- * killable state.
+ * This function is just like usb_blk_msg(), except that it waits in a
+ * killable state and there is no limit on the timeout length.
  *
  * Return:
  * If successful, 0. Otherwise a negative error number. The number of actual
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 57ceeb02a7cb..04277af4bb9d 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1862,6 +1862,9 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size,
  *                         SYNCHRONOUS CALL SUPPORT                  *
  *-------------------------------------------------------------------*/
 
+/* Maximum value allowed for timeout in synchronous routines below */
+#define USB_MAX_SYNCHRONOUS_TIMEOUT		60000	/* ms */
+
 extern int usb_control_msg(struct usb_device *dev, unsigned int pipe,
 	__u8 request, __u8 requesttype, __u16 value, __u16 index,
 	void *data, __u16 size, int timeout);

From 45dba8011efac11a2f360383221b541f5ea53ce5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:19:43 +0100
Subject: [PATCH 1200/1303] usb: misc: uss720: properly clean up reference in
 uss720_probe()

If get_1284_register() fails, the usb device reference count is
incorrect and needs to be properly dropped before returning.  That will
happen when the kref is dropped in the call to destroy_priv(), so jump
to that error path instead of returning directly.

Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022342-smokiness-stove-d792@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/uss720.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index ec8bd968c4de..a8af7615b1bf 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -736,7 +736,7 @@ static int uss720_probe(struct usb_interface *intf,
 	ret = get_1284_register(pp, 0, &reg, GFP_KERNEL);
 	dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg);
 	if (ret < 0)
-		return ret;
+		goto probe_abort;
 
 	ret = usb_find_last_int_in_endpoint(interface, &epd);
 	if (!ret) {

From 9f6a983cfa22ac662c86e60816d3a357d4b551e9 Mon Sep 17 00:00:00 2001
From: Jie Deng <dengjie03@kylinos.cn>
Date: Fri, 27 Feb 2026 16:49:31 +0800
Subject: [PATCH 1201/1303] usb: core: new quirk to handle devices with zero
 configurations

Some USB devices incorrectly report bNumConfigurations as 0 in their
device descriptor, which causes the USB core to reject them during
enumeration.
logs:
usb 1-2: device descriptor read/64, error -71
usb 1-2: no configurations
usb 1-2: can't read configurations, error -22

However, these devices actually work correctly when
treated as having a single configuration.

Add a new quirk USB_QUIRK_FORCE_ONE_CONFIG to handle such devices.
When this quirk is set, assume the device has 1 configuration instead
of failing with -EINVAL.

This quirk is applied to the device with VID:PID 5131:2007 which
exhibits this behavior.

Signed-off-by: Jie Deng <dengjie03@kylinos.cn>
Link: https://patch.msgid.link/20260227084931.1527461-1-dengjie03@kylinos.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 3 +++
 drivers/usb/core/config.c                       | 6 +++++-
 drivers/usb/core/quirks.c                       | 5 +++++
 include/linux/usb/quirks.h                      | 3 +++
 4 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index cb850e5290c2..7d907efe9f49 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -8183,6 +8183,9 @@ Kernel parameters
 				p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
 					(Reduce timeout of the SET_ADDRESS
 					request from 5000 ms to 500 ms);
+				q = USB_QUIRK_FORCE_ONE_CONFIG (Device
+					claims zero configurations,
+					forcing to 1);
 			Example: quirks=0781:5580:bk,0a5c:5834:gij
 
 	usbhid.mousepoll=
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 1cd5fa61dc76..6a1fd967e0a6 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -927,7 +927,11 @@ int usb_get_configuration(struct usb_device *dev)
 		dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG;
 	}
 
-	if (ncfg < 1) {
+	if (ncfg < 1 && dev->quirks & USB_QUIRK_FORCE_ONE_CONFIG) {
+		dev_info(ddev, "Device claims zero configurations, forcing to 1\n");
+		dev->descriptor.bNumConfigurations = 1;
+		ncfg = 1;
+	} else if (ncfg < 1) {
 		dev_err(ddev, "no configurations\n");
 		return -EINVAL;
 	}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index e347236d83e8..7bd408db05f4 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -140,6 +140,8 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 			case 'p':
 				flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT;
 				break;
+			case 'q':
+				flags |= USB_QUIRK_FORCE_ONE_CONFIG;
 			/* Ignore unrecognized flag characters */
 			}
 		}
@@ -589,6 +591,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* VCOM device */
 	{ USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* Noji-MCS SmartCard Reader */
+	{ USB_DEVICE(0x5131, 0x2007), .driver_info = USB_QUIRK_FORCE_ONE_CONFIG },
+
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 2f7bd2fdc616..b3cc7beab4a3 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -78,4 +78,7 @@
 /* skip BOS descriptor request */
 #define USB_QUIRK_NO_BOS			BIT(17)
 
+/* Device claims zero configurations, forcing to 1 */
+#define USB_QUIRK_FORCE_ONE_CONFIG		BIT(18)
+
 #endif /* __LINUX_USB_QUIRKS_H */

From 7f58b4148ef5d8ee0fb7d8113dcc38ff5374babc Mon Sep 17 00:00:00 2001
From: John Keeping <jkeeping@inmusicbrands.com>
Date: Fri, 27 Feb 2026 11:15:39 +0000
Subject: [PATCH 1202/1303] usb: gadget: f_hid: fix SuperSpeed descriptors

When adding dynamic configuration for bInterval, the value was removed
from the static SuperSpeed endpoint descriptors but was not set from the
configured value in hidg_bind().  Thus at SuperSpeed the interrupt
endpoints have bInterval as zero which is not valid per the USB
specification.

Add the missing setting for SuperSpeed endpoints.

Fixes: ea34925f5b2ee ("usb: gadget: hid: allow dynamic interval configuration via configfs")
Cc: stable <stable@kernel.org>
Signed-off-by: John Keeping <jkeeping@inmusicbrands.com>
Acked-by: Peter Korsgaard <peter@korsgaard.com>
Link: https://patch.msgid.link/20260227111540.431521-1-jkeeping@inmusicbrands.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_hid.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 8c855c00b887..8812ebf33d14 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -1207,9 +1207,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	if (!hidg->interval_user_set) {
 		hidg_fs_in_ep_desc.bInterval = 10;
 		hidg_hs_in_ep_desc.bInterval = 4;
+		hidg_ss_in_ep_desc.bInterval = 4;
 	} else {
 		hidg_fs_in_ep_desc.bInterval = hidg->interval;
 		hidg_hs_in_ep_desc.bInterval = hidg->interval;
+		hidg_ss_in_ep_desc.bInterval = hidg->interval;
 	}
 
 	hidg_ss_out_comp_desc.wBytesPerInterval =
@@ -1239,9 +1241,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 		if (!hidg->interval_user_set) {
 			hidg_fs_out_ep_desc.bInterval = 10;
 			hidg_hs_out_ep_desc.bInterval = 4;
+			hidg_ss_out_ep_desc.bInterval = 4;
 		} else {
 			hidg_fs_out_ep_desc.bInterval = hidg->interval;
 			hidg_hs_out_ep_desc.bInterval = hidg->interval;
+			hidg_ss_out_ep_desc.bInterval = hidg->interval;
 		}
 		status = usb_assign_descriptors(f,
 			    hidg_fs_descriptors_intout,

From 8479891d1f04a8ce55366fe4ca361ccdb96f02e1 Mon Sep 17 00:00:00 2001
From: Seungjin Bae <eeodqql09@gmail.com>
Date: Sat, 28 Feb 2026 05:43:25 -0500
Subject: [PATCH 1203/1303] usb: gadget: f_mass_storage: Fix potential integer
 overflow in check_command_size_in_blocks()

The `check_command_size_in_blocks()` function calculates the data size
in bytes by left shifting `common->data_size_from_cmnd` by the block
size (`common->curlun->blkbits`). However, it does not validate whether
this shift operation will cause an integer overflow.

Initially, the block size is set up in `fsg_lun_open()` , and the
`common->data_size_from_cmnd` is set up in `do_scsi_command()`. During
initialization, there is no integer overflow check for the interaction
between two variables.

So if a malicious USB host sends a SCSI READ or WRITE command
requesting a large amount of data (`common->data_size_from_cmnd`), the
left shift operation can wrap around. This results in a truncated data
size, which can bypass boundary checks and potentially lead to memory
corruption or out-of-bounds accesses.

Fix this by using the check_shl_overflow() macro to safely perform the
shift and catch any overflows.

Fixes: 144974e7f9e3 ("usb: gadget: mass_storage: support multi-luns with different logic block size")
Signed-off-by: Seungjin Bae <eeodqql09@gmail.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://patch.msgid.link/20260228104324.1696455-2-eeodqql09@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_mass_storage.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 6af96e2b44eb..b7b06cb79ff5 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -180,6 +180,7 @@
 #include <linux/kthread.h>
 #include <linux/sched/signal.h>
 #include <linux/limits.h>
+#include <linux/overflow.h>
 #include <linux/pagemap.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
@@ -1853,8 +1854,15 @@ static int check_command_size_in_blocks(struct fsg_common *common,
 		int cmnd_size, enum data_direction data_dir,
 		unsigned int mask, int needs_medium, const char *name)
 {
-	if (common->curlun)
-		common->data_size_from_cmnd <<= common->curlun->blkbits;
+	if (common->curlun) {
+		if (check_shl_overflow(common->data_size_from_cmnd,
+				       common->curlun->blkbits,
+				       &common->data_size_from_cmnd)) {
+			common->phase_error = 1;
+			return -EINVAL;
+		}
+	}
+
 	return check_command(common, cmnd_size, data_dir,
 			mask, needs_medium, name);
 }

From 14ae24cba291bddfdc296bbcbfd00cd09d0498ef Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 1 Mar 2026 12:44:40 +0000
Subject: [PATCH 1204/1303] usb: cdc-acm: Restore CAP_BRK functionnality to
 CH343

The CH343 USB/serial adapter is as buggy as it is popular (very).
One of its quirks is that despite being capable of signalling a
BREAK condition, it doesn't advertise it.

This used to work nonetheless until 66aad7d8d3ec5 ("usb: cdc-acm:
return correct error code on unsupported break") applied some
reasonable restrictions, preventing breaks from being emitted on
devices that do not advertise CAP_BRK.

Add a quirk for this particular device, so that breaks can still
be produced on some of my machines attached to my console server.

Fixes: 66aad7d8d3ec5 ("usb: cdc-acm: return correct error code on unsupported break")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable <stable@kernel.org>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/20260301124440.1192752-1-maz@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 5 +++++
 drivers/usb/class/cdc-acm.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index ad38c746270a..7ede29d4c7c1 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1379,6 +1379,8 @@ static int acm_probe(struct usb_interface *intf,
 		acm->ctrl_caps = h.usb_cdc_acm_descriptor->bmCapabilities;
 	if (quirks & NO_CAP_LINE)
 		acm->ctrl_caps &= ~USB_CDC_CAP_LINE;
+	if (quirks & MISSING_CAP_BRK)
+		acm->ctrl_caps |= USB_CDC_CAP_BRK;
 	acm->ctrlsize = ctrlsize;
 	acm->readsize = readsize;
 	acm->rx_buflimit = num_rx_buf;
@@ -2002,6 +2004,9 @@ static const struct usb_device_id acm_ids[] = {
 	.driver_info = IGNORE_DEVICE,
 	},
 
+	/* CH343 supports CAP_BRK, but doesn't advertise it */
+	{ USB_DEVICE(0x1a86, 0x55d3), .driver_info = MISSING_CAP_BRK, },
+
 	/* control interfaces without any protocol set */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_PROTO_NONE) },
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 759ac15631d3..76f73853a60b 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -113,3 +113,4 @@ struct acm {
 #define CLEAR_HALT_CONDITIONS		BIT(5)
 #define SEND_ZERO_PACKET		BIT(6)
 #define DISABLE_ECHO			BIT(7)
+#define MISSING_CAP_BRK			BIT(8)

From 3cbc242b88c607f55da3d0d0d336b49bf1e20412 Mon Sep 17 00:00:00 2001
From: Fan Wu <fanwu01@zju.edu.cn>
Date: Tue, 3 Mar 2026 07:33:44 +0000
Subject: [PATCH 1205/1303] usb: renesas_usbhs: fix use-after-free in ISR
 during device removal

In usbhs_remove(), the driver frees resources (including the pipe array)
while the interrupt handler (usbhs_interrupt) is still registered. If an
interrupt fires after usbhs_pipe_remove() but before the driver is fully
unbound, the ISR may access freed memory, causing a use-after-free.

Fix this by calling devm_free_irq() before freeing resources. This ensures
the interrupt handler is both disabled and synchronized (waits for any
running ISR to complete) before usbhs_pipe_remove() is called.

Fixes: f1407d5c6624 ("usb: renesas_usbhs: Add Renesas USBHS common code")
Cc: stable <stable@kernel.org>
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Link: https://patch.msgid.link/20260303073344.34577-1-fanwu01@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index cf4a0367d6d6..8c93bde4b816 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -815,6 +815,15 @@ static void usbhs_remove(struct platform_device *pdev)
 
 	usbhs_platform_call(priv, hardware_exit, pdev);
 	reset_control_assert(priv->rsts);
+
+	/*
+	 * Explicitly free the IRQ to ensure the interrupt handler is
+	 * disabled and synchronized before freeing resources.
+	 * devm_free_irq() calls free_irq() which waits for any running
+	 * ISR to complete, preventing UAF.
+	 */
+	devm_free_irq(&pdev->dev, priv->irq, priv);
+
 	usbhs_mod_remove(priv);
 	usbhs_fifo_remove(priv);
 	usbhs_pipe_remove(priv);

From 8df672bfe3ec2268c2636584202755898e547173 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Wed, 4 Mar 2026 14:01:12 +0100
Subject: [PATCH 1206/1303] usb: class: cdc-wdm: fix reordering issue in read
 code path

Quoting the bug report:

Due to compiler optimization or CPU out-of-order execution, the
desc->length update can be reordered before the memmove. If this
happens, wdm_read() can see the new length and call copy_to_user() on
uninitialized memory. This also violates LKMM data race rules [1].

Fix it by using WRITE_ONCE and memory barriers.

Fixes: afba937e540c9 ("USB: CDC WDM driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Closes: https://lore.kernel.org/linux-usb/CALbr=LbrUZn_cfp7CfR-7Z5wDTHF96qeuM=3fO2m-q4cDrnC4A@mail.gmail.com/
Reported-by: Gui-Dong Han <hanguidong02@gmail.com>
Reviewed-by: Gui-Dong Han <hanguidong02@gmail.com>
Link: https://patch.msgid.link/20260304130116.1721682-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-wdm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index f2d94cfc70af..7556c0dac908 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -225,7 +225,8 @@ static void wdm_in_callback(struct urb *urb)
 		/* we may already be in overflow */
 		if (!test_bit(WDM_OVERFLOW, &desc->flags)) {
 			memmove(desc->ubuf + desc->length, desc->inbuf, length);
-			desc->length += length;
+			smp_wmb(); /* against wdm_read() */
+			WRITE_ONCE(desc->length, desc->length + length);
 		}
 	}
 skip_error:
@@ -533,6 +534,7 @@ static ssize_t wdm_read
 		return -ERESTARTSYS;
 
 	cntr = READ_ONCE(desc->length);
+	smp_rmb(); /* against wdm_in_callback() */
 	if (cntr == 0) {
 		desc->read = 0;
 retry:

From c1c8550e70401159184130a1afc6261db01fc0ce Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Thu, 5 Mar 2026 00:36:37 +0200
Subject: [PATCH 1207/1303] usb: xhci: Fix memory leak in xhci_disable_slot()

xhci_alloc_command() allocates a command structure and, when the
second argument is true, also allocates a completion structure.
Currently, the error handling path in xhci_disable_slot() only frees
the command structure using kfree(), causing the completion structure
to leak.

Use xhci_free_command() instead of kfree(). xhci_free_command() correctly
frees both the command structure and the associated completion structure.
Since the command structure is allocated with zero-initialization,
command->in_ctx is NULL and will not be erroneously freed by
xhci_free_command().

This bug was found using an experimental static analysis tool we are
developing. The tool is based on the LLVM framework and is specifically
designed to detect memory management issues. It is currently under
active development and not yet publicly available, but we plan to
open-source it after our research is published.

The bug was originally detected on v6.13-rc1 using our static analysis
tool, and we have verified that the issue persists in the latest mainline
kernel.

We performed build testing on x86_64 with allyesconfig using GCC=11.4.0.
Since triggering these error paths in xhci_disable_slot() requires specific
hardware conditions or abnormal state, we were unable to construct a test
case to reliably trigger these specific error paths at runtime.

Fixes: 7faac1953ed1 ("xhci: avoid race between disable slot command and host runtime suspend")
CC: stable@vger.kernel.org
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index c36ab323d68e..ef6d8662adec 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4146,7 +4146,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 	if (state == 0xffffffff || (xhci->xhc_state & XHCI_STATE_DYING) ||
 			(xhci->xhc_state & XHCI_STATE_HALTED)) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		kfree(command);
+		xhci_free_command(xhci, command);
 		return -ENODEV;
 	}
 
@@ -4154,7 +4154,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 				slot_id);
 	if (ret) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		kfree(command);
+		xhci_free_command(xhci, command);
 		return ret;
 	}
 	xhci_ring_cmd_db(xhci);

From d6d5febd12452b7fd951fdd15c3ec262f01901a4 Mon Sep 17 00:00:00 2001
From: Dayu Jiang <jiangdayu@xiaomi.com>
Date: Thu, 5 Mar 2026 00:36:38 +0200
Subject: [PATCH 1208/1303] usb: xhci: Prevent interrupt storm on host
 controller error (HCE)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The xHCI controller reports a Host Controller Error (HCE) in UAS Storage
Device plug/unplug scenarios on Android devices. HCE is checked in
xhci_irq() function and causes an interrupt storm (since the interrupt
isn’t cleared), leading to severe system-level faults.

When the xHC controller reports HCE in the interrupt handler, the driver
only logs a warning and assumes xHC activity will stop as stated in xHCI
specification. An interrupt storm does however continue on some hosts
even after HCE, and only ceases after manually disabling xHC interrupt
and stopping the controller by calling xhci_halt().

Add xhci_halt() to xhci_irq() function where STS_HCE status is checked,
mirroring the existing error handling pattern used for STS_FATAL errors.

This only fixes the interrupt storm. Proper HCE recovery requires resetting
and re-initializing the xHC.

CC: stable@vger.kernel.org
Signed-off-by: Dayu Jiang <jiangdayu@xiaomi.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 9315ba18310d..1cbefee3c4ca 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3195,6 +3195,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 
 	if (status & STS_HCE) {
 		xhci_warn(xhci, "WARNING: Host Controller Error\n");
+		xhci_halt(xhci);
 		goto out;
 	}
 

From ae4ff9dead5efa2025eddfcdb29411432bf40a7c Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 5 Mar 2026 00:36:39 +0200
Subject: [PATCH 1209/1303] xhci: Fix NULL pointer dereference when reading
 portli debugfs files

Michal reported and debgged a NULL pointer dereference bug in the
recently added portli debugfs files

Oops is caused when there are more port registers counted in
xhci->max_ports than ports reported by Supported Protocol capabilities.
This is possible if max_ports is more than maximum port number, or
if there are gaps between ports of different speeds the 'Supported
Protocol' capabilities.

In such cases port->rhub will be NULL so we can't reach xhci behind it.
Add an explicit NULL check for this case, and print portli in hex
without dereferencing port->rhub.

Reported-by: Michal Pecio <michal.pecio@gmail.com>
Closes: https://lore.kernel.org/linux-usb/20260304103856.48b785fd.michal.pecio@gmail.com
Fixes: 384c57ec7205 ("usb: xhci: Add debugfs support for xHCI Port Link Info (PORTLI) register.")
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-debugfs.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 890fc5e892f1..ade178ab34a7 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -386,11 +386,19 @@ static const struct file_operations port_fops = {
 static int xhci_portli_show(struct seq_file *s, void *unused)
 {
 	struct xhci_port	*port = s->private;
-	struct xhci_hcd		*xhci = hcd_to_xhci(port->rhub->hcd);
+	struct xhci_hcd		*xhci;
 	u32			portli;
 
 	portli = readl(&port->port_reg->portli);
 
+	/* port without protocol capability isn't added to a roothub */
+	if (!port->rhub) {
+		seq_printf(s, "0x%08x\n", portli);
+		return 0;
+	}
+
+	xhci = hcd_to_xhci(port->rhub->hcd);
+
 	/* PORTLI fields are valid if port is a USB3 or eUSB2V2 port */
 	if (port->rhub == &xhci->usb3_rhub)
 		seq_printf(s, "0x%08x LEC=%u RLC=%u TLC=%u\n", portli,

From 56135c0c60b07729401af9d329fa9c0eded845a6 Mon Sep 17 00:00:00 2001
From: Junzhong Pan <panjunzhong@linux.spacemit.com>
Date: Fri, 6 Mar 2026 11:30:09 +0800
Subject: [PATCH 1210/1303] usb: gadget: uvc: fix interval_duration calculation

To correctly convert bInterval as interval_duration:
  interval_duration = 2^(bInterval-1) * frame_interval

Current code uses a wrong left shift operand, computing 2^bInterval
instead of 2^(bInterval-1).

Fixes: 010dc57cb516 ("usb: gadget: uvc: fix interval_duration calculation")
Cc: stable <stable@kernel.org>
Signed-off-by: Junzhong Pan <panjunzhong@linux.spacemit.com>
Reviewed-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://patch.msgid.link/20260306-fix-uvc-interval-v1-1-9a2df6859859@linux.spacemit.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_video.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 7cea641b06b4..2f9700b3f1b6 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -513,7 +513,7 @@ uvc_video_prep_requests(struct uvc_video *video)
 		return;
 	}
 
-	interval_duration = 2 << (video->ep->desc->bInterval - 1);
+	interval_duration = 1 << (video->ep->desc->bInterval - 1);
 	if (cdev->gadget->speed < USB_SPEED_HIGH)
 		interval_duration *= 10000;
 	else

From 0326ff28d56b4fa202de36ffc8462a354f383a64 Mon Sep 17 00:00:00 2001
From: Christoffer Sandberg <cs@tuxedo.de>
Date: Fri, 6 Mar 2026 18:28:14 +0100
Subject: [PATCH 1211/1303] usb/core/quirks: Add Huawei ME906S-device to wakeup
 quirk

Similar to other Huawei LTE modules using this quirk, this version with
another vid/pid suffers from spurious wakeups.

Setting the quirk fixes the issue for this device as well.

Cc: stable <stable@kernel.org>
Signed-off-by: Christoffer Sandberg <cs@tuxedo.de>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://patch.msgid.link/20260306172817.2098898-1-wse@tuxedocomputers.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 7bd408db05f4..e3f402e0c351 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -209,6 +209,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* HP v222w 16GB Mini USB Drive */
 	{ USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Huawei 4G LTE module ME906S  */
+	{ USB_DEVICE(0x03f0, 0xa31d), .driver_info =
+			USB_QUIRK_DISCONNECT_SUSPEND },
+
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 

From 17ab4d4078e22be7fd8fd6fc710c15c085a4cb1b Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 9 Mar 2026 14:02:04 +0100
Subject: [PATCH 1212/1303] usb: dwc3: pci: add support for the Intel Nova Lake
 -H

This patch adds the necessary PCI ID for Intel Nova Lake -H
devices.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: stable <stable@kernel.org>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260309130204.208661-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6ecadc81bd6b..6c1cbb722ca8 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -56,6 +56,7 @@
 #define PCI_DEVICE_ID_INTEL_CNPH		0xa36e
 #define PCI_DEVICE_ID_INTEL_CNPV		0xa3b0
 #define PCI_DEVICE_ID_INTEL_RPL			0xa70e
+#define PCI_DEVICE_ID_INTEL_NVLH		0xd37f
 #define PCI_DEVICE_ID_INTEL_PTLH		0xe332
 #define PCI_DEVICE_ID_INTEL_PTLH_PCH		0xe37e
 #define PCI_DEVICE_ID_INTEL_PTLU		0xe432
@@ -447,6 +448,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, CNPH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, CNPV, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, RPL, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, NVLH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLH_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLU, &dwc3_pci_intel_swnode) },

From e8557acfa079a54b59a21f447c82a31aec7717df Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 10 Mar 2026 20:41:05 +0000
Subject: [PATCH 1213/1303] usb: typec: altmode/displayport: set displayport
 signaling rate in configure message

dp_altmode_configure sets the signaling rate to the current
configuration's rate and then shifts the value to the Select
Configuration bitfield. On the initial configuration, dp->data.conf
is 0 to begin with, so the signaling rate field is never set, which
leads to some DisplayPort Alt Mode partners sending NAK to the
Configure message.

Set the signaling rate to the capabilities supported by both the
port and the port partner. If the cable supports DisplayPort Alt Mode,
then include its capabilities as well.

Fixes: a17fae8fc38e ("usb: typec: Add Displayport Alternate Mode 2.1 Support")
Cc: stable <stable@kernel.org>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260310204106.3939862-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/displayport.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index d185688a16b1..35d9c3086990 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -100,9 +100,14 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con)
 {
 	u8 pin_assign = 0;
 	u32 conf;
+	u32 signal;
 
 	/* DP Signalling */
-	conf = (dp->data.conf & DP_CONF_SIGNALLING_MASK) >> DP_CONF_SIGNALLING_SHIFT;
+	signal = DP_CAP_DP_SIGNALLING(dp->port->vdo) & DP_CAP_DP_SIGNALLING(dp->alt->vdo);
+	if (dp->plug_prime)
+		signal &= DP_CAP_DP_SIGNALLING(dp->plug_prime->vdo);
+
+	conf = signal << DP_CONF_SIGNALLING_SHIFT;
 
 	switch (con) {
 	case DP_STATUS_CON_DISABLED:

From 11199720fac2debbe718aec11e026ab3330dc80d Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:46 +0800
Subject: [PATCH 1214/1303] Revert "usb: gadget: f_ncm: Fix atomic context
 locking issue"

This reverts commit 0d6c8144ca4d93253de952a5ea0028c19ed7ab68.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-1-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c           | 29 +++++++++++--------
 .../usb/gadget/function/u_ether_configfs.h    | 11 ++++++-
 drivers/usb/gadget/function/u_ncm.h           |  1 +
 3 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 4da19864d70b..14fc7dce6f39 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -58,7 +58,6 @@ struct f_ncm {
 	u8				notify_state;
 	atomic_t			notify_count;
 	bool				is_open;
-	bool				is_connected;
 
 	const struct ndp_parser_opts	*parser_opts;
 	bool				is_crc;
@@ -865,6 +864,7 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
+	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,12 +887,13 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		if (ncm->is_connected) {
-			DBG(cdev, "reset ncm\n");
-			ncm->is_connected = false;
-			gether_disconnect(&ncm->port);
-			ncm_reset_values(ncm);
-		}
+		scoped_guard(mutex, &opts->lock)
+			if (opts->net) {
+				DBG(cdev, "reset ncm\n");
+				opts->net = NULL;
+				gether_disconnect(&ncm->port);
+				ncm_reset_values(ncm);
+			}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -925,7 +926,8 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			ncm->is_connected = true;
+			scoped_guard(mutex, &opts->lock)
+				opts->net = net;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1372,14 +1374,16 @@ static int ncm_unwrap_ntb(struct gether *port,
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
+	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	if (ncm->is_connected) {
-		ncm->is_connected = false;
-		gether_disconnect(&ncm->port);
-	}
+	scoped_guard(mutex, &opts->lock)
+		if (opts->net) {
+			opts->net = NULL;
+			gether_disconnect(&ncm->port);
+		}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1683,6 +1687,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
 
+	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
 	gether_setup_opts_default(&opts->net_opts, "usb");
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 25d8fb05b598..217990a266b2 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -327,9 +327,18 @@ out:									\
 					      char *page)			\
 	{									\
 		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
+		const char *name;						\
 										\
 		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%s\n", opts->net_opts.name);		\
+		rtnl_lock();							\
+		if (opts->net_opts.ifname_set)					\
+			name = opts->net_opts.name;				\
+		else if (opts->net)						\
+			name = netdev_name(opts->net);				\
+		else								\
+			name = "(inactive net_device)";				\
+		rtnl_unlock();							\
+		return sysfs_emit(page, "%s\n", name);				\
 	}									\
 										\
 	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 6d7538855744..d99330fe31e8 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -19,6 +19,7 @@
 
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
+	struct net_device		*net;
 
 	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;

From f2524c0e6ff0a5f72f1e1a32441c69d3b56430c4 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:47 +0800
Subject: [PATCH 1215/1303] Revert "usb: legacy: ncm: Fix NPE in gncm_bind"

This reverts commit fde0634ad9856b3943a2d1a8cc8de174a63ac840.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-2-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/legacy/ncm.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index e8d565534053..0f1b45e3abd1 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -15,10 +15,8 @@
 /* #define DEBUG */
 /* #define VERBOSE_DEBUG */
 
-#include <linux/hex.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/usb/composite.h>
 
 #include "u_ether.h"
@@ -131,7 +129,6 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 	struct usb_gadget	*gadget = cdev->gadget;
 	struct f_ncm_opts	*ncm_opts;
 	int			status;
-	u8			mac[ETH_ALEN];
 
 	f_ncm_inst = usb_get_function_instance("ncm");
 	if (IS_ERR(f_ncm_inst))
@@ -139,15 +136,11 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 
 	ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst);
 
-	ncm_opts->net_opts.qmult = qmult;
-	if (host_addr && mac_pton(host_addr, mac)) {
-		memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN);
+	gether_set_qmult(ncm_opts->net, qmult);
+	if (!gether_set_host_addr(ncm_opts->net, host_addr))
 		pr_info("using host ethernet address: %s", host_addr);
-	}
-	if (dev_addr && mac_pton(dev_addr, mac)) {
-		memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN);
+	if (!gether_set_dev_addr(ncm_opts->net, dev_addr))
 		pr_info("using self ethernet address: %s", dev_addr);
-	}
 
 	/* Allocate string descriptor numbers ... note that string
 	 * contents can be overridden by the composite_dev glue.

From 37893bc5de2460c543ec1aa8250c37a305234054 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:48 +0800
Subject: [PATCH 1216/1303] Revert "usb: gadget: f_ncm: align net_device
 lifecycle with bind/unbind"

This reverts commit 56a512a9b4107079f68701e7d55da8507eb963d9.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-3-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c | 128 ++++++++++++++--------------
 drivers/usb/gadget/function/u_ncm.h |   4 +-
 2 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 14fc7dce6f39..3d772c9beb91 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -83,11 +83,6 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 	return container_of(f, struct f_ncm, port.func);
 }
 
-static inline struct f_ncm_opts *func_to_ncm_opts(struct usb_function *f)
-{
-	return container_of(f->fi, struct f_ncm_opts, func_inst);
-}
-
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -864,7 +859,6 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,13 +881,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		scoped_guard(mutex, &opts->lock)
-			if (opts->net) {
-				DBG(cdev, "reset ncm\n");
-				opts->net = NULL;
-				gether_disconnect(&ncm->port);
-				ncm_reset_values(ncm);
-			}
+		if (ncm->netdev) {
+			DBG(cdev, "reset ncm\n");
+			ncm->netdev = NULL;
+			gether_disconnect(&ncm->port);
+			ncm_reset_values(ncm);
+		}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -926,8 +919,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			scoped_guard(mutex, &opts->lock)
-				opts->net = net;
+			ncm->netdev = net;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1374,16 +1366,14 @@ static int ncm_unwrap_ntb(struct gether *port,
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	scoped_guard(mutex, &opts->lock)
-		if (opts->net) {
-			opts->net = NULL;
-			gether_disconnect(&ncm->port);
-		}
+	if (ncm->netdev) {
+		ncm->netdev = NULL;
+		gether_disconnect(&ncm->port);
+	}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1443,44 +1433,39 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*ncm_opts = func_to_ncm_opts(f);
 	struct usb_string	*us;
 	int			status = 0;
 	struct usb_ep		*ep;
+	struct f_ncm_opts	*ncm_opts;
 
 	struct usb_os_desc_table	*os_desc_table __free(kfree) = NULL;
-	struct net_device		*netdev __free(free_gether_netdev) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
 		return -EINVAL;
 
+	ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+
 	if (cdev->use_os_string) {
 		os_desc_table = kzalloc(sizeof(*os_desc_table), GFP_KERNEL);
 		if (!os_desc_table)
 			return -ENOMEM;
 	}
 
-	netdev = gether_setup_default();
-	if (IS_ERR(netdev))
-		return -ENOMEM;
-
-	scoped_guard(mutex, &ncm_opts->lock) {
-		gether_apply_opts(netdev, &ncm_opts->net_opts);
-		netdev->mtu = ncm_opts->max_segment_size - ETH_HLEN;
+	mutex_lock(&ncm_opts->lock);
+	gether_set_gadget(ncm_opts->net, cdev->gadget);
+	if (!ncm_opts->bound) {
+		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
+		status = gether_register_netdev(ncm_opts->net);
 	}
+	mutex_unlock(&ncm_opts->lock);
 
-	gether_set_gadget(netdev, cdev->gadget);
-	status = gether_register_netdev(netdev);
 	if (status)
 		return status;
 
-	/* export host's Ethernet address in CDC format */
-	status = gether_get_host_addr_cdc(netdev, ncm->ethaddr,
-					  sizeof(ncm->ethaddr));
-	if (status < 12)
-		return -EINVAL;
-	ncm_string_defs[STRING_MAC_IDX].s = ncm->ethaddr;
+	ncm_opts->bound = true;
+
+	ncm_string_defs[1].s = ncm->ethaddr;
 
 	us = usb_gstrings_attach(cdev, ncm_strings,
 				 ARRAY_SIZE(ncm_string_defs));
@@ -1578,8 +1563,6 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 		f->os_desc_n = 1;
 	}
 	ncm->notify_req = no_free_ptr(request);
-	ncm->netdev = no_free_ptr(netdev);
-	ncm->port.ioport = netdev_priv(ncm->netdev);
 
 	DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n",
 			ncm->port.in_ep->name, ncm->port.out_ep->name,
@@ -1594,19 +1577,19 @@ static inline struct f_ncm_opts *to_f_ncm_opts(struct config_item *item)
 }
 
 /* f_ncm_item_ops */
-USB_ETHER_OPTS_ITEM(ncm);
+USB_ETHERNET_CONFIGFS_ITEM(ncm);
 
 /* f_ncm_opts_dev_addr */
-USB_ETHER_OPTS_ATTR_DEV_ADDR(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_DEV_ADDR(ncm);
 
 /* f_ncm_opts_host_addr */
-USB_ETHER_OPTS_ATTR_HOST_ADDR(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_HOST_ADDR(ncm);
 
 /* f_ncm_opts_qmult */
-USB_ETHER_OPTS_ATTR_QMULT(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm);
 
 /* f_ncm_opts_ifname */
-USB_ETHER_OPTS_ATTR_IFNAME(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm);
 
 static ssize_t ncm_opts_max_segment_size_show(struct config_item *item,
 					      char *page)
@@ -1672,27 +1655,34 @@ static void ncm_free_inst(struct usb_function_instance *f)
 	struct f_ncm_opts *opts;
 
 	opts = container_of(f, struct f_ncm_opts, func_inst);
+	if (opts->bound)
+		gether_cleanup(netdev_priv(opts->net));
+	else
+		free_netdev(opts->net);
 	kfree(opts->ncm_interf_group);
 	kfree(opts);
 }
 
 static struct usb_function_instance *ncm_alloc_inst(void)
 {
-	struct usb_function_instance *ret;
+	struct f_ncm_opts *opts;
 	struct usb_os_desc *descs[1];
 	char *names[1];
 	struct config_group *ncm_interf_group;
 
-	struct f_ncm_opts *opts __free(kfree) = kzalloc_obj(*opts);
+	opts = kzalloc_obj(*opts);
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
-
-	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
-	gether_setup_opts_default(&opts->net_opts, "usb");
 
 	mutex_init(&opts->lock);
 	opts->func_inst.free_func_inst = ncm_free_inst;
+	opts->net = gether_setup_default();
+	if (IS_ERR(opts->net)) {
+		struct net_device *net = opts->net;
+		kfree(opts);
+		return ERR_CAST(net);
+	}
 	opts->max_segment_size = ETH_FRAME_LEN;
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
@@ -1703,22 +1693,26 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	ncm_interf_group =
 		usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs,
 					       names, THIS_MODULE);
-	if (IS_ERR(ncm_interf_group))
+	if (IS_ERR(ncm_interf_group)) {
+		ncm_free_inst(&opts->func_inst);
 		return ERR_CAST(ncm_interf_group);
+	}
 	opts->ncm_interf_group = ncm_interf_group;
 
-	ret = &opts->func_inst;
-	retain_and_null_ptr(opts);
-	return ret;
+	return &opts->func_inst;
 }
 
 static void ncm_free(struct usb_function *f)
 {
-	struct f_ncm_opts *opts = func_to_ncm_opts(f);
+	struct f_ncm *ncm;
+	struct f_ncm_opts *opts;
 
-	scoped_guard(mutex, &opts->lock)
-		opts->refcnt--;
-	kfree(func_to_ncm(f));
+	ncm = func_to_ncm(f);
+	opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+	kfree(ncm);
+	mutex_lock(&opts->lock);
+	opts->refcnt--;
+	mutex_unlock(&opts->lock);
 }
 
 static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
@@ -1742,15 +1736,13 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
-
-	ncm->port.ioport = NULL;
-	gether_cleanup(netdev_priv(ncm->netdev));
 }
 
 static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
 {
 	struct f_ncm		*ncm;
 	struct f_ncm_opts	*opts;
+	int status;
 
 	/* allocate and initialize one new instance */
 	ncm = kzalloc(sizeof(*ncm), GFP_KERNEL);
@@ -1758,12 +1750,22 @@ static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
 		return ERR_PTR(-ENOMEM);
 
 	opts = container_of(fi, struct f_ncm_opts, func_inst);
+	mutex_lock(&opts->lock);
+	opts->refcnt++;
 
-	scoped_guard(mutex, &opts->lock)
-		opts->refcnt++;
+	/* export host's Ethernet address in CDC format */
+	status = gether_get_host_addr_cdc(opts->net, ncm->ethaddr,
+				      sizeof(ncm->ethaddr));
+	if (status < 12) { /* strlen("01234567890a") */
+		kfree(ncm);
+		mutex_unlock(&opts->lock);
+		return ERR_PTR(-EINVAL);
+	}
 
 	spin_lock_init(&ncm->lock);
 	ncm_reset_values(ncm);
+	ncm->port.ioport = netdev_priv(opts->net);
+	mutex_unlock(&opts->lock);
 	ncm->port.is_fixed = true;
 	ncm->port.supports_multi_frame = true;
 
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index d99330fe31e8..49ec095cdb4b 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -15,13 +15,11 @@
 
 #include <linux/usb/composite.h>
 
-#include "u_ether.h"
-
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
+	bool				bound;
 
-	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;
 	char				ncm_ext_compat_id[16];

From 46662d3a1ad40282ba9f753cccc6f909ec4468cc Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:49 +0800
Subject: [PATCH 1217/1303] Revert "usb: gadget: u_ether: Add auto-cleanup
 helper for freeing net_device"

This reverts commit 0c0981126b99288ed354d3d414c8a5fd42ac9e25.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-4-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 15 ---------------
 drivers/usb/gadget/function/u_ether.h |  2 --
 2 files changed, 17 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 338f6e2a85a9..15685b2f8887 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1126,21 +1126,6 @@ void gether_cleanup(struct eth_dev *dev)
 }
 EXPORT_SYMBOL_GPL(gether_cleanup);
 
-void gether_unregister_free_netdev(struct net_device *net)
-{
-	if (!net)
-		return;
-
-	struct eth_dev *dev = netdev_priv(net);
-
-	if (net->reg_state == NETREG_REGISTERED) {
-		unregister_netdev(net);
-		flush_work(&dev->work);
-	}
-	free_netdev(net);
-}
-EXPORT_SYMBOL_GPL(gether_unregister_free_netdev);
-
 /**
  * gether_connect - notify network layer that USB link is active
  * @link: the USB link, set up with endpoints, descriptors matching
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index a212a8ec5eb1..63a0240df4d7 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -283,8 +283,6 @@ int gether_get_ifname(struct net_device *net, char *name, int len);
 int gether_set_ifname(struct net_device *net, const char *name, int len);
 
 void gether_cleanup(struct eth_dev *dev);
-void gether_unregister_free_netdev(struct net_device *net);
-DEFINE_FREE(free_gether_netdev, struct net_device *, gether_unregister_free_netdev(_T));
 
 void gether_setup_opts_default(struct gether_opts *opts, const char *name);
 void gether_apply_opts(struct net_device *net, struct gether_opts *opts);

From 3549d0ae5f7e647ffd09d69f927a18ae7a520f6f Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:50 +0800
Subject: [PATCH 1218/1303] Revert "usb: gadget: u_ether: use <linux/hex.h>
 header file"

This reverts commit 7a7930c0f934fb0c46de6e7ca08e14e11df35dd6.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-5-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether_configfs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 217990a266b2..39d3a261496d 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -14,7 +14,6 @@
 #define __U_ETHER_CONFIGFS_H
 
 #include <linux/cleanup.h>
-#include <linux/hex.h>
 #include <linux/if_ether.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>

From 3131c1aff7cdffb96239f06f98e16188cbc2083f Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:51 +0800
Subject: [PATCH 1219/1303] Revert "usb: gadget: u_ether: add gether_opts for
 config caching"

This reverts commit e065c6a7e46c2ee9c677fdbf50035323d2de1215.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-6-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c         |  30 ---
 drivers/usb/gadget/function/u_ether.h         |  28 ---
 .../usb/gadget/function/u_ether_configfs.h    | 176 ------------------
 3 files changed, 234 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 15685b2f8887..c47965d850d4 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1040,36 +1040,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len)
 }
 EXPORT_SYMBOL_GPL(gether_set_ifname);
 
-void gether_setup_opts_default(struct gether_opts *opts, const char *name)
-{
-	opts->qmult = QMULT_DEFAULT;
-	snprintf(opts->name, sizeof(opts->name), "%s%%d", name);
-	eth_random_addr(opts->dev_mac);
-	opts->addr_assign_type = NET_ADDR_RANDOM;
-	eth_random_addr(opts->host_mac);
-}
-EXPORT_SYMBOL_GPL(gether_setup_opts_default);
-
-void gether_apply_opts(struct net_device *net, struct gether_opts *opts)
-{
-	struct eth_dev *dev = netdev_priv(net);
-
-	dev->qmult = opts->qmult;
-
-	if (opts->ifname_set) {
-		strscpy(net->name, opts->name, sizeof(net->name));
-		dev->ifname_set = true;
-	}
-
-	memcpy(dev->host_mac, opts->host_mac, sizeof(dev->host_mac));
-
-	if (opts->addr_assign_type == NET_ADDR_SET) {
-		memcpy(dev->dev_mac, opts->dev_mac, sizeof(dev->dev_mac));
-		net->addr_assign_type = opts->addr_assign_type;
-	}
-}
-EXPORT_SYMBOL_GPL(gether_apply_opts);
-
 void gether_suspend(struct gether *link)
 {
 	struct eth_dev *dev = link->ioport;
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index 63a0240df4d7..34be220cef77 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -38,31 +38,6 @@
 
 struct eth_dev;
 
-/**
- * struct gether_opts - Options for Ethernet gadget function instances
- * @name: Pattern for the network interface name (e.g., "usb%d").
- *        Used to generate the net device name.
- * @qmult: Queue length multiplier for high/super speed.
- * @host_mac: The MAC address to be used by the host side.
- * @dev_mac: The MAC address to be used by the device side.
- * @ifname_set: True if the interface name pattern has been set by userspace.
- * @addr_assign_type: The method used for assigning the device MAC address
- *                    (e.g., NET_ADDR_RANDOM, NET_ADDR_SET).
- *
- * This structure caches network-related settings provided through configfs
- * before the net_device is fully instantiated. This allows for early
- * configuration while deferring net_device allocation until the function
- * is bound.
- */
-struct gether_opts {
-	char			name[IFNAMSIZ];
-	unsigned int		qmult;
-	u8			host_mac[ETH_ALEN];
-	u8			dev_mac[ETH_ALEN];
-	bool			ifname_set;
-	unsigned char		addr_assign_type;
-};
-
 /*
  * This represents the USB side of an "ethernet" link, managed by a USB
  * function which provides control and (maybe) framing.  Two functions
@@ -284,9 +259,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len);
 
 void gether_cleanup(struct eth_dev *dev);
 
-void gether_setup_opts_default(struct gether_opts *opts, const char *name);
-void gether_apply_opts(struct net_device *net, struct gether_opts *opts);
-
 void gether_suspend(struct gether *link);
 void gether_resume(struct gether *link);
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 39d3a261496d..51f0d79e5eca 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -13,12 +13,6 @@
 #ifndef __U_ETHER_CONFIGFS_H
 #define __U_ETHER_CONFIGFS_H
 
-#include <linux/cleanup.h>
-#include <linux/if_ether.h>
-#include <linux/mutex.h>
-#include <linux/netdevice.h>
-#include <linux/rtnetlink.h>
-
 #define USB_ETHERNET_CONFIGFS_ITEM(_f_)					\
 	static void _f_##_attr_release(struct config_item *item)	\
 	{								\
@@ -203,174 +197,4 @@ out:									\
 									\
 	CONFIGFS_ATTR(_f_##_opts_, _n_)
 
-#define USB_ETHER_OPTS_ITEM(_f_)						\
-	static void _f_##_attr_release(struct config_item *item)		\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		usb_put_function_instance(&opts->func_inst);			\
-	}									\
-										\
-	static struct configfs_item_operations _f_##_item_ops = {		\
-		.release	= _f_##_attr_release,				\
-	}
-
-#define USB_ETHER_OPTS_ATTR_DEV_ADDR(_f_)					\
-	static ssize_t _f_##_opts_dev_addr_show(struct config_item *item,	\
-						char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%pM\n", opts->net_opts.dev_mac);	\
-	}									\
-										\
-	static ssize_t _f_##_opts_dev_addr_store(struct config_item *item,	\
-						 const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u8 new_addr[ETH_ALEN];						\
-		const char *p = page;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		for (int i = 0; i < ETH_ALEN; i++) {				\
-			unsigned char num;					\
-			if ((*p == '.') || (*p == ':'))				\
-				p++;						\
-			num = hex_to_bin(*p++) << 4;				\
-			num |= hex_to_bin(*p++);				\
-			new_addr[i] = num;					\
-		}								\
-		if (!is_valid_ether_addr(new_addr))				\
-			return -EINVAL;						\
-		memcpy(opts->net_opts.dev_mac, new_addr, ETH_ALEN);		\
-		opts->net_opts.addr_assign_type = NET_ADDR_SET;			\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, dev_addr)
-
-#define USB_ETHER_OPTS_ATTR_HOST_ADDR(_f_)					\
-	static ssize_t _f_##_opts_host_addr_show(struct config_item *item,	\
-						 char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%pM\n", opts->net_opts.host_mac);	\
-	}									\
-										\
-	static ssize_t _f_##_opts_host_addr_store(struct config_item *item,	\
-						  const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u8 new_addr[ETH_ALEN];						\
-		const char *p = page;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		for (int i = 0; i < ETH_ALEN; i++) {				\
-			unsigned char num;					\
-			if ((*p == '.') || (*p == ':'))				\
-				p++;						\
-			num = hex_to_bin(*p++) << 4;				\
-			num |= hex_to_bin(*p++);				\
-			new_addr[i] = num;					\
-		}								\
-		if (!is_valid_ether_addr(new_addr))				\
-			return -EINVAL;						\
-		memcpy(opts->net_opts.host_mac, new_addr, ETH_ALEN);		\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, host_addr)
-
-#define USB_ETHER_OPTS_ATTR_QMULT(_f_)						\
-	static ssize_t _f_##_opts_qmult_show(struct config_item *item,		\
-					     char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%u\n", opts->net_opts.qmult);		\
-	}									\
-										\
-	static ssize_t _f_##_opts_qmult_store(struct config_item *item,		\
-					      const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u32 val;							\
-		int ret;							\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		ret = kstrtou32(page, 0, &val);					\
-		if (ret)							\
-			return ret;						\
-										\
-		opts->net_opts.qmult = val;					\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, qmult)
-
-#define USB_ETHER_OPTS_ATTR_IFNAME(_f_)						\
-	static ssize_t _f_##_opts_ifname_show(struct config_item *item,		\
-					      char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		const char *name;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		rtnl_lock();							\
-		if (opts->net_opts.ifname_set)					\
-			name = opts->net_opts.name;				\
-		else if (opts->net)						\
-			name = netdev_name(opts->net);				\
-		else								\
-			name = "(inactive net_device)";				\
-		rtnl_unlock();							\
-		return sysfs_emit(page, "%s\n", name);				\
-	}									\
-										\
-	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
-					       const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		char tmp[IFNAMSIZ];						\
-		const char *p;							\
-		size_t c_len = len;						\
-										\
-		if (c_len > 0 && page[c_len - 1] == '\n')			\
-			c_len--;						\
-										\
-		if (c_len >= sizeof(tmp))					\
-			return -E2BIG;						\
-										\
-		strscpy(tmp, page, c_len + 1);					\
-		if (!dev_valid_name(tmp))					\
-			return -EINVAL;						\
-										\
-		/* Require exactly one %d */					\
-		p = strchr(tmp, '%');						\
-		if (!p || p[1] != 'd' || strchr(p + 2, '%'))			\
-			return -EINVAL;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-		strscpy(opts->net_opts.name, tmp, sizeof(opts->net_opts.name));	\
-		opts->net_opts.ifname_set = true;				\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, ifname)
-
 #endif /* __U_ETHER_CONFIGFS_H */

From ec35c1969650e7cb6c8a91020e568ed46e3551b0 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:52 +0800
Subject: [PATCH 1220/1303] usb: gadget: f_ncm: Fix net_device lifecycle with
 device_move

The network device outlived its parent gadget device during
disconnection, resulting in dangling sysfs links and null pointer
dereference problems.

A prior attempt to solve this by removing SET_NETDEV_DEV entirely [1]
was reverted due to power management ordering concerns and a NO-CARRIER
regression.

A subsequent attempt to defer net_device allocation to bind [2] broke
1:1 mapping between function instance and network device, making it
impossible for configfs to report the resolved interface name. This
results in a regression where the DHCP server fails on pmOS.

Use device_move to reparent the net_device between the gadget device and
/sys/devices/virtual/ across bind/unbind cycles. This preserves the
network interface across USB reconnection, allowing the DHCP server to
retain their binding.

Introduce gether_attach_gadget()/gether_detach_gadget() helpers and use
__free(detach_gadget) macro to undo attachment on bind failure. The
bind_count ensures device_move executes only on the first bind.

[1] https://lore.kernel.org/lkml/f2a4f9847617a0929d62025748384092e5f35cce.camel@crapouillou.net/
[2] https://lore.kernel.org/linux-usb/795ea759-7eaf-4f78-81f4-01ffbf2d7961@ixit.cz/

Fixes: 40d133d7f542 ("usb: gadget: f_ncm: convert to new function interface with backward compatibility")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-7-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c   | 36 ++++++++++++++++++---------
 drivers/usb/gadget/function/u_ether.c | 22 ++++++++++++++++
 drivers/usb/gadget/function/u_ether.h | 26 +++++++++++++++++++
 drivers/usb/gadget/function/u_ncm.h   |  2 +-
 4 files changed, 73 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 3d772c9beb91..a6fa5ed3d6cb 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1439,6 +1439,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	struct f_ncm_opts	*ncm_opts;
 
 	struct usb_os_desc_table	*os_desc_table __free(kfree) = NULL;
+	struct net_device		*net __free(detach_gadget) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
@@ -1452,18 +1453,19 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 			return -ENOMEM;
 	}
 
-	mutex_lock(&ncm_opts->lock);
-	gether_set_gadget(ncm_opts->net, cdev->gadget);
-	if (!ncm_opts->bound) {
-		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
-		status = gether_register_netdev(ncm_opts->net);
-	}
-	mutex_unlock(&ncm_opts->lock);
+	scoped_guard(mutex, &ncm_opts->lock)
+		if (ncm_opts->bind_count == 0) {
+			if (!device_is_registered(&ncm_opts->net->dev)) {
+				ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
+				gether_set_gadget(ncm_opts->net, cdev->gadget);
+				status = gether_register_netdev(ncm_opts->net);
+			} else
+				status = gether_attach_gadget(ncm_opts->net, cdev->gadget);
 
-	if (status)
-		return status;
-
-	ncm_opts->bound = true;
+			if (status)
+				return status;
+			net = ncm_opts->net;
+		}
 
 	ncm_string_defs[1].s = ncm->ethaddr;
 
@@ -1564,6 +1566,9 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 	ncm->notify_req = no_free_ptr(request);
 
+	ncm_opts->bind_count++;
+	retain_and_null_ptr(net);
+
 	DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n",
 			ncm->port.in_ep->name, ncm->port.out_ep->name,
 			ncm->notify->name);
@@ -1655,7 +1660,7 @@ static void ncm_free_inst(struct usb_function_instance *f)
 	struct f_ncm_opts *opts;
 
 	opts = container_of(f, struct f_ncm_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -1718,9 +1723,12 @@ static void ncm_free(struct usb_function *f)
 static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_ncm *ncm = func_to_ncm(f);
+	struct f_ncm_opts *ncm_opts;
 
 	DBG(c->cdev, "ncm unbind\n");
 
+	ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+
 	hrtimer_cancel(&ncm->task_timer);
 
 	kfree(f->os_desc_table);
@@ -1736,6 +1744,10 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
+
+	ncm_opts->bind_count--;
+	if (ncm_opts->bind_count == 0)
+		gether_detach_gadget(ncm_opts->net);
 }
 
 static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index c47965d850d4..1a9e7c495e2e 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -897,6 +897,28 @@ void gether_set_gadget(struct net_device *net, struct usb_gadget *g)
 }
 EXPORT_SYMBOL_GPL(gether_set_gadget);
 
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g)
+{
+	int ret;
+
+	ret = device_move(&net->dev, &g->dev, DPM_ORDER_DEV_AFTER_PARENT);
+	if (ret)
+		return ret;
+
+	gether_set_gadget(net, g);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gether_attach_gadget);
+
+void gether_detach_gadget(struct net_device *net)
+{
+	struct eth_dev *dev = netdev_priv(net);
+
+	device_move(&net->dev, NULL, DPM_ORDER_NONE);
+	dev->gadget = NULL;
+}
+EXPORT_SYMBOL_GPL(gether_detach_gadget);
+
 int gether_set_dev_addr(struct net_device *net, const char *dev_addr)
 {
 	struct eth_dev *dev;
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index 34be220cef77..c85a1cf3c115 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -150,6 +150,32 @@ static inline struct net_device *gether_setup_default(void)
  */
 void gether_set_gadget(struct net_device *net, struct usb_gadget *g);
 
+/**
+ * gether_attach_gadget - Reparent net_device to the gadget device.
+ * @net: The network device to reparent.
+ * @g: The target USB gadget device to parent to.
+ *
+ * This function moves the network device to be a child of the USB gadget
+ * device in the device hierarchy. This is typically done when the function
+ * is bound to a configuration.
+ *
+ * Returns 0 on success, or a negative error code on failure.
+ */
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g);
+
+/**
+ * gether_detach_gadget - Detach net_device from its gadget parent.
+ * @net: The network device to detach.
+ *
+ * This function moves the network device to be a child of the virtual
+ * devices parent, effectively detaching it from the USB gadget device
+ * hierarchy. This is typically done when the function is unbound
+ * from a configuration but the instance is not yet freed.
+ */
+void gether_detach_gadget(struct net_device *net);
+
+DEFINE_FREE(detach_gadget, struct net_device *, if (_T) gether_detach_gadget(_T))
+
 /**
  * gether_set_dev_addr - initialize an ethernet-over-usb link with eth address
  * @net: device representing this link
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 49ec095cdb4b..b1f3db8b68c1 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -18,7 +18,7 @@
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
-	bool				bound;
+	int				bind_count;
 
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;

From 6b275bfaa16be3fb1689fa6794e445ecd127a1b4 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 9 Mar 2026 15:43:12 +0800
Subject: [PATCH 1221/1303] Revert "tcpm: allow looking for role_sw device in
 the main node"

This reverts commit 1366cd228b0c67b60a2c0c26ef37fe9f7cfedb7f.

The fwnode_usb_role_switch_get() returns NULL only if no connection is
found, returns ERR_PTR(-EPROBE_DEFER) if connection is found but deferred
probe is needed, or a valid pointer of usb_role_switch.

When switching from a NULL check to IS_ERR_OR_NULL(), usb_role_switch_get()
returns NULL and overwrites the ERR_PTR(-EPROBE_DEFER) returned by
fwnode_usb_role_switch_get(). This causes the deferred probe indication to
be lost, preventing the USB role switch from ever being retrieved.

Fixes: 1366cd228b0c ("tcpm: allow looking for role_sw device in the main node")
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Tested-by: Arnaud Ferraris <arnaud.ferraris@collabora.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260309074313.2809867-2-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 1d2f3af034c5..8e0e14a2704e 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->partner_desc.identity = &port->partner_ident;
 
 	port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode);
-	if (IS_ERR_OR_NULL(port->role_sw))
+	if (!port->role_sw)
 		port->role_sw = usb_role_switch_get(port->dev);
 	if (IS_ERR(port->role_sw)) {
 		err = PTR_ERR(port->role_sw);

From 8345b1539faa49fcf9c9439c3cbd97dac6eca171 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 9 Mar 2026 15:43:13 +0800
Subject: [PATCH 1222/1303] usb: roles: get usb role switch from parent only
 for usb-b-connector

usb_role_switch_is_parent() was walking up to the parent node and checking
for the "usb-role-switch" property regardless of the type of the passed
fwnode. This could cause unrelated device nodes to be probed as potential
role switch parent, leading to spurious matches and "-EPROBE_DEFER" being
returned infinitely.

Till now only Type-B connector node will have a parent node which may
present "usb-role-switch" property and register the role switch device.
For Type-C connector node, its parent node will always be a Type-C chip
device which will never register the role switch device. However, it may
still present a non-boolean "usb-role-switch = <&usb_controller>" property
for historical compatibility.

So restrict the helper to only operate on Type-B connector when attempting
to get the role switch from parent node.

Fixes: 6fadd72943b8 ("usb: roles: get usb-role-switch from parent")
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Tested-by: Arnaud Ferraris <arnaud.ferraris@collabora.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260309074313.2809867-3-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/roles/class.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index b8e28ceca51e..edec139b68b5 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -139,9 +139,14 @@ static void *usb_role_switch_match(const struct fwnode_handle *fwnode, const cha
 static struct usb_role_switch *
 usb_role_switch_is_parent(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *parent = fwnode_get_parent(fwnode);
+	struct fwnode_handle *parent;
 	struct device *dev;
 
+	if (!fwnode_device_is_compatible(fwnode, "usb-b-connector"))
+		return NULL;
+
+	parent = fwnode_get_parent(fwnode);
+
 	if (!fwnode_property_present(parent, "usb-role-switch")) {
 		fwnode_handle_put(parent);
 		return NULL;

From 163cc462dea7d5b75be4db49ca78a2b99c55375e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 16:17:28 +0100
Subject: [PATCH 1223/1303] gpib: lpvo_usb: fix unintended binding of FTDI
 8U232AM devices

The LPVO USB GPIB adapter apparently uses an FTDI 8U232AM with the
default PID, but this device id is already handled by the ftdi_sio
serial driver.

Stop binding to the default PID to avoid breaking existing setups with
FTDI 8U232AM.

Anyone using this driver should blacklist the ftdi_sio driver and add
the device id manually through sysfs (e.g. using udev rules).

Fixes: fce79512a96a ("staging: gpib: Add LPVO DIY USB GPIB driver")
Fixes: e6ab504633e4 ("staging: gpib: Destage gpib")
Cc: Dave Penkler <dpenkler@gmail.com>
Cc: stable <stable@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260305151729.10501-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
index 6fc4e3452b88..ee781d2f0b8e 100644
--- a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
+++ b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
@@ -38,8 +38,10 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices");
 /*
  * Table of devices that work with this driver.
  *
- * Currently, only one device is known to be used in the
- * lpvo_usb_gpib adapter (FTDI 0403:6001).
+ * Currently, only one device is known to be used in the lpvo_usb_gpib
+ * adapter (FTDI 0403:6001) but as this device id is already handled by the
+ * ftdi_sio USB serial driver the LPVO driver must not bind to it by default.
+ *
  * If your adapter uses a different chip, insert a line
  * in the following table with proper <Vendor-id>, <Product-id>.
  *
@@ -50,7 +52,6 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices");
  */
 
 static const struct usb_device_id skel_table[] = {
-	{ USB_DEVICE(0x0403, 0x6001) },
 	{ }					   /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, skel_table);

From 0073a17b466684413ac87cf8ff6c19560db44e7a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 9 Mar 2026 23:53:24 +0100
Subject: [PATCH 1224/1303] gpu: nova-core: gsp: fix UB in DmaGspMem pointer
 accessors

The DmaGspMem pointer accessor methods (gsp_write_ptr, gsp_read_ptr,
cpu_read_ptr, cpu_write_ptr, advance_cpu_read_ptr,
advance_cpu_write_ptr) dereference a raw pointer to DMA memory, creating
an intermediate reference before calling volatile read/write methods.

This is undefined behavior since DMA memory can be concurrently modified
by the device.

Fix this by moving the implementations into a gsp_mem module in fw.rs
that uses the dma_read!() / dma_write!() macros, making the original
methods on DmaGspMem thin forwarding wrappers.

An alternative approach would have been to wrap the shared memory in
Opaque, but that would have required even more unsafe code.

Since the gsp_mem module lives in fw.rs (to access firmware-specific
binding field names), GspMem, Msgq and their relevant fields are
temporarily widened to pub(super). This will be reverted once IoView
projections are available.

Cc: Gary Guo <gary@garyguo.net>
Closes: https://lore.kernel.org/nouveau/DGUT14ILG35P.1UMNRKU93JUM1@kernel.org/
Fixes: 75f6b1de8133 ("gpu: nova-core: gsp: Add GSP command queue bindings and handling")
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://patch.msgid.link/20260309225408.27714-1-dakr@kernel.org
[ Use pub(super) where possible; replace bitwise-and with modulo
  operator analogous to [1]. - Danilo ]
Link: https://lore.kernel.org/all/20260129-nova-core-cmdq1-v3-1-2ede85493a27@nvidia.com/ [1]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp/cmdq.rs |  71 +++++----------------
 drivers/gpu/nova-core/gsp/fw.rs   | 101 ++++++++++++++++++++----------
 2 files changed, 84 insertions(+), 88 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 9c5efd2daf45..03a4f3599849 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -2,11 +2,7 @@
 
 use core::{
     cmp,
-    mem,
-    sync::atomic::{
-        fence,
-        Ordering, //
-    }, //
+    mem, //
 };
 
 use kernel::{
@@ -146,30 +142,32 @@ struct MsgqData {
 #[repr(C)]
 // There is no struct defined for this in the open-gpu-kernel-source headers.
 // Instead it is defined by code in `GspMsgQueuesInit()`.
-struct Msgq {
+// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module.
+pub(super) struct Msgq {
     /// Header for sending messages, including the write pointer.
-    tx: MsgqTxHeader,
+    pub(super) tx: MsgqTxHeader,
     /// Header for receiving messages, including the read pointer.
-    rx: MsgqRxHeader,
+    pub(super) rx: MsgqRxHeader,
     /// The message queue proper.
     msgq: MsgqData,
 }
 
 /// Structure shared between the driver and the GSP and containing the command and message queues.
 #[repr(C)]
-struct GspMem {
+// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module.
+pub(super) struct GspMem {
     /// Self-mapping page table entries.
     ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>,
     /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the
     /// write and read pointers that the CPU updates.
     ///
     /// This member is read-only for the GSP.
-    cpuq: Msgq,
+    pub(super) cpuq: Msgq,
     /// GSP queue: the GSP writes messages here, and the driver reads them. It also contains the
     /// write and read pointers that the GSP updates.
     ///
     /// This member is read-only for the driver.
-    gspq: Msgq,
+    pub(super) gspq: Msgq,
 }
 
 impl GspMem {
@@ -331,12 +329,7 @@ fn allocate_command(&mut self, size: usize) -> Result<GspCommand<'_>> {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn gsp_write_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).gspq.tx.write_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::gsp_write_ptr(&self.0)
     }
 
     // Returns the index of the memory page the GSP will read the next command from.
@@ -345,12 +338,7 @@ fn gsp_write_ptr(&self) -> u32 {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn gsp_read_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).gspq.rx.read_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::gsp_read_ptr(&self.0)
     }
 
     // Returns the index of the memory page the CPU can read the next message from.
@@ -359,27 +347,12 @@ fn gsp_read_ptr(&self) -> u32 {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn cpu_read_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The ['CoherentAllocation'] contains at least one object.
-        //  - By the invariants of CoherentAllocation the pointer is valid.
-        (unsafe { (*gsp_mem).cpuq.rx.read_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::cpu_read_ptr(&self.0)
     }
 
     // Informs the GSP that it can send `elem_count` new pages into the message queue.
     fn advance_cpu_read_ptr(&mut self, elem_count: u32) {
-        let rptr = self.cpu_read_ptr().wrapping_add(elem_count) % MSGQ_NUM_PAGES;
-
-        // Ensure read pointer is properly ordered.
-        fence(Ordering::SeqCst);
-
-        let gsp_mem = self.0.start_ptr_mut();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        unsafe { (*gsp_mem).cpuq.rx.set_read_ptr(rptr) };
+        super::fw::gsp_mem::advance_cpu_read_ptr(&self.0, elem_count)
     }
 
     // Returns the index of the memory page the CPU can write the next command to.
@@ -388,26 +361,12 @@ fn advance_cpu_read_ptr(&mut self, elem_count: u32) {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn cpu_write_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).cpuq.tx.write_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::cpu_write_ptr(&self.0)
     }
 
     // Informs the GSP that it can process `elem_count` new pages from the command queue.
     fn advance_cpu_write_ptr(&mut self, elem_count: u32) {
-        let wptr = self.cpu_write_ptr().wrapping_add(elem_count) & MSGQ_NUM_PAGES;
-        let gsp_mem = self.0.start_ptr_mut();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        unsafe { (*gsp_mem).cpuq.tx.set_write_ptr(wptr) };
-
-        // Ensure all command data is visible before triggering the GSP read.
-        fence(Ordering::SeqCst);
+        super::fw::gsp_mem::advance_cpu_write_ptr(&self.0, elem_count)
     }
 }
 
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index 83ff91614e36..040b30ec3089 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -40,6 +40,75 @@
     },
 };
 
+// TODO: Replace with `IoView` projections once available; the `unwrap()` calls go away once we
+// switch to the new `dma::Coherent` API.
+pub(super) mod gsp_mem {
+    use core::sync::atomic::{
+        fence,
+        Ordering, //
+    };
+
+    use kernel::{
+        dma::CoherentAllocation,
+        dma_read,
+        dma_write,
+        prelude::*, //
+    };
+
+    use crate::gsp::cmdq::{
+        GspMem,
+        MSGQ_NUM_PAGES, //
+    };
+
+    pub(in crate::gsp) fn gsp_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn gsp_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn cpu_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &CoherentAllocation<GspMem>, count: u32) {
+        let rptr = cpu_read_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
+
+        // Ensure read pointer is properly ordered.
+        fence(Ordering::SeqCst);
+
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result {
+            dma_write!(qs, [0]?.cpuq.rx.0.readPtr, rptr);
+            Ok(())
+        }()
+        .unwrap()
+    }
+
+    pub(in crate::gsp) fn cpu_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn advance_cpu_write_ptr(qs: &CoherentAllocation<GspMem>, count: u32) {
+        let wptr = cpu_write_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
+
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result {
+            dma_write!(qs, [0]?.cpuq.tx.0.writePtr, wptr);
+            Ok(())
+        }()
+        .unwrap();
+
+        // Ensure all command data is visible before triggering the GSP read.
+        fence(Ordering::SeqCst);
+    }
+}
+
 /// Empty type to group methods related to heap parameters for running the GSP firmware.
 enum GspFwHeapParams {}
 
@@ -708,22 +777,6 @@ pub(crate) fn new(msgq_size: u32, rx_hdr_offset: u32, msg_count: u32) -> Self {
             entryOff: num::usize_into_u32::<GSP_PAGE_SIZE>(),
         })
     }
-
-    /// Returns the value of the write pointer for this queue.
-    pub(crate) fn write_ptr(&self) -> u32 {
-        let ptr = core::ptr::from_ref(&self.0.writePtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.read_volatile() }
-    }
-
-    /// Sets the value of the write pointer for this queue.
-    pub(crate) fn set_write_ptr(&mut self, val: u32) {
-        let ptr = core::ptr::from_mut(&mut self.0.writePtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.write_volatile(val) }
-    }
 }
 
 // SAFETY: Padding is explicit and does not contain uninitialized data.
@@ -739,22 +792,6 @@ impl MsgqRxHeader {
     pub(crate) fn new() -> Self {
         Self(Default::default())
     }
-
-    /// Returns the value of the read pointer for this queue.
-    pub(crate) fn read_ptr(&self) -> u32 {
-        let ptr = core::ptr::from_ref(&self.0.readPtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.read_volatile() }
-    }
-
-    /// Sets the value of the read pointer for this queue.
-    pub(crate) fn set_read_ptr(&mut self, val: u32) {
-        let ptr = core::ptr::from_mut(&mut self.0.readPtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.write_volatile(val) }
-    }
 }
 
 // SAFETY: Padding is explicit and does not contain uninitialized data.

From a9683730e8b1d632674f81844ed03ddfbe4821c0 Mon Sep 17 00:00:00 2001
From: Casey Connolly <casey.connolly@linaro.org>
Date: Fri, 6 Mar 2026 18:47:07 +0100
Subject: [PATCH 1225/1303] ASoC: detect empty DMI strings

Some bootloaders like recent versions of U-Boot may install some DMI
properties with empty values rather than not populate them. This manages
to make its way through the validator and cleanup resulting in a rogue
hyphen being appended to the card longname.

Fixes: 4e01e5dbba96 ("ASoC: improve the DMI long card code in asoc-core")
Signed-off-by: Casey Connolly <casey.connolly@linaro.org>
Link: https://patch.msgid.link/20260306174707.283071-2-casey.connolly@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index cf826c2a8b59..573693e21780 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1863,12 +1863,15 @@ static void cleanup_dmi_name(char *name)
 
 /*
  * Check if a DMI field is valid, i.e. not containing any string
- * in the black list.
+ * in the black list and not the empty string.
  */
 static int is_dmi_valid(const char *field)
 {
 	int i = 0;
 
+	if (!field[0])
+		return 0;
+
 	while (dmi_blacklist[i]) {
 		if (strstr(field, dmi_blacklist[i]))
 			return 0;

From 464b1c115852fe025635ae2065e00caced184d92 Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Wed, 11 Mar 2026 17:36:17 +0800
Subject: [PATCH 1226/1303] slab: fix memory leak when refill_sheaf() fails

When refill_sheaf() partially fills one sheaf (e.g., fills 5 objects
but need to fill 10), it will update sheaf->size and return -ENOMEM.
However, the callers (alloc_full_sheaf() and __pcs_replace_empty_main())
directly call free_empty_sheaf() on failure, which only does kfree(sheaf),
causing the partially allocated objects memory in sheaf->objects[] leaked.

Fix this by calling sheaf_flush_unused() before free_empty_sheaf() to
free objects of sheaf->objects[]. And also add a WARN_ON() in
free_empty_sheaf() to catch any future cases where a non-empty sheaf is
being freed.

Fixes: ed30c4adfc2b ("slab: add optimized sheaf refill from partial list")
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Link: https://patch.msgid.link/20260311093617.4155965-1-wangqing7171@gmail.com
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index 6371838d2352..2b2d33cc735c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2790,6 +2790,7 @@ static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf)
 	if (s->flags & SLAB_KMALLOC)
 		mark_obj_codetag_empty(sheaf);
 
+	VM_WARN_ON_ONCE(sheaf->size > 0);
 	kfree(sheaf);
 
 	stat(s, SHEAF_FREE);
@@ -2821,6 +2822,7 @@ static int refill_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf,
 	return 0;
 }
 
+static void sheaf_flush_unused(struct kmem_cache *s, struct slab_sheaf *sheaf);
 
 static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 {
@@ -2830,6 +2832,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 		return NULL;
 
 	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
+		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
 		return NULL;
 	}
@@ -4616,6 +4619,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 			 * we must be very low on memory so don't bother
 			 * with the barn
 			 */
+			sheaf_flush_unused(s, empty);
 			free_empty_sheaf(s, empty);
 		}
 	} else {

From cf534a09fb621b0aa875613e3cd88aee336e16d7 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Tue, 3 Mar 2026 09:51:58 +1300
Subject: [PATCH 1227/1303] KVM: selftests: Increase 'maxnode' for guest_memfd
 tests

Increase 'maxnode' when using 'get_mempolicy' syscall in guest_memfd
mmap and NUMA policy tests to fix a failure on one Intel GNR platform.

On a CXL-capable platform, the memory affinity of CXL memory regions may
not be covered by the SRAT.  Since each CXL memory region is enumerated
via a CFMWS table, at early boot the kernel parses all CFMWS tables to
detect all CXL memory regions and assigns a 'faked' NUMA node for each
of them, starting from the highest NUMA node ID enumerated via the SRAT.

This increases the 'nr_node_ids'.  E.g., on the aforementioned Intel GNR
platform which has 4 NUMA nodes and 18 CFMWS tables, it increases to 22.

This results in the 'get_mempolicy' syscall failure on that platform,
because currently 'maxnode' is hard-coded to 8 but the 'get_mempolicy'
syscall requires the 'maxnode' to be not smaller than the 'nr_node_ids'.

Increase the 'maxnode' to the number of bits of 'nodemask', which is
'unsigned long', to fix this.

This may not cover all systems.  Perhaps a better way is to always set
the 'nodemask' and 'maxnode' based on the actual maximum NUMA node ID on
the system, but for now just do the simple way.

Reported-by: Yi Lai <yi1.lai@intel.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221014
Closes: https://lore.kernel.org/all/bug-221014-28872@https.bugzilla.kernel.org%2F
Signed-off-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Yuan Yao <yaoyuan@linux.alibaba.com>
Link: https://patch.msgid.link/20260302205158.178058-1-kai.huang@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/guest_memfd_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 618c937f3c90..cc329b57ce2e 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -80,7 +80,7 @@ static void test_mbind(int fd, size_t total_size)
 {
 	const unsigned long nodemask_0 = 1; /* nid: 0 */
 	unsigned long nodemask = 0;
-	unsigned long maxnode = 8;
+	unsigned long maxnode = BITS_PER_TYPE(nodemask);
 	int policy;
 	char *mem;
 	int ret;

From 4c0134639694fcdc4ab041d7c53d6188a3e18040 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Mar 2026 11:03:38 -0800
Subject: [PATCH 1228/1303] KVM: PPC: e500: Fix build error due to using
 kmalloc_obj() with wrong type

Fix a build error in kvmppc_e500_tlb_init() that was introduced by the
conversion to use kzalloc_objs(), as KVM confusingly uses the size of the
structure that is one and only field in tlbe_priv:

  arch/powerpc/kvm/e500_mmu.c:923:33: error: assignment to 'struct tlbe_priv *'
    from incompatible pointer type 'struct tlbe_ref *' [-Wincompatible-pointer-types]
  923 |         vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref,
      |                                 ^

KVM has been flawed since commit 0164c0f0c404 ("KVM: PPC: e500: clear up
confusion between host and guest entries"), but the issue went unnoticed
until kmalloc_obj() came along and enforced types, as "struct tlbe_priv"
was just a wrapper of "struct tlbe_ref" (why on earth the two ever existed
separately...).

Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Cc: Kees Cook <kees@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Link: https://patch.msgid.link/20260303190339.974325-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/e500_mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 48580c85f23b..75ed1496ead5 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -920,12 +920,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
 
-	vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref,
+	vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv,
 					       vcpu_e500->gtlb_params[0].entries);
 	if (!vcpu_e500->gtlb_priv[0])
 		goto free_vcpu;
 
-	vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_ref,
+	vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv,
 					       vcpu_e500->gtlb_params[1].entries);
 	if (!vcpu_e500->gtlb_priv[1])
 		goto free_vcpu;

From fe2a08eca5caa77398bfa321bd321d087b0b44b0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Mar 2026 11:03:39 -0800
Subject: [PATCH 1229/1303] KVM: PPC: e500: Rip out "struct tlbe_ref"

Complete the ~13 year journey started by commit 47bf379742bf
("kvm/ppc/e500: eliminate tlb_refs"), and actually remove "struct
tlbe_ref".

No functional change intended (verified disassembly of e500_mmu.o and
e500_mmu_host.o is identical before and after).

Link: https://patch.msgid.link/20260303190339.974325-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/e500.h          |  6 +--
 arch/powerpc/kvm/e500_mmu_host.c | 91 +++++++++++++++-----------------
 2 files changed, 45 insertions(+), 52 deletions(-)

diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index f9acf866c709..e4469ad73a2e 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -39,15 +39,11 @@ enum vcpu_ftr {
 /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */
 #define E500_TLB_MAS2_ATTR	(0x7f)
 
-struct tlbe_ref {
+struct tlbe_priv {
 	kvm_pfn_t pfn;		/* valid only for TLB0, except briefly */
 	unsigned int flags;	/* E500_TLB_* */
 };
 
-struct tlbe_priv {
-	struct tlbe_ref ref;
-};
-
 #ifdef CONFIG_KVM_E500V2
 struct vcpu_id_table;
 #endif
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 06caf8bbbe2b..37e0d3d9e244 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe =
 		get_entry(vcpu_e500, tlbsel, esel);
-	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
+	struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
 	/* Don't bother with unmapped entries */
-	if (!(ref->flags & E500_TLB_VALID)) {
-		WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
-		     "%s: flags %x\n", __func__, ref->flags);
+	if (!(tlbe->flags & E500_TLB_VALID)) {
+		WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+		     "%s: flags %x\n", __func__, tlbe->flags);
 		WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
 	}
 
-	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
+	if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) {
 		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
 		int hw_tlb_indx;
 		unsigned long flags;
@@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 		}
 		mb();
 		vcpu_e500->g2h_tlb1_map[esel] = 0;
-		ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
+		tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
 		local_irq_restore(flags);
 	}
 
-	if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) {
+	if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) {
 		/*
 		 * TLB1 entry is backed by 4k pages. This should happen
 		 * rarely and is not worth optimizing. Invalidate everything.
 		 */
 		kvmppc_e500_tlbil_all(vcpu_e500);
-		ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
+		tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
 	}
 
 	/*
 	 * If TLB entry is still valid then it's a TLB0 entry, and thus
 	 * backed by at most one host tlbe per shadow pid
 	 */
-	if (ref->flags & E500_TLB_VALID)
+	if (tlbe->flags & E500_TLB_VALID)
 		kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
 
 	/* Mark the TLB as not backed by the host anymore */
-	ref->flags = 0;
+	tlbe->flags = 0;
 }
 
 static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
@@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
 }
 
-static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
-					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 kvm_pfn_t pfn, unsigned int wimg,
-					 bool writable)
+static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe,
+					  struct kvm_book3e_206_tlb_entry *gtlbe,
+					  kvm_pfn_t pfn, unsigned int wimg,
+					  bool writable)
 {
-	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
+	tlbe->pfn = pfn;
+	tlbe->flags = E500_TLB_VALID;
 	if (writable)
-		ref->flags |= E500_TLB_WRITABLE;
+		tlbe->flags |= E500_TLB_WRITABLE;
 
 	/* Use guest supplied MAS2_G and MAS2_E */
-	ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
+	tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
 }
 
-static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
+static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe)
 {
-	if (ref->flags & E500_TLB_VALID) {
+	if (tlbe->flags & E500_TLB_VALID) {
 		/* FIXME: don't log bogus pfn for TLB1 */
-		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
-		ref->flags = 0;
+		trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags);
+		tlbe->flags = 0;
 	}
 }
 
@@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int i;
 
 	for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
-		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-			struct tlbe_ref *ref =
-				&vcpu_e500->gtlb_priv[tlbsel][i].ref;
-			kvmppc_e500_ref_release(ref);
-		}
+		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++)
+			kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]);
 	}
 }
 
@@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
 static void kvmppc_e500_setup_stlbe(
 	struct kvm_vcpu *vcpu,
 	struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tsize, struct tlbe_ref *ref, u64 gvaddr,
+	int tsize, struct tlbe_priv *tlbe, u64 gvaddr,
 	struct kvm_book3e_206_tlb_entry *stlbe)
 {
-	kvm_pfn_t pfn = ref->pfn;
+	kvm_pfn_t pfn = tlbe->pfn;
 	u32 pr = vcpu->arch.shared->msr & MSR_PR;
-	bool writable = !!(ref->flags & E500_TLB_WRITABLE);
+	bool writable = !!(tlbe->flags & E500_TLB_WRITABLE);
 
-	BUG_ON(!(ref->flags & E500_TLB_VALID));
+	BUG_ON(!(tlbe->flags & E500_TLB_VALID));
 
 	/* Force IPROT=0 for all guest mappings. */
 	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
+	stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
 			e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr);
 }
@@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe(
 static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
-	struct tlbe_ref *ref)
+	struct tlbe_priv *tlbe)
 {
 	struct kvm_memory_slot *slot;
 	unsigned int psize;
@@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		}
 	}
 
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable);
+	kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable);
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
-				ref, gvaddr, stlbe);
+				tlbe, gvaddr, stlbe);
 	writable = tlbe_is_writable(stlbe);
 
 	/* Clear i-cache for new pages */
@@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
 				struct kvm_book3e_206_tlb_entry *stlbe)
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe;
-	struct tlbe_ref *ref;
+	struct tlbe_priv *tlbe;
 	int stlbsel = 0;
 	int sesel = 0;
 	int r;
 
 	gtlbe = get_entry(vcpu_e500, 0, esel);
-	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
+	tlbe = &vcpu_e500->gtlb_priv[0][esel];
 
 	r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
 			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-			gtlbe, 0, stlbe, ref);
+			gtlbe, 0, stlbe, tlbe);
 	if (r)
 		return r;
 
@@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
 }
 
 static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
-				     struct tlbe_ref *ref,
+				     struct tlbe_priv *tlbe,
 				     int esel)
 {
 	unsigned int sesel = vcpu_e500->host_tlb1_nv++;
@@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
 		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
 	}
 
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP;
 	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
 	vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
-	WARN_ON(!(ref->flags & E500_TLB_VALID));
+	WARN_ON(!(tlbe->flags & E500_TLB_VALID));
 
 	return sesel;
 }
@@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
-	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
+	struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel];
 	int sesel;
 	int r;
 
 	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
-				   ref);
+				   tlbe);
 	if (r)
 		return r;
 
 	/* Use TLB0 when we can only map a page with 4k */
 	if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) {
-		vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0;
+		vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0;
 		write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0);
 		return 0;
 	}
 
 	/* Otherwise map into TLB1 */
-	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel);
 	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
 
 	return 0;
@@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
 		/* Triggers after clear_tlb_privs or on initial mapping */
-		if (!(priv->ref.flags & E500_TLB_VALID)) {
+		if (!(priv->flags & E500_TLB_VALID)) {
 			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
 		} else {
 			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
-						&priv->ref, eaddr, &stlbe);
+						priv, eaddr, &stlbe);
 			write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0);
 		}
 		break;

From 4b3b8a8b0df1a5e7a1af04ff512df2c80db35dc8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Carlos=20L=C3=B3pez?= <clopez@suse.de>
Date: Mon, 9 Feb 2026 16:31:09 +0100
Subject: [PATCH 1230/1303] KVM: x86: synthesize CPUID bits only if CPU
 capability is set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

KVM incorrectly synthesizes CPUID bits for KVM-only leaves, as the
following branch in kvm_cpu_cap_init() is never taken:

    if (leaf < NCAPINTS)
        kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf];

This means that bits set via SYNTHESIZED_F() for KVM-only leaves are
unconditionally set. This for example can cause issues for SEV-SNP
guests running on Family 19h CPUs, as TSA_SQ_NO and TSA_L1_NO are
always enabled by KVM in 80000021[ECX]. When userspace issues a
SNP_LAUNCH_UPDATE command to update the CPUID page for the guest, SNP
firmware will explicitly reject the command if the page sets sets these
bits on vulnerable CPUs.

To fix this, check in SYNTHESIZED_F() that the corresponding X86
capability is set before adding it to to kvm_cpu_cap_features.

Fixes: 31272abd5974 ("KVM: SVM: Advertise TSA CPUID bits to guests")
Link: https://lore.kernel.org/all/20260208164233.30405-1-clopez@suse.de/
Signed-off-by: Carlos López <clopez@suse.de>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Link: https://patch.msgid.link/20260209153108.70667-2-clopez@suse.de
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index d2486506a808..8137927e7387 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -776,7 +776,10 @@ do {									\
 #define SYNTHESIZED_F(name)					\
 ({								\
 	kvm_cpu_cap_synthesized |= feature_bit(name);		\
-	F(name);						\
+								\
+	BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES);	\
+	if (boot_cpu_has(X86_FEATURE_##name))			\
+		F(name);					\
 })
 
 /*

From a5264387c2ee42fca92ac792199008fc60ee82f1 Mon Sep 17 00:00:00 2001
From: Manuel Andreas <manuel.andreas@tum.de>
Date: Thu, 19 Feb 2026 21:05:49 +0100
Subject: [PATCH 1231/1303] KVM: x86: hyper-v: Validate all GVAs during PV TLB
 flush

In KVM guests with Hyper-V hypercalls enabled, the hypercalls
HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST and HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX
allow a guest to request invalidation of portions of a virtual TLB.
For this, the hypercall parameter includes a list of GVAs that are supposed
to be invalidated.

Currently, only the base GVA is checked to be canonical. In reality, this
check needs to be performed for the entire range of GVAs, as checking only
the base GVA enables guests running on Intel hardware to trigger a
WARN_ONCE in the host (see Fixes commit below).

Move the check for non-canonical addresses to be performed for every GVA
of the supplied range to avoid the splat, and to be more in line with the
Hyper-V specification, since, although unlikely, a range starting with an
invalid GVA may still contain GVAs that are valid.

Fixes: fa787ac07b3c ("KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush")
Signed-off-by: Manuel Andreas <manuel.andreas@tum.de>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://patch.msgid.link/00a7a31b-573b-4d92-91f8-7d7e2f88ea48@tum.de
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 30202942289a..9b140bbdc1d8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1981,16 +1981,17 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
-		if (is_noncanonical_invlpg_address(entries[i], vcpu))
-			continue;
-
 		/*
 		 * Lower 12 bits of 'address' encode the number of additional
 		 * pages to flush.
 		 */
 		gva = entries[i] & PAGE_MASK;
-		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++)
+		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) {
+			if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu))
+				continue;
+
 			kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+		}
 
 		++vcpu->stat.tlb_flush;
 	}

From f78e627a01bd4ec0219566d2c9c40f3c3614f875 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 20 Feb 2026 14:02:16 -0800
Subject: [PATCH 1232/1303] KVM: VMX: Fix a wrong MSR update in
 add_atomic_switch_msr()

The previous change had a bug to update a guest MSR with a host value.

Fixes: c3d6a7210a4de9096 ("KVM: VMX: Dedup code for adding MSR to VMCS's auto list")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20260220220216.389475-1-namhyung@kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 967b58a8ab9d..83d057cfa816 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1149,7 +1149,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	}
 
 	vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm);
-	vmx_add_auto_msr(&m->guest, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm);
+	vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm);
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx)

From b54e4707a64be93a8ab3348e32e89817229b5eaa Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 4 Feb 2026 04:12:06 -0500
Subject: [PATCH 1233/1303] KVM: x86: Fix SRCU list traversal in
 kvm_fire_mask_notifiers()

The mask_notifier_list is protected by kvm->irq_srcu, but the traversal
in kvm_fire_mask_notifiers() incorrectly uses hlist_for_each_entry_rcu().
This leads to lockdep warnings because the standard RCU iterator expects
to be under rcu_read_lock(), not SRCU.

Replace the RCU variant with hlist_for_each_entry_srcu() and provide
the proper srcu_read_lock_held() annotation to ensure correct
synchronization and silence lockdep.

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://patch.msgid.link/20260204091206.2617-1-lirongqing@baidu.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/ioapic.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index bb257793b6cb..eed96ff6e722 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -321,7 +321,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
-		hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link)
+		hlist_for_each_entry_srcu(kimn, &ioapic->mask_notifier_list, link,
+				srcu_read_lock_held(&kvm->irq_srcu))
 			if (kimn->irq == gsi)
 				kimn->func(kimn, mask);
 	srcu_read_unlock(&kvm->irq_srcu, idx);

From e2ffe85b6d2bb7780174b87aa4468a39be17eb81 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Thu, 5 Feb 2026 15:15:26 -0800
Subject: [PATCH 1234/1303] KVM: x86: Introduce
 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM

Add KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM to allow L1 to set
FREEZE_IN_SMM in vmcs12's GUEST_IA32_DEBUGCTL field, as permitted
prior to commit 6b1dd26544d0 ("KVM: VMX: Preserve host's
DEBUGCTLMSR_FREEZE_IN_SMM while running the guest").  Enable the quirk
by default for backwards compatibility (like all quirks); userspace
can disable it via KVM_CAP_DISABLE_QUIRKS2 for consistency with the
constraints on WRMSR(IA32_DEBUGCTL).

Note that the quirk only bypasses the consistency check.  The vmcs02 bit is
still owned by the host, and PMCs are not frozen during virtualized SMM.
In particular, if a host administrator decides that PMCs should not be
frozen during physical SMM, then L1 has no say in the matter.

Fixes: 095686e6fcb4 ("KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter")
Cc: stable@vger.kernel.org
Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260205231537.1278753-1-jmattson@google.com
[sean: tag for stable@, clean-up and fix goofs in the comment and docs]
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Rename quirk. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |  8 ++++++++
 arch/x86/include/asm/kvm_host.h |  3 ++-
 arch/x86/include/uapi/asm/kvm.h |  1 +
 arch/x86/kvm/vmx/nested.c       | 22 ++++++++++++++++++----
 4 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 6f85e1b321dd..19365b284395 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8543,6 +8543,14 @@ KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
                                     guest software, for example if it does not
                                     expose a bochs graphics device (which is
                                     known to have had a buggy driver).
+
+KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM   By default, KVM relaxes the consistency
+                                      check for GUEST_IA32_DEBUGCTL in vmcs12
+                                      to allow FREEZE_IN_SMM to be set.  When
+                                      this quirk is disabled, KVM requires this
+                                      bit to be cleared.  Note that the vmcs02
+                                      bit is still completely controlled by the
+                                      host, regardless of the quirk setting.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ff07c45e3c73..6e4e3ef9b8c7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
 	 KVM_X86_QUIRK_SLOT_ZAP_ALL |		\
 	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS |	\
-	 KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+	 KVM_X86_QUIRK_IGNORE_GUEST_PAT |	\
+	 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)
 
 #define KVM_X86_CONDITIONAL_QUIRKS		\
 	(KVM_X86_QUIRK_CD_NW_CLEARED |		\
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 846a63215ce1..0d4538fa6c31 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -476,6 +476,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 #define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
+#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 248635da6766..603c98de2cc8 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP)))
 		return -EINVAL;
 
-	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
-	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
-		return -EINVAL;
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+		u64 debugctl = vmcs12->guest_ia32_debugctl;
+
+		/*
+		 * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in
+		 * vmcs12's DEBUGCTL under a quirk for backwards compatibility.
+		 * Note that the quirk only relaxes the consistency check.  The
+		 * vmcc02 bit is still under the control of the host.  In
+		 * particular, if a host administrator decides to clear the bit,
+		 * then L1 has no say in the matter.
+		 */
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM))
+			debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM;
+
+		if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+		    CC(!vmx_is_valid_debugctl(vcpu, debugctl, false)))
+			return -EINVAL;
+	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
 	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))

From 3989a6d036c8ec82c0de3614bed23a1dacd45de5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Feb 2026 11:07:09 -0800
Subject: [PATCH 1235/1303] KVM: SVM: Initialize AVIC VMCB fields if AVIC is
 enabled with in-kernel APIC

Initialize all per-vCPU AVIC control fields in the VMCB if AVIC is enabled
in KVM and the VM has an in-kernel local APIC, i.e. if it's _possible_ the
vCPU could activate AVIC at any point in its lifecycle.  Configuring the
VMCB if and only if AVIC is active "works" purely because of optimizations
in kvm_create_lapic() to speculatively set apicv_active if AVIC is enabled
*and* to defer updates until the first KVM_RUN.  In quotes because KVM
likely won't do the right thing if kvm_apicv_activated() is false, i.e. if
a vCPU is created while APICv is inhibited at the VM level for whatever
reason.  E.g. if the inhibit is *removed* before KVM_REQ_APICV_UPDATE is
handled in KVM_RUN, then __kvm_vcpu_update_apicv() will elide calls to
vendor code due to seeing "apicv_active == activate".

Cleaning up the initialization code will also allow fixing a bug where KVM
incorrectly leaves CR8 interception enabled when AVIC is activated without
creating a mess with respect to whether AVIC is activated or not.

Cc: stable@vger.kernel.org
Fixes: 67034bb9dd5e ("KVM: SVM: Add irqchip_split() checks before enabling AVIC")
Fixes: 6c3e4422dd20 ("svm: Add support for dynamic APICv")
Reviewed-by: Naveen N Rao (AMD) <naveen@kernel.org>
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260203190711.458413-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/avic.c | 2 +-
 arch/x86/kvm/svm/svm.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index f92214b1a938..44e07c27b190 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -368,7 +368,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 	vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table));
 	vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE;
 
-	if (kvm_apicv_activated(svm->vcpu.kvm))
+	if (kvm_vcpu_apicv_active(&svm->vcpu))
 		avic_activate_vmcb(svm);
 	else
 		avic_deactivate_vmcb(svm);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8f8bc863e214..7806321c37bc 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1189,7 +1189,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event)
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS))
 		svm->vmcb->control.erap_ctl |= ERAP_CONTROL_ALLOW_LARGER_RAP;
 
-	if (kvm_vcpu_apicv_active(vcpu))
+	if (enable_apicv && irqchip_in_kernel(vcpu->kvm))
 		avic_init_vmcb(svm, vmcb);
 
 	if (vnmi)

From 87d0f901a9bd8ae6be57249c737f20ac0cace93d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Feb 2026 11:07:10 -0800
Subject: [PATCH 1236/1303] KVM: SVM: Set/clear CR8 write interception when
 AVIC is (de)activated

Explicitly set/clear CR8 write interception when AVIC is (de)activated to
fix a bug where KVM leaves the interception enabled after AVIC is
activated.  E.g. if KVM emulates INIT=>WFS while AVIC is deactivated, CR8
will remain intercepted in perpetuity.

On its own, the dangling CR8 intercept is "just" a performance issue, but
combined with the TPR sync bug fixed by commit d02e48830e3f ("KVM: SVM:
Sync TPR from LAPIC into VMCB::V_TPR even if AVIC is active"), the danging
intercept is fatal to Windows guests as the TPR seen by hardware gets
wildly out of sync with reality.

Note, VMX isn't affected by the bug as TPR_THRESHOLD is explicitly ignored
when Virtual Interrupt Delivery is enabled, i.e. when APICv is active in
KVM's world.  I.e. there's no need to trigger update_cr8_intercept(), this
is firmly an SVM implementation flaw/detail.

WARN if KVM gets a CR8 write #VMEXIT while AVIC is active, as KVM should
never enter the guest with AVIC enabled and CR8 writes intercepted.

Fixes: 3bbf3565f48c ("svm: Do not intercept CR8 when enable AVIC")
Cc: stable@vger.kernel.org
Cc: Jim Mattson <jmattson@google.com>
Cc: Naveen N Rao (AMD) <naveen@kernel.org>
Cc: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Reviewed-by: Naveen N Rao (AMD) <naveen@kernel.org>
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260203190711.458413-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Squash fix to avic_deactivate_vmcb. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/avic.c | 7 +++++--
 arch/x86/kvm/svm/svm.c  | 7 ++++---
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 44e07c27b190..f7ec7914e3c4 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -189,12 +189,12 @@ static void avic_activate_vmcb(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
-
 	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
 	vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu);
-
 	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
 
+	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	/*
 	 * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR
 	 * accesses, while interrupt injection to a running vCPU can be
@@ -226,6 +226,9 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm)
 	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
 	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
 
+	if (!sev_es_guest(svm->vcpu.kvm))
+		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	/*
 	 * If running nested and the guest uses its own MSR bitmap, there
 	 * is no need to update L0's msr bitmap
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7806321c37bc..2772f22df7ed 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1077,8 +1077,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event)
 	svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
 	svm_set_intercept(svm, INTERCEPT_CR3_WRITE);
 	svm_set_intercept(svm, INTERCEPT_CR4_WRITE);
-	if (!kvm_vcpu_apicv_active(vcpu))
-		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
+	svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
 
 	set_dr_intercepts(svm);
 
@@ -2674,9 +2673,11 @@ static int dr_interception(struct kvm_vcpu *vcpu)
 
 static int cr8_write_interception(struct kvm_vcpu *vcpu)
 {
+	u8 cr8_prev = kvm_get_cr8(vcpu);
 	int r;
 
-	u8 cr8_prev = kvm_get_cr8(vcpu);
+	WARN_ON_ONCE(kvm_vcpu_apicv_active(vcpu));
+
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(vcpu);
 	if (lapic_in_kernel(vcpu))

From 5a30e8aea079b3e4e79d6ce7a878f5f42efe9d0b Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 12:40:40 +0100
Subject: [PATCH 1237/1303] KVM: VMX: check validity of VMCS controls when
 returning from SMM

The VMCS12 is not available while in SMM.  However, it can be overwritten
if userspace manages to trigger copy_enlightened_to_vmcs12() - for example
via KVM_GET_NESTED_STATE.

Because of this, the VMCS12 has to be checked for validity before it is
used to generate the VMCS02.  Move the check code out of vmx_set_nested_state()
(the other "not a VMLAUNCH/VMRESUME" path that emulates a nested vmentry)
and reuse it in vmx_leave_smm().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 39 +++++++++++++++++++++++++++------------
 arch/x86/kvm/vmx/nested.h |  1 +
 arch/x86/kvm/vmx/vmx.c    |  4 ++++
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 603c98de2cc8..937aeb474af7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6856,13 +6856,34 @@ void vmx_leave_nested(struct kvm_vcpu *vcpu)
 	free_nested(vcpu);
 }
 
+int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu)
+{
+	enum vm_entry_failure_code ignored;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
+	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
+		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
+
+		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
+		    !shadow_vmcs12->hdr.shadow_vmcs)
+			return -EINVAL;
+	}
+
+	if (nested_vmx_check_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_host_state(vcpu, vmcs12) ||
+	    nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				struct kvm_nested_state *kvm_state)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12;
-	enum vm_entry_failure_code ignored;
 	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
 		&user_kvm_nested_state->data.vmx[0];
 	int ret;
@@ -6993,25 +7014,20 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	vmx->nested.mtf_pending =
 		!!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
 
-	ret = -EINVAL;
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
 		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
 
+		ret = -EINVAL;
 		if (kvm_state->size <
 		    sizeof(*kvm_state) +
 		    sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12))
 			goto error_guest_mode;
 
+		ret = -EFAULT;
 		if (copy_from_user(shadow_vmcs12,
 				   user_vmx_nested_state->shadow_vmcs12,
-				   sizeof(*shadow_vmcs12))) {
-			ret = -EFAULT;
-			goto error_guest_mode;
-		}
-
-		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    !shadow_vmcs12->hdr.shadow_vmcs)
+				   sizeof(*shadow_vmcs12)))
 			goto error_guest_mode;
 	}
 
@@ -7022,9 +7038,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			kvm_state->hdr.vmx.preemption_timer_deadline;
 	}
 
-	if (nested_vmx_check_controls(vcpu, vmcs12) ||
-	    nested_vmx_check_host_state(vcpu, vmcs12) ||
-	    nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
+	ret = nested_vmx_check_restored_vmcs12(vcpu);
+	if (ret < 0)
 		goto error_guest_mode;
 
 	vmx->nested.dirty_vmcs12 = true;
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b844c5d59025..213a448104af 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -22,6 +22,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);
+int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 83d057cfa816..bccc91a999d9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8528,6 +8528,10 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	}
 
 	if (vmx->nested.smm.guest_mode) {
+		/* Triple fault if the state is invalid.  */
+		if (nested_vmx_check_restored_vmcs12(vcpu) < 0)
+			return 1;
+
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
 		if (ret)
 			return ret;

From be5fa8737d42c5ba16d2ea72c23681f8abbb07e8 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 12:40:52 +0100
Subject: [PATCH 1238/1303] KVM: SVM: check validity of VMCB controls when
 returning from SMM

The VMCB12 is stored in guest memory and can be mangled while in SMM; it
is then reloaded by svm_leave_smm(), but it is not checked again for
validity.

Move the cached vmcb12 control and save consistency checks out of
svm_set_nested_state() and into a helper, and reuse it in
svm_leave_smm().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/nested.c | 12 ++++++++++--
 arch/x86/kvm/svm/svm.c    |  4 ++++
 arch/x86/kvm/svm/svm.h    |  1 +
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 53ab6ce3cc26..b36c33255bed 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -418,6 +418,15 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu)
 	return __nested_vmcb_check_controls(vcpu, ctl);
 }
 
+int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu)
+{
+	if (!nested_vmcb_check_save(vcpu) ||
+	    !nested_vmcb_check_controls(vcpu))
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * If a feature is not advertised to L1, clear the corresponding vmcb12
  * intercept.
@@ -1028,8 +1037,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
 	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
 
-	if (!nested_vmcb_check_save(vcpu) ||
-	    !nested_vmcb_check_controls(vcpu)) {
+	if (nested_svm_check_cached_vmcb12(vcpu) < 0) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_info_1  = 0;
 		vmcb12->control.exit_info_2  = 0;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2772f22df7ed..4eb2c36b8ff2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4880,6 +4880,10 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	vmcb12 = map.hva;
 	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
 	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
+
+	if (nested_svm_check_cached_vmcb12(vcpu) < 0)
+		goto unmap_save;
+
 	ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
 
 	if (ret)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index ebd7b36b1ceb..6942e6b0eda6 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -797,6 +797,7 @@ static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
 
 int nested_svm_exit_handled(struct vcpu_svm *svm);
 int nested_svm_check_permissions(struct kvm_vcpu *vcpu);
+int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu);
 int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);

From c52b534f26574ddf2f67cf07992ae2c25e8932c8 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 13:43:57 +0100
Subject: [PATCH 1239/1303] selftests: kvm: extract common functionality out of
 smm_test.c

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/x86/smm.h | 17 ++++++++++++
 .../testing/selftests/kvm/lib/x86/processor.c | 26 ++++++++++++++++++
 tools/testing/selftests/kvm/x86/smm_test.c    | 27 ++-----------------
 3 files changed, 45 insertions(+), 25 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/x86/smm.h

diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h
new file mode 100644
index 000000000000..19337c34f13e
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86/smm.h
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef SELFTEST_KVM_SMM_H
+#define SELFTEST_KVM_SMM_H
+
+#include "kvm_util.h"
+
+#define SMRAM_SIZE	65536
+#define SMRAM_MEMSLOT	((1 << 16) | 1)
+#define SMRAM_PAGES	(SMRAM_SIZE / PAGE_SIZE)
+
+void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
+		 uint64_t smram_gpa,
+		 const void *smi_handler, size_t handler_size);
+
+void inject_smi(struct kvm_vcpu *vcpu);
+
+#endif /* SELFTEST_KVM_SMM_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index fab18e9be66c..23a44941e283 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -8,6 +8,7 @@
 #include "kvm_util.h"
 #include "pmu.h"
 #include "processor.h"
+#include "smm.h"
 #include "svm_util.h"
 #include "sev.h"
 #include "vmx.h"
@@ -1444,3 +1445,28 @@ bool kvm_arch_has_default_irqchip(void)
 {
 	return true;
 }
+
+void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
+		 uint64_t smram_gpa,
+		 const void *smi_handler, size_t handler_size)
+{
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa,
+				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, smram_gpa,
+				       SMRAM_MEMSLOT) == smram_gpa,
+		    "Could not allocate guest physical addresses for SMRAM");
+
+	memset(addr_gpa2hva(vm, smram_gpa), 0x0, SMRAM_SIZE);
+	memcpy(addr_gpa2hva(vm, smram_gpa) + 0x8000, smi_handler, handler_size);
+	vcpu_set_msr(vcpu, MSR_IA32_SMBASE, smram_gpa);
+}
+
+void inject_smi(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_events events;
+
+	vcpu_events_get(vcpu, &events);
+	events.smi.pending = 1;
+	events.flags |= KVM_VCPUEVENT_VALID_SMM;
+	vcpu_events_set(vcpu, &events);
+}
diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c
index 55c88d664a94..ade8412bf94a 100644
--- a/tools/testing/selftests/kvm/x86/smm_test.c
+++ b/tools/testing/selftests/kvm/x86/smm_test.c
@@ -14,13 +14,11 @@
 #include "test_util.h"
 
 #include "kvm_util.h"
+#include "smm.h"
 
 #include "vmx.h"
 #include "svm_util.h"
 
-#define SMRAM_SIZE 65536
-#define SMRAM_MEMSLOT ((1 << 16) | 1)
-#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
 #define SMRAM_GPA 0x1000000
 #define SMRAM_STAGE 0xfe
 
@@ -113,18 +111,6 @@ static void guest_code(void *arg)
 	sync_with_host(DONE);
 }
 
-void inject_smi(struct kvm_vcpu *vcpu)
-{
-	struct kvm_vcpu_events events;
-
-	vcpu_events_get(vcpu, &events);
-
-	events.smi.pending = 1;
-	events.flags |= KVM_VCPUEVENT_VALID_SMM;
-
-	vcpu_events_set(vcpu, &events);
-}
-
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t nested_gva = 0;
@@ -140,16 +126,7 @@ int main(int argc, char *argv[])
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
-				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
-	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
-		    == SMRAM_GPA, "could not allocate guest physical addresses?");
-
-	memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
-	memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
-	       sizeof(smi_handler));
-
-	vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA);
+	setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler));
 
 	if (kvm_has_cap(KVM_CAP_NESTED_STATE)) {
 		if (kvm_cpu_has(X86_FEATURE_SVM))

From 3e745694b032b405ff1ced74a8b3b95cdd00a385 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 13:44:40 +0100
Subject: [PATCH 1240/1303] selftests: kvm: add a test that VMX validates
 controls on RSM

Add a test checking that invalid eVMCS contents are validated after an
RSM instruction is emulated.

The failure mode is simply that the RSM succeeds, because KVM virtualizes
NMIs anyway while running L2; the two pin-based execution controls used
by the test are entirely handled by KVM and not by the processor.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 .../kvm/x86/evmcs_smm_controls_test.c         | 150 ++++++++++++++++++
 2 files changed, 151 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index fdec90e85467..dc68371f76a3 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cpuid_test
 TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
 TEST_GEN_PROGS_x86 += x86/feature_msrs_test
+TEST_GEN_PROGS_x86 += x86/evmcs_smm_controls_test
 TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test
 TEST_GEN_PROGS_x86 += x86/fastops_test
 TEST_GEN_PROGS_x86 += x86/fix_hypercall_test
diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c
new file mode 100644
index 000000000000..af7c90103396
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2026, Red Hat, Inc.
+ *
+ * Test that vmx_leave_smm() validates vmcs12 controls before re-entering
+ * nested guest mode on RSM.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "smm.h"
+#include "hyperv.h"
+#include "vmx.h"
+
+#define SMRAM_GPA	0x1000000
+#define SMRAM_STAGE	0xfe
+
+#define SYNC_PORT	0xe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+/*
+ * SMI handler: runs in real-address mode.
+ * Reports SMRAM_STAGE via port IO, then does RSM.
+ */
+static uint8_t smi_handler[] = {
+	0xb0, SMRAM_STAGE,    /* mov $SMRAM_STAGE, %al */
+	0xe4, SYNC_PORT,      /* in $SYNC_PORT, %al */
+	0x0f, 0xaa,           /* rsm */
+};
+
+static inline void sync_with_host(uint64_t phase)
+{
+	asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n"
+		     : "+a" (phase));
+}
+
+static void l2_guest_code(void)
+{
+	sync_with_host(1);
+
+	/* After SMI+RSM with invalid controls, we should not reach here. */
+	vmcall();
+}
+
+static void guest_code(struct vmx_pages *vmx_pages,
+		       struct hyperv_test_pages *hv_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	/* Set up Hyper-V enlightenments and eVMCS */
+	wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+	enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist);
+	evmcs_enable();
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_evmcs(hv_pages));
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_ASSERT(!vmlaunch());
+
+	/* L2 exits via vmcall if test fails */
+	sync_with_host(2);
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0;
+	struct hyperv_test_pages *hv;
+	struct hv_enlightened_vmcs *evmcs;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct kvm_regs regs;
+	int stage_reported;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler));
+
+	vcpu_set_hv_cpuid(vcpu);
+	vcpu_enable_evmcs(vcpu);
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva);
+	vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva);
+
+	vcpu_run(vcpu);
+
+	/* L2 is running and syncs with host.  */
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+	vcpu_regs_get(vcpu, &regs);
+	stage_reported = regs.rax & 0xff;
+	TEST_ASSERT(stage_reported == 1,
+		    "Expected stage 1, got %d", stage_reported);
+
+	/* Inject SMI while L2 is running.  */
+	inject_smi(vcpu);
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+	vcpu_regs_get(vcpu, &regs);
+	stage_reported = regs.rax & 0xff;
+	TEST_ASSERT(stage_reported == SMRAM_STAGE,
+		    "Expected SMM handler stage %#x, got %#x",
+		    SMRAM_STAGE, stage_reported);
+
+	/*
+	 * Guest is now paused in the SMI handler, about to execute RSM.
+	 * Hack the eVMCS page to set-up invalid pin-based execution
+	 * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING).
+	 */
+	evmcs = hv->enlightened_vmcs_hva;
+	evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS;
+	evmcs->hv_clean_fields = 0;
+
+	/*
+	 * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE,
+	 * copying the invalid pin_based_vm_exec_control into cached_vmcs12.
+	 */
+	union {
+		struct kvm_nested_state state;
+		char state_[16384];
+	} nested_state_buf;
+
+	memset(&nested_state_buf, 0, sizeof(nested_state_buf));
+	nested_state_buf.state.size = sizeof(nested_state_buf);
+	vcpu_nested_state_get(vcpu, &nested_state_buf.state);
+
+	/*
+	 * Resume the guest.  The SMI handler executes RSM, which calls
+	 * vmx_leave_smm().  nested_vmx_check_controls() should detect
+	 * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault.
+	 */
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN);
+
+	kvm_vm_free(vm);
+	return 0;
+}

From 6b1ca262a943a3307ee905faac0f4ff61ec3d656 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 10 Mar 2026 20:33:39 +0100
Subject: [PATCH 1241/1303] KVM: x86: clarify leave_smm() return value

The return value of vmx_leave_smm() is unrelated from that of
nested_vmx_enter_non_root_mode().  Check explicitly for success
(which happens to be 0) and return 1 just like everywhere
else in vmx_leave_smm().

Likewise, in svm_leave_smm() return 0/1 instead of the 0/1/-errno
returned by tenter_svm_guest_mode().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.c | 6 +++---
 arch/x86/kvm/vmx/vmx.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4eb2c36b8ff2..e6477affac9a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4884,11 +4884,11 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	if (nested_svm_check_cached_vmcb12(vcpu) < 0)
 		goto unmap_save;
 
-	ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
-
-	if (ret)
+	if (enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa,
+				 vmcb12, false) != 0)
 		goto unmap_save;
 
+	ret = 0;
 	svm->nested.nested_run_pending = 1;
 
 unmap_save:
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bccc91a999d9..8b24e682535b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8533,8 +8533,8 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 			return 1;
 
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
-		if (ret)
-			return ret;
+		if (ret != NVMX_VMENTRY_SUCCESS)
+			return 1;
 
 		vmx->nested.nested_run_pending = 1;
 		vmx->nested.smm.guest_mode = false;

From 33efc6346e8cf75219673fe1ca1916ab40643728 Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Tue, 24 Feb 2026 16:28:00 -0500
Subject: [PATCH 1242/1303] drm/amd/display: Add missing DCCG register entries
 for DCN20-DCN316

Commit 4c595e75110e ("drm/amd/display: Migrate DCCG registers access
from hwseq to dccg component.") moved register writes from hwseq to
dccg2_*() functions but did not add the registers to the DCCG register
list macros. The struct fields default to 0, so REG_WRITE() targets
MMIO offset 0, causing a GPU hang on resume (seen on DCN21/DCN30
during IGT kms_cursor_crc@cursor-suspend).

Add
- MICROSECOND_TIME_BASE_DIV
- MILLISECOND_TIME_BASE_DIV
- DCCG_GATE_DISABLE_CNTL
- DCCG_GATE_DISABLE_CNTL2
- DC_MEM_GLOBAL_PWR_REQ_CNTL
to macros in  dcn20_dccg.h, dcn301_dccg.h, dcn31_dccg.h, and dcn314_dccg.h.

Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.")
Reported-by: Rafael Passos <rafael@rcpassos.me>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e6e2b956fc814de766d3480be7018297c41d3ce0)
---
 drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h   | 6 +++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h | 8 +++++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h   | 5 ++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h | 5 ++++-
 4 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
index 3711d400773a..4c4e61bc91b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
@@ -38,7 +38,11 @@
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\
 	SR(DISPCLK_FREQ_CHANGE_CNTL),\
-	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL)
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_REG_LIST_DCN2() \
 	DCCG_COMMON_REG_LIST_DCN_BASE(),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
index 067e49cb238e..e2381ca0be0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
@@ -34,7 +34,13 @@
 	DCCG_SRII(DTO_PARAM, DPPCLK, 1),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 2),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 3),\
-	SR(REFCLK_CNTL)
+	SR(REFCLK_CNTL),\
+	SR(DISPCLK_FREQ_CHANGE_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
index bf659920d4cc..b5e3849ef12a 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
@@ -64,9 +64,12 @@
 	SR(DSCCLK1_DTO_PARAM),\
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
-	SR(HDMISTREAMCLK0_DTO_PARAM)
+	SR(HDMISTREAMCLK0_DTO_PARAM),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 
 #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
index a609635f35db..ecbdc05f7c45 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
@@ -70,11 +70,14 @@
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK3_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
 	SR(HDMISTREAMCLK0_DTO_PARAM),\
 	SR(OTG_PIXEL_RATE_DIV),\
-	SR(DTBCLK_P_CNTL)
+	SR(DTBCLK_P_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\

From becbab4a5a02156000f3aaff8bb70e8fd3e0d4cf Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Wed, 25 Feb 2026 21:48:36 -0500
Subject: [PATCH 1243/1303] drm/amd/display: Check for S0i3 to be done before
 DCCG init on DCN21

[WHY]
On DCN21, dccg2_init() is called in dcn10_init_hw() before
bios_golden_init(). During S0i3 resume, BIOS sets MICROSECOND_TIME_BASE_DIV
to 0x00120464 as a marker. dccg2_init() overwrites this to 0x00120264,
causing dcn21_s0i3_golden_init_wa() to misdetect the state and skip golden
init.
Eventually during the resume sequence, a flip timeout occurs.

[HOW]
Skip DCCG on dccg2_is_s0i3_golden_init_wa_done() on DCN21.

Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.")
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c61eda434336cf2c033aa35efdc9a08b31d2fdfa)
---
 .../amd/display/dc/dccg/dcn21/dcn21_dccg.c    | 21 ++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
index 75c69348027e..c4d4eea140f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
@@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 
+/*
+ * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to
+ * 0x00120464 as a marker that golden init has already been done.
+ * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init()
+ * to decide whether to skip golden init.
+ *
+ * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to
+ * 0x00120264, destroying the marker before it can be read.
+ *
+ * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the
+ * WA can function correctly. bios_golden_init() will handle init in that case.
+ */
+static void dccg21_init(struct dccg *dccg)
+{
+	if (dccg2_is_s0i3_golden_init_wa_done(dccg))
+		return;
+
+	dccg2_init(dccg);
+}
 
 static const struct dccg_funcs dccg21_funcs = {
 	.update_dpp_dto = dccg21_update_dpp_dto,
@@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = {
 	.set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en,
 	.otg_add_pixel = dccg2_otg_add_pixel,
 	.otg_drop_pixel = dccg2_otg_drop_pixel,
-	.dccg_init = dccg2_init,
+	.dccg_init = dccg21_init,
 	.refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */
 	.allow_clock_gating = dccg2_allow_clock_gating,
 	.enable_memory_low_power = dccg2_enable_memory_low_power,

From 2ce75a0b7e1bfddbcb9bc8aeb2e5e7fa99971acf Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Tue, 9 Dec 2025 15:13:23 -0500
Subject: [PATCH 1244/1303] drm/amdkfd: Unreserve bo if queue update failed

Error handling path should unreserve bo then return failed.

Fixes: 305cd109b761 ("drm/amdkfd: Validate user queue update")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c24afed7de9ecce341825d8ab55a43a254348b33)
---
 drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 8ea31699d38b..f5d2847e1cbb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm,
 					 p->queue_size)) {
 			pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n",
 				 p->queue_address, p->queue_size);
+			amdgpu_bo_unreserve(vm->root.bo);
 			return -EFAULT;
 		}
 

From 3646ff28780b4c52c5b5081443199e7a430110e5 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Mar 2026 11:58:22 -0500
Subject: [PATCH 1245/1303] drm/amd: Set num IP blocks to 0 if discovery fails

If discovery has failed for any reason (such as no support for a block)
then there is no need to unwind all the IP blocks in fini. In this
condition there can actually be failures during the unwind too.

Reset num_ip_blocks to zero during failure path and skip the unnecessary
cleanup path.

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fae5984296b981c8cc3acca35b701c1f332a6cd8)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 761ee5ebb4f5..d8296dfc5e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		break;
 	default:
 		r = amdgpu_discovery_set_ip_blocks(adev);
-		if (r)
+		if (r) {
+			adev->num_ip_blocks = 0;
 			return r;
+		}
 		break;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 77e2133de5cf..7f19554b9ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
-	if (adev == NULL)
+	if (adev == NULL || !adev->num_ip_blocks)
 		return;
 
 	amdgpu_unregister_gpu_instance(adev);

From dca01b0a264642929732c4db4a07e7b213304c15 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Mar 2026 19:16:52 +0100
Subject: [PATCH 1246/1303] Documentation: kvm: fix formatting of the quirks
 table

A recently added quirk does not fit in the left column of the table,
so it all has to be reformatted and realigned.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 210 ++++++++++++++++-----------------
 1 file changed, 105 insertions(+), 105 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 19365b284395..032516783e96 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8435,123 +8435,123 @@ KVM_CHECK_EXTENSION.
 
 The valid bits in cap.args[0] are:
 
-=================================== ============================================
- KVM_X86_QUIRK_LINT0_REENABLED      By default, the reset value for the LVT
-                                    LINT0 register is 0x700 (APIC_MODE_EXTINT).
-                                    When this quirk is disabled, the reset value
-                                    is 0x10000 (APIC_LVT_MASKED).
+========================================   ================================================
+KVM_X86_QUIRK_LINT0_REENABLED              By default, the reset value for the LVT
+                                           LINT0 register is 0x700 (APIC_MODE_EXTINT).
+                                           When this quirk is disabled, the reset value
+                                           is 0x10000 (APIC_LVT_MASKED).
 
- KVM_X86_QUIRK_CD_NW_CLEARED        By default, KVM clears CR0.CD and CR0.NW on
-                                    AMD CPUs to workaround buggy guest firmware
-                                    that runs in perpetuity with CR0.CD, i.e.
-                                    with caches in "no fill" mode.
+KVM_X86_QUIRK_CD_NW_CLEARED                By default, KVM clears CR0.CD and CR0.NW on
+                                           AMD CPUs to workaround buggy guest firmware
+                                           that runs in perpetuity with CR0.CD, i.e.
+                                           with caches in "no fill" mode.
 
-                                    When this quirk is disabled, KVM does not
-                                    change the value of CR0.CD and CR0.NW.
+                                           When this quirk is disabled, KVM does not
+                                           change the value of CR0.CD and CR0.NW.
 
- KVM_X86_QUIRK_LAPIC_MMIO_HOLE      By default, the MMIO LAPIC interface is
-                                    available even when configured for x2APIC
-                                    mode. When this quirk is disabled, KVM
-                                    disables the MMIO LAPIC interface if the
-                                    LAPIC is in x2APIC mode.
+KVM_X86_QUIRK_LAPIC_MMIO_HOLE              By default, the MMIO LAPIC interface is
+                                           available even when configured for x2APIC
+                                           mode. When this quirk is disabled, KVM
+                                           disables the MMIO LAPIC interface if the
+                                           LAPIC is in x2APIC mode.
 
- KVM_X86_QUIRK_OUT_7E_INC_RIP       By default, KVM pre-increments %rip before
-                                    exiting to userspace for an OUT instruction
-                                    to port 0x7e. When this quirk is disabled,
-                                    KVM does not pre-increment %rip before
-                                    exiting to userspace.
+KVM_X86_QUIRK_OUT_7E_INC_RIP               By default, KVM pre-increments %rip before
+                                           exiting to userspace for an OUT instruction
+                                           to port 0x7e. When this quirk is disabled,
+                                           KVM does not pre-increment %rip before
+                                           exiting to userspace.
 
- KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets
-                                    CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if
-                                    IA32_MISC_ENABLE[bit 18] (MWAIT) is set.
-                                    Additionally, when this quirk is disabled,
-                                    KVM clears CPUID.01H:ECX[bit 3] if
-                                    IA32_MISC_ENABLE[bit 18] is cleared.
+KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT         When this quirk is disabled, KVM sets
+                                           CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if
+                                           IA32_MISC_ENABLE[bit 18] (MWAIT) is set.
+                                           Additionally, when this quirk is disabled,
+                                           KVM clears CPUID.01H:ECX[bit 3] if
+                                           IA32_MISC_ENABLE[bit 18] is cleared.
 
- KVM_X86_QUIRK_FIX_HYPERCALL_INSN   By default, KVM rewrites guest
-                                    VMMCALL/VMCALL instructions to match the
-                                    vendor's hypercall instruction for the
-                                    system. When this quirk is disabled, KVM
-                                    will no longer rewrite invalid guest
-                                    hypercall instructions. Executing the
-                                    incorrect hypercall instruction will
-                                    generate a #UD within the guest.
+KVM_X86_QUIRK_FIX_HYPERCALL_INSN           By default, KVM rewrites guest
+                                           VMMCALL/VMCALL instructions to match the
+                                           vendor's hypercall instruction for the
+                                           system. When this quirk is disabled, KVM
+                                           will no longer rewrite invalid guest
+                                           hypercall instructions. Executing the
+                                           incorrect hypercall instruction will
+                                           generate a #UD within the guest.
 
-KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
-                                    they are intercepted) as NOPs regardless of
-                                    whether or not MONITOR/MWAIT are supported
-                                    according to guest CPUID.  When this quirk
-                                    is disabled and KVM_X86_DISABLE_EXITS_MWAIT
-                                    is not set (MONITOR/MWAIT are intercepted),
-                                    KVM will inject a #UD on MONITOR/MWAIT if
-                                    they're unsupported per guest CPUID.  Note,
-                                    KVM will modify MONITOR/MWAIT support in
-                                    guest CPUID on writes to MISC_ENABLE if
-                                    KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
-                                    disabled.
+KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS        By default, KVM emulates MONITOR/MWAIT (if
+                                           they are intercepted) as NOPs regardless of
+                                           whether or not MONITOR/MWAIT are supported
+                                           according to guest CPUID.  When this quirk
+                                           is disabled and KVM_X86_DISABLE_EXITS_MWAIT
+                                           is not set (MONITOR/MWAIT are intercepted),
+                                           KVM will inject a #UD on MONITOR/MWAIT if
+                                           they're unsupported per guest CPUID.  Note,
+                                           KVM will modify MONITOR/MWAIT support in
+                                           guest CPUID on writes to MISC_ENABLE if
+                                           KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
+                                           disabled.
 
-KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, for KVM_X86_DEFAULT_VM VMs, KVM
-                                    invalidates all SPTEs in all memslots and
-                                    address spaces when a memslot is deleted or
-                                    moved.  When this quirk is disabled (or the
-                                    VM type isn't KVM_X86_DEFAULT_VM), KVM only
-                                    ensures the backing memory of the deleted
-                                    or moved memslot isn't reachable, i.e KVM
-                                    _may_ invalidate only SPTEs related to the
-                                    memslot.
+KVM_X86_QUIRK_SLOT_ZAP_ALL                 By default, for KVM_X86_DEFAULT_VM VMs, KVM
+                                           invalidates all SPTEs in all memslots and
+                                           address spaces when a memslot is deleted or
+                                           moved.  When this quirk is disabled (or the
+                                           VM type isn't KVM_X86_DEFAULT_VM), KVM only
+                                           ensures the backing memory of the deleted
+                                           or moved memslot isn't reachable, i.e KVM
+                                           _may_ invalidate only SPTEs related to the
+                                           memslot.
 
-KVM_X86_QUIRK_STUFF_FEATURE_MSRS    By default, at vCPU creation, KVM sets the
-                                    vCPU's MSR_IA32_PERF_CAPABILITIES (0x345),
-                                    MSR_IA32_ARCH_CAPABILITIES (0x10a),
-                                    MSR_PLATFORM_INFO (0xce), and all VMX MSRs
-                                    (0x480..0x492) to the maximal capabilities
-                                    supported by KVM.  KVM also sets
-                                    MSR_IA32_UCODE_REV (0x8b) to an arbitrary
-                                    value (which is different for Intel vs.
-                                    AMD).  Lastly, when guest CPUID is set (by
-                                    userspace), KVM modifies select VMX MSR
-                                    fields to force consistency between guest
-                                    CPUID and L2's effective ISA.  When this
-                                    quirk is disabled, KVM zeroes the vCPU's MSR
-                                    values (with two exceptions, see below),
-                                    i.e. treats the feature MSRs like CPUID
-                                    leaves and gives userspace full control of
-                                    the vCPU model definition.  This quirk does
-                                    not affect VMX MSRs CR0/CR4_FIXED1 (0x487
-                                    and 0x489), as KVM does now allow them to
-                                    be set by userspace (KVM sets them based on
-                                    guest CPUID, for safety purposes).
+KVM_X86_QUIRK_STUFF_FEATURE_MSRS           By default, at vCPU creation, KVM sets the
+                                           vCPU's MSR_IA32_PERF_CAPABILITIES (0x345),
+                                           MSR_IA32_ARCH_CAPABILITIES (0x10a),
+                                           MSR_PLATFORM_INFO (0xce), and all VMX MSRs
+                                           (0x480..0x492) to the maximal capabilities
+                                           supported by KVM.  KVM also sets
+                                           MSR_IA32_UCODE_REV (0x8b) to an arbitrary
+                                           value (which is different for Intel vs.
+                                           AMD).  Lastly, when guest CPUID is set (by
+                                           userspace), KVM modifies select VMX MSR
+                                           fields to force consistency between guest
+                                           CPUID and L2's effective ISA.  When this
+                                           quirk is disabled, KVM zeroes the vCPU's MSR
+                                           values (with two exceptions, see below),
+                                           i.e. treats the feature MSRs like CPUID
+                                           leaves and gives userspace full control of
+                                           the vCPU model definition.  This quirk does
+                                           not affect VMX MSRs CR0/CR4_FIXED1 (0x487
+                                           and 0x489), as KVM does now allow them to
+                                           be set by userspace (KVM sets them based on
+                                           guest CPUID, for safety purposes).
 
-KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
-                                    guest PAT and forces the effective memory
-                                    type to WB in EPT.  The quirk is not available
-                                    on Intel platforms which are incapable of
-                                    safely honoring guest PAT (i.e., without CPU
-                                    self-snoop, KVM always ignores guest PAT and
-                                    forces effective memory type to WB).  It is
-                                    also ignored on AMD platforms or, on Intel,
-                                    when a VM has non-coherent DMA devices
-                                    assigned; KVM always honors guest PAT in
-                                    such case. The quirk is needed to avoid
-                                    slowdowns on certain Intel Xeon platforms
-                                    (e.g. ICX, SPR) where self-snoop feature is
-                                    supported but UC is slow enough to cause
-                                    issues with some older guests that use
-                                    UC instead of WC to map the video RAM.
-                                    Userspace can disable the quirk to honor
-                                    guest PAT if it knows that there is no such
-                                    guest software, for example if it does not
-                                    expose a bochs graphics device (which is
-                                    known to have had a buggy driver).
+KVM_X86_QUIRK_IGNORE_GUEST_PAT             By default, on Intel platforms, KVM ignores
+                                           guest PAT and forces the effective memory
+                                           type to WB in EPT.  The quirk is not available
+                                           on Intel platforms which are incapable of
+                                           safely honoring guest PAT (i.e., without CPU
+                                           self-snoop, KVM always ignores guest PAT and
+                                           forces effective memory type to WB).  It is
+                                           also ignored on AMD platforms or, on Intel,
+                                           when a VM has non-coherent DMA devices
+                                           assigned; KVM always honors guest PAT in
+                                           such case. The quirk is needed to avoid
+                                           slowdowns on certain Intel Xeon platforms
+                                           (e.g. ICX, SPR) where self-snoop feature is
+                                           supported but UC is slow enough to cause
+                                           issues with some older guests that use
+                                           UC instead of WC to map the video RAM.
+                                           Userspace can disable the quirk to honor
+                                           guest PAT if it knows that there is no such
+                                           guest software, for example if it does not
+                                           expose a bochs graphics device (which is
+                                           known to have had a buggy driver).
 
 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM   By default, KVM relaxes the consistency
-                                      check for GUEST_IA32_DEBUGCTL in vmcs12
-                                      to allow FREEZE_IN_SMM to be set.  When
-                                      this quirk is disabled, KVM requires this
-                                      bit to be cleared.  Note that the vmcs02
-                                      bit is still completely controlled by the
-                                      host, regardless of the quirk setting.
-=================================== ============================================
+                                           check for GUEST_IA32_DEBUGCTL in vmcs12
+                                           to allow FREEZE_IN_SMM to be set.  When
+                                           this quirk is disabled, KVM requires this
+                                           bit to be cleared.  Note that the vmcs02
+                                           bit is still completely controlled by the
+                                           host, regardless of the quirk setting.
+========================================   ================================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
 ------------------------

From f879365c5bb210ed0d0b0aae1a0202d0c0b4b9d0 Mon Sep 17 00:00:00 2001
From: CL Wang <cl634@andestech.com>
Date: Tue, 3 Mar 2026 10:47:37 +0800
Subject: [PATCH 1247/1303] spi: atcspi200: Handle invalid buswidth and fix
 compiler warning

The kernel test robot reported a compile-time error regarding the
FIELD_PREP() value being too large for the TRANS_DUAL_QUAD field:

  error: FIELD_PREP: value too large for the field
  note: in expansion of macro 'TRANS_DUAL_QUAD'
  tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1);

This occurs because TRANS_DUAL_QUAD is defined as a 2-bit field, and
GCC's static analysis cannot deduce that `ffs(op->data.buswidth) - 1`
will strictly fall within the 0~3 range. Although the SPI framework
guarantees that `op->data.buswidth` is valid at runtime (e.g., 1, 2,
4, 8), an explicit bounds check is necessary to satisfy the compiler.

To resolve the build warning, introduce a safe fallback mechanism.
If an unexpected buswidth is encountered, the driver will trigger
a WARN_ON_ONCE to leave a trace and fall back to width_code = 0
(standard 1-bit SPI mode). This approach guarantees predictable
hardware behavior.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602140738.P7ZozxzI-lkp@intel.com/
Suggested-by: Pei Xiao <xiaopei01@kylinos.cn>
Signed-off-by: CL Wang <cl634@andestech.com>
Link: https://patch.msgid.link/20260303024737.1791196-1-cl634@andestech.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-atcspi200.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c
index fef6954d27e1..2665f31a49ce 100644
--- a/drivers/spi/spi-atcspi200.c
+++ b/drivers/spi/spi-atcspi200.c
@@ -195,7 +195,15 @@ static void atcspi_set_trans_ctl(struct atcspi_dev *spi,
 	if (op->addr.buswidth > 1)
 		tc |= TRANS_ADDR_FMT;
 	if (op->data.nbytes) {
-		tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1);
+		unsigned int width_code;
+
+		width_code = ffs(op->data.buswidth) - 1;
+		if (unlikely(width_code > 3)) {
+			WARN_ON_ONCE(1);
+			width_code = 0;
+		}
+		tc |= TRANS_DUAL_QUAD(width_code);
+
 		if (op->data.dir == SPI_MEM_DATA_IN) {
 			if (op->dummy.nbytes)
 				tc |= TRANS_MODE_DMY_READ |

From 30c64fb9839949f085c8eb55b979cbd8a4c51f00 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Tue, 10 Mar 2026 12:43:27 +0800
Subject: [PATCH 1248/1303] ASoC: amd: acp-mach-common: Add missing error check
 for clock acquisition

The acp_card_rt5682_init() and acp_card_rt5682s_init() functions did not
check the return values of clk_get(). This could lead to a kernel crash
when the invalid pointers are later dereferenced by clock core
functions.

Fix this by:
1. Changing clk_get() to the device-managed devm_clk_get().
2. Adding IS_ERR() checks immediately after each clock acquisition.

Fixes: 8b7256266848 ("ASoC: amd: acp: Add support for RT5682-VS codec")
Fixes: d4c750f2c7d4 ("ASoC: amd: acp: Add generic machine driver support for ACP cards")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Link: https://patch.msgid.link/20260310044327.2582018-1-nichen@iscas.ac.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-mach-common.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index 4d99472c75ba..09f6c9a2c041 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -127,8 +127,13 @@ static int acp_card_rt5682_init(struct snd_soc_pcm_runtime *rtd)
 	if (drvdata->hs_codec_id != RT5682)
 		return -EINVAL;
 
-	drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk");
-	drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk");
+	drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+	if (IS_ERR(drvdata->wclk))
+		return PTR_ERR(drvdata->wclk);
+
+	drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+	if (IS_ERR(drvdata->bclk))
+		return PTR_ERR(drvdata->bclk);
 
 	ret = snd_soc_dapm_new_controls(dapm, rt5682_widgets,
 					ARRAY_SIZE(rt5682_widgets));
@@ -370,8 +375,13 @@ static int acp_card_rt5682s_init(struct snd_soc_pcm_runtime *rtd)
 		return -EINVAL;
 
 	if (!drvdata->soc_mclk) {
-		drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk");
-		drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk");
+		drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+		if (IS_ERR(drvdata->wclk))
+			return PTR_ERR(drvdata->wclk);
+
+		drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+		if (IS_ERR(drvdata->bclk))
+			return PTR_ERR(drvdata->bclk);
 	}
 
 	ret = snd_soc_dapm_new_controls(dapm, rt5682s_widgets,

From 96189080265e6bb5dde3a4afbaf947af493e3f82 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:21:37 -0600
Subject: [PATCH 1249/1303] io_uring: ensure ctx->rings is stable for task work
 flags manipulation

If DEFER_TASKRUN | SETUP_TASKRUN is used and task work is added while
the ring is being resized, it's possible for the OR'ing of
IORING_SQ_TASKRUN to happen in the small window of swapping into the
new rings and the old rings being freed.

Prevent this by adding a 2nd ->rings pointer, ->rings_rcu, which is
protected by RCU. The task work flags manipulation is inside RCU
already, and if the resize ring freeing is done post an RCU synchronize,
then there's no need to add locking to the fast path of task work
additions.

Note: this is only done for DEFER_TASKRUN, as that's the only setup mode
that supports ring resizing. If this ever changes, then they too need to
use the io_ctx_mark_taskrun() helper.

Link: https://lore.kernel.org/io-uring/20260309062759.482210-1-naup96721@gmail.com/
Cc: stable@vger.kernel.org
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Reported-by: Hao-Yu Yang <naup96721@gmail.com>
Suggested-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  1 +
 io_uring/io_uring.c            |  2 ++
 io_uring/register.c            | 11 +++++++++++
 io_uring/tw.c                  | 22 ++++++++++++++++++++--
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3e4a82a6f817..dd1420bfcb73 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -388,6 +388,7 @@ struct io_ring_ctx {
 	 * regularly bounce b/w CPUs.
 	 */
 	struct {
+		struct io_rings	__rcu	*rings_rcu;
 		struct llist_head	work_llist;
 		struct llist_head	retry_llist;
 		unsigned long		check_cq;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ccab8562d273..20fdc442e014 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2066,6 +2066,7 @@ static void io_rings_free(struct io_ring_ctx *ctx)
 	io_free_region(ctx->user, &ctx->sq_region);
 	io_free_region(ctx->user, &ctx->ring_region);
 	ctx->rings = NULL;
+	RCU_INIT_POINTER(ctx->rings_rcu, NULL);
 	ctx->sq_sqes = NULL;
 }
 
@@ -2703,6 +2704,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 	if (ret)
 		return ret;
 	ctx->rings = rings = io_region_get_ptr(&ctx->ring_region);
+	rcu_assign_pointer(ctx->rings_rcu, rings);
 	if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
 		ctx->sq_array = (u32 *)((char *)rings + rl->sq_array_offset);
 
diff --git a/io_uring/register.c b/io_uring/register.c
index a839b22fd392..5f3eb018fb32 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -633,7 +633,15 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 	ctx->sq_entries = p->sq_entries;
 	ctx->cq_entries = p->cq_entries;
 
+	/*
+	 * Just mark any flag we may have missed and that the application
+	 * should act on unconditionally. Worst case it'll be an extra
+	 * syscall.
+	 */
+	atomic_or(IORING_SQ_TASKRUN | IORING_SQ_NEED_WAKEUP, &n.rings->sq_flags);
 	ctx->rings = n.rings;
+	rcu_assign_pointer(ctx->rings_rcu, n.rings);
+
 	ctx->sq_sqes = n.sq_sqes;
 	swap_old(ctx, o, n, ring_region);
 	swap_old(ctx, o, n, sq_region);
@@ -642,6 +650,9 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 out:
 	spin_unlock(&ctx->completion_lock);
 	mutex_unlock(&ctx->mmap_lock);
+	/* Wait for concurrent io_ctx_mark_taskrun() */
+	if (to_free == &o)
+		synchronize_rcu_expedited();
 	io_register_free_rings(ctx, to_free);
 
 	if (ctx->sq_data)
diff --git a/io_uring/tw.c b/io_uring/tw.c
index 1ee2b8ab07c8..2f2b4ac4b126 100644
--- a/io_uring/tw.c
+++ b/io_uring/tw.c
@@ -152,6 +152,21 @@ void tctx_task_work(struct callback_head *cb)
 	WARN_ON_ONCE(ret);
 }
 
+/*
+ * Sets IORING_SQ_TASKRUN in the sq_flags shared with userspace, using the
+ * RCU protected rings pointer to be safe against concurrent ring resizing.
+ */
+static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx)
+{
+	lockdep_assert_in_rcu_read_lock();
+
+	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) {
+		struct io_rings *rings = rcu_dereference(ctx->rings_rcu);
+
+		atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags);
+	}
+}
+
 void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
@@ -206,8 +221,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	 */
 
 	if (!head) {
-		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
-			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+		io_ctx_mark_taskrun(ctx);
 		if (ctx->has_evfd)
 			io_eventfd_signal(ctx, false);
 	}
@@ -231,6 +245,10 @@ void io_req_normal_work_add(struct io_kiocb *req)
 	if (!llist_add(&req->io_task_work.node, &tctx->task_list))
 		return;
 
+	/*
+	 * Doesn't need to use ->rings_rcu, as resizing isn't supported for
+	 * !DEFER_TASKRUN.
+	 */
 	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 

From 177c69432161f6e4bab07ccacf8a1748a6898a6b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:35:49 -0600
Subject: [PATCH 1250/1303] io_uring/eventfd: use ctx->rings_rcu for flags
 checking

Similarly to what commit e78f7b70e837 did for local task work additions,
use ->rings_rcu under RCU rather than dereference ->rings directly. See
that commit for more details.

Cc: stable@vger.kernel.org
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/eventfd.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c
index 78f8ab7db104..ab789e1ebe91 100644
--- a/io_uring/eventfd.c
+++ b/io_uring/eventfd.c
@@ -76,11 +76,15 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event)
 {
 	bool skip = false;
 	struct io_ev_fd *ev_fd;
-
-	if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
-		return;
+	struct io_rings *rings;
 
 	guard(rcu)();
+
+	rings = rcu_dereference(ctx->rings_rcu);
+	if (!rings)
+		return;
+	if (READ_ONCE(rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
+		return;
 	ev_fd = rcu_dereference(ctx->io_ev_fd);
 	/*
 	 * Check again if ev_fd exists in case an io_eventfd_unregister call

From 6f02c6b196036dbb6defb4647d8707d29b7fe95b Mon Sep 17 00:00:00 2001
From: Tom Ryan <ryan36005@gmail.com>
Date: Mon, 9 Mar 2026 22:20:02 -0700
Subject: [PATCH 1251/1303] io_uring: fix physical SQE bounds check for
 SQE_MIXED 128-byte ops

When IORING_SETUP_SQE_MIXED is used without IORING_SETUP_NO_SQARRAY,
the boundary check for 128-byte SQE operations in io_init_req()
validated the logical SQ head position rather than the physical SQE
index.

The existing check:

  !(ctx->cached_sq_head & (ctx->sq_entries - 1))

ensures the logical position isn't at the end of the ring, which is
correct for NO_SQARRAY rings where physical == logical. However, when
sq_array is present, an unprivileged user can remap any logical
position to an arbitrary physical index via sq_array. Setting
sq_array[N] = sq_entries - 1 places a 128-byte operation at the last
physical SQE slot, causing the 128-byte memcpy in
io_uring_cmd_sqe_copy() to read 64 bytes past the end of the SQE
array.

Replace the cached_sq_head alignment check with a direct validation
of the physical SQE index, which correctly handles both sq_array and
NO_SQARRAY cases.

Fixes: 1cba30bf9fdd ("io_uring: add support for IORING_SETUP_SQE_MIXED")
Signed-off-by: Tom Ryan <ryan36005@gmail.com>
Link: https://patch.msgid.link/20260310052003.72871-1-ryan36005@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 20fdc442e014..20ec8fdafcae 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1745,7 +1745,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		 * well as 2 contiguous entries.
 		 */
 		if (!(ctx->flags & IORING_SETUP_SQE_MIXED) || *left < 2 ||
-		    !(ctx->cached_sq_head & (ctx->sq_entries - 1)))
+		    (unsigned)(sqe - ctx->sq_sqes) >= ctx->sq_entries - 1)
 			return io_init_fail_req(req, -EINVAL);
 		/*
 		 * A 128b operation on a mixed SQ uses two entries, so we have

From 35b16a7a2c4fc458304447128b86514ce9f70f3c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 10 Mar 2026 13:59:51 -0400
Subject: [PATCH 1252/1303] perf synthetic-events: Fix stale build ID in module
 MMAP2 records

perf_event__synthesize_modules() allocates a single union perf_event and
reuses it across every kernel module callback.

After the first module is processed, perf_record_mmap2__read_build_id()
sets PERF_RECORD_MISC_MMAP_BUILD_ID in header.misc and writes that
module's build ID into the event.

On subsequent iterations the callback overwrites start, len, pid, and
filename for the next module but never clears the stale build ID fields
or the MMAP_BUILD_ID flag.

When perf_record_mmap2__read_build_id() runs for the second module it
sees the flag, reads the stale build ID into a dso_id, and
__dso__improve_id() permanently poisons the DSO with the wrong build ID.

Every module after the first therefore receives the first module's build
ID in its MMAP2 record.

On a system with the sunrpc and nfsd modules loaded, this causes perf
script and perf report to show [unknown] for all module symbols.

The latent bug has existed since commit d9f2ecbc5e47fca7 ("perf dso:
Move build_id to dso_id") introduced the PERF_RECORD_MISC_MMAP_BUILD_ID
check in perf_record_mmap2__read_build_id().

Commit 53b00ff358dc75b1 ("perf record: Make --buildid-mmap the default")
then exposed it to all users by making the MMAP2-with-build-ID path the
default.  Both commits were merged in the same series.

Clear the MMAP_BUILD_ID flag and zero the build_id union before each
call to perf_record_mmap2__read_build_id() so that every module starts
with a clean slate.

Fixes: d9f2ecbc5e47fca7 ("perf dso: Move build_id to dso_id")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/synthetic-events.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index ef79433ebc3a..ddf1cbda1902 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -703,6 +703,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
 
 		memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1);
 
+		/* Clear stale build ID from previous module iteration */
+		event->mmap2.header.misc &= ~PERF_RECORD_MISC_MMAP_BUILD_ID;
+		memset(event->mmap2.build_id, 0, sizeof(event->mmap2.build_id));
+		event->mmap2.build_id_size = 0;
+
 		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
 	} else {
 		size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64));

From 4167b8914463132654e01e16259847d097f8a7f7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:38 +0200
Subject: [PATCH 1253/1303] i3c: mipi-i3c-hci: Use ETIMEDOUT instead of ETIME
 for timeout errors

The MIPI I3C HCI driver currently returns -ETIME for various timeout
conditions, while other I3C master drivers consistently use -ETIMEDOUT
for the same class of errors.  Align the HCI driver with the rest of the
subsystem by replacing all uses of -ETIME with -ETIMEDOUT.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-2-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 2 +-
 drivers/i3c/master/mipi-i3c-hci/cmd_v2.c | 2 +-
 drivers/i3c/master/mipi-i3c-hci/core.c   | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index fe260461e7e6..831a261f6c56 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -334,7 +334,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 		hci->io->queue_xfer(hci, xfer, 1);
 		if (!wait_for_completion_timeout(&done, HZ) &&
 		    hci->io->dequeue_xfer(hci, xfer, 1)) {
-			ret = -ETIME;
+			ret = -ETIMEDOUT;
 			break;
 		}
 		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
index 3729e6419581..054beee36da5 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
@@ -275,7 +275,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 		hci->io->queue_xfer(hci, xfer, 2);
 		if (!wait_for_completion_timeout(&done, HZ) &&
 		    hci->io->dequeue_xfer(hci, xfer, 2)) {
-			ret = -ETIME;
+			ret = -ETIMEDOUT;
 			break;
 		}
 		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 5879bba78164..dbe93df0c70e 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -261,7 +261,7 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 		goto out;
 	if (!wait_for_completion_timeout(&done, HZ) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = prefixed; i < nxfers; i++) {
@@ -340,7 +340,7 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev,
 		goto out;
 	if (!wait_for_completion_timeout(&done, HZ) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = 0; i < nxfers; i++) {
@@ -388,7 +388,7 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 		goto out;
 	if (!wait_for_completion_timeout(&done, m->i2c.timeout) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = 0; i < nxfers; i++) {

From fa9586bd77ada1e3861c7bef65f6bb9dcf8d9481 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:39 +0200
Subject: [PATCH 1254/1303] i3c: mipi-i3c-hci: Fix Hot-Join NACK

The MIPI I3C HCI host controller driver does not implement Hot-Join
handling, yet Hot-Join response control defaults to allowing devices to
Hot-Join the bus.  Configure HC_CONTROL_HOT_JOIN_CTRL to NACK all Hot-Join
attempts.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-3-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index dbe93df0c70e..4877a321edf9 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -152,7 +152,8 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m)
 	if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD)
 		amd_set_resp_buf_thld(hci);
 
-	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE);
+	/* Enable bus with Hot-Join disabled */
+	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 	dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL));
 
 	return 0;
@@ -764,7 +765,8 @@ static int i3c_hci_runtime_resume(struct device *dev)
 
 	hci->io->resume(hci);
 
-	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE);
+	/* Enable bus with Hot-Join disabled */
+	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 
 	return 0;
 }

From f3bcbfe1b8b0b836b772927f75f8cb6e759eb00a Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:40 +0200
Subject: [PATCH 1255/1303] i3c: mipi-i3c-hci: Factor out DMA mapping from
 queuing path

Prepare for fixing a race in the DMA ring enqueue path when handling
parallel transfers.  Move all DMA mapping out of hci_dma_queue_xfer()
and into a new helper that performs the mapping up front.

This refactoring allows the upcoming fix to extend the spinlock coverage
around the enqueue operation without performing DMA mapping under the
spinlock.

No functional change is intended in this patch.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-4-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 49 ++++++++++++++++++---------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index b903a2da1fd1..ba451f026386 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -439,6 +439,33 @@ static void hci_dma_unmap_xfer(struct i3c_hci *hci,
 	}
 }
 
+static struct i3c_dma *hci_dma_map_xfer(struct device *dev, struct hci_xfer *xfer)
+{
+	enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	bool need_bounce = device_iommu_mapped(dev) && xfer->rnw && (xfer->data_len & 3);
+
+	return i3c_master_dma_map_single(dev, xfer->data, xfer->data_len, need_bounce, dir);
+}
+
+static int hci_dma_map_xfer_list(struct i3c_hci *hci, struct device *dev,
+				 struct hci_xfer *xfer_list, int n)
+{
+	for (int i = 0; i < n; i++) {
+		struct hci_xfer *xfer = xfer_list + i;
+
+		if (!xfer->data)
+			continue;
+
+		xfer->dma = hci_dma_map_xfer(dev, xfer);
+		if (!xfer->dma) {
+			hci_dma_unmap_xfer(hci, xfer_list, i);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
 static int hci_dma_queue_xfer(struct i3c_hci *hci,
 			      struct hci_xfer *xfer_list, int n)
 {
@@ -446,6 +473,11 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
 	u32 op1_val, op2_val;
+	int ret;
+
+	ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n);
+	if (ret)
+		return ret;
 
 	/* For now we only use ring 0 */
 	ring = 0;
@@ -456,9 +488,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	for (i = 0; i < n; i++) {
 		struct hci_xfer *xfer = xfer_list + i;
 		u32 *ring_data = rh->xfer + rh->xfer_struct_sz * enqueue_ptr;
-		enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE :
-							  DMA_TO_DEVICE;
-		bool need_bounce;
 
 		/* store cmd descriptor */
 		*ring_data++ = xfer->cmd_desc[0];
@@ -477,18 +506,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 
 		/* 2nd and 3rd words of Data Buffer Descriptor Structure */
 		if (xfer->data) {
-			need_bounce = device_iommu_mapped(rings->sysdev) &&
-				      xfer->rnw &&
-				      xfer->data_len != ALIGN(xfer->data_len, 4);
-			xfer->dma = i3c_master_dma_map_single(rings->sysdev,
-							      xfer->data,
-							      xfer->data_len,
-							      need_bounce,
-							      dir);
-			if (!xfer->dma) {
-				hci_dma_unmap_xfer(hci, xfer_list, i);
-				return -ENOMEM;
-			}
 			*ring_data++ = lower_32_bits(xfer->dma->addr);
 			*ring_data++ = upper_32_bits(xfer->dma->addr);
 		} else {
@@ -511,7 +528,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 		op2_val = rh_reg_read(RING_OPERATION2);
 		if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) {
 			/* the ring is full */
-			hci_dma_unmap_xfer(hci, xfer_list, i + 1);
+			hci_dma_unmap_xfer(hci, xfer_list, n);
 			return -EBUSY;
 		}
 	}

From fa12bb903bc3ed1826e355d267fe134bde95e23c Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:41 +0200
Subject: [PATCH 1256/1303] i3c: mipi-i3c-hci: Consolidate spinlocks

The MIPI I3C HCI driver currently uses separate spinlocks for different
contexts (PIO vs. DMA rings).  This split is unnecessary and complicates
upcoming fixes.  The driver does not support concurrent PIO and DMA
operation, and it only supports a single DMA ring, so a single lock is
sufficient for all paths.

Introduce a unified spinlock in struct i3c_hci, switch both PIO and DMA
code to use it, and remove the per-context locks.

No functional change is intended in this patch.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-5-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c |  2 ++
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 14 ++++++--------
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  1 +
 drivers/i3c/master/mipi-i3c-hci/pio.c  | 16 +++++++---------
 4 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 4877a321edf9..faf5eae2409f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -926,6 +926,8 @@ static int i3c_hci_probe(struct platform_device *pdev)
 	if (!hci)
 		return -ENOMEM;
 
+	spin_lock_init(&hci->lock);
+
 	/*
 	 * Multi-bus instances share the same MMIO address range, but not
 	 * necessarily in separate contiguous sub-ranges. To avoid overlapping
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index ba451f026386..2442cedd5c2a 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -131,7 +131,6 @@ struct hci_rh_data {
 	unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz;
 	unsigned int done_ptr, ibi_chunk_ptr;
 	struct hci_xfer **src_xfers;
-	spinlock_t lock;
 	struct completion op_done;
 };
 
@@ -344,7 +343,6 @@ static int hci_dma_init(struct i3c_hci *hci)
 			goto err_out;
 		rh = &rings->headers[i];
 		rh->regs = hci->base_regs + offset;
-		spin_lock_init(&rh->lock);
 		init_completion(&rh->op_done);
 
 		rh->xfer_entries = XFER_RING_ENTRIES;
@@ -534,12 +532,12 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	}
 
 	/* take care to update the hardware enqueue pointer atomically */
-	spin_lock_irq(&rh->lock);
+	spin_lock_irq(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_ENQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock_irq(&rh->lock);
+	spin_unlock_irq(&hci->lock);
 
 	return 0;
 }
@@ -637,12 +635,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 	}
 
 	/* take care to update the software dequeue pointer atomically */
-	spin_lock(&rh->lock);
+	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&rh->lock);
+	spin_unlock(&hci->lock);
 }
 
 static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev,
@@ -823,12 +821,12 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh)
 
 done:
 	/* take care to update the ibi dequeue pointer atomically */
-	spin_lock(&rh->lock);
+	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_IBI_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&rh->lock);
+	spin_unlock(&hci->lock);
 
 	/* update the chunk pointer */
 	rh->ibi_chunk_ptr += ibi_chunks;
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 337b7ab1cb06..f1dd502c071f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -50,6 +50,7 @@ struct i3c_hci {
 	const struct hci_io_ops *io;
 	void *io_data;
 	const struct hci_cmd_ops *cmd;
+	spinlock_t lock;
 	atomic_t next_cmd_tid;
 	bool irq_inactive;
 	u32 caps;
diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c
index f8825ac81408..02866c2237fa 100644
--- a/drivers/i3c/master/mipi-i3c-hci/pio.c
+++ b/drivers/i3c/master/mipi-i3c-hci/pio.c
@@ -123,7 +123,6 @@ struct hci_pio_ibi_data {
 };
 
 struct hci_pio_data {
-	spinlock_t lock;
 	struct hci_xfer *curr_xfer, *xfer_queue;
 	struct hci_xfer *curr_rx, *rx_queue;
 	struct hci_xfer *curr_tx, *tx_queue;
@@ -212,7 +211,6 @@ static int hci_pio_init(struct i3c_hci *hci)
 		return -ENOMEM;
 
 	hci->io_data = pio;
-	spin_lock_init(&pio->lock);
 
 	__hci_pio_init(hci, &size_val);
 
@@ -631,7 +629,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 		xfer[i].data_left = xfer[i].data_len;
 	}
 
-	spin_lock_irq(&pio->lock);
+	spin_lock_irq(&hci->lock);
 	prev_queue_tail = pio->xfer_queue;
 	pio->xfer_queue = &xfer[n - 1];
 	if (pio->curr_xfer) {
@@ -645,7 +643,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 			pio_reg_read(INTR_STATUS),
 			pio_reg_read(INTR_SIGNAL_ENABLE));
 	}
-	spin_unlock_irq(&pio->lock);
+	spin_unlock_irq(&hci->lock);
 	return 0;
 }
 
@@ -716,14 +714,14 @@ static bool hci_pio_dequeue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int
 	struct hci_pio_data *pio = hci->io_data;
 	int ret;
 
-	spin_lock_irq(&pio->lock);
+	spin_lock_irq(&hci->lock);
 	dev_dbg(&hci->master.dev, "n=%d status=%#x/%#x", n,
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
 	dev_dbg(&hci->master.dev, "main_status = %#x/%#x",
 		readl(hci->base_regs + 0x20), readl(hci->base_regs + 0x28));
 
 	ret = hci_pio_dequeue_xfer_common(hci, pio, xfer, n);
-	spin_unlock_irq(&pio->lock);
+	spin_unlock_irq(&hci->lock);
 	return ret;
 }
 
@@ -1016,13 +1014,13 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	struct hci_pio_data *pio = hci->io_data;
 	u32 status;
 
-	spin_lock(&pio->lock);
+	spin_lock(&hci->lock);
 	status = pio_reg_read(INTR_STATUS);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		status, pio->enabled_irqs);
 	status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS;
 	if (!status) {
-		spin_unlock(&pio->lock);
+		spin_unlock(&hci->lock);
 		return false;
 	}
 
@@ -1058,7 +1056,7 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
-	spin_unlock(&pio->lock);
+	spin_unlock(&hci->lock);
 	return true;
 }
 

From 4decbbc8a8cf0a69ab011d7c2c88ed3cd0a00ddd Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:42 +0200
Subject: [PATCH 1257/1303] i3c: mipi-i3c-hci: Fix race in DMA ring enqueue for
 parallel xfers

The I3C subsystem allows multiple transfers to be queued concurrently.
However, the MIPI I3C HCI driver's DMA enqueue path, hci_dma_queue_xfer(),
lacks sufficient serialization.

In particular, the allocation of the enqueue_ptr and its subsequent update
in the RING_OPERATION1 register, must be done atomically.  Otherwise, for
example, it would be possible for 2 transfers to be allocated the same
enqueue_ptr.

Extend the use of the existing spinlock for that purpose.  Keep a count of
the number of xfers enqueued so that it is easy to determine if the ring
has enough space.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-6-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 32 +++++++++++++--------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 2442cedd5c2a..74b255ad6d0f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -129,7 +129,7 @@ struct hci_rh_data {
 	dma_addr_t xfer_dma, resp_dma, ibi_status_dma, ibi_data_dma;
 	unsigned int xfer_entries, ibi_status_entries, ibi_chunks_total;
 	unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz;
-	unsigned int done_ptr, ibi_chunk_ptr;
+	unsigned int done_ptr, ibi_chunk_ptr, xfer_space;
 	struct hci_xfer **src_xfers;
 	struct completion op_done;
 };
@@ -260,6 +260,7 @@ static void hci_dma_init_rh(struct i3c_hci *hci, struct hci_rh_data *rh, int i)
 
 	rh->done_ptr = 0;
 	rh->ibi_chunk_ptr = 0;
+	rh->xfer_space = rh->xfer_entries;
 }
 
 static void hci_dma_init_rings(struct i3c_hci *hci)
@@ -470,7 +471,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rings_data *rings = hci->io_data;
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
-	u32 op1_val, op2_val;
+	u32 op1_val;
 	int ret;
 
 	ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n);
@@ -481,6 +482,14 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	ring = 0;
 	rh = &rings->headers[ring];
 
+	spin_lock_irq(&hci->lock);
+
+	if (n > rh->xfer_space) {
+		spin_unlock_irq(&hci->lock);
+		hci_dma_unmap_xfer(hci, xfer_list, n);
+		return -EBUSY;
+	}
+
 	op1_val = rh_reg_read(RING_OPERATION1);
 	enqueue_ptr = FIELD_GET(RING_OP1_CR_ENQ_PTR, op1_val);
 	for (i = 0; i < n; i++) {
@@ -518,22 +527,10 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 		xfer->ring_entry = enqueue_ptr;
 
 		enqueue_ptr = (enqueue_ptr + 1) % rh->xfer_entries;
-
-		/*
-		 * We may update the hardware view of the enqueue pointer
-		 * only if we didn't reach its dequeue pointer.
-		 */
-		op2_val = rh_reg_read(RING_OPERATION2);
-		if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) {
-			/* the ring is full */
-			hci_dma_unmap_xfer(hci, xfer_list, n);
-			return -EBUSY;
-		}
 	}
 
-	/* take care to update the hardware enqueue pointer atomically */
-	spin_lock_irq(&hci->lock);
-	op1_val = rh_reg_read(RING_OPERATION1);
+	rh->xfer_space -= n;
+
 	op1_val &= ~RING_OP1_CR_ENQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
@@ -601,6 +598,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 {
 	u32 op1_val, op2_val, resp, *ring_resp;
 	unsigned int tid, done_ptr = rh->done_ptr;
+	unsigned int done_cnt = 0;
 	struct hci_xfer *xfer;
 
 	for (;;) {
@@ -632,10 +630,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 
 		done_ptr = (done_ptr + 1) % rh->xfer_entries;
 		rh->done_ptr = done_ptr;
+		done_cnt += 1;
 	}
 
 	/* take care to update the software dequeue pointer atomically */
 	spin_lock(&hci->lock);
+	rh->xfer_space += done_cnt;
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);

From 1dca8aee80eea76d2aae21265de5dd64f6ba0f09 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:43 +0200
Subject: [PATCH 1258/1303] i3c: mipi-i3c-hci: Fix race in DMA ring dequeue

The HCI DMA dequeue path (hci_dma_dequeue_xfer()) may be invoked for
multiple transfers that timeout around the same time.  However, the
function is not serialized and can race with itself.

When a timeout occurs, hci_dma_dequeue_xfer() stops the ring, processes
incomplete transfers, and then restarts the ring.  If another timeout
triggers a parallel call into the same function, the two instances may
interfere with each other - stopping or restarting the ring at unexpected
times.

Add a mutex so that hci_dma_dequeue_xfer() is serialized with respect to
itself.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-7-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 1 +
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 2 ++
 drivers/i3c/master/mipi-i3c-hci/hci.h  | 1 +
 3 files changed, 4 insertions(+)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index faf5eae2409f..061e84a5c412 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -927,6 +927,7 @@ static int i3c_hci_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	spin_lock_init(&hci->lock);
+	mutex_init(&hci->control_mutex);
 
 	/*
 	 * Multi-bus instances share the same MMIO address range, but not
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 74b255ad6d0f..f7d411e5e11f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -547,6 +547,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	unsigned int i;
 	bool did_unqueue = false;
 
+	guard(mutex)(&hci->control_mutex);
+
 	/* stop the ring */
 	rh_reg_write(RING_CONTROL, RING_CTRL_ABORT);
 	if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index f1dd502c071f..9c63d80f7fc4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -51,6 +51,7 @@ struct i3c_hci {
 	void *io_data;
 	const struct hci_cmd_ops *cmd;
 	spinlock_t lock;
+	struct mutex control_mutex;
 	atomic_t next_cmd_tid;
 	bool irq_inactive;
 	u32 caps;

From f0b5159637ca0b8feaaa95de0f5ea38f1ba26729 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:44 +0200
Subject: [PATCH 1259/1303] i3c: mipi-i3c-hci: Fix race between DMA ring
 dequeue and interrupt handler

The DMA ring bookkeeping in the MIPI I3C HCI driver is updated from two
contexts: the DMA ring dequeue path (hci_dma_dequeue_xfer()) and the
interrupt handler (hci_dma_xfer_done()).  Both modify the ring's
in-flight transfer state - specifically rh->src_xfers[] and
xfer->ring_entry - but without any serialization.  This allows the two
paths to race, potentially leading to inconsistent ring state.

Serialize access to the shared ring state by extending the existing
spinlock to cover the DMA dequeue path and the entire interrupt handler.
Since the core IRQ handler now holds this lock, remove the per-function
locking from the PIO and DMA sub-handlers.

Additionally, clear the completed entry in rh->src_xfers[] in
hci_dma_xfer_done() so it cannot be matched or completed again.

Finally, place the ring restart sequence under the same lock in
hci_dma_dequeue_xfer() to avoid concurrent enqueue or completion
operations while the ring state is being modified.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-8-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c |  2 ++
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 11 +++++------
 drivers/i3c/master/mipi-i3c-hci/pio.c  |  6 +-----
 3 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 061e84a5c412..adf35b7fa498 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -567,6 +567,8 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 	irqreturn_t result = IRQ_NONE;
 	u32 val;
 
+	guard(spinlock)(&hci->lock);
+
 	/*
 	 * The IRQ can be shared, so the handler may be called when the IRQ is
 	 * due to a different device. That could happen when runtime suspended,
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index f7d411e5e11f..d7840ff69e59 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -560,6 +560,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 		WARN_ON(1);
 	}
 
+	spin_lock_irq(&hci->lock);
+
 	for (i = 0; i < n; i++) {
 		struct hci_xfer *xfer = xfer_list + i;
 		int idx = xfer->ring_entry;
@@ -593,6 +595,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	/* restart the ring */
 	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
 
+	spin_unlock_irq(&hci->lock);
+
 	return did_unqueue;
 }
 
@@ -618,6 +622,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 			dev_dbg(&hci->master.dev, "orphaned ring entry");
 		} else {
 			hci_dma_unmap_xfer(hci, xfer, 1);
+			rh->src_xfers[done_ptr] = NULL;
 			xfer->ring_entry = -1;
 			xfer->response = resp;
 			if (tid != xfer->cmd_tid) {
@@ -635,14 +640,11 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 		done_cnt += 1;
 	}
 
-	/* take care to update the software dequeue pointer atomically */
-	spin_lock(&hci->lock);
 	rh->xfer_space += done_cnt;
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&hci->lock);
 }
 
 static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev,
@@ -822,13 +824,10 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh)
 	i3c_master_queue_ibi(dev, slot);
 
 done:
-	/* take care to update the ibi dequeue pointer atomically */
-	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_IBI_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&hci->lock);
 
 	/* update the chunk pointer */
 	rh->ibi_chunk_ptr += ibi_chunks;
diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c
index 02866c2237fa..8f48a81e65ab 100644
--- a/drivers/i3c/master/mipi-i3c-hci/pio.c
+++ b/drivers/i3c/master/mipi-i3c-hci/pio.c
@@ -1014,15 +1014,12 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	struct hci_pio_data *pio = hci->io_data;
 	u32 status;
 
-	spin_lock(&hci->lock);
 	status = pio_reg_read(INTR_STATUS);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		status, pio->enabled_irqs);
 	status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS;
-	if (!status) {
-		spin_unlock(&hci->lock);
+	if (!status)
 		return false;
-	}
 
 	if (status & STAT_IBI_STATUS_THLD)
 		hci_pio_process_ibi(hci, pio);
@@ -1056,7 +1053,6 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
-	spin_unlock(&hci->lock);
 	return true;
 }
 

From b795e68bf3073d67bebbb5a44d93f49efc5b8cc7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:45 +0200
Subject: [PATCH 1260/1303] i3c: mipi-i3c-hci: Correct RING_CTRL_ABORT handling
 in DMA dequeue

The logic used to abort the DMA ring contains several flaws:

 1. The driver unconditionally issues a ring abort even when the ring has
    already stopped.
 2. The completion used to wait for abort completion is never
    re-initialized, resulting in incorrect wait behavior.
 3. The abort sequence unintentionally clears RING_CTRL_ENABLE, which
    resets hardware ring pointers and disrupts the controller state.
 4. If the ring is already stopped, the abort operation should be
    considered successful without attempting further action.

Fix the abort handling by checking whether the ring is running before
issuing an abort, re-initializing the completion when needed, ensuring that
RING_CTRL_ENABLE remains asserted during abort, and treating an already
stopped ring as a successful condition.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-9-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index d7840ff69e59..a3e8e01a35c9 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -546,18 +546,25 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh = &rings->headers[xfer_list[0].ring_number];
 	unsigned int i;
 	bool did_unqueue = false;
+	u32 ring_status;
 
 	guard(mutex)(&hci->control_mutex);
 
-	/* stop the ring */
-	rh_reg_write(RING_CONTROL, RING_CTRL_ABORT);
-	if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) {
-		/*
-		 * We're deep in it if ever this condition is ever met.
-		 * Hardware might still be writing to memory, etc.
-		 */
-		dev_crit(&hci->master.dev, "unable to abort the ring\n");
-		WARN_ON(1);
+	ring_status = rh_reg_read(RING_STATUS);
+	if (ring_status & RING_STATUS_RUNNING) {
+		/* stop the ring */
+		reinit_completion(&rh->op_done);
+		rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_ABORT);
+		wait_for_completion_timeout(&rh->op_done, HZ);
+		ring_status = rh_reg_read(RING_STATUS);
+		if (ring_status & RING_STATUS_RUNNING) {
+			/*
+			 * We're deep in it if ever this condition is ever met.
+			 * Hardware might still be writing to memory, etc.
+			 */
+			dev_crit(&hci->master.dev, "unable to abort the ring\n");
+			WARN_ON(1);
+		}
 	}
 
 	spin_lock_irq(&hci->lock);

From ec3cfd835f7c4bbd23bc9ad909d2fdc772a578bb Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:46 +0200
Subject: [PATCH 1261/1303] i3c: mipi-i3c-hci: Add missing TID field to no-op
 command descriptor

The internal control command descriptor used for no-op commands includes a
Transaction ID (TID) field, but the no-op command constructed in
hci_dma_dequeue_xfer() omitted it.  As a result, the hardware receives a
no-op descriptor without the expected TID.

This bug has gone unnoticed because the TID is currently not validated in
the no-op completion path, but the descriptor format requires it to be
present.

Add the missing TID field when generating a no-op descriptor so that its
layout matches the defined command structure.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-10-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd.h | 1 +
 drivers/i3c/master/mipi-i3c-hci/dma.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd.h b/drivers/i3c/master/mipi-i3c-hci/cmd.h
index 1d6dd2c5d01a..b1bf87daa651 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd.h
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd.h
@@ -17,6 +17,7 @@
 #define CMD_0_TOC			W0_BIT_(31)
 #define CMD_0_ROC			W0_BIT_(30)
 #define CMD_0_ATTR			W0_MASK(2, 0)
+#define CMD_0_TID			W0_MASK(6, 3)
 
 /*
  * Response Descriptor Structure
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index a3e8e01a35c9..239a195df7c7 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -582,7 +582,7 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 			u32 *ring_data = rh->xfer + rh->xfer_struct_sz * idx;
 
 			/* store no-op cmd descriptor */
-			*ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7);
+			*ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7) | FIELD_PREP(CMD_0_TID, xfer->cmd_tid);
 			*ring_data++ = 0;
 			if (hci->cmd == &mipi_i3c_hci_cmd_v2) {
 				*ring_data++ = 0;

From b6d586431ae20d5157ee468d0ef62ad26798ef13 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:47 +0200
Subject: [PATCH 1262/1303] i3c: mipi-i3c-hci: Restart DMA ring correctly after
 dequeue abort

The DMA dequeue path attempts to restart the ring after aborting an
in-flight transfer, but the current sequence is incomplete. The controller
must be brought out of the aborted state and the ring control registers
must be programmed in the correct order: first clearing ABORT, then
re-enabling the ring and asserting RUN_STOP to resume operation.

Add the missing controller resume step and update the ring control writes
so that the ring is restarted using the proper sequence.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-11-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 239a195df7c7..41b83f07fdab 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -600,7 +600,9 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	}
 
 	/* restart the ring */
+	mipi_i3c_hci_resume(hci);
 	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
+	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_RUN_STOP);
 
 	spin_unlock_irq(&hci->lock);
 

From 7ac45bc68f089887ab3a70358057edb7e6b6084e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:48 +0200
Subject: [PATCH 1263/1303] i3c: mipi-i3c-hci: Consolidate common xfer
 processing logic

Several parts of the MIPI I3C HCI driver duplicate the same sequence for
queuing a transfer, waiting for completion, and handling timeouts. This
logic appears in five separate locations and will be affected by an
upcoming fix.

Refactor the repeated code into a new helper, i3c_hci_process_xfer(), and
store the timeout value in the hci_xfer structure so that callers do not
need to pass it as a separate parameter.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-12-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c |  8 ++---
 drivers/i3c/master/mipi-i3c-hci/cmd_v2.c |  8 ++---
 drivers/i3c/master/mipi-i3c-hci/core.c   | 43 ++++++++++++++----------
 drivers/i3c/master/mipi-i3c-hci/hci.h    |  2 ++
 4 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index 831a261f6c56..75d452d7f6af 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -331,12 +331,10 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			CMD_A0_ROC | CMD_A0_TOC;
 		xfer->cmd_desc[1] = 0;
 		xfer->completion = &done;
-		hci->io->queue_xfer(hci, xfer, 1);
-		if (!wait_for_completion_timeout(&done, HZ) &&
-		    hci->io->dequeue_xfer(hci, xfer, 1)) {
-			ret = -ETIMEDOUT;
+		xfer->timeout = HZ;
+		ret = i3c_hci_process_xfer(hci, xfer, 1);
+		if (ret)
 			break;
-		}
 		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
 		     RESP_STATUS(xfer->response) == RESP_ERR_NACK) &&
 		    RESP_DATA_LENGTH(xfer->response) == 1) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
index 054beee36da5..39eec26a363c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
@@ -253,6 +253,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 	xfer[0].rnw = true;
 	xfer[0].cmd_desc[1] = CMD_A1_DATA_LENGTH(8);
 	xfer[1].completion = &done;
+	xfer[1].timeout = HZ;
 
 	for (;;) {
 		ret = i3c_master_get_free_addr(&hci->master, next_addr);
@@ -272,12 +273,9 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 			CMD_A0_ASSIGN_ADDRESS(next_addr) |
 			CMD_A0_ROC |
 			CMD_A0_TOC;
-		hci->io->queue_xfer(hci, xfer, 2);
-		if (!wait_for_completion_timeout(&done, HZ) &&
-		    hci->io->dequeue_xfer(hci, xfer, 2)) {
-			ret = -ETIMEDOUT;
+		ret = i3c_hci_process_xfer(hci, xfer, 2);
+		if (ret)
 			break;
-		}
 		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index adf35b7fa498..4a80671536f0 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -213,6 +213,25 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci)
 	reg_write(DCT_SECTION, FIELD_PREP(DCT_TABLE_INDEX, 0));
 }
 
+int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
+{
+	struct completion *done = xfer[n - 1].completion;
+	unsigned long timeout = xfer[n - 1].timeout;
+	int ret;
+
+	ret = hci->io->queue_xfer(hci, xfer, n);
+	if (ret)
+		return ret;
+
+	if (!wait_for_completion_timeout(done, timeout) &&
+	    hci->io->dequeue_xfer(hci, xfer, n)) {
+		dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
 static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 				struct i3c_ccc_cmd *ccc)
 {
@@ -253,18 +272,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = HZ;
 
 	if (prefixed)
 		xfer--;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, HZ) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = prefixed; i < nxfers; i++) {
 		if (ccc->rnw)
 			ccc->dests[i - prefixed].payload.len =
@@ -335,15 +350,11 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = HZ;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, HZ) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = 0; i < nxfers; i++) {
 		if (i3c_xfers[i].rnw)
 			i3c_xfers[i].len = RESP_DATA_LENGTH(xfer[i].response);
@@ -383,15 +394,11 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = m->i2c.timeout;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, m->i2c.timeout) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = 0; i < nxfers; i++) {
 		if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) {
 			ret = -EIO;
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 9c63d80f7fc4..850016e3d4fe 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -89,6 +89,7 @@ struct hci_xfer {
 	unsigned int data_len;
 	unsigned int cmd_tid;
 	struct completion *completion;
+	unsigned long timeout;
 	union {
 		struct {
 			/* PIO specific */
@@ -156,5 +157,6 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci);
 void amd_set_od_pp_timing(struct i3c_hci *hci);
 void amd_set_resp_buf_thld(struct i3c_hci *hci);
 void i3c_hci_sync_irq_inactive(struct i3c_hci *hci);
+int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 
 #endif

From e44d2719225e618dde74c7056f8e6949f884095e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:49 +0200
Subject: [PATCH 1264/1303] i3c: mipi-i3c-hci: Fix race in DMA error handling
 in interrupt context

The DMA ring halts whenever a transfer encounters an error. The interrupt
handler previously attempted to detect this situation and restart the ring
if a transfer completed at the same time. However, this restart logic runs
entirely in interrupt context and is inherently racy: it interacts with
other paths manipulating the ring state, and fully serializing it within
the interrupt handler is not practical.

Move this error-recovery logic out of the interrupt handler and into the
transfer-processing path (i3c_hci_process_xfer()), where serialization and
state management are already controlled. Introduce a new optional I/O-ops
callback, handle_error(), invoked when a completed transfer reports an
error. For DMA operation, the implementation simply calls the existing
dequeue function, which safely aborts and restarts the ring when needed.

This removes the fragile ring-restart logic from the interrupt handler and
centralizes error handling where proper sequencing can be ensured.

Fixes: ccdb2e0e3b00d ("i3c: mipi-i3c-hci: Add Intel specific quirk to ring resuming")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-13-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 19 ++++++++++++----
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 31 +++++++-------------------
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  1 +
 3 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 4a80671536f0..b98952d12d7c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -223,10 +223,21 @@ int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 	if (ret)
 		return ret;
 
-	if (!wait_for_completion_timeout(done, timeout) &&
-	    hci->io->dequeue_xfer(hci, xfer, n)) {
-		dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
-		return -ETIMEDOUT;
+	if (!wait_for_completion_timeout(done, timeout)) {
+		if (hci->io->dequeue_xfer(hci, xfer, n)) {
+			dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
+			return -ETIMEDOUT;
+		}
+		return 0;
+	}
+
+	if (hci->io->handle_error) {
+		bool error = false;
+
+		for (int i = 0; i < n && !error; i++)
+			error = RESP_STATUS(xfer[i].response);
+		if (error)
+			return hci->io->handle_error(hci, xfer, n);
 	}
 
 	return 0;
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 41b83f07fdab..e487ef52f6b4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -609,6 +609,11 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	return did_unqueue;
 }
 
+static int hci_dma_handle_error(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n)
+{
+	return hci_dma_dequeue_xfer(hci, xfer_list, n) ? -EIO : 0;
+}
+
 static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 {
 	u32 op1_val, op2_val, resp, *ring_resp;
@@ -870,29 +875,8 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci)
 			hci_dma_xfer_done(hci, rh);
 		if (status & INTR_RING_OP)
 			complete(&rh->op_done);
-
-		if (status & INTR_TRANSFER_ABORT) {
-			u32 ring_status;
-
-			dev_notice_ratelimited(&hci->master.dev,
-				"Ring %d: Transfer Aborted\n", i);
-			mipi_i3c_hci_resume(hci);
-			ring_status = rh_reg_read(RING_STATUS);
-			if (!(ring_status & RING_STATUS_RUNNING) &&
-			    status & INTR_TRANSFER_COMPLETION &&
-			    status & INTR_TRANSFER_ERR) {
-				/*
-				 * Ring stop followed by run is an Intel
-				 * specific required quirk after resuming the
-				 * halted controller. Do it only when the ring
-				 * is not in running state after a transfer
-				 * error.
-				 */
-				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
-				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE |
-							   RING_CTRL_RUN_STOP);
-			}
-		}
+		if (status & INTR_TRANSFER_ABORT)
+			dev_dbg(&hci->master.dev, "Ring %d: Transfer Aborted\n", i);
 		if (status & INTR_IBI_RING_FULL)
 			dev_err_ratelimited(&hci->master.dev,
 				"Ring %d: IBI Ring Full Condition\n", i);
@@ -908,6 +892,7 @@ const struct hci_io_ops mipi_i3c_hci_dma = {
 	.cleanup		= hci_dma_cleanup,
 	.queue_xfer		= hci_dma_queue_xfer,
 	.dequeue_xfer		= hci_dma_dequeue_xfer,
+	.handle_error		= hci_dma_handle_error,
 	.irq_handler		= hci_dma_irq_handler,
 	.request_ibi		= hci_dma_request_ibi,
 	.free_ibi		= hci_dma_free_ibi,
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 850016e3d4fe..9ac9d0e342f4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -123,6 +123,7 @@ struct hci_io_ops {
 	bool (*irq_handler)(struct i3c_hci *hci);
 	int (*queue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	bool (*dequeue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
+	int (*handle_error)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	int (*request_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev,
 			   const struct i3c_ibi_setup *req);
 	void (*free_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev);

From c6396b835a5e599c4df656112140f065bb544a24 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:50 +0200
Subject: [PATCH 1265/1303] i3c: mipi-i3c-hci: Fix handling of shared IRQs
 during early initialization

Shared interrupts may fire unexpectedly, including during periods when the
controller is not yet fully initialized. Commit b9a15012a1452
("i3c: mipi-i3c-hci: Add optional Runtime PM support") addressed this issue
for the runtime-suspended state, but the same problem can also occur before
the bus is enabled for the first time.

Ensure the IRQ handler ignores interrupts until initialization is complete
by making consistent use of the existing irq_inactive flag.  The flag is
now set to false immediately before enabling the bus.

To guarantee correct ordering with respect to the IRQ handler, protect
all transitions of irq_inactive with the same spinlock used inside the
handler.

Fixes: b8460480f62e1 ("i3c: mipi-i3c-hci: Allow for Multi-Bus Instances")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-14-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index b98952d12d7c..d5e91af7d569 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -152,6 +152,9 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m)
 	if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD)
 		amd_set_resp_buf_thld(hci);
 
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = false;
+
 	/* Enable bus with Hot-Join disabled */
 	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 	dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL));
@@ -184,8 +187,9 @@ void i3c_hci_sync_irq_inactive(struct i3c_hci *hci)
 	int irq = platform_get_irq(pdev, 0);
 
 	reg_write(INTR_SIGNAL_ENABLE, 0x0);
-	hci->irq_inactive = true;
 	synchronize_irq(irq);
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = true;
 }
 
 static void i3c_hci_bus_cleanup(struct i3c_master_controller *m)
@@ -781,10 +785,11 @@ static int i3c_hci_runtime_resume(struct device *dev)
 
 	mipi_i3c_hci_dat_v1.restore(hci);
 
-	hci->irq_inactive = false;
-
 	hci->io->resume(hci);
 
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = false;
+
 	/* Enable bus with Hot-Join disabled */
 	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 
@@ -975,6 +980,8 @@ static int i3c_hci_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	hci->irq_inactive = true;
+
 	irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, irq, i3c_hci_irq_handler,
 			       IRQF_SHARED, NULL, hci);

From 9a258d1336f7ff3add8b92d566d3a421f03bf4d2 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:51 +0200
Subject: [PATCH 1266/1303] i3c: mipi-i3c-hci: Fallback to software reset when
 bus disable fails

Disruption of the MIPI I3C HCI controller's internal state can cause
i3c_hci_bus_disable() to fail when attempting to shut down the bus.

In the code paths where bus disable is invoked - bus clean-up and runtime
suspend - the controller does not need to remain operational afterward, so
a full controller reset is a safe recovery mechanism.

Add a fallback to issue a software reset when disabling the bus fails.
This ensures the bus is reliably halted even if the controller's state
machine is stuck or unresponsive.

The fallback is used both during bus clean-up and in the runtime suspend
path.  In the latter case, ensure interrupts are quiesced after reset.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-15-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 65 ++++++++++++++------------
 1 file changed, 35 insertions(+), 30 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index d5e91af7d569..284f3ed7af8c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -181,6 +181,34 @@ static int i3c_hci_bus_disable(struct i3c_hci *hci)
 	return ret;
 }
 
+static int i3c_hci_software_reset(struct i3c_hci *hci)
+{
+	u32 regval;
+	int ret;
+
+	/*
+	 * SOFT_RST must be clear before we write to it.
+	 * Then we must wait until it clears again.
+	 */
+	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
+				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
+	if (ret) {
+		dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__);
+		return ret;
+	}
+
+	reg_write(RESET_CONTROL, SOFT_RST);
+
+	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
+				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
+	if (ret) {
+		dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__);
+		return ret;
+	}
+
+	return 0;
+}
+
 void i3c_hci_sync_irq_inactive(struct i3c_hci *hci)
 {
 	struct platform_device *pdev = to_platform_device(hci->master.dev.parent);
@@ -196,7 +224,8 @@ static void i3c_hci_bus_cleanup(struct i3c_master_controller *m)
 {
 	struct i3c_hci *hci = to_i3c_hci(m);
 
-	i3c_hci_bus_disable(hci);
+	if (i3c_hci_bus_disable(hci))
+		i3c_hci_software_reset(hci);
 	hci->io->cleanup(hci);
 }
 
@@ -626,34 +655,6 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 	return result;
 }
 
-static int i3c_hci_software_reset(struct i3c_hci *hci)
-{
-	u32 regval;
-	int ret;
-
-	/*
-	 * SOFT_RST must be clear before we write to it.
-	 * Then we must wait until it clears again.
-	 */
-	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
-				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
-	if (ret) {
-		dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__);
-		return ret;
-	}
-
-	reg_write(RESET_CONTROL, SOFT_RST);
-
-	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
-				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
-	if (ret) {
-		dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__);
-		return ret;
-	}
-
-	return 0;
-}
-
 static inline bool is_version_1_1_or_newer(struct i3c_hci *hci)
 {
 	return hci->version_major > 1 || (hci->version_major == 1 && hci->version_minor > 0);
@@ -764,8 +765,12 @@ static int i3c_hci_runtime_suspend(struct device *dev)
 	int ret;
 
 	ret = i3c_hci_bus_disable(hci);
-	if (ret)
+	if (ret) {
+		/* Fall back to software reset to disable the bus */
+		ret = i3c_hci_software_reset(hci);
+		i3c_hci_sync_irq_inactive(hci);
 		return ret;
+	}
 
 	hci->io->suspend(hci);
 

From f26ecaa0f0abfe5db173416214098a00d3b7db79 Mon Sep 17 00:00:00 2001
From: Peter Yin <peteryin.openbmc@gmail.com>
Date: Mon, 2 Mar 2026 15:56:42 +0800
Subject: [PATCH 1267/1303] i3c: master: dw-i3c: Fix missing of_node for
 virtual I2C adapter

The DesignWare I3C master driver creates a virtual I2C adapter to
provide backward compatibility with I2C devices. However, the current
implementation does not associate this virtual adapter with any
Device Tree node.

Propagate the of_node from the I3C master platform device to the
virtual I2C adapter's device structure. This ensures that standard
I2C aliases are correctly resolved and bus numbering remains consistent.

Signed-off-by: Peter Yin <peteryin.openbmc@gmail.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260302075645.1492766-1-peteryin.openbmc@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index d87bde3f7700..d334c217c7a3 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1659,6 +1659,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master,
 		pm_runtime_get_noresume(&pdev->dev);
 
 	INIT_WORK(&master->hj_work, dw_i3c_hj_work);
+
+	device_set_of_node_from_dev(&master->base.i2c.dev, &pdev->dev);
 	ret = i3c_master_register(&master->base, &pdev->dev,
 				  &dw_mipi_i3c_ops, false);
 	if (ret)

From f311a05784634febd299f03476b80f3f18489767 Mon Sep 17 00:00:00 2001
From: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Date: Fri, 13 Feb 2026 14:00:48 +0800
Subject: [PATCH 1268/1303] i3c: dw-i3c-master: Set SIR_REJECT in DAT on device
 attach and reattach

The DesignWare I3C master controller ACKs IBIs as soon as a valid
Device Address Table (DAT) entry is present. This can create a race
between device attachment (after DAA) and the point where the client
driver enables IBIs via i3c_device_enable_ibi().

Set DEV_ADDR_TABLE_SIR_REJECT in the DAT entry during
attach_i3c_dev() and reattach_i3c_dev() so that IBIs are rejected
by default. The bit is managed thereafter by the existing
dw_i3c_master_set_sir_enabled() function, which clears it in
enable_ibi() after ENEC is issued, and restores it in disable_ibi()
after DISEC.

Fixes: 1dd728f5d4d4 ("i3c: master: Add driver for Synopsys DesignWare IP")
Signed-off-by: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/53f5b8cbdd8af789ec38b95b02873f32f9182dd6.1770962368.git.adrianhoyin.ng@altera.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index d334c217c7a3..d6bdb32397fb 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1024,7 +1024,7 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev,
 		master->free_pos &= ~BIT(pos);
 	}
 
-	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr),
+	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr) | DEV_ADDR_TABLE_SIR_REJECT,
 	       master->regs +
 	       DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index));
 
@@ -1053,7 +1053,7 @@ static int dw_i3c_master_attach_i3c_dev(struct i3c_dev_desc *dev)
 	master->free_pos &= ~BIT(pos);
 	i3c_dev_set_master_data(dev, data);
 
-	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr),
+	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr) | DEV_ADDR_TABLE_SIR_REJECT,
 	       master->regs +
 	       DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index));
 

From d4c7210d2f3ea481a6481f03040a64d9077a6172 Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Wed, 11 Mar 2026 20:17:23 -0300
Subject: [PATCH 1269/1303] smb: client: fix iface port assignment in
 parse_server_interfaces

parse_server_interfaces() initializes interface socket addresses with
CIFS_PORT. When the mount uses a non-default port this overwrites the
configured destination port.

Later, cifs_chan_update_iface() copies this sockaddr into server->dstaddr,
causing reconnect attempts to use the wrong port after server interface
updates.

Use the existing port from server->dstaddr instead.

Cc: stable@vger.kernel.org
Fixes: fe856be475f7 ("CIFS: parse and store info on iface queries")
Tested-by: Dr. Thomas Orgis <thomas.orgis@uni-hamburg.de>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 7f2d3459cbf9..612057318de2 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -628,6 +628,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 	struct smb_sockaddr_in6 *p6;
 	struct cifs_server_iface *info = NULL, *iface = NULL, *niface = NULL;
 	struct cifs_server_iface tmp_iface;
+	__be16 port;
 	ssize_t bytes_left;
 	size_t next = 0;
 	int nb_iface = 0;
@@ -662,6 +663,15 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 		goto out;
 	}
 
+	spin_lock(&ses->server->srv_lock);
+	if (ses->server->dstaddr.ss_family == AF_INET)
+		port = ((struct sockaddr_in *)&ses->server->dstaddr)->sin_port;
+	else if (ses->server->dstaddr.ss_family == AF_INET6)
+		port = ((struct sockaddr_in6 *)&ses->server->dstaddr)->sin6_port;
+	else
+		port = cpu_to_be16(CIFS_PORT);
+	spin_unlock(&ses->server->srv_lock);
+
 	while (bytes_left >= (ssize_t)sizeof(*p)) {
 		memset(&tmp_iface, 0, sizeof(tmp_iface));
 		/* default to 1Gbps when link speed is unset */
@@ -682,7 +692,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 			memcpy(&addr4->sin_addr, &p4->IPv4Address, 4);
 
 			/* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */
-			addr4->sin_port = cpu_to_be16(CIFS_PORT);
+			addr4->sin_port = port;
 
 			cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__,
 				 &addr4->sin_addr);
@@ -696,7 +706,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 			/* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */
 			addr6->sin6_flowinfo = 0;
 			addr6->sin6_scope_id = 0;
-			addr6->sin6_port = cpu_to_be16(CIFS_PORT);
+			addr6->sin6_port = port;
 
 			cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__,
 				 &addr6->sin6_addr);

From 40e75e42f49ca54b4ff41f3edb94f5ef0299140c Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 11 Mar 2026 15:00:52 -0300
Subject: [PATCH 1270/1303] smb: client: fix open handle lookup in cifs_open()

When looking up open handles to be re-used in cifs_open(), calling
cifs_get_{writable,readable}_path() is wrong as it will look up for
the first matching open handle, and if @file->f_flags doesn't match,
it will ignore the remaining open handles in
cifsInodeInfo::openFileList that might potentially match
@file->f_flags.

For writable and readable handles, fix this by calling
__cifs_get_writable_file() and __find_readable_file(), respectively,
with FIND_OPEN_FLAGS set.

With the patch, the following program ends up with two opens instead
of three sent over the wire.

```
  #define _GNU_SOURCE
  #include <unistd.h>
  #include <string.h>
  #include <fcntl.h>

  int main(int argc, char *argv[])
  {
          int fd;

          fd = open("/mnt/1/foo", O_CREAT | O_WRONLY | O_TRUNC, 0664);
          close(fd);
          fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY);
          close(fd);
          fd = open("/mnt/1/foo", O_WRONLY);
          close(fd);
          fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY);
          close(fd);
          return 0;
  }
```

```
$ mount.cifs //srv/share /mnt/1 -o ...
$ gcc test.c && ./a.out
```

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c   |   2 +-
 fs/smb/client/cifsfs.c    |   2 +-
 fs/smb/client/cifsglob.h  |  12 ++---
 fs/smb/client/cifsproto.h |  26 +++++++--
 fs/smb/client/file.c      | 111 ++++++++++++++++++++++----------------
 fs/smb/client/inode.c     |   6 +--
 fs/smb/client/smb1ops.c   |   2 +-
 fs/smb/client/smb2inode.c |  22 ++++----
 fs/smb/client/smb2ops.c   |   4 +-
 9 files changed, 112 insertions(+), 75 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index f4cb3018a358..c920039d733c 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -1489,7 +1489,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 	struct cifsFileInfo *open_file = NULL;
 
 	if (inode)
-		open_file = find_readable_file(CIFS_I(inode), true);
+		open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY);
 	if (!open_file)
 		return get_cifs_acl_by_path(cifs_sb, path, pacllen, info);
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index b6e3db993cc6..32d0305a1239 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1269,7 +1269,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s
 	struct cifsFileInfo *writeable_srcfile;
 	int rc = -EINVAL;
 
-	writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY);
+	writeable_srcfile = find_writable_file(src_cifsi, FIND_FSUID_ONLY);
 	if (writeable_srcfile) {
 		if (src_tcon->ses->server->ops->set_file_size)
 			rc = src_tcon->ses->server->ops->set_file_size(
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index bb0fe4b60240..7877d327dbb0 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1885,12 +1885,12 @@ static inline bool is_replayable_error(int error)
 }
 
 
-/* cifs_get_writable_file() flags */
-enum cifs_writable_file_flags {
-	FIND_WR_ANY			= 0U,
-	FIND_WR_FSUID_ONLY		= (1U << 0),
-	FIND_WR_WITH_DELETE		= (1U << 1),
-	FIND_WR_NO_PENDING_DELETE	= (1U << 2),
+enum cifs_find_flags {
+	FIND_ANY		= 0U,
+	FIND_FSUID_ONLY		= (1U << 0),
+	FIND_WITH_DELETE	= (1U << 1),
+	FIND_NO_PENDING_DELETE	= (1U << 2),
+	FIND_OPEN_FLAGS		= (1U << 3),
 };
 
 #define   MID_FREE 0
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 800a7e418c32..884bfa1cf0b4 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -138,12 +138,14 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata,
 				      ssize_t result);
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 					int flags);
-int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
-			   struct cifsFileInfo **ret_file);
+int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+			     unsigned int find_flags, unsigned int open_flags,
+			     struct cifsFileInfo **ret_file);
 int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, int flags,
 			   struct cifsFileInfo **ret_file);
-struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
-					bool fsuid_only);
+struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode,
+					  unsigned int find_flags,
+					  unsigned int open_flags);
 int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 			   struct cifsFileInfo **ret_file);
 int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
@@ -596,4 +598,20 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable,
 	}
 }
 
+static inline int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+					 unsigned int find_flags,
+					 struct cifsFileInfo **ret_file)
+{
+	find_flags &= ~FIND_OPEN_FLAGS;
+	return __cifs_get_writable_file(cifs_inode, find_flags, 0, ret_file);
+}
+
+static inline struct cifsFileInfo *
+find_readable_file(struct cifsInodeInfo *cinode, unsigned int find_flags)
+{
+	find_flags &= ~FIND_OPEN_FLAGS;
+	find_flags |= FIND_NO_PENDING_DELETE;
+	return __find_readable_file(cinode, find_flags, 0);
+}
+
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 13dda87f7711..27f61fe7e4e2 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -255,7 +255,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq)
 	struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq);
 	int ret;
 
-	ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile);
+	ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_ANY, &req->cfile);
 	if (ret) {
 		cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret);
 		return;
@@ -956,7 +956,7 @@ int cifs_file_flush(const unsigned int xid, struct inode *inode,
 		return tcon->ses->server->ops->flush(xid, tcon,
 						     &cfile->fid);
 	}
-	rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
+	rc = cifs_get_writable_file(CIFS_I(inode), FIND_ANY, &cfile);
 	if (!rc) {
 		tcon = tlink_tcon(cfile->tlink);
 		rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid);
@@ -981,7 +981,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 		return -ERESTARTSYS;
 	mapping_set_error(inode->i_mapping, rc);
 
-	cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+	cfile = find_writable_file(cinode, FIND_FSUID_ONLY);
 	rc = cifs_file_flush(xid, inode, cfile);
 	if (!rc) {
 		if (cfile) {
@@ -1061,32 +1061,29 @@ int cifs_open(struct inode *inode, struct file *file)
 
 	/* Get the cached handle as SMB2 close is deferred */
 	if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) {
-		rc = cifs_get_writable_path(tcon, full_path,
-					    FIND_WR_FSUID_ONLY |
-					    FIND_WR_NO_PENDING_DELETE,
-					    &cfile);
+		rc = __cifs_get_writable_file(CIFS_I(inode),
+					      FIND_FSUID_ONLY |
+					      FIND_NO_PENDING_DELETE |
+					      FIND_OPEN_FLAGS,
+					      file->f_flags, &cfile);
 	} else {
-		rc = cifs_get_readable_path(tcon, full_path, &cfile);
+		cfile = __find_readable_file(CIFS_I(inode),
+					     FIND_NO_PENDING_DELETE |
+					     FIND_OPEN_FLAGS,
+					     file->f_flags);
+		rc = cfile ? 0 : -ENOENT;
 	}
 	if (rc == 0) {
-		unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
-		unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
-
-		if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
-		    (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
-			file->private_data = cfile;
-			spin_lock(&CIFS_I(inode)->deferred_lock);
-			cifs_del_deferred_close(cfile);
-			spin_unlock(&CIFS_I(inode)->deferred_lock);
-			goto use_cache;
-		}
-		_cifsFileInfo_put(cfile, true, false);
-	} else {
-		/* hard link on the defeered close file */
-		rc = cifs_get_hardlink_path(tcon, inode, file);
-		if (rc)
-			cifs_close_deferred_file(CIFS_I(inode));
+		file->private_data = cfile;
+		spin_lock(&CIFS_I(inode)->deferred_lock);
+		cifs_del_deferred_close(cfile);
+		spin_unlock(&CIFS_I(inode)->deferred_lock);
+		goto use_cache;
 	}
+	/* hard link on the deferred close file */
+	rc = cifs_get_hardlink_path(tcon, inode, file);
+	if (rc)
+		cifs_close_deferred_file(CIFS_I(inode));
 
 	if (server->oplocks)
 		oplock = REQ_OPLOCK;
@@ -2512,10 +2509,33 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
 	netfs_write_subrequest_terminated(&wdata->subreq, result);
 }
 
-struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
-					bool fsuid_only)
+static bool open_flags_match(struct cifsInodeInfo *cinode,
+			     unsigned int oflags, unsigned int cflags)
+{
+	struct inode *inode = &cinode->netfs.inode;
+	int crw = 0, orw = 0;
+
+	oflags &= ~(O_CREAT | O_EXCL | O_TRUNC);
+	cflags &= ~(O_CREAT | O_EXCL | O_TRUNC);
+
+	if (cifs_fscache_enabled(inode)) {
+		if (OPEN_FMODE(cflags) & FMODE_WRITE)
+			crw = 1;
+		if (OPEN_FMODE(oflags) & FMODE_WRITE)
+			orw = 1;
+	}
+	if (cifs_convert_flags(oflags, orw) != cifs_convert_flags(cflags, crw))
+		return false;
+
+	return (oflags & (O_SYNC | O_DIRECT)) == (cflags & (O_SYNC | O_DIRECT));
+}
+
+struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode,
+					  unsigned int find_flags,
+					  unsigned int open_flags)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode);
+	bool fsuid_only = find_flags & FIND_FSUID_ONLY;
 	struct cifsFileInfo *open_file = NULL;
 
 	/* only filter by fsuid on multiuser mounts */
@@ -2529,6 +2549,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
 		if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
 			continue;
+		if ((find_flags & FIND_NO_PENDING_DELETE) &&
+		    open_file->status_file_deleted)
+			continue;
+		if ((find_flags & FIND_OPEN_FLAGS) &&
+		    !open_flags_match(cifs_inode, open_flags,
+				      open_file->f_flags))
+			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) {
 			if ((!open_file->invalidHandle)) {
 				/* found a good file */
@@ -2547,17 +2574,17 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 }
 
 /* Return -EBADF if no handle is found and general rc otherwise */
-int
-cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
-		       struct cifsFileInfo **ret_file)
+int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+			     unsigned int find_flags, unsigned int open_flags,
+			     struct cifsFileInfo **ret_file)
 {
 	struct cifsFileInfo *open_file, *inv_file = NULL;
 	struct cifs_sb_info *cifs_sb;
 	bool any_available = false;
 	int rc = -EBADF;
 	unsigned int refind = 0;
-	bool fsuid_only = flags & FIND_WR_FSUID_ONLY;
-	bool with_delete = flags & FIND_WR_WITH_DELETE;
+	bool fsuid_only = find_flags & FIND_FSUID_ONLY;
+	bool with_delete = find_flags & FIND_WITH_DELETE;
 	*ret_file = NULL;
 
 	/*
@@ -2591,9 +2618,13 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
 			continue;
 		if (with_delete && !(open_file->fid.access & DELETE))
 			continue;
-		if ((flags & FIND_WR_NO_PENDING_DELETE) &&
+		if ((find_flags & FIND_NO_PENDING_DELETE) &&
 		    open_file->status_file_deleted)
 			continue;
+		if ((find_flags & FIND_OPEN_FLAGS) &&
+		    !open_flags_match(cifs_inode, open_flags,
+				      open_file->f_flags))
+			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
@@ -2710,17 +2741,7 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 		cinode = CIFS_I(d_inode(cfile->dentry));
 		spin_unlock(&tcon->open_file_lock);
 		free_dentry_path(page);
-		*ret_file = find_readable_file(cinode, 0);
-		if (*ret_file) {
-			spin_lock(&cinode->open_file_lock);
-			if ((*ret_file)->status_file_deleted) {
-				spin_unlock(&cinode->open_file_lock);
-				cifsFileInfo_put(*ret_file);
-				*ret_file = NULL;
-			} else {
-				spin_unlock(&cinode->open_file_lock);
-			}
-		}
+		*ret_file = find_readable_file(cinode, FIND_ANY);
 		return *ret_file ? 0 : -ENOENT;
 	}
 
@@ -2792,7 +2813,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		}
 
 		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
-			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			smbfile = find_writable_file(CIFS_I(inode), FIND_ANY);
 			if (smbfile) {
 				rc = server->ops->flush(xid, tcon, &smbfile->fid);
 				cifsFileInfo_put(smbfile);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 3e844c55ab8a..143fa2e665ed 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -2997,7 +2997,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
 		}
 	}
 
-	cfile = find_readable_file(cifs_i, false);
+	cfile = find_readable_file(cifs_i, FIND_ANY);
 	if (cfile == NULL)
 		return -EINVAL;
 
@@ -3050,7 +3050,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
 						size, false);
 		cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc);
 	} else {
-		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY);
 		if (open_file) {
 			tcon = tlink_tcon(open_file->tlink);
 			server = tcon->ses->server;
@@ -3219,7 +3219,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 					    open_file->fid.netfid,
 					    open_file->pid);
 	} else {
-		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY);
 		if (open_file) {
 			pTcon = tlink_tcon(open_file->tlink);
 			rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args,
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 9643eca0cb70..9694117050a6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -960,7 +960,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 	struct cifs_tcon *tcon;
 
 	/* if the file is already open for write, just use that fileid */
-	open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+	open_file = find_writable_file(cinode, FIND_FSUID_ONLY);
 
 	if (open_file) {
 		fid.netfid = open_file->fid.netfid;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 5280c5c869ad..364bdcff9c9d 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1156,7 +1156,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name,
 	cifs_i = CIFS_I(inode);
 	dosattrs = cifs_i->cifsAttrs | ATTR_READONLY;
 	data.Attributes = cpu_to_le32(dosattrs);
-	cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile);
+	cifs_get_writable_path(tcon, name, FIND_ANY, &cfile);
 	oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES,
 			     FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE);
 	tmprc = smb2_compound_op(xid, tcon, cifs_sb, name,
@@ -1336,14 +1336,13 @@ int smb2_rename_path(const unsigned int xid,
 	__u32 co = file_create_options(source_dentry);
 
 	drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb);
-	cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile);
+	cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile);
 
 	int rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
 				  co, DELETE, SMB2_OP_RENAME, cfile, source_dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease");
-		cifs_get_writable_path(tcon, from_name,
-				       FIND_WR_WITH_DELETE, &cfile);
+		cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile);
 		rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
 				  co, DELETE, SMB2_OP_RENAME, cfile, NULL);
 	}
@@ -1377,7 +1376,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 
 	in_iov.iov_base = &eof;
 	in_iov.iov_len = sizeof(eof);
-	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+	cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 
 	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_DATA,
 			     FILE_OPEN, 0, ACL_NO_MODE);
@@ -1387,7 +1386,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 			      cfile, NULL, NULL, dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease");
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb,
 				      full_path, &oparms, &in_iov,
 				      &(int){SMB2_OP_SET_EOF}, 1,
@@ -1417,7 +1416,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) {
 		if (buf->Attributes == 0)
 			goto out; /* would be a no op, no sense sending this */
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 	}
 
 	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES,
@@ -1476,7 +1475,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data,
 
 	if (tcon->posix_extensions) {
 		cmds[1] = SMB2_OP_POSIX_QUERY_INFO;
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
 				      in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
 		if (!rc) {
@@ -1485,7 +1484,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data,
 		}
 	} else {
 		cmds[1] = SMB2_OP_QUERY_INFO;
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
 				      in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
 		if (!rc) {
@@ -1636,13 +1635,12 @@ int smb2_rename_pending_delete(const char *full_path,
 	iov[1].iov_base = utf16_path;
 	iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path);
 
-	cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile);
+	cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
 			      cmds, num_cmds, cfile, NULL, NULL, dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease\n");
-		cifs_get_writable_path(tcon, full_path,
-				       FIND_WR_WITH_DELETE, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
 				      cmds, num_cmds, cfile, NULL, NULL, NULL);
 	}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 612057318de2..98ac4e86bf99 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3362,7 +3362,7 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb,
 	struct cifsFileInfo *open_file = NULL;
 
 	if (inode && !(info & SACL_SECINFO))
-		open_file = find_readable_file(CIFS_I(inode), true);
+		open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY);
 	if (!open_file || (info & SACL_SECINFO))
 		return get_smb2_acl_by_path(cifs_sb, path, pacllen, info);
 
@@ -3908,7 +3908,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs
 	 * some servers (Windows2016) will not reflect recent writes in
 	 * QUERY_ALLOCATED_RANGES until SMB2_flush is called.
 	 */
-	wrcfile = find_writable_file(cifsi, FIND_WR_ANY);
+	wrcfile = find_writable_file(cifsi, FIND_ANY);
 	if (wrcfile) {
 		filemap_write_and_wait(inode->i_mapping);
 		smb2_flush_file(xid, tcon, &wrcfile->fid);

From e3beefd3af09f8e460ddaf39063d3d7664d7ab59 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 11 Mar 2026 10:48:54 +0530
Subject: [PATCH 1271/1303] cifs: make default value of retrans as zero

When retrans mount option was introduced, the default value was set
as 1. However, in the light of some bugs that this has exposed recently
we should change it to 0 and retain the old behaviour before this option
was introduced.

Cc: <stable@vger.kernel.org>
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 54090739535f..a4a7c7eee038 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1997,7 +1997,7 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->backupuid_specified = false; /* no backup intent for a user */
 	ctx->backupgid_specified = false; /* no backup intent for a group */
 
-	ctx->retrans = 1;
+	ctx->retrans = 0;
 	ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT;
 	ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT;
 	ctx->nonativesocket = 0;

From 94a4b1f959989de9c54d43c3a102fb1ee92e1414 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 7 Mar 2026 17:50:53 -0300
Subject: [PATCH 1272/1303] ipv6: move the disable_ipv6_mod knob to core code

From: Jakub Kicinski <kuba@kernel.org>

Make sure disable_ipv6_mod itself is not part of the IPv6 module,
in case core code wants to refer to it. We will remove support
for IPv6=m soon, this change helps make fixes we commit before
that less messy.

Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-1-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ipv6.h | 7 ++++++-
 net/ipv4/af_inet.c   | 6 ++++++
 net/ipv6/af_inet6.c  | 8 --------
 3 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 443053a76dcf..a7421382a916 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -333,7 +333,12 @@ struct tcp6_timewait_sock {
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
-bool ipv6_mod_enabled(void);
+extern int disable_ipv6_mod;
+
+static inline bool ipv6_mod_enabled(void)
+{
+	return disable_ipv6_mod == 0;
+}
 
 static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8036e76aa1e4..c7731e300a44 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -124,6 +124,12 @@
 
 #include <trace/events/sock.h>
 
+/* Keep the definition of IPv6 disable here for now, to avoid annoying linker
+ * issues in case IPv6=m
+ */
+int disable_ipv6_mod;
+EXPORT_SYMBOL(disable_ipv6_mod);
+
 /* The inetsw table contains everything that inet_create needs to
  * build a new socket.
  */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 23cc9b4cb2f1..4cbd45b68088 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -86,8 +86,6 @@ struct ipv6_params ipv6_defaults = {
 	.autoconf = 1,
 };
 
-static int disable_ipv6_mod;
-
 module_param_named(disable, disable_ipv6_mod, int, 0444);
 MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional");
 
@@ -97,12 +95,6 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
 module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
 MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
 
-bool ipv6_mod_enabled(void)
-{
-	return disable_ipv6_mod == 0;
-}
-EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
-
 static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
 	const int offset = sk->sk_prot->ipv6_pinfo_offset;

From 30021e969d48e5819d5ae56936c2f34c0f7ce997 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:54 -0300
Subject: [PATCH 1273/1303] net: bonding: Fix nd_tbl NULL dereference when IPv6
 is disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. If bonding ARP/NS validation is enabled, an IPv6
NS/NA packet received on a slave can reach bond_validate_na(), which
calls bond_has_this_ip6(). That path calls ipv6_chk_addr() and can
crash in __ipv6_chk_addr_and_flags().

 BUG: kernel NULL pointer dereference, address: 00000000000005d8
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:__ipv6_chk_addr_and_flags+0x69/0x170
 Call Trace:
  <IRQ>
  ipv6_chk_addr+0x1f/0x30
  bond_validate_na+0x12e/0x1d0 [bonding]
  ? __pfx_bond_handle_frame+0x10/0x10 [bonding]
  bond_rcv_validate+0x1a0/0x450 [bonding]
  bond_handle_frame+0x5e/0x290 [bonding]
  ? srso_alias_return_thunk+0x5/0xfbef5
  __netif_receive_skb_core.constprop.0+0x3e8/0xe50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? update_cfs_rq_load_avg+0x1a/0x240
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __enqueue_entity+0x5e/0x240
  __netif_receive_skb_one_core+0x39/0xa0
  process_backlog+0x9c/0x150
  __napi_poll+0x30/0x200
  ? srso_alias_return_thunk+0x5/0xfbef5
  net_rx_action+0x338/0x3b0
  handle_softirqs+0xc9/0x2a0
  do_softirq+0x42/0x60
  </IRQ>
  <TASK>
  __local_bh_enable_ip+0x62/0x70
  __dev_queue_xmit+0x2d3/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? packet_parse_headers+0x10a/0x1a0
  packet_sendmsg+0x10da/0x1700
  ? kick_pool+0x5f/0x140
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __queue_work+0x12d/0x4f0
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by checking ipv6_mod_enabled() before dispatching IPv6 packets to
bond_na_rcv(). If IPv6 is disabled, return early from bond_rcv_validate()
and avoid the path to ipv6_chk_addr().

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-2-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c1fb92602e46..707419270ebf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3428,7 +3428,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond,
 	} else if (is_arp) {
 		return bond_arp_rcv(skb, bond, slave);
 #if IS_ENABLED(CONFIG_IPV6)
-	} else if (is_ipv6) {
+	} else if (is_ipv6 && likely(ipv6_mod_enabled())) {
 		return bond_na_rcv(skb, bond, slave);
 #endif
 	} else {

From dcb4e2231469523d20cf0a2477d68245795c205d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:55 -0300
Subject: [PATCH 1274/1303] bpf: bpf_out_neigh_v4: Fix nd_tbl NULL dereference
 when IPv6 is disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called which
initializes it. If bpf_redirect_neigh() is called from tc with an explicit
nexthop of nh_family == AF_INET6, bpf_out_neigh_v4() takes the AF_INET6
branch and calls ip_neigh_gw6(), which relies on ipv6_stub->nd_tbl.

 BUG: kernel NULL pointer dereference, address: 0000000000000248
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:skb_do_redirect+0xb93/0xf00
 Call Trace:
  <TASK>
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __tcf_classify.constprop.0+0x83/0x160
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tcf_classify+0x2b/0x50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tc_run+0xb8/0x120
  ? srso_alias_return_thunk+0x5/0xfbef5
  __dev_queue_xmit+0x6fa/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? alloc_skb_with_frags+0x58/0x200
  packet_sendmsg+0x10da/0x1700
  ? srso_alias_return_thunk+0x5/0xfbef5
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by adding an early check in the AF_INET6 branch of
bpf_out_neigh_v4(). If IPv6 is disabled, unlock RCU and drop the packet.

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-3-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index a77d23fe2359..fd38b6f8b7a8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2335,6 +2335,10 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
 
 		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	} else if (nh->nh_family == AF_INET6) {
+		if (unlikely(!ipv6_mod_enabled())) {
+			rcu_read_unlock();
+			goto out_drop;
+		}
 		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
 		is_v6gw = true;
 	} else if (nh->nh_family == AF_INET) {

From d56b5d163458c45ab8fa1f00bd875af01b3ce28c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:56 -0300
Subject: [PATCH 1275/1303] bpf: bpf_out_neigh_v6: Fix nd_tbl NULL dereference
 when IPv6 is disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called which
initializes it. If bpf_redirect_neigh() is called with explicit AF_INET6
nexthop parameters, __bpf_redirect_neigh_v6() can skip the IPv6 FIB lookup
and call bpf_out_neigh_v6() directly. bpf_out_neigh_v6() then calls
ip_neigh_gw6(), which uses ipv6_stub->nd_tbl.

 BUG: kernel NULL pointer dereference, address: 0000000000000248
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:skb_do_redirect+0x44f/0xf40
 Call Trace:
  <TASK>
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __tcf_classify.constprop.0+0x83/0x160
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tcf_classify+0x2b/0x50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tc_run+0xb8/0x120
  ? srso_alias_return_thunk+0x5/0xfbef5
  __dev_queue_xmit+0x6fa/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  packet_sendmsg+0x10da/0x1700
  ? srso_alias_return_thunk+0x5/0xfbef5
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by adding an early check in bpf_out_neigh_v6(). If IPv6 is
disabled, drop the packet before neighbor lookup.

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-4-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index fd38b6f8b7a8..78b548158fb0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2228,6 +2228,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
 			return -ENOMEM;
 	}
 
+	if (unlikely(!ipv6_mod_enabled()))
+		goto out_drop;
+
 	rcu_read_lock();
 	if (!nh) {
 		dst = skb_dst(skb);

From 99c8c16a4aad0b37293cae213e15957c573cf79b Mon Sep 17 00:00:00 2001
From: "Bastien Curutchet (Schneider Electric)" <bastien.curutchet@bootlin.com>
Date: Mon, 9 Mar 2026 14:15:43 +0100
Subject: [PATCH 1276/1303] net: dsa: microchip: Fix error path in PTP IRQ
 setup

If request_threaded_irq() fails during the PTP message IRQ setup, the
newly created IRQ mapping is never disposed. Indeed, the
ksz_ptp_irq_setup()'s error path only frees the mappings that were
successfully set up.

Dispose the newly created mapping if the associated
request_threaded_irq() fails at setup.

Cc: stable@vger.kernel.org
Fixes: d0b8fec8ae505 ("net: dsa: microchip: Fix symetry in ksz_ptp_msg_irq_{setup/free}()")
Signed-off-by: Bastien Curutchet (Schneider Electric) <bastien.curutchet@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20260309-ksz-ptp-irq-fix-v1-1-757b3b985955@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_ptp.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index 4a2cc57a628f..8b98039320ad 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -1108,6 +1108,7 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
 	struct ksz_irq *ptpirq = &port->ptpirq;
 	struct ksz_ptp_irq *ptpmsg_irq;
+	int ret;
 
 	ptpmsg_irq = &port->ptpmsg_irq[n];
 	ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n);
@@ -1119,9 +1120,13 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 
 	strscpy(ptpmsg_irq->name, name[n]);
 
-	return request_threaded_irq(ptpmsg_irq->num, NULL,
-				    ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
-				    ptpmsg_irq->name, ptpmsg_irq);
+	ret = request_threaded_irq(ptpmsg_irq->num, NULL,
+				   ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
+				   ptpmsg_irq->name, ptpmsg_irq);
+	if (ret)
+		irq_dispose_mapping(ptpmsg_irq->num);
+
+	return ret;
 }
 
 int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)

From 6c5a9baa15de240e747263aba435a0951da8d8d2 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Tue, 10 Mar 2026 13:07:30 -0400
Subject: [PATCH 1277/1303] tipc: fix divide-by-zero in
 tipc_sk_filter_connect()

A user can set conn_timeout to any value via
setsockopt(TIPC_CONN_TIMEOUT), including values less than 4.  When a
SYN is rejected with TIPC_ERR_OVERLOAD and the retry path in
tipc_sk_filter_connect() executes:

    delay %= (tsk->conn_timeout / 4);

If conn_timeout is in the range [0, 3], the integer division yields 0,
and the modulo operation triggers a divide-by-zero exception, causing a
kernel oops/panic.

Fix this by clamping conn_timeout to a minimum of 4 at the point of use
in tipc_sk_filter_connect().

Oops: divide error: 0000 [#1] SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 119 Comm: poc-F144 Not tainted 7.0.0-rc2+
RIP: 0010:tipc_sk_filter_rcv (net/tipc/socket.c:2236 net/tipc/socket.c:2362)
Call Trace:
 tipc_sk_backlog_rcv (include/linux/instrumented.h:82 include/linux/atomic/atomic-instrumented.h:32 include/net/sock.h:2357 net/tipc/socket.c:2406)
 __release_sock (include/net/sock.h:1185 net/core/sock.c:3213)
 release_sock (net/core/sock.c:3797)
 tipc_connect (net/tipc/socket.c:2570)
 __sys_connect (include/linux/file.h:62 include/linux/file.h:83 net/socket.c:2098)

Fixes: 6787927475e5 ("tipc: buffer overflow handling in listener socket")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Link: https://patch.msgid.link/20260310170730.28841-1-mehulrao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4c618c2b871d..9329919fb07f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2233,6 +2233,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
 		if (skb_queue_empty(&sk->sk_write_queue))
 			break;
 		get_random_bytes(&delay, 2);
+		if (tsk->conn_timeout < 4)
+			tsk->conn_timeout = 4;
 		delay %= (tsk->conn_timeout / 4);
 		delay = msecs_to_jiffies(delay + 100);
 		sk_reset_timer(sk, &sk->sk_timer, jiffies + delay);

From e8f0dc024ce55451ebd54bad975134ba802e4fcc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Wed, 11 Mar 2026 12:12:37 +0100
Subject: [PATCH 1278/1303] net: dsa: realtek: Fix LED group port bit for
 non-zero LED group
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The rtl8366rb_led_group_port_mask() function always returns LED port
bit in LED group 0; the switch statement returns the same thing in all
non-default cases.

This means that the driver does not currently support configuring LEDs
in non-zero LED groups.

Fix this.

Fixes: 32d617005475a71e ("net: dsa: realtek: add LED drivers for rtl8366rb")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260311111237.29002-1-kabel@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8366rb-leds.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
index 99c890681ae6..509ffd3f8db5 100644
--- a/drivers/net/dsa/realtek/rtl8366rb-leds.c
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -12,11 +12,11 @@ static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
 	case 0:
 		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
 	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_1_CTRL_MASK, BIT(port));
 	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_2_X_CTRL_MASK, BIT(port));
 	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_3_CTRL_MASK, BIT(port));
 	default:
 		return 0;
 	}

From cbada1048847a348797aec63a1d8056621cbe653 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Mar 2026 22:59:16 +0100
Subject: [PATCH 1279/1303] neighbour: restore protocol != 0 check in pneigh
 update

Prior to commit dc2a27e524ac ("neighbour: Update pneigh_entry in
pneigh_create()."), a pneigh's protocol was updated only when the
value of the NDA_PROTOCOL attribute was non-0. While moving the code,
that check was removed. This is a small change of user-visible
behavior, and inconsistent with the (non-proxy) neighbour behavior.

Fixes: dc2a27e524ac ("neighbour: Update pneigh_entry in pneigh_create().")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/38c61de1bb032871a886aff9b9b52fe1cdd4cada.1772894876.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a95cfe77f7f0..c56a4e7bf790 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -820,7 +820,8 @@ int pneigh_create(struct neigh_table *tbl, struct net *net,
 update:
 	WRITE_ONCE(n->flags, flags);
 	n->permanent = permanent;
-	WRITE_ONCE(n->protocol, protocol);
+	if (protocol)
+		WRITE_ONCE(n->protocol, protocol);
 out:
 	mutex_unlock(&tbl->phash_lock);
 	return err;

From 68e76fc12df091b04ede5f6244385a35abae0a80 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Mar 2026 22:59:17 +0100
Subject: [PATCH 1280/1303] selftests: rtnetlink: add neighbour update test

Check that protocol and flags are updated correctly for
neighbour and pneigh entries.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/d28f72b5b4ff4c9ecbbbde06146a938dcc4c264a.1772894876.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 55 ++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 248c2b91fe42..5a5ff88321d5 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -28,6 +28,7 @@ ALL_TESTS="
 	kci_test_fdb_get
 	kci_test_fdb_del
 	kci_test_neigh_get
+	kci_test_neigh_update
 	kci_test_bridge_parent_id
 	kci_test_address_proto
 	kci_test_enslave_bonding
@@ -1160,6 +1161,60 @@ kci_test_neigh_get()
 	end_test "PASS: neigh get"
 }
 
+kci_test_neigh_update()
+{
+	dstip=10.0.2.4
+	dstmac=de:ad:be:ef:13:37
+	local ret=0
+
+	for proxy in "" "proxy" ; do
+		# add a neighbour entry without any flags
+		run_cmd ip neigh add $proxy $dstip dev "$devdummy" lladdr $dstmac nud permanent
+		run_cmd_grep $dstip ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .*\(managed\|use\|router\|extern\)" ip neigh show $proxy
+
+		# set the extern_learn flag, but no other
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" extern_learn
+		run_cmd_grep "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .* \(managed\|use\|router\)" ip neigh show $proxy
+
+		# flags are reset when not provided
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy"
+		run_cmd_grep $dstip ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy
+
+		# add a protocol
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol boot
+		run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy
+
+		# protocol is retained when not provided
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy"
+		run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy
+
+		# change protocol
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol static
+		run_cmd_grep "$dstip dev $devdummy .* proto static" ip neigh show $proxy
+
+		# also check an extended flag for non-proxy neighs
+		if [ "$proxy" = "" ]; then
+			run_cmd ip neigh change $proxy $dstip dev "$devdummy" managed
+			run_cmd_grep "$dstip dev $devdummy managed" ip neigh show $proxy
+
+			run_cmd ip neigh change $proxy $dstip dev "$devdummy" lladdr $dstmac
+			run_cmd_grep_fail "$dstip dev $devdummy managed" ip neigh show $proxy
+		fi
+
+		run_cmd ip neigh del $proxy $dstip dev "$devdummy"
+	done
+
+	if [ $ret -ne 0 ];then
+		end_test "FAIL: neigh update"
+		return 1
+	fi
+
+	end_test "PASS: neigh update"
+}
+
 kci_test_bridge_parent_id()
 {
 	local ret=0

From 87c2302813abc55c46485711a678e3c312b00666 Mon Sep 17 00:00:00 2001
From: Shiraz Saleem <shirazsaleem@microsoft.com>
Date: Mon, 9 Mar 2026 10:24:43 -0700
Subject: [PATCH 1281/1303] net/mana: Null service_wq on setup error to prevent
 double destroy

In mana_gd_setup() error path, set gc->service_wq to NULL after
destroy_workqueue() to match the cleanup in mana_gd_cleanup().
This prevents a use-after-free if the workqueue pointer is checked
after a failed setup.

Fixes: f975a0955276 ("net: mana: Fix double destroy_workqueue on service rescan PCI path")
Signed-off-by: Shiraz Saleem <shirazsaleem@microsoft.com>
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260309172443.688392-1-kotaranov@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 37d2f108a839..786186c9a115 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1934,6 +1934,7 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	mana_gd_remove_irqs(pdev);
 free_workqueue:
 	destroy_workqueue(gc->service_wq);
+	gc->service_wq = NULL;
 	dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err);
 	return err;
 }

From 840c9d13cb1ca96683a5307ee8e221be163a2c1e Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Tue, 10 Mar 2026 21:39:40 +0530
Subject: [PATCH 1282/1303] net: ethernet: ti: am65-cpsw-nuss: Fix rx_filter
 value for PTP support

The "rx_filter" member of "hwtstamp_config" structure is an enum field and
does not support bitwise OR combination of multiple filter values. It
causes error while linuxptp application tries to match rx filter version.
Fix this by storing the requested filter type in a new port field.

Fixes: 97248adb5a3b ("net: ti: am65-cpsw: Update hw timestamping filter for PTPv1 RX packets")
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Link: https://patch.msgid.link/20260310160940.109822-1-c-vankar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 16 +++++++++-------
 drivers/net/ethernet/ti/am65-cpsw-nuss.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 967918050433..265ce5479915 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1351,7 +1351,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	ndev_priv = netdev_priv(ndev);
 	am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark);
 	skb_put(skb, pkt_len);
-	if (port->rx_ts_enabled)
+	if (port->rx_ts_filter)
 		am65_cpts_rx_timestamp(common->cpts, skb);
 	skb_mark_for_recycle(skb);
 	skb->protocol = eth_type_trans(skb, ndev);
@@ -1811,11 +1811,14 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 
 	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		port->rx_ts_enabled = false;
+		port->rx_ts_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
@@ -1825,8 +1828,8 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		port->rx_ts_enabled = true;
-		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -1863,7 +1866,7 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 		ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN |
 			   AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN;
 
-	if (port->rx_ts_enabled)
+	if (port->rx_ts_filter)
 		ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN |
 			   AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN;
 
@@ -1888,8 +1891,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev,
 	cfg->flags = 0;
 	cfg->tx_type = port->tx_ts_enabled ?
 		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg->rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT |
-			HWTSTAMP_FILTER_PTP_V1_L4_EVENT : HWTSTAMP_FILTER_NONE;
+	cfg->rx_filter = port->rx_ts_filter;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 917c37e4e89b..7750448e4746 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -52,7 +52,7 @@ struct am65_cpsw_port {
 	bool				disabled;
 	struct am65_cpsw_slave_data	slave;
 	bool				tx_ts_enabled;
-	bool				rx_ts_enabled;
+	enum hwtstamp_rx_filters	rx_ts_filter;
 	struct am65_cpsw_qos		qos;
 	struct devlink_port		devlink_port;
 	struct bpf_prog			*xdp_prog;

From dc26ca99b835e21e76a58b1463b84adb0ca34f58 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 11:48:16 -0700
Subject: [PATCH 1283/1303] octeontx2-af: devlink: fix NIX RAS reporter
 recovery condition

The NIX RAS health reporter recovery routine checks nix_af_rvu_int to
decide whether to re-enable NIX_AF_RAS interrupts. This is the RVU
interrupt status field and is unrelated to RAS events, so the recovery
flow may incorrectly skip re-enabling NIX_AF_RAS interrupts.

Check nix_af_rvu_ras instead before writing NIX_AF_RAS_ENA_W1S.

Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20260310184824.1183651-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index fb15c794efc9..7ef3da0f6a88 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -475,7 +475,7 @@ static int rvu_hw_nix_ras_recover(struct devlink_health_reporter *reporter,
 	if (blkaddr < 0)
 		return blkaddr;
 
-	if (nix_event_ctx->nix_af_rvu_int)
+	if (nix_event_ctx->nix_af_rvu_ras)
 		rvu_write64(rvu, blkaddr, NIX_AF_RAS_ENA_W1S, ~0ULL);
 
 	return 0;

From 87f7dff3ec75b91def0024ebaaf732457f47a63b Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 11:48:17 -0700
Subject: [PATCH 1284/1303] octeontx2-af: devlink: fix NIX RAS reporter to use
 RAS interrupt status

The NIX RAS health report path uses nix_af_rvu_err when handling the
NIX_AF_RVU_RAS case, so the report prints the ERR interrupt status rather
than the RAS interrupt status.

Use nix_af_rvu_ras for the NIX_AF_RVU_RAS report.

Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20260310184824.1183651-2-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 7ef3da0f6a88..a29f1ea04c7d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -327,10 +327,10 @@ static int rvu_nix_report_show(struct devlink_fmsg *fmsg, void *ctx,
 		rvu_report_pair_end(fmsg);
 		break;
 	case NIX_AF_RVU_RAS:
-		intr_val = nix_event_context->nix_af_rvu_err;
+		intr_val = nix_event_context->nix_af_rvu_ras;
 		rvu_report_pair_start(fmsg, "NIX_AF_RAS");
 		devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ",
-					  nix_event_context->nix_af_rvu_err);
+					  nix_event_context->nix_af_rvu_ras);
 		devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:");
 		if (intr_val & BIT_ULL(34))
 			devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S");

From 0a8321dde01ffdbd9455a028194d57484def59eb Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Sun, 1 Mar 2026 00:17:59 +0530
Subject: [PATCH 1285/1303] powerpc/mem: Move CMA reservations to
 arch_mm_preinit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model"),
changed the initialization order of "pageblock_order" from...
start_kernel()
    - setup_arch()
       - initmem_init()
         - sparse_init()
           - set_pageblock_order();  // this sets the pageblock_order
       - xxx_cma_reserve();

to...
start_kernel()
    - setup_arch()
       - xxx_cma_reserve();
    - mm_core_init_early()
       - free_area_init()
          - sparse_init()
             - set_pageblock_order() // this sets the pageblock_order.

So this means, pageblock_order is not initialized before these cma
reservation function calls, hence we are seeing CMA failures like...

[    0.000000] kvm_cma_reserve: reserving 3276 MiB for global area
[    0.000000] cma: pageblock_order not yet initialized. Called during early boot?
[    0.000000] cma: Failed to reserve 3276 MiB
....
[    0.000000][    T0] cma: pageblock_order not yet initialized. Called during early boot?
[    0.000000][    T0] cma: Failed to reserve 1024 MiB

This patch moves these CMA reservations to arch_mm_preinit() which
happens in mm_core_init() (which happens after pageblock_order is
initialized), but before the memblock moves the free memory to buddy.

Fixes: 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model")
Suggested-by: Mike Rapoport <rppt@kernel.org>
Reported-and-tested-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Closes: https://lore.kernel.org/linuxppc-dev/4c338a29-d190-44f3-8874-6cfa0a031f0b@linux.ibm.com/
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Tested-by: Dan Horák <dan@danny.cz>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/6e532cf0db5be99afbe20eed699163d5e86cd71f.1772303986.git.ritesh.list@gmail.com
---
 arch/powerpc/kernel/setup-common.c | 10 ----------
 arch/powerpc/mm/mem.c              | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index cb5b73adc250..b1761909c23f 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,7 +35,6 @@
 #include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
-#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p)
 
 	initmem_init();
 
-	/*
-	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
-	 * hugetlb. These must be called after initmem_init(), so that
-	 * pageblock_order is initialised.
-	 */
-	fadump_cma_init();
-	kdump_cma_reserve();
-	kvm_cma_reserve();
-
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 
 	if (ppc_md.setup_arch)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index a985fc96b953..b7982d0243d4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -30,6 +30,10 @@
 #include <asm/setup.h>
 #include <asm/fixmap.h>
 
+#include <asm/fadump.h>
+#include <asm/kexec.h>
+#include <asm/kvm_ppc.h>
+
 #include <mm/mmu_decl.h>
 
 unsigned long long memory_limit __initdata;
@@ -268,6 +272,16 @@ void __init paging_init(void)
 
 void __init arch_mm_preinit(void)
 {
+
+	/*
+	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM
+	 * and hugetlb. These must be called after pageblock_order is
+	 * initialised.
+	 */
+	fadump_cma_init();
+	kdump_cma_reserve();
+	kvm_cma_reserve();
+
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
 	 * a 4-bit field for slices.

From e9bbfb4bfa86c6b5515b868d6982ac60505d7e39 Mon Sep 17 00:00:00 2001
From: Viktor Malik <vmalik@redhat.com>
Date: Mon, 9 Mar 2026 15:40:45 +0100
Subject: [PATCH 1286/1303] powerpc, perf: Check that current->mm is alive
 before getting user callchain

It may happen that mm is already released, which leads to kernel panic.
This adds the NULL check for current->mm, similarly to
commit 20afc60f892d ("x86, perf: Check that current->mm is alive before getting user callchain").

I was getting this panic when running a profiling BPF program
(profile.py from bcc-tools):

    [26215.051935] Kernel attempted to read user page (588) - exploit attempt? (uid: 0)
    [26215.051950] BUG: Kernel NULL pointer dereference on read at 0x00000588
    [26215.051952] Faulting instruction address: 0xc00000000020fac0
    [26215.051957] Oops: Kernel access of bad area, sig: 11 [#1]
    [...]
    [26215.052049] Call Trace:
    [26215.052050] [c000000061da6d30] [c00000000020fc10] perf_callchain_user_64+0x2d0/0x490 (unreliable)
    [26215.052054] [c000000061da6dc0] [c00000000020f92c] perf_callchain_user+0x1c/0x30
    [26215.052057] [c000000061da6de0] [c0000000005ab2a0] get_perf_callchain+0x100/0x360
    [26215.052063] [c000000061da6e70] [c000000000573bc8] bpf_get_stackid+0x88/0xf0
    [26215.052067] [c000000061da6ea0] [c008000000042258] bpf_prog_16d4ab9ab662f669_do_perf_event+0xf8/0x274
    [...]

In addition, move storing the top-level stack entry to generic
perf_callchain_user to make sure the top-evel entry is always captured,
even if current->mm is NULL.

Fixes: 20002ded4d93 ("perf_counter: powerpc: Add callchain support")
Signed-off-by: Viktor Malik <vmalik@redhat.com>
Tested-by: Qiao Zhao <qzhao@redhat.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Reviewed-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
[Maddy: fixed message to avoid checkpatch format style error]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260309144045.169427-1-vmalik@redhat.com
---
 arch/powerpc/perf/callchain.c    | 5 +++++
 arch/powerpc/perf/callchain_32.c | 1 -
 arch/powerpc/perf/callchain_64.c | 1 -
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 26aa26482c9a..992cc5c98214 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
+
+	if (!current->mm)
+		return;
+
 	if (!is_32bit_task())
 		perf_callchain_user_64(entry, regs);
 	else
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ddcc2d8aa64a..0de21c5d272c 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 115d1c105e8a..30fb61c5f0cb 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned long __user *) sp;

From 6bc9c0a905228bea5c53ec195fe54f5f0233dccc Mon Sep 17 00:00:00 2001
From: Sayali Patil <sayalip@linux.ibm.com>
Date: Wed, 4 Mar 2026 17:52:00 +0530
Subject: [PATCH 1287/1303] powerpc: fix KUAP warning in VMX usercopy path

On powerpc with PREEMPT_FULL or PREEMPT_LAZY and function tracing enabled,
KUAP warnings can be triggered from the VMX usercopy path under memory
stress workloads.

KUAP requires that no subfunctions are called once userspace access has
been enabled. The existing VMX copy implementation violates this
requirement by invoking enter_vmx_usercopy() from the assembly path after
userspace access has already been enabled. If preemption occurs
in this window, the AMR state may not be preserved correctly,
leading to unexpected userspace access state and resulting in
KUAP warnings.

Fix this by restructuring the VMX usercopy flow so that VMX selection
and VMX state management are centralized in raw_copy_tofrom_user(),
which is invoked by the raw_copy_{to,from,in}_user() wrappers.

The new flow is:

  - raw_copy_{to,from,in}_user() calls raw_copy_tofrom_user()
  - raw_copy_tofrom_user() decides whether to use the VMX path
    based on size and CPU capability
  - Call enter_vmx_usercopy() before enabling userspace access
  - Enable userspace access as per the copy direction
    and perform the VMX copy
  - Disable userspace access as per the copy direction
  - Call exit_vmx_usercopy()
  - Fall back to the base copy routine if the VMX copy faults

With this change, the VMX assembly routines no longer perform VMX state
management or call helper functions; they only implement the
copy operations.
The previous feature-section based VMX selection inside
__copy_tofrom_user_power7() is removed, and a dedicated
__copy_tofrom_user_power7_vmx() entry point is introduced.

This ensures correct KUAP ordering, avoids subfunction calls
while KUAP is unlocked, and eliminates the warnings while preserving
the VMX fast path.

Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Reported-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Closes: https://lore.kernel.org/all/20260109064917.777587-2-sshegde@linux.ibm.com/
Suggested-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Co-developed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Signed-off-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260304122201.153049-1-sayalip@linux.ibm.com
---
 arch/powerpc/include/asm/uaccess.h | 69 ++++++++++++++++++++----------
 arch/powerpc/lib/copyuser_64.S     |  1 +
 arch/powerpc/lib/copyuser_power7.S | 45 +++++++------------
 arch/powerpc/lib/vmx-helper.c      |  2 +
 4 files changed, 65 insertions(+), 52 deletions(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 570b3d91e2e4..17e63244e885 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -15,6 +15,9 @@
 #define TASK_SIZE_MAX		TASK_SIZE_USER64
 #endif
 
+/* Threshold above which VMX copy path is used */
+#define VMX_COPY_THRESHOLD 3328
+
 #include <asm-generic/access_ok.h>
 
 /*
@@ -326,40 +329,62 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
-#ifdef __powerpc64__
+unsigned long __copy_tofrom_user_base(void __user *to,
+				      const void __user *from, unsigned long size);
+
+unsigned long __copy_tofrom_user_power7_vmx(void __user *to,
+					    const void __user *from, unsigned long size);
+
+static __always_inline bool will_use_vmx(unsigned long n)
+{
+	return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) &&
+	       n > VMX_COPY_THRESHOLD;
+}
+
+static __always_inline unsigned long
+raw_copy_tofrom_user(void __user *to, const void __user *from,
+		     unsigned long n, unsigned long dir)
+{
+	unsigned long ret;
+
+	if (will_use_vmx(n) && enter_vmx_usercopy()) {
+		allow_user_access(to, dir);
+		ret = __copy_tofrom_user_power7_vmx(to, from, n);
+		prevent_user_access(dir);
+		exit_vmx_usercopy();
+
+		if (unlikely(ret)) {
+			allow_user_access(to, dir);
+			ret = __copy_tofrom_user_base(to, from, n);
+			prevent_user_access(dir);
+		}
+		return ret;
+	}
+
+	allow_user_access(to, dir);
+	ret = __copy_tofrom_user(to, from, n);
+	prevent_user_access(dir);
+	return ret;
+}
+
+#ifdef CONFIG_PPC64
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
-
 	barrier_nospec();
-	allow_user_access(to, KUAP_READ_WRITE);
-	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(KUAP_READ_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE);
 }
-#endif /* __powerpc64__ */
+#endif /* CONFIG_PPC64 */
 
-static inline unsigned long raw_copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(NULL, KUAP_READ);
-	ret = __copy_tofrom_user((__force void __user *)to, from, n);
-	prevent_user_access(KUAP_READ);
-	return ret;
+	return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(to, KUAP_WRITE);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
-	prevent_user_access(KUAP_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE);
 }
 
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 9af969d2cc0c..25a99108caff 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -562,3 +562,4 @@ exc;	std	r10,32(3)
 	li	r5,4096
 	b	.Ldst_aligned
 EXPORT_SYMBOL(__copy_tofrom_user)
+EXPORT_SYMBOL(__copy_tofrom_user_base)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 8474c682a178..17dbcfbae25f 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -5,13 +5,9 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 
-#ifndef SELFTEST_CASE
-/* 0 == don't use VMX, 1 == use VMX */
-#define SELFTEST_CASE	0
-#endif
-
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
@@ -47,10 +43,14 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	CFUNC(exit_vmx_usercopy)
+	ld      r6,STK_REG(R31)(r1)	/* original destination pointer */
+	ld      r5,STK_REG(R29)(r1)	/* original number of bytes */
+	subf    r7,r6,r3		/* #bytes copied */
+	subf    r3,r7,r5		/* #bytes not copied in r3 */
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
-	b	.Lexit
+	addi    r1,r1,STACKFRAMESIZE
+	blr
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
@@ -74,7 +74,6 @@
 
 _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
-	cmpldi	cr1,r5,3328
 
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
@@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7)
 
 	blt	.Lshort_copy
 
-#ifdef CONFIG_ALTIVEC
-test_feature = SELFTEST_CASE
-BEGIN_FTR_SECTION
-	bgt	cr1,.Lvmx_copy
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif
 
 .Lnonvmx_copy:
 	/* Get the source 8B aligned */
@@ -263,23 +256,14 @@ err1;	stb	r0,0(r3)
 15:	li	r3,0
 	blr
 
-.Lunwind_stack_nonvmx_copy:
-	addi	r1,r1,STACKFRAMESIZE
-	b	.Lnonvmx_copy
-
-.Lvmx_copy:
 #ifdef CONFIG_ALTIVEC
+_GLOBAL(__copy_tofrom_user_power7_vmx)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	CFUNC(enter_vmx_usercopy)
-	cmpwi	cr1,r3,0
-	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STK_REG(R31)(r1)
-	ld	r4,STK_REG(R30)(r1)
-	ld	r5,STK_REG(R29)(r1)
-	mtlr	r0
 
+	std     r3,STK_REG(R31)(r1)
+	std     r5,STK_REG(R29)(r1)
 	/*
 	 * We prefetch both the source and destination using enhanced touch
 	 * instructions. We use a stream ID of 0 for the load side and
@@ -300,8 +284,6 @@ err1;	stb	r0,0(r3)
 
 	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
-	beq	cr1,.Lunwind_stack_nonvmx_copy
-
 	/*
 	 * If source and destination are not relatively aligned we use a
 	 * slower permute loop.
@@ -478,7 +460,8 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -681,5 +664,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
+EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx)
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 54340912398f..554b248002b4 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,6 +27,7 @@ int enter_vmx_usercopy(void)
 
 	return 1;
 }
+EXPORT_SYMBOL(enter_vmx_usercopy);
 
 /*
  * This function must return 0 because we tail call optimise when calling
@@ -49,6 +50,7 @@ int exit_vmx_usercopy(void)
 		set_dec(1);
 	return 0;
 }
+EXPORT_SYMBOL(exit_vmx_usercopy);
 
 int enter_vmx_ops(void)
 {

From 146c9ab38b48004b40735b6c1e1c2b5adf6436f9 Mon Sep 17 00:00:00 2001
From: Sayali Patil <sayalip@linux.ibm.com>
Date: Wed, 4 Mar 2026 17:52:01 +0530
Subject: [PATCH 1288/1303] powerpc/selftests/copyloops: extend selftest to
 exercise __copy_tofrom_user_power7_vmx

The new PowerPC VMX fast path (__copy_tofrom_user_power7_vmx) is not
exercised by existing copyloops selftests. This patch updates
the selftest to exercise the VMX variant, ensuring the VMX copy path
is validated.

Changes include:
  - COPY_LOOP=test___copy_tofrom_user_power7_vmx with -D VMX_TEST is used
    in existing selftest build targets.
  - Inclusion of ../utils.c to provide get_auxv_entry() for hardware
    feature detection.
  - At runtime, the test skips execution if Altivec is not available.
  - Copy sizes above VMX_COPY_THRESHOLD are used to ensure the VMX
    path is taken.

This enables validation of the VMX fast path without affecting systems
that do not support Altivec.

Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260304122201.153049-2-sayalip@linux.ibm.com
---
 .../selftests/powerpc/copyloops/.gitignore        |  4 ++--
 .../testing/selftests/powerpc/copyloops/Makefile  | 11 ++++++++---
 tools/testing/selftests/powerpc/copyloops/stubs.S |  8 --------
 .../selftests/powerpc/copyloops/validate.c        | 15 ++++++++++++++-
 4 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index 7283e8b07b75..80d4270a71ac 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -2,8 +2,8 @@
 copyuser_64_t0
 copyuser_64_t1
 copyuser_64_t2
-copyuser_p7_t0
-copyuser_p7_t1
+copyuser_p7
+copyuser_p7_vmx
 memcpy_64_t0
 memcpy_64_t1
 memcpy_64_t2
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 42940f92d832..0c8efb0bddeb 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
-		copyuser_p7_t0 copyuser_p7_t1 \
+		copyuser_p7 copyuser_p7_vmx \
 		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
 		memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \
 		copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \
@@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%:	copyuser_64.S $(EXTRA_SOURCES)
 		-D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \
 		-o $@ $^
 
-$(OUTPUT)/copyuser_p7_t%:	copyuser_power7.S $(EXTRA_SOURCES)
+$(OUTPUT)/copyuser_p7:	copyuser_power7.S $(EXTRA_SOURCES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) \
 		-D COPY_LOOP=test___copy_tofrom_user_power7 \
-		-D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \
+		-o $@ $^
+
+$(OUTPUT)/copyuser_p7_vmx:       copyuser_power7.S $(EXTRA_SOURCES) ../utils.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test___copy_tofrom_user_power7_vmx \
+		-D VMX_TEST \
 		-o $@ $^
 
 # Strictly speaking, we only need the memcpy_64 test cases for big-endian
diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S
index ec8bcf2bf1c2..3a9cb8c9a3ee 100644
--- a/tools/testing/selftests/powerpc/copyloops/stubs.S
+++ b/tools/testing/selftests/powerpc/copyloops/stubs.S
@@ -1,13 +1,5 @@
 #include <asm/ppc_asm.h>
 
-FUNC_START(enter_vmx_usercopy)
-	li	r3,1
-	blr
-
-FUNC_START(exit_vmx_usercopy)
-	li	r3,0
-	blr
-
 FUNC_START(enter_vmx_ops)
 	li	r3,1
 	blr
diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c
index 0f6873618552..fb822534fbe9 100644
--- a/tools/testing/selftests/powerpc/copyloops/validate.c
+++ b/tools/testing/selftests/powerpc/copyloops/validate.c
@@ -12,6 +12,10 @@
 #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE)
 #define POISON 0xa5
 
+#ifdef VMX_TEST
+#define VMX_COPY_THRESHOLD 3328
+#endif
+
 unsigned long COPY_LOOP(void *to, const void *from, unsigned long size);
 
 static void do_one(char *src, char *dst, unsigned long src_off,
@@ -81,8 +85,12 @@ int test_copy_loop(void)
 	/* Fill with sequential bytes */
 	for (i = 0; i < BUFLEN; i++)
 		fill[i] = i & 0xff;
-
+#ifdef VMX_TEST
+	/* Force sizes above kernel VMX threshold (3328) */
+	for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) {
+#else
 	for (len = 1; len < MAX_LEN; len++) {
+#endif
 		for (src_off = 0; src_off < MAX_OFFSET; src_off++) {
 			for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) {
 				do_one(src, dst, src_off, dst_off, len,
@@ -96,5 +104,10 @@ int test_copy_loop(void)
 
 int main(void)
 {
+#ifdef VMX_TEST
+	/* Skip if Altivec not present */
+	SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported");
+#endif
+
 	return test_harness(test_copy_loop, str(COPY_LOOP));
 }

From fdbaa9d2b78e0da9e1aeb303bbdc3adfe6d8e749 Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Wed, 11 Mar 2026 11:50:49 +0100
Subject: [PATCH 1289/1303] rust: pin-init: replace shadowed return token by
 `unsafe`-to-create token

We use a unit struct `__InitOk` in the closure generated by the
initializer macros as the return value. We shadow it by creating a
struct with the same name again inside of the closure, preventing early
returns of `Ok` in the initializer (before all fields have been
initialized).

In the face of Type Alias Impl Trait (TAIT) and the next trait solver,
this solution no longer works [1]. The shadowed struct can be named
through type inference. In addition, there is an RFC proposing to add
the feature of path inference to Rust, which would similarly allow [2].

Thus remove the shadowed token and replace it with an `unsafe` to create
token.

The reason we initially used the shadowing solution was because an
alternative solution used a builder pattern. Gary writes [3]:

    In the early builder-pattern based InitOk, having a single InitOk
    type for token is unsound because one can launder an InitOk token
    used for one place to another initializer. I used a branded lifetime
    solution, and then you figured out that using a shadowed type would
    work better because nobody could construct it at all.

The laundering issue does not apply to the approach we ended up with
today.

With this change, the example by Tim Chirananthavat in [1] no longer
compiles and results in this error:

    error: cannot construct `pin_init::__internal::InitOk` with struct literal syntax due to private fields
      --> src/main.rs:26:17
       |
    26 |                 InferredType {}
       |                 ^^^^^^^^^^^^
       |
       = note: private field `0` that was not provided
    help: you might have meant to use the `new` associated function
       |
    26 -                 InferredType {}
    26 +                 InferredType::new()
       |

Applying the suggestion of using the `::new()` function, results in
another expected error:

    error[E0133]: call to unsafe function `pin_init::__internal::InitOk::new` is unsafe and requires unsafe block
      --> src/main.rs:26:17
       |
    26 |                 InferredType::new()
       |                 ^^^^^^^^^^^^^^^^^^^ call to unsafe function
       |
       = note: consult the function's documentation for information on how to avoid undefined behavior

Reported-by: Tim Chirananthavat <theemathas@gmail.com>
Link: https://github.com/rust-lang/rust/issues/153535 [1]
Link: https://github.com/rust-lang/rfcs/pull/3444#issuecomment-4016145373 [2]
Link: https://github.com/rust-lang/rust/issues/153535#issuecomment-4017620804 [3]
Fixes: fc6c6baa1f40 ("rust: init: add initialization macros")
Cc: stable@vger.kernel.org
Signed-off-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260311105056.1425041-1-lossin@kernel.org
[ Added period as mentioned. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 22 +++++++---------------
 rust/pin-init/src/__internal.rs    | 28 ++++++++++++++++++++++++----
 2 files changed, 31 insertions(+), 19 deletions(-)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index 738f62c8105c..2fe918f4d82a 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -148,11 +148,6 @@ fn assert_zeroable<T: ?::core::marker::Sized>(_: *mut T)
     let init_fields = init_fields(&fields, pinned, &data, &slot);
     let field_check = make_field_check(&fields, init_kind, &path);
     Ok(quote! {{
-        // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return
-        // type and shadow it later when we insert the arbitrary user code. That way there will be
-        // no possibility of returning without `unsafe`.
-        struct __InitOk;
-
         // Get the data about fields from the supplied type.
         // SAFETY: TODO
         let #data = unsafe {
@@ -162,18 +157,15 @@ fn assert_zeroable<T: ?::core::marker::Sized>(_: *mut T)
             #path::#get_data()
         };
         // Ensure that `#data` really is of type `#data` and help with type inference:
-        let init = ::pin_init::__internal::#data_trait::make_closure::<_, __InitOk, #error>(
+        let init = ::pin_init::__internal::#data_trait::make_closure::<_, #error>(
             #data,
             move |slot| {
-                {
-                    // Shadow the structure so it cannot be used to return early.
-                    struct __InitOk;
-                    #zeroable_check
-                    #this
-                    #init_fields
-                    #field_check
-                }
-                Ok(__InitOk)
+                #zeroable_check
+                #this
+                #init_fields
+                #field_check
+                // SAFETY: we are the `init!` macro that is allowed to call this.
+                Ok(unsafe { ::pin_init::__internal::InitOk::new() })
             }
         );
         let init = move |slot| -> ::core::result::Result<(), #error> {
diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs
index 90f18e9a2912..90adbdc1893b 100644
--- a/rust/pin-init/src/__internal.rs
+++ b/rust/pin-init/src/__internal.rs
@@ -46,6 +46,24 @@ unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E> {
     }
 }
 
+/// Token type to signify successful initialization.
+///
+/// Can only be constructed via the unsafe [`Self::new`] function. The initializer macros use this
+/// token type to prevent returning `Ok` from an initializer without initializing all fields.
+pub struct InitOk(());
+
+impl InitOk {
+    /// Creates a new token.
+    ///
+    /// # Safety
+    ///
+    /// This function may only be called from the `init!` macro in `../internal/src/init.rs`.
+    #[inline(always)]
+    pub unsafe fn new() -> Self {
+        Self(())
+    }
+}
+
 /// This trait is only implemented via the `#[pin_data]` proc-macro. It is used to facilitate
 /// the pin projections within the initializers.
 ///
@@ -68,9 +86,10 @@ pub unsafe trait PinData: Copy {
     type Datee: ?Sized + HasPinData;
 
     /// Type inference helper function.
-    fn make_closure<F, O, E>(self, f: F) -> F
+    #[inline(always)]
+    fn make_closure<F, E>(self, f: F) -> F
     where
-        F: FnOnce(*mut Self::Datee) -> Result<O, E>,
+        F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>,
     {
         f
     }
@@ -98,9 +117,10 @@ pub unsafe trait InitData: Copy {
     type Datee: ?Sized + HasInitData;
 
     /// Type inference helper function.
-    fn make_closure<F, O, E>(self, f: F) -> F
+    #[inline(always)]
+    fn make_closure<F, E>(self, f: F) -> F
     where
-        F: FnOnce(*mut Self::Datee) -> Result<O, E>,
+        F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>,
     {
         f
     }

From 487f9b3dc6e507a982f1b984aa6bfbd9dc4b0567 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Wed, 11 Mar 2026 21:19:34 -0700
Subject: [PATCH 1290/1303] rust: cpufreq: suppress clippy::double_parens in
 Policy doctest

The kernel fmt! proc macro wraps each format argument as &(arg). Passing a
tuple such as (a, b) produces &((a, b)) after expansion. Clippy flags that
as double_parens, but it is a false positive fixed in Clippy 1.92 [1] [2].

Suppress the warning on the affected doctest function with a reason
attribute so it can be removed once the minimum toolchain moves past 1.92.

[ We may end up deciding to support per-version Clippy lints, in which
  case we will need [3].

  In the future, if [4] gets fixed, we may be able to use
  `Delimiter::None` as Gary suggested in [5].

  Link: https://lore.kernel.org/rust-for-linux/20260307170929.153892-1-ojeda@kernel.org/ [3]
  Link: https://github.com/rust-lang/rust/issues/67062 [4]
  Link: https://lore.kernel.org/rust-for-linux/DGUA5GY2DGYN.3PG0FKLG7GFN1@garyguo.net/ [5]

    - Miguel ]

Link: https://github.com/rust-lang/rust-clippy/issues/15852 [1]
Link: https://github.com/rust-lang/rust-clippy/pull/15939 [2]
Suggested-by: Gary Guo <gary@garyguo.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://patch.msgid.link/20260312041934.362840-2-jhubbard@nvidia.com
[ Reworded to replace GitHub-like short link with full URLs in Link tags.
  Reworded reason string to match the style of a couple others we have
  elsewhere. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/cpufreq.rs | 1 +
 1 file changed, 1 insertion(+)

diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 76faa1ac8501..f5adee48d40c 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -401,6 +401,7 @@ pub fn to_table(mut self) -> Result<TableBox> {
 /// ```
 /// use kernel::cpufreq::{DEFAULT_TRANSITION_LATENCY_NS, Policy};
 ///
+/// #[allow(clippy::double_parens, reason = "False positive before 1.92.0")]
 /// fn update_policy(policy: &mut Policy) {
 ///     policy
 ///         .set_dvfs_possible_from_any_cpu(true)

From 592c61f3bfceaa29f8275696bd67c3dfad7ef72e Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Thu, 12 Mar 2026 12:10:14 +0100
Subject: [PATCH 1291/1303] rust: kbuild: allow `unused_features`

Starting with the upcoming Rust 1.96.0 (to be released 2026-05-28),
`rustc` introduces the new lint `unused_features` [1], which warns [2]:

    warning: feature `used_with_arg` is declared but not used
     --> <crate attribute>:1:93
      |
    1 | #![feature(asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg)]
      |                                                                                             ^^^^^^^^^^^^^
      |
      = note: `#[warn(unused_features)]` (part of `#[warn(unused)]`) on by default

The original goal of using `-Zcrate-attr` automatically was that there
is a consistent set of features enabled and managed globally for all
Rust kernel code (modulo exceptions like the `rust/` crated).

While we could require crates to enable features manually (even if we
still keep the `-Zallow-features=` list, i.e. removing the `-Zcrate-attr`
list), it is not really worth making all developers worry about it just
for a new lint.

The features are expected to eventually become stable anyway (most already
did), and thus having to remove features in every file that may use them
is not worth it either.

Thus just allow the new lint globally.

The lint actually existed for a long time, which is why `rustc` does
not complain about an unknown lint in the stable versions we support,
but it was "disabled" years ago [3], and now it was made to work again.

For extra context, the new implementation of the lint has already been
improved to avoid linting about features that became stable thanks to
Benno's report and the ensuing discussion [4] [5], but while that helps,
it is still the case that we may have features enabled that are not used
for one reason or another in a particular crate.

Cc: stable@vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs).
Link: https://github.com/rust-lang/rust/pull/152164 [1]
Link: https://github.com/Rust-for-Linux/pin-init/pull/114 [2]
Link: https://github.com/rust-lang/rust/issues/44232 [3]
Link: https://github.com/rust-lang/rust/issues/153523 [4]
Link: https://github.com/rust-lang/rust/pull/153610 [5]
Reviewed-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260312111014.74198-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Makefile b/Makefile
index 73a39592f112..587345f16c97 100644
--- a/Makefile
+++ b/Makefile
@@ -476,6 +476,7 @@ KBUILD_USERLDFLAGS := $(USERLDFLAGS)
 export rust_common_flags := --edition=2021 \
 			    -Zbinary_dep_depinfo=y \
 			    -Astable_features \
+			    -Aunused_features \
 			    -Dnon_ascii_idents \
 			    -Dunsafe_op_in_unsafe_fn \
 			    -Wmissing_docs \

From c2c185be5c85d37215397c8e8781abf0a69bec1f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 12 Mar 2026 08:59:25 -0600
Subject: [PATCH 1292/1303] io_uring/kbuf: check if target buffer list is still
 legacy on recycle

There's a gap between when the buffer was grabbed and when it
potentially gets recycled, where if the list is empty, someone could've
upgraded it to a ring provided type. This can happen if the request
is forced via io-wq. The legacy recycling is missing checking if the
buffer_list still exists, and if it's of the correct type. Add those
checks.

Cc: stable@vger.kernel.org
Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index dae5b4ab3819..e7f444953dfb 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -111,9 +111,18 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 
 	buf = req->kbuf;
 	bl = io_buffer_get_list(ctx, buf->bgid);
-	list_add(&buf->list, &bl->buf_list);
-	bl->nbufs++;
+	/*
+	 * If the buffer list was upgraded to a ring-based one, or removed,
+	 * while the request was in-flight in io-wq, drop it.
+	 */
+	if (bl && !(bl->flags & IOBL_BUF_RING)) {
+		list_add(&buf->list, &bl->buf_list);
+		bl->nbufs++;
+	} else {
+		kfree(buf);
+	}
 	req->flags &= ~REQ_F_BUFFER_SELECTED;
+	req->kbuf = NULL;
 
 	io_ring_submit_unlock(ctx, issue_flags);
 	return true;

From c38b8f5f791ecce13ab77e2257f8fd2444ba80f6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Mar 2026 04:39:08 +0000
Subject: [PATCH 1293/1303] net: prevent NULL deref in ip[6]tunnel_xmit()

Blamed commit missed that both functions can be called with dev == NULL.

Also add unlikely() hints for these conditions that only fuzzers can hit.

Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions")
Signed-off-by: Eric Dumazet <edumazet@google.com>
CC: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260312043908.2790803-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip6_tunnel.h  | 10 ++++++----
 net/ipv4/ip_tunnel_core.c | 10 ++++++----
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 1253cbb4b0a4..359b595f1df9 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -156,10 +156,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 {
 	int pkt_len, err;
 
-	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
-		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
-				     dev->name);
-		DEV_STATS_INC(dev, tx_errors);
+	if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
+		if (dev) {
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
+			DEV_STATS_INC(dev, tx_errors);
+		}
 		kfree_skb(skb);
 		return;
 	}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index b1b6bf949f65..5683c328990f 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -58,10 +58,12 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	struct iphdr *iph;
 	int err;
 
-	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
-		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
-				     dev->name);
-		DEV_STATS_INC(dev, tx_errors);
+	if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
+		if (dev) {
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
+			DEV_STATS_INC(dev, tx_errors);
+		}
 		ip_rt_put(rt);
 		kfree_skb(skb);
 		return;

From d2ea4ff1ce50787a98a3900b3fb1636f3620b7cf Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 10 Mar 2026 14:18:41 -0700
Subject: [PATCH 1294/1303] KVM: selftests: Verify SEV+ guests can read and
 write EFER, CR0, CR4, and CR8

Add "do no harm" testing of EFER, CR0, CR4, and CR8 for SEV+ guests to
verify that the guest can read and write the registers, without hitting
e.g. a #VC on SEV-ES guests due to KVM incorrectly trying to intercept a
register.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260310211841.2552361-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/x86/processor.h     | 23 ++++++++++++++
 .../selftests/kvm/x86/sev_smoke_test.c        | 30 +++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 4ebae4269e68..469a22122157 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -557,6 +557,11 @@ static inline uint64_t get_cr0(void)
 	return cr0;
 }
 
+static inline void set_cr0(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory");
+}
+
 static inline uint64_t get_cr3(void)
 {
 	uint64_t cr3;
@@ -566,6 +571,11 @@ static inline uint64_t get_cr3(void)
 	return cr3;
 }
 
+static inline void set_cr3(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory");
+}
+
 static inline uint64_t get_cr4(void)
 {
 	uint64_t cr4;
@@ -580,6 +590,19 @@ static inline void set_cr4(uint64_t val)
 	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
 }
 
+static inline uint64_t get_cr8(void)
+{
+	uint64_t cr8;
+
+	__asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8));
+	return cr8;
+}
+
+static inline void set_cr8(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory");
+}
+
 static inline void set_idt(const struct desc_ptr *idt_desc)
 {
 	__asm__ __volatile__("lidt %0"::"m"(*idt_desc));
diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index 86ad1c7d068f..8bd37a476f15 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -13,6 +13,30 @@
 #include "linux/psp-sev.h"
 #include "sev.h"
 
+static void guest_sev_test_msr(uint32_t msr)
+{
+	uint64_t val = rdmsr(msr);
+
+	wrmsr(msr, val);
+	GUEST_ASSERT(val == rdmsr(msr));
+}
+
+#define guest_sev_test_reg(reg)			\
+do {						\
+	uint64_t val = get_##reg();		\
+						\
+	set_##reg(val);				\
+	GUEST_ASSERT(val == get_##reg());	\
+} while (0)
+
+static void guest_sev_test_regs(void)
+{
+	guest_sev_test_msr(MSR_EFER);
+	guest_sev_test_reg(cr0);
+	guest_sev_test_reg(cr3);
+	guest_sev_test_reg(cr4);
+	guest_sev_test_reg(cr8);
+}
 
 #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)
 
@@ -24,6 +48,8 @@ static void guest_snp_code(void)
 	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED);
 	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED);
 
+	guest_sev_test_regs();
+
 	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
 	vmgexit();
 }
@@ -34,6 +60,8 @@ static void guest_sev_es_code(void)
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED);
 
+	guest_sev_test_regs();
+
 	/*
 	 * TODO: Add GHCB and ucall support for SEV-ES guests.  For now, simply
 	 * force "termination" to signal "done" via the GHCB MSR protocol.
@@ -47,6 +75,8 @@ static void guest_sev_code(void)
 	GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV));
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
 
+	guest_sev_test_regs();
+
 	GUEST_DONE();
 }
 

From 39ebc8d7f561e1b64eca87353ef9b18e2825e591 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:41 +0000
Subject: [PATCH 1295/1303] lib/bootconfig: fix off-by-one in xbc_verify_tree()
 unclosed brace error

__xbc_open_brace() pushes entries with post-increment
(open_brace[brace_index++]), so brace_index always points one past
the last valid entry.  xbc_verify_tree() reads open_brace[brace_index]
to report which brace is unclosed, but this is one past the last
pushed entry and contains stale/zero data, causing the error message
to reference the wrong node.

Use open_brace[brace_index - 1] to correctly identify the unclosed
brace.  brace_index is known to be > 0 here since we are inside the
if (brace_index) guard.

Link: https://lore.kernel.org/all/20260312191143.28719-2-objecting@objecting.org/

Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 449369a60846..ce25714351d5 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -802,7 +802,7 @@ static int __init xbc_verify_tree(void)
 
 	/* Brace closing */
 	if (brace_index) {
-		n = &xbc_nodes[open_brace[brace_index]];
+		n = &xbc_nodes[open_brace[brace_index - 1]];
 		return xbc_parse_error("Brace is not closed",
 					xbc_node_get_data(n));
 	}

From 82f73ef9c41e0623e0a8bdce4fa44a7237709f0c Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Tue, 10 Mar 2026 13:51:24 +0530
Subject: [PATCH 1296/1303] powerpc/iommu: fix lockdep warning during PCI
 enumeration

Commit a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev()
helper") introduced iommu_driver_get_domain_for_dev() for driver
code paths that hold iommu_group->mutex while attaching a device
to an IOMMU domain.

The same commit also added a lockdep assertion in
iommu_get_domain_for_dev() to ensure that callers do not hold
iommu_group->mutex when invoking it.

On powerpc platforms, when PCI device ownership is switched from
BLOCKED to the PLATFORM domain, the attach callback
spapr_tce_platform_iommu_attach_dev() still calls
iommu_get_domain_for_dev(). This happens while iommu_group->mutex
is held during domain switching, which triggers the lockdep warning
below during PCI enumeration:

WARNING: drivers/iommu/iommu.c:2252 at iommu_get_domain_for_dev+0x38/0x80, CPU#2: swapper/0/1
Modules linked in:
CPU: 2 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc2+ #35 PREEMPT
Hardware name: IBM,9105-22A Power11 (architected) 0x820200 0xf000007 of:IBM,FW1120.00 (RB1120_115) hv:phyp pSeries
NIP:  c000000000c244c4 LR: c00000000005b5a4 CTR: c00000000005b578
REGS: c00000000a7bf280 TRAP: 0700   Not tainted  (7.0.0-rc2+)
MSR:  8000000002029033 <SF,VEC,EE,ME,IR,DR,RI,LE>  CR: 22004422  XER: 0000000a
CFAR: c000000000c24508 IRQMASK: 0
GPR00: c00000000005b5a4 c00000000a7bf520 c000000001dc8100 0000000000000001
GPR04: c00000000f972f10 0000000000000000 0000000000000000 0000000000000001
GPR08: 0000001ffbc60000 0000000000000001 0000000000000000 0000000000000000
GPR12: c00000000005b578 c000001fffffe480 c000000000011618 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR20: ffffffffffffefff 0000000000000000 c000000002d30eb0 0000000000000001
GPR24: c0000000017881f8 0000000000000000 0000000000000001 c00000000f972e00
GPR28: c00000000bbba0d0 0000000000000000 c00000000bbba0d0 c00000000f972e00
NIP [c000000000c244c4] iommu_get_domain_for_dev+0x38/0x80
LR [c00000000005b5a4] spapr_tce_platform_iommu_attach_dev+0x2c/0x98
Call Trace:
 iommu_get_domain_for_dev+0x68/0x80 (unreliable)
 spapr_tce_platform_iommu_attach_dev+0x2c/0x98
 __iommu_attach_device+0x44/0x220
 __iommu_device_set_domain+0xf4/0x194
 __iommu_group_set_domain_internal+0xec/0x228
 iommu_setup_default_domain+0x5f4/0x6a4
 __iommu_probe_device+0x674/0x724
 iommu_probe_device+0x50/0xb4
 iommu_add_device+0x48/0x198
 pci_dma_dev_setup_pSeriesLP+0x198/0x4f0
 pcibios_bus_add_device+0x80/0x464
 pci_bus_add_device+0x40/0x100
 pci_bus_add_devices+0x54/0xb0
 pcibios_init+0xd8/0x140
 do_one_initcall+0x8c/0x598
 kernel_init_freeable+0x3ec/0x850
 kernel_init+0x34/0x270
 ret_from_kernel_user_thread+0x14/0x1c

Fix this by using iommu_driver_get_domain_for_dev() instead of
iommu_get_domain_for_dev() in spapr_tce_platform_iommu_attach_dev(),
which is the appropriate helper for callers holding the group mutex.

Cc: stable@vger.kernel.org
Fixes: a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev() helper")
Closes: https://patchwork.ozlabs.org/project/linuxppc-dev/patch/d5c834ff-4c95-44dd-8bef-57242d63aeee@linux.ibm.com/
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
[Maddy: Added Closes, tested and reviewed by tags]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260310082129.3630996-1-nilay@linux.ibm.com
---
 arch/powerpc/kernel/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0ce71310b7d9..d122e8447831 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 				    struct device *dev,
 				    struct iommu_domain *old)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev);
 	struct iommu_table_group *table_group;
 	struct iommu_group *grp;
 

From 560f763baa0f2c9a44da4294c06af071405ac46f Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:42 +0000
Subject: [PATCH 1297/1303] lib/bootconfig: check bounds before writing in
 __xbc_open_brace()

The bounds check for brace_index happens after the array write.
While the current call pattern prevents an actual out-of-bounds
access (the previous call would have returned an error), the
write-before-check pattern is fragile and would become a real
out-of-bounds write if the error return were ever not propagated.

Move the bounds check before the array write so the function is
self-contained and safe regardless of caller behavior.

Link: https://lore.kernel.org/all/20260312191143.28719-3-objecting@objecting.org/

Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index ce25714351d5..9c3d59fb96ed 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -532,9 +532,9 @@ static char *skip_spaces_until_newline(char *p)
 static int __init __xbc_open_brace(char *p)
 {
 	/* Push the last key as open brace */
-	open_brace[brace_index++] = xbc_node_index(last_parent);
 	if (brace_index >= XBC_DEPTH_MAX)
 		return xbc_parse_error("Exceed max depth of braces", p);
+	open_brace[brace_index++] = xbc_node_index(last_parent);
 
 	return 0;
 }

From 1120a36bb1e9b9e22de75ecb4ef0b998f73a97f1 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:43 +0000
Subject: [PATCH 1298/1303] lib/bootconfig: fix snprintf truncation check in
 xbc_node_compose_key_after()

snprintf() returns the number of characters that would have been
written excluding the NUL terminator.  Output is truncated when the
return value is >= the buffer size, not just > the buffer size.

When ret == size, the current code takes the non-truncated path,
advancing buf by ret and reducing size to 0.  This is wrong because
the output was actually truncated (the last character was replaced by
NUL).  Fix by using >= so the truncation path is taken correctly.

Link: https://lore.kernel.org/all/20260312191143.28719-4-objecting@objecting.org/

Fixes: 76db5a27a827 ("bootconfig: Add Extra Boot Config support")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 9c3d59fb96ed..2da049216fe0 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -316,7 +316,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root,
 			       depth ? "." : "");
 		if (ret < 0)
 			return ret;
-		if (ret > size) {
+		if (ret >= size) {
 			size = 0;
 		} else {
 			size -= ret;

From e2715ea5fb352cd43fce437b91aa0fd50aaaf384 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 13:18:55 +0900
Subject: [PATCH 1299/1303] bootconfig: Add bootconfig tests about braces

Add more bootconfig tests for checking the error message of
non closing brace and max number of nested braces.

Link: https://lore.kernel.org/all/177337553551.416919.11217619471547711262.stgit@devnote2/

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 .../samples/bad-non-closed-brace.bconf        |  4 ++++
 .../samples/bad-over-max-brace.bconf          | 19 +++++++++++++++++++
 .../samples/exp-good-nested-brace.bconf       |  1 +
 .../samples/good-nested-brace.bconf           | 18 ++++++++++++++++++
 tools/bootconfig/test-bootconfig.sh           |  9 +++++++++
 5 files changed, 51 insertions(+)
 create mode 100644 tools/bootconfig/samples/bad-non-closed-brace.bconf
 create mode 100644 tools/bootconfig/samples/bad-over-max-brace.bconf
 create mode 100644 tools/bootconfig/samples/exp-good-nested-brace.bconf
 create mode 100644 tools/bootconfig/samples/good-nested-brace.bconf

diff --git a/tools/bootconfig/samples/bad-non-closed-brace.bconf b/tools/bootconfig/samples/bad-non-closed-brace.bconf
new file mode 100644
index 000000000000..6ed9f3363dde
--- /dev/null
+++ b/tools/bootconfig/samples/bad-non-closed-brace.bconf
@@ -0,0 +1,4 @@
+foo {
+ bar {
+   buz
+ }
diff --git a/tools/bootconfig/samples/bad-over-max-brace.bconf b/tools/bootconfig/samples/bad-over-max-brace.bconf
new file mode 100644
index 000000000000..74b5dc9e21dc
--- /dev/null
+++ b/tools/bootconfig/samples/bad-over-max-brace.bconf
@@ -0,0 +1,19 @@
+key1 {
+key2 {
+key3 {
+key4 {
+key5 {
+key6 {
+key7 {
+key8 {
+key9 {
+key10 {
+key11 {
+key12 {
+key13 {
+key14 {
+key15 {
+key16 {
+key17 {
+}}}}}}}}}}}}}}}}}
+
diff --git a/tools/bootconfig/samples/exp-good-nested-brace.bconf b/tools/bootconfig/samples/exp-good-nested-brace.bconf
new file mode 100644
index 000000000000..19e0f51b4553
--- /dev/null
+++ b/tools/bootconfig/samples/exp-good-nested-brace.bconf
@@ -0,0 +1 @@
+key1.key2.key3.key4.key5.key6.key7.key8.key9.key10.key11.key12.key13.key14.key15.key16;
diff --git a/tools/bootconfig/samples/good-nested-brace.bconf b/tools/bootconfig/samples/good-nested-brace.bconf
new file mode 100644
index 000000000000..980d094f296e
--- /dev/null
+++ b/tools/bootconfig/samples/good-nested-brace.bconf
@@ -0,0 +1,18 @@
+key1 {
+key2 {
+key3 {
+key4 {
+key5 {
+key6 {
+key7 {
+key8 {
+key9 {
+key10 {
+key11 {
+key12 {
+key13 {
+key14 {
+key15 {
+key16 {
+}}}}}}}}}}}}}}}}
+
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index be9bd18b1d56..fc69f815ce4a 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -171,6 +171,15 @@ $BOOTCONF $INITRD > $OUTFILE
 xfail grep -q 'val[[:space:]]' $OUTFILE
 xpass grep -q 'val2[[:space:]]' $OUTFILE
 
+echo "Showing correct line:column of no closing brace"
+cat > $TEMPCONF << EOF
+foo {
+bar {
+}
+EOF
+$BOOTCONF -a $TEMPCONF $INITRD 2> $OUTFILE
+xpass grep -q "1:1" $OUTFILE
+
 echo "=== expected failure cases ==="
 for i in samples/bad-* ; do
   xfail $BOOTCONF -a $i $INITRD

From e113f0b46d19626ec15388bcb91432c9a4fd6261 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 23:14:14 +0900
Subject: [PATCH 1300/1303] kprobes: avoid crash when rmmod/insmod after ftrace
 killed

After we hit ftrace is killed by some errors, the kernel crash if
we remove modules in which kprobe probes.

BUG: unable to handle page fault for address: fffffbfff805000d
PGD 817fcc067 P4D 817fcc067 PUD 817fc8067 PMD 101555067 PTE 0
Oops: Oops: 0000 [#1] SMP KASAN PTI
CPU: 4 UID: 0 PID: 2012 Comm: rmmod Tainted: G        W  OE
Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
RIP: 0010:kprobes_module_callback+0x89/0x790
RSP: 0018:ffff88812e157d30 EFLAGS: 00010a02
RAX: 1ffffffff805000d RBX: dffffc0000000000 RCX: ffffffff86a8de90
RDX: ffffed1025c2af9b RSI: 0000000000000008 RDI: ffffffffc0280068
RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed1025c2af9a
R10: ffff88812e157cd7 R11: 205d323130325420 R12: 0000000000000002
R13: ffffffffc0290488 R14: 0000000000000002 R15: ffffffffc0280040
FS:  00007fbc450dd740(0000) GS:ffff888420331000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffffbfff805000d CR3: 000000010f624000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 notifier_call_chain+0xc6/0x280
 blocking_notifier_call_chain+0x60/0x90
 __do_sys_delete_module.constprop.0+0x32a/0x4e0
 do_syscall_64+0x5d/0xfa0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

This is because the kprobe on ftrace does not correctly handles
the kprobe_ftrace_disabled flag set by ftrace_kill().

To prevent this error, check kprobe_ftrace_disabled in
__disarm_kprobe_ftrace() and skip all ftrace related operations.

Link: https://lore.kernel.org/all/176473947565.1727781.13110060700668331950.stgit@mhiramat.tok.corp.google.com/

Reported-by: Ye Bin <yebin10@huawei.com>
Closes: https://lore.kernel.org/all/20251125020536.2484381-1-yebin@huaweicloud.com/
Fixes: ae6aa16fdc16 ("kprobes: introduce ftrace based optimization")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/kprobes.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab25b4aa9095..025af57ad3ed 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1178,6 +1178,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	int ret;
 
 	lockdep_assert_held(&kprobe_mutex);
+	if (unlikely(kprobe_ftrace_disabled)) {
+		/* Now ftrace is disabled forever, disarm is already done. */
+		return 0;
+	}
 
 	if (*cnt == 1) {
 		ret = unregister_ftrace_function(ops);

From 5ef268cb7a0aac55521fd9881f1939fa94a8988e Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 23:04:11 +0900
Subject: [PATCH 1301/1303] kprobes: Remove unneeded warnings from
 __arm_kprobe_ftrace()

Remove unneeded warnings for handled errors from __arm_kprobe_ftrace()
because all caller handled the error correctly.

Link: https://lore.kernel.org/all/177261531182.1312989.8737778408503961141.stgit@mhiramat.tok.corp.google.com/

Reported-by: Zw Tang <shicenci@gmail.com>
Closes: https://lore.kernel.org/all/CAPHJ_V+J6YDb_wX2nhXU6kh466Dt_nyDSas-1i_Y8s7tqY-Mzw@mail.gmail.com/
Fixes: 9c89bb8e3272 ("kprobes: treewide: Cleanup the error messages for kprobes")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/kprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 025af57ad3ed..bfc89083daa9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1144,12 +1144,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	lockdep_assert_held(&kprobe_mutex);
 
 	ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0);
-	if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret))
+	if (ret < 0)
 		return ret;
 
 	if (*cnt == 0) {
 		ret = register_ftrace_function(ops);
-		if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) {
+		if (ret < 0) {
 			/*
 			 * At this point, sinec ops is not registered, we should be sefe from
 			 * registering empty filter.

From d0d9b1f4f5391e6a00cee81d73ed2e8f98446d5f Mon Sep 17 00:00:00 2001
From: Vyacheslav Vahnenko <vahnenko2003@gmail.com>
Date: Fri, 13 Mar 2026 15:36:38 +0300
Subject: [PATCH 1302/1303] USB: ezcap401 needs USB_QUIRK_NO_BOS to function on
 10gbs usb speed

Add USB_QUIRK_NO_BOS for ezcap401 capture card, without it dmesg will show
"unable to get BOS descriptor or descriptor too short" and "unable to
read config index 0 descriptor/start: -71" errors and device will not
able to work at full speed at 10gbs

Signed-off-by: Vyacheslav Vahnenko <vahnenko2003@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260313123638.20481-1-vahnenko2003@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index e3f402e0c351..5523a8e29021 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -589,6 +589,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */
 	{ USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* ezcap401 - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x32ed, 0x0401), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* DELL USB GEN2 */
 	{ USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME },
 

From f338e77383789c0cae23ca3d48adcc5e9e137e3c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 15 Mar 2026 13:52:05 -0700
Subject: [PATCH 1303/1303] Linux 7.0-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index ec0f2d8466ea..c9b7bee102e8 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*