This is the 5.10.83 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmGnMAIACgkQONu9yGCS
 aT6DvhAAnicmgFqzIcVpZmh+zd1VQFVQmFnlJTdfanz48k9JzkciCIjsSmnMvDZG
 oPA2xIZf1oXMkxRLO+PYrUP0Y2G5XT5ADh4qAdkxTD2QtNduq5G5iH6UdZzgyey7
 awhWpi/U2aE2imwbV95c1ZfSG7nNMf/XWG36uGAqUKBGQZLeoAvWy3jHqcFoIL0+
 UfbAu8TN06dTizQ7IiJzM/CrqlxSRA5EnF4D58n7Hf0etVR7BdFBCGSgefnR8Dog
 /zYGw2Jb0WczN6Qzws/WZm4zIC83NBYRdeaqKTIMF+0E5SrlCk1nE8Nc/WHzGazK
 Co8k4zm84DY5mpkCxTqGIgZ12Whho+kB8McAKeJ3Yzvq8qjKscPt+8nVLjyj/h8Q
 SNt1hTeHwTu5TGNMyNEWBjdnvuKv2XeyArpbPUsAofBdiMy8g/pkPiCOE9hoRV3N
 hPMrAw6jfZC6etie30ngsepE/3r0H0/n/U3Sh5mf12gY02zBQkMlJcMi86FNnxgk
 wcKgwYJca2elr3y2jSvOzs8k0OhTvaqEo0QnObR3ivooEiEbD9q2mTYidHgETM0V
 x/5Aqb+09suyER6vL4G1i0agbO6sn2AAepGTRLGTDAbHHFP9aG1VbIZwoORZ1fII
 VPGOq7/l0xYlIA/o0NUemcxPpGTvEkeKba7MVTbzxWcTdcF67g0=
 =J7jt
 -----END PGP SIGNATURE-----

Merge 5.10.83 into android-5.10

Changes in 5.10.83
	bpf: Fix toctou on read-only map's constant scalar tracking
	ACPI: Get acpi_device's parent from the parent field
	USB: serial: option: add Telit LE910S1 0x9200 composition
	USB: serial: option: add Fibocom FM101-GL variants
	usb: dwc2: gadget: Fix ISOC flow for elapsed frames
	usb: dwc2: hcd_queue: Fix use of floating point literal
	usb: dwc3: gadget: Ignore NoStream after End Transfer
	usb: dwc3: gadget: Check for L1/L2/U3 for Start Transfer
	usb: dwc3: gadget: Fix null pointer exception
	net: nexthop: fix null pointer dereference when IPv6 is not enabled
	usb: chipidea: ci_hdrc_imx: fix potential error pointer dereference in probe
	usb: typec: fusb302: Fix masking of comparator and bc_lvl interrupts
	usb: hub: Fix usb enumeration issue due to address0 race
	usb: hub: Fix locking issues with address0_mutex
	binder: fix test regression due to sender_euid change
	ALSA: ctxfi: Fix out-of-range access
	ALSA: hda/realtek: Add quirk for ASRock NUC Box 1100
	ALSA: hda/realtek: Fix LED on HP ProBook 435 G7
	media: cec: copy sequence field for the reply
	Revert "parisc: Fix backtrace to always include init funtion names"
	HID: wacom: Use "Confidence" flag to prevent reporting invalid contacts
	staging/fbtft: Fix backlight
	staging: greybus: Add missing rwsem around snd_ctl_remove() calls
	staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect()
	fuse: release pipe buf after last use
	xen: don't continue xenstore initialization in case of errors
	xen: detect uninitialized xenbus in xenbus_init
	KVM: PPC: Book3S HV: Prevent POWER7/8 TLB flush flushing SLB
	tracing/uprobe: Fix uprobe_perf_open probes iteration
	tracing: Fix pid filtering when triggers are attached
	mmc: sdhci-esdhc-imx: disable CMDQ support
	mmc: sdhci: Fix ADMA for PAGE_SIZE >= 64KiB
	mdio: aspeed: Fix "Link is Down" issue
	powerpc/32: Fix hardlockup on vmap stack overflow
	PCI: aardvark: Deduplicate code in advk_pcie_rd_conf()
	PCI: aardvark: Update comment about disabling link training
	PCI: aardvark: Implement re-issuing config requests on CRS response
	PCI: aardvark: Simplify initialization of rootcap on virtual bridge
	PCI: aardvark: Fix link training
	proc/vmcore: fix clearing user buffer by properly using clear_user()
	netfilter: ctnetlink: fix filtering with CTA_TUPLE_REPLY
	netfilter: ctnetlink: do not erase error code with EINVAL
	netfilter: ipvs: Fix reuse connection if RS weight is 0
	netfilter: flowtable: fix IPv6 tunnel addr match
	ARM: dts: BCM5301X: Fix I2C controller interrupt
	ARM: dts: BCM5301X: Add interrupt properties to GPIO node
	ARM: dts: bcm2711: Fix PCIe interrupts
	ASoC: qdsp6: q6routing: Conditionally reset FrontEnd Mixer
	ASoC: qdsp6: q6asm: fix q6asm_dai_prepare error handling
	ASoC: topology: Add missing rwsem around snd_ctl_remove() calls
	ASoC: codecs: wcd934x: return error code correctly from hw_params
	net: ieee802154: handle iftypes as u32
	firmware: arm_scmi: pm: Propagate return value to caller
	NFSv42: Don't fail clone() unless the OP_CLONE operation failed
	ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE
	drm/nouveau/acr: fix a couple NULL vs IS_ERR() checks
	scsi: mpt3sas: Fix kernel panic during drive powercycle test
	drm/vc4: fix error code in vc4_create_object()
	net: marvell: prestera: fix double free issue on err path
	iavf: Prevent changing static ITR values if adaptive moderation is on
	ALSA: intel-dsp-config: add quirk for JSL devices based on ES8336 codec
	mptcp: fix delack timer
	firmware: smccc: Fix check for ARCH_SOC_ID not implemented
	ipv6: fix typos in __ip6_finish_output()
	nfp: checking parameter process for rx-usecs/tx-usecs is invalid
	net: stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume
	net: stmmac: retain PTP clock time during SIOCSHWTSTAMP ioctls
	net: ipv6: add fib6_nh_release_dsts stub
	net: nexthop: release IPv6 per-cpu dsts when replacing a nexthop group
	ice: fix vsi->txq_map sizing
	ice: avoid bpf_prog refcount underflow
	scsi: core: sysfs: Fix setting device state to SDEV_RUNNING
	scsi: scsi_debug: Zero clear zones at reset write pointer
	erofs: fix deadlock when shrink erofs slab
	net/smc: Ensure the active closing peer first closes clcsock
	mlxsw: Verify the accessed index doesn't exceed the array length
	mlxsw: spectrum: Protect driver from buggy firmware
	net: marvell: mvpp2: increase MTU limit when XDP enabled
	nvmet-tcp: fix incomplete data digest send
	net/ncsi : Add payload to be 32-bit aligned to fix dropped packets
	PM: hibernate: use correct mode for swsusp_close()
	drm/amd/display: Set plane update flags for all planes in reset
	tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows
	lan743x: fix deadlock in lan743x_phy_link_status_change()
	net: phylink: Force link down and retrigger resolve on interface change
	net: phylink: Force retrigger in case of latched link-fail indicator
	net/smc: Fix NULL pointer dereferencing in smc_vlan_by_tcpsk()
	net/smc: Fix loop in smc_listen
	nvmet: use IOCB_NOWAIT only if the filesystem supports it
	igb: fix netpoll exit with traffic
	MIPS: loongson64: fix FTLB configuration
	MIPS: use 3-level pgtable for 64KB page size on MIPS_VA_BITS_48
	tls: splice_read: fix record type check
	tls: fix replacing proto_ops
	net/sched: sch_ets: don't peek at classes beyond 'nbands'
	net: vlan: fix underflow for the real_dev refcnt
	net/smc: Don't call clcsock shutdown twice when smc shutdown
	net: hns3: fix VF RSS failed problem after PF enable multi-TCs
	net: mscc: ocelot: don't downgrade timestamping RX filters in SIOCSHWTSTAMP
	net: mscc: ocelot: correctly report the timestamping RX filters in ethtool
	tcp: correctly handle increased zerocopy args struct size
	sched/scs: Reset task stack state in bringup_cpu()
	f2fs: set SBI_NEED_FSCK flag when inconsistent node block found
	ceph: properly handle statfs on multifs setups
	smb3: do not error on fsync when readonly
	iommu/amd: Clarify AMD IOMMUv2 initialization messages
	vhost/vsock: fix incorrect used length reported to the guest
	tracing: Check pid filtering when creating events
	xen: sync include/xen/interface/io/ring.h with Xen's newest version
	xen/blkfront: read response from backend only once
	xen/blkfront: don't take local copy of a request from the ring page
	xen/blkfront: don't trust the backend response data blindly
	xen/netfront: read response from backend only once
	xen/netfront: don't read data from request on the ring page
	xen/netfront: disentangle tx_skb_freelist
	xen/netfront: don't trust the backend response data blindly
	tty: hvc: replace BUG_ON() with negative return value
	s390/mm: validate VMA in PGSTE manipulation functions
	shm: extend forced shm destroy to support objects from several IPC nses
	net: stmmac: platform: fix build warning when with !CONFIG_PM_SLEEP
	drm/amdgpu/gfx9: switch to golden tsc registers for renoir+
	Linux 5.10.83

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ief47fb0c545e95bd269b07477eacd4c8713f287d

Documentation/networking/ipvs-sysctl.rst

@@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
 
 	0: disable any special handling on port reuse. The new
 	connection will be delivered to the same real server that was
-	servicing the previous connection. This will effectively
+	servicing the previous connection.
-	disable expire_nodest_conn.
 
 	bit 1: enable rescheduling of new connections when it is safe.
 	That is, whenever expire_nodest_conn and for TCP sockets, when

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 82
+SUBLEVEL = 83
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/arm/boot/dts/bcm2711.dtsi

@@ -480,11 +480,17 @@ pcie0: pcie@7d500000 {
 			#address-cells = <3>;
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
-			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pcie", "msi";
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
 			interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &gicv2 GIC_SPI 144
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &gicv2 GIC_SPI 145
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &gicv2 GIC_SPI 146
 							IRQ_TYPE_LEVEL_HIGH>;
 			msi-controller;
 			msi-parent = <&pcie0>;

arch/arm/boot/dts/bcm5301x.dtsi

@@ -242,6 +242,8 @@ chipcommon: chipcommon@0 {
 
 			gpio-controller;
 			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		pcie0: pcie@12000 {
@@ -408,7 +410,7 @@ uart2: serial@18008000 {
 	i2c0: i2c@18009000 {
 		compatible = "brcm,iproc-i2c";
 		reg = <0x18009000 0x50>;
-		interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clock-frequency = <100000>;

arch/arm/mach-socfpga/core.h

@@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr;
 u32 socfpga_sdram_self_refresh(u32 sdr_base);
 extern unsigned int socfpga_sdram_self_refresh_sz;
 
-extern char secondary_trampoline, secondary_trampoline_end;
+extern char secondary_trampoline[], secondary_trampoline_end[];
 
 extern unsigned long socfpga_cpu1start_addr;
 

arch/arm/mach-socfpga/platsmp.c

@@ -20,14 +20,14 @@
 
 static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		/* This will put CPU #1 into reset. */
 		writel(RSTMGR_MPUMODRST_CPU1,
 		       rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST);
 
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff));
@@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr +
 		       SOCFPGA_A10_RSTMGR_MODMPURST);
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff));

arch/mips/Kconfig

@@ -3189,7 +3189,7 @@ config STACKTRACE_SUPPORT
 config PGTABLE_LEVELS
 	int
 	default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48
-	default 3 if 64BIT && !PAGE_SIZE_64KB
+	default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48)
 	default 2
 
 config MIPS_AUTO_PFN_OFFSET

arch/mips/kernel/cpu-probe.c

@@ -1721,8 +1721,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c)
 
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 {
-	decode_configs(c);
-
 	/* All Loongson processors covered here define ExcCode 16 as GSExc. */
 	c->options |= MIPS_CPU_GSEXCEX;
 
@@ -1783,6 +1781,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		panic("Unknown Loongson Processor ID!");
 		break;
 	}
+
+	decode_configs(c);
 }
 #else
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { }

arch/parisc/kernel/vmlinux.lds.S

@@ -57,8 +57,6 @@ SECTIONS
 {
 	. = KERNEL_BINARY_TEXT_START;
 
-	_stext = .;	/* start of kernel text, includes init code & data */
-
 	__init_begin = .;
 	HEAD_TEXT_SECTION
 	MLONGCALL_DISCARD(INIT_TEXT_SECTION(8))
@@ -82,6 +80,7 @@ SECTIONS
 	/* freed after init ends here */
 
 	_text = .;		/* Text and read-only data */
+	_stext = .;
 	MLONGCALL_KEEP(INIT_TEXT_SECTION(8))
 	.text ALIGN(PAGE_SIZE) : {
 		TEXT_TEXT

arch/powerpc/kernel/head_32.h

@@ -333,11 +333,11 @@
 	mfspr	r1, SPRN_SPRG_THREAD
 	lwz	r1, TASK_CPU - THREAD(r1)
 	slwi	r1, r1, 3
-	addis	r1, r1, emergency_ctx@ha
+	addis	r1, r1, emergency_ctx-PAGE_OFFSET@ha
 #else
-	lis	r1, emergency_ctx@ha
+	lis	r1, emergency_ctx-PAGE_OFFSET@ha
 #endif
-	lwz	r1, emergency_ctx@l(r1)
+	lwz	r1, emergency_ctx-PAGE_OFFSET@l(r1)
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
 	EXCEPTION_PROLOG_2
 	SAVE_NVGPRS(r11)

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -867,6 +867,7 @@ static void flush_guest_tlb(struct kvm *kvm)
 				       "r" (0) : "memory");
 		}
 		asm volatile("ptesync": : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
 		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
 	} else {
 		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
@@ -877,7 +878,9 @@ static void flush_guest_tlb(struct kvm *kvm)
 			rb += PPC_BIT(51);	/* increment set number */
 		}
 		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
 	}
 }
 

arch/s390/mm/pgtable.c

@@ -988,6 +988,7 @@ EXPORT_SYMBOL(get_guest_storage_key);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste)
 {
+	struct vm_area_struct *vma;
 	unsigned long pgstev;
 	spinlock_t *ptl;
 	pgste_t pgste;
@@ -997,6 +998,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 	WARN_ON_ONCE(orc > ESSA_MAX);
 	if (unlikely(orc > ESSA_MAX))
 		return -EINVAL;
+
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
@@ -1089,10 +1094,14 @@ EXPORT_SYMBOL(pgste_perform_essa);
 int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
 			unsigned long bits, unsigned long value)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pgste_t new;
 	pte_t *ptep;
 
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
@@ -1117,9 +1126,13 @@ EXPORT_SYMBOL(set_pgste_bits);
  */
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
+	vma = find_vma(mm, hva);
+	if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;

drivers/acpi/property.c

@@ -1110,15 +1110,10 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
 		/* All data nodes have parent pointer so just return that */
 		return to_acpi_data_node(fwnode)->parent;
 	} else if (is_acpi_device_node(fwnode)) {
-		acpi_handle handle, parent_handle;
+		struct device *dev = to_acpi_device_node(fwnode)->dev.parent;
 
-		handle = to_acpi_device_node(fwnode)->handle;
+		if (dev)
-		if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) {
+			return acpi_fwnode_handle(to_acpi_device(dev));
-			struct acpi_device *adev;
-
-			if (!acpi_bus_get_device(parent_handle, &adev))
-				return acpi_fwnode_handle(adev);
-		}
 	}
 
 	return NULL;

drivers/block/xen-blkfront.c

@@ -80,6 +80,7 @@ enum blkif_state {
 	BLKIF_STATE_DISCONNECTED,
 	BLKIF_STATE_CONNECTED,
 	BLKIF_STATE_SUSPENDED,
+	BLKIF_STATE_ERROR,
 };
 
 struct grant {
@@ -89,6 +90,7 @@ struct grant {
 };
 
 enum blk_req_status {
+	REQ_PROCESSING,
 	REQ_WAITING,
 	REQ_DONE,
 	REQ_ERROR,
@@ -543,10 +545,10 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,
 
 	id = get_id_from_freelist(rinfo);
 	rinfo->shadow[id].request = req;
-	rinfo->shadow[id].status = REQ_WAITING;
+	rinfo->shadow[id].status = REQ_PROCESSING;
 	rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID;
 
-	(*ring_req)->u.rw.id = id;
+	rinfo->shadow[id].req.u.rw.id = id;
 
 	return id;
 }
@@ -554,11 +556,12 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,
 static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_info *rinfo)
 {
 	struct blkfront_info *info = rinfo->dev_info;
-	struct blkif_request *ring_req;
+	struct blkif_request *ring_req, *final_ring_req;
 	unsigned long id;
 
 	/* Fill out a communications ring structure. */
-	id = blkif_ring_get_request(rinfo, req, &ring_req);
+	id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+	ring_req = &rinfo->shadow[id].req;
 
 	ring_req->operation = BLKIF_OP_DISCARD;
 	ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
@@ -569,8 +572,9 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf
 	else
 		ring_req->u.discard.flag = 0;
 
-	/* Keep a private copy so we can reissue requests when recovering. */
+	/* Copy the request to the ring page. */
-	rinfo->shadow[id].req = *ring_req;
+	*final_ring_req = *ring_req;
+	rinfo->shadow[id].status = REQ_WAITING;
 
 	return 0;
 }
@@ -703,6 +707,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 {
 	struct blkfront_info *info = rinfo->dev_info;
 	struct blkif_request *ring_req, *extra_ring_req = NULL;
+	struct blkif_request *final_ring_req, *final_extra_ring_req = NULL;
 	unsigned long id, extra_id = NO_ASSOCIATED_ID;
 	bool require_extra_req = false;
 	int i;
@@ -747,7 +752,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 	}
 
 	/* Fill out a communications ring structure. */
-	id = blkif_ring_get_request(rinfo, req, &ring_req);
+	id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+	ring_req = &rinfo->shadow[id].req;
 
 	num_sg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg);
 	num_grant = 0;
@@ -798,7 +804,9 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		ring_req->u.rw.nr_segments = num_grant;
 		if (unlikely(require_extra_req)) {
 			extra_id = blkif_ring_get_request(rinfo, req,
-							  &extra_ring_req);
+							  &final_extra_ring_req);
+			extra_ring_req = &rinfo->shadow[extra_id].req;
+
 			/*
 			 * Only the first request contains the scatter-gather
 			 * list.
@@ -840,10 +848,13 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 	if (setup.segments)
 		kunmap_atomic(setup.segments);
 
-	/* Keep a private copy so we can reissue requests when recovering. */
+	/* Copy request(s) to the ring page. */
-	rinfo->shadow[id].req = *ring_req;
+	*final_ring_req = *ring_req;
-	if (unlikely(require_extra_req))
+	rinfo->shadow[id].status = REQ_WAITING;
-		rinfo->shadow[extra_id].req = *extra_ring_req;
+	if (unlikely(require_extra_req)) {
+		*final_extra_ring_req = *extra_ring_req;
+		rinfo->shadow[extra_id].status = REQ_WAITING;
+	}
 
 	if (new_persistent_gnts)
 		gnttab_free_grant_references(setup.gref_head);
@@ -1415,8 +1426,8 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp)
 static int blkif_get_final_status(enum blk_req_status s1,
 				  enum blk_req_status s2)
 {
-	BUG_ON(s1 == REQ_WAITING);
+	BUG_ON(s1 < REQ_DONE);
-	BUG_ON(s2 == REQ_WAITING);
+	BUG_ON(s2 < REQ_DONE);
 
 	if (s1 == REQ_ERROR || s2 == REQ_ERROR)
 		return BLKIF_RSP_ERROR;
@@ -1449,7 +1460,7 @@ static bool blkif_completion(unsigned long *id,
 		s->status = blkif_rsp_to_req_status(bret->status);
 
 		/* Wait the second response if not yet here. */
-		if (s2->status == REQ_WAITING)
+		if (s2->status < REQ_DONE)
 			return false;
 
 		bret->status = blkif_get_final_status(s->status,
@@ -1557,7 +1568,7 @@ static bool blkif_completion(unsigned long *id,
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 {
 	struct request *req;
-	struct blkif_response *bret;
+	struct blkif_response bret;
 	RING_IDX i, rp;
 	unsigned long flags;
 	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
@@ -1568,54 +1579,76 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
  again:
-	rp = rinfo->ring.sring->rsp_prod;
+	rp = READ_ONCE(rinfo->ring.sring->rsp_prod);
-	rmb(); /* Ensure we see queued responses up to 'rp'. */
+	virt_rmb(); /* Ensure we see queued responses up to 'rp'. */
+	if (RING_RESPONSE_PROD_OVERFLOW(&rinfo->ring, rp)) {
+		pr_alert("%s: illegal number of responses %u\n",
+			 info->gd->disk_name, rp - rinfo->ring.rsp_cons);
+		goto err;
+	}
 
 	for (i = rinfo->ring.rsp_cons; i != rp; i++) {
 		unsigned long id;
+		unsigned int op;
+
+		RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
+		id = bret.id;
 
-		bret = RING_GET_RESPONSE(&rinfo->ring, i);
-		id   = bret->id;
 		/*
 		 * The backend has messed up and given us an id that we would
 		 * never have given to it (we stamp it up to BLK_RING_SIZE -
 		 * look in get_id_from_freelist.
 		 */
 		if (id >= BLK_RING_SIZE(info)) {
-			WARN(1, "%s: response to %s has incorrect id (%ld)\n",
+			pr_alert("%s: response has incorrect id (%ld)\n",
-			     info->gd->disk_name, op_name(bret->operation), id);
+				 info->gd->disk_name, id);
-			/* We can't safely get the 'struct request' as
+			goto err;
-			 * the id is busted. */
-			continue;
 		}
+		if (rinfo->shadow[id].status != REQ_WAITING) {
+			pr_alert("%s: response references no pending request\n",
+				 info->gd->disk_name);
+			goto err;
+		}
+
+		rinfo->shadow[id].status = REQ_PROCESSING;
 		req  = rinfo->shadow[id].request;
 
-		if (bret->operation != BLKIF_OP_DISCARD) {
+		op = rinfo->shadow[id].req.operation;
+		if (op == BLKIF_OP_INDIRECT)
+			op = rinfo->shadow[id].req.u.indirect.indirect_op;
+		if (bret.operation != op) {
+			pr_alert("%s: response has wrong operation (%u instead of %u)\n",
+				 info->gd->disk_name, bret.operation, op);
+			goto err;
+		}
+
+		if (bret.operation != BLKIF_OP_DISCARD) {
 			/*
 			 * We may need to wait for an extra response if the
 			 * I/O request is split in 2
 			 */
-			if (!blkif_completion(&id, rinfo, bret))
+			if (!blkif_completion(&id, rinfo, &bret))
 				continue;
 		}
 
 		if (add_id_to_freelist(rinfo, id)) {
 			WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n",
-			     info->gd->disk_name, op_name(bret->operation), id);
+			     info->gd->disk_name, op_name(bret.operation), id);
 			continue;
 		}
 
-		if (bret->status == BLKIF_RSP_OKAY)
+		if (bret.status == BLKIF_RSP_OKAY)
 			blkif_req(req)->error = BLK_STS_OK;
 		else
 			blkif_req(req)->error = BLK_STS_IOERR;
 
-		switch (bret->operation) {
+		switch (bret.operation) {
 		case BLKIF_OP_DISCARD:
-			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
-				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+
-					   info->gd->disk_name, op_name(bret->operation));
+				pr_warn_ratelimited("blkfront: %s: %s op failed\n",
+					   info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
@@ -1625,15 +1658,15 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
-			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+			if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
-				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+				pr_warn_ratelimited("blkfront: %s: %s op failed\n",
-				       info->gd->disk_name, op_name(bret->operation));
+				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
-			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
+			if (unlikely(bret.status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
-				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
+				pr_warn_ratelimited("blkfront: %s: empty %s op failed\n",
-				       info->gd->disk_name, op_name(bret->operation));
+				       info->gd->disk_name, op_name(bret.operation));
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
 			if (unlikely(blkif_req(req)->error)) {
@@ -1646,9 +1679,10 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			fallthrough;
 		case BLKIF_OP_READ:
 		case BLKIF_OP_WRITE:
-			if (unlikely(bret->status != BLKIF_RSP_OKAY))
+			if (unlikely(bret.status != BLKIF_RSP_OKAY))
-				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
+				dev_dbg_ratelimited(&info->xbdev->dev,
-					"request: %x\n", bret->status);
+					"Bad return from blkdev data request: %#x\n",
+					bret.status);
 
 			break;
 		default:
@@ -1674,6 +1708,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 
 	return IRQ_HANDLED;
+
+ err:
+	info->connected = BLKIF_STATE_ERROR;
+
+	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+
+	pr_alert("%s disabled for further use\n", info->gd->disk_name);
+	return IRQ_HANDLED;
 }
 
 

drivers/firmware/arm_scmi/scmi_pm_domain.c

@@ -112,9 +112,7 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 	scmi_pd_data->domains = domains;
 	scmi_pd_data->num_domains = num_domains;
 
-	of_genpd_add_provider_onecell(np, scmi_pd_data);
+	return of_genpd_add_provider_onecell(np, scmi_pd_data);
-
-	return 0;
 }
 
 static const struct scmi_device_id scmi_id_table[] = {

drivers/firmware/smccc/soc_id.c

@@ -50,7 +50,7 @@ static int __init smccc_soc_init(void)
 	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 			     ARM_SMCCC_ARCH_SOC_ID, &res);
 
-	if (res.a0 == SMCCC_RET_NOT_SUPPORTED) {
+	if ((int)res.a0 == SMCCC_RET_NOT_SUPPORTED) {
 		pr_info("ARCH_SOC_ID not implemented, skipping ....\n");
 		return 0;
 	}

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -137,6 +137,11 @@ MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin");
 #define mmTCP_CHAN_STEER_5_ARCT								0x0b0c
 #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX							0
 
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir                0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir_BASE_IDX       1
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir                0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir_BASE_IDX       1
+
 enum ta_ras_gfx_subblock {
 	/*CPC*/
 	TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -4147,19 +4152,38 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
 
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
-	uint64_t clock;
+	uint64_t clock, clock_lo, clock_hi, hi_check;
 
-	amdgpu_gfx_off_ctrl(adev, false);
+	switch (adev->asic_type) {
-	mutex_lock(&adev->gfx.gpu_clock_mutex);
+	case CHIP_RENOIR:
-	if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
+		preempt_disable();
-		clock = gfx_v9_0_kiq_read_clock(adev);
+		clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
-	} else {
+		clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
-		WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+		hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
-		clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+		/* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
-			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+		 * roughly every 42 seconds.
+		 */
+		if (hi_check != clock_hi) {
+			clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
+			clock_hi = hi_check;
+		}
+		preempt_enable();
+		clock = clock_lo | (clock_hi << 32ULL);
+		break;
+	default:
+		amdgpu_gfx_off_ctrl(adev, false);
+		mutex_lock(&adev->gfx.gpu_clock_mutex);
+		if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
+			clock = gfx_v9_0_kiq_read_clock(adev);
+		} else {
+			WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+			clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+				((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+		}
+		mutex_unlock(&adev->gfx.gpu_clock_mutex);
+		amdgpu_gfx_off_ctrl(adev, true);
+		break;
 	}
-	mutex_unlock(&adev->gfx.gpu_clock_mutex);
-	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1963,8 +1963,8 @@ static int dm_resume(void *handle)
 
 		for (i = 0; i < dc_state->stream_count; i++) {
 			dc_state->streams[i]->mode_changed = true;
-			for (j = 0; j < dc_state->stream_status->plane_count; j++) {
+			for (j = 0; j < dc_state->stream_status[i].plane_count; j++) {
-				dc_state->stream_status->plane_states[j]->update_flags.raw
+				dc_state->stream_status[i].plane_states[j]->update_flags.raw
 					= 0xffffffff;
 			}
 		}

drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c

@@ -207,11 +207,13 @@ int
 gm200_acr_wpr_parse(struct nvkm_acr *acr)
 {
 	const struct wpr_header *hdr = (void *)acr->wpr_fw->data;
+	struct nvkm_acr_lsfw *lsfw;
 
 	while (hdr->falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID) {
 		wpr_header_dump(&acr->subdev, hdr);
-		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
+		lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id);
-			return -ENOMEM;
+		if (IS_ERR(lsfw))
+			return PTR_ERR(lsfw);
 	}
 
 	return 0;

drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c

@@ -161,11 +161,13 @@ int
 gp102_acr_wpr_parse(struct nvkm_acr *acr)
 {
 	const struct wpr_header_v1 *hdr = (void *)acr->wpr_fw->data;
+	struct nvkm_acr_lsfw *lsfw;
 
 	while (hdr->falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID) {
 		wpr_header_v1_dump(&acr->subdev, hdr);
-		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
+		lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id);
-			return -ENOMEM;
+		if (IS_ERR(lsfw))
+			return PTR_ERR(lsfw);
 	}
 
 	return 0;

drivers/gpu/drm/vc4/vc4_bo.c

@@ -389,7 +389,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	bo->madv = VC4_MADV_WILLNEED;
 	refcount_set(&bo->usecnt, 0);

drivers/hid/wacom_wac.c

@@ -2578,6 +2578,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
 		return;
 
 	switch (equivalent_usage) {
+	case HID_DG_CONFIDENCE:
+		wacom_wac->hid_data.confidence = value;
+		break;
 	case HID_GD_X:
 		wacom_wac->hid_data.x = value;
 		break;
@@ -2610,7 +2613,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
 	}
 
 	if (usage->usage_index + 1 == field->report_count) {
-		if (equivalent_usage == wacom_wac->hid_data.last_slot_field)
+		if (equivalent_usage == wacom_wac->hid_data.last_slot_field &&
+		    wacom_wac->hid_data.confidence)
 			wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
 	}
 }
@@ -2625,6 +2629,8 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
 
 	wacom_wac->is_invalid_bt_frame = false;
 
+	hid_data->confidence = true;
+
 	for (i = 0; i < report->maxfield; i++) {
 		struct hid_field *field = report->field[i];
 		int j;

drivers/hid/wacom_wac.h

@@ -300,6 +300,7 @@ struct hid_data {
 	bool tipswitch;
 	bool barrelswitch;
 	bool barrelswitch2;
+	bool confidence;
 	int x;
 	int y;
 	int pressure;

drivers/iommu/amd/iommu_v2.c

@@ -927,10 +927,8 @@ static int __init amd_iommu_v2_init(void)
 {
 	int ret;
 
-	pr_info("AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de>\n");
-
 	if (!amd_iommu_v2_supported()) {
-		pr_info("AMD IOMMUv2 functionality not available on this system\n");
+		pr_info("AMD IOMMUv2 functionality not available on this system - This is not a bug.\n");
 		/*
 		 * Load anyway to provide the symbols to other modules
 		 * which may use AMD IOMMUv2 optionally.
@@ -947,6 +945,8 @@ static int __init amd_iommu_v2_init(void)
 
 	amd_iommu_register_ppr_notifier(&ppr_nb);
 
+	pr_info("AMD IOMMUv2 loaded and initialized\n");
+
 	return 0;
 
 out:

drivers/media/cec/core/cec-adap.c

@@ -1199,6 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap,
 			if (abort)
 				dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT;
 			msg->flags = dst->flags;
+			msg->sequence = dst->sequence;
 			/* Remove it from the wait_queue */
 			list_del_init(&data->list);
 

drivers/mmc/host/sdhci-esdhc-imx.c

@@ -263,7 +263,6 @@ static struct esdhc_soc_data usdhc_imx8qxp_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
 			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200
 			| ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES
-			| ESDHC_FLAG_CQHCI
 			| ESDHC_FLAG_STATE_LOST_IN_LPMODE
 			| ESDHC_FLAG_CLK_RATE_LOST_IN_PM_RUNTIME,
 };
@@ -272,7 +271,6 @@ static struct esdhc_soc_data usdhc_imx8mm_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
 			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200
 			| ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES
-			| ESDHC_FLAG_CQHCI
 			| ESDHC_FLAG_STATE_LOST_IN_LPMODE,
 };
 

drivers/mmc/host/sdhci.c

@@ -774,7 +774,19 @@ static void sdhci_adma_table_pre(struct sdhci_host *host,
 			len -= offset;
 		}
 
-		BUG_ON(len > 65536);
+		/*
+		 * The block layer forces a minimum segment size of PAGE_SIZE,
+		 * so 'len' can be too big here if PAGE_SIZE >= 64KiB. Write
+		 * multiple descriptors, noting that the ADMA table is sized
+		 * for 4KiB chunks anyway, so it will be big enough.
+		 */
+		while (len > host->max_adma) {
+			int n = 32 * 1024; /* 32KiB*/
+
+			__sdhci_adma_write_desc(host, &desc, addr, n, ADMA2_TRAN_VALID);
+			addr += n;
+			len -= n;
+		}
 
 		/* tran, valid */
 		if (len)
@@ -3955,6 +3967,7 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 	 * descriptor for each segment, plus 1 for a nop end descriptor.
 	 */
 	host->adma_table_cnt = SDHCI_MAX_SEGS * 2 + 1;
+	host->max_adma = 65536;
 
 	return host;
 }
@@ -4618,10 +4631,12 @@ int sdhci_setup_host(struct sdhci_host *host)
 	 * be larger than 64 KiB though.
 	 */
 	if (host->flags & SDHCI_USE_ADMA) {
-		if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC)
+		if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC) {
+			host->max_adma = 65532; /* 32-bit alignment */
 			mmc->max_seg_size = 65535;
-		else
+		} else {
 			mmc->max_seg_size = 65536;
+		}
 	} else {
 		mmc->max_seg_size = mmc->max_req_size;
 	}

drivers/mmc/host/sdhci.h

@@ -339,7 +339,8 @@ struct sdhci_adma2_64_desc {
 
 /*
  * Maximum segments assuming a 512KiB maximum requisition size and a minimum
- * 4KiB page size.
+ * 4KiB page size. Note this also allows enough for multiple descriptors in
+ * case of PAGE_SIZE >= 64KiB.
  */
 #define SDHCI_MAX_SEGS		128
 
@@ -541,6 +542,7 @@ struct sdhci_host {
 	unsigned int blocks;	/* remaining PIO blocks */
 
 	int sg_count;		/* Mapped sg entries */
+	int max_adma;		/* Max. length in ADMA descriptor */
 
 	void *adma_table;	/* ADMA descriptor table */
 	void *align_buffer;	/* Bounce buffer */

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

@@ -679,9 +679,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	roundup_size = ilog2(roundup_size);
 
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) {
-		tc_valid[i] = !!(hdev->hw_tc_map & BIT(i));
+		tc_valid[i] = 1;
 		tc_size[i] = roundup_size;
-		tc_offset[i] = rss_size * i;
+		tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0;
 	}
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false);

drivers/net/ethernet/intel/iavf/iavf_ethtool.c

@@ -719,12 +719,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
  *
  * Change the ITR settings for a specific queue.
  **/
-static void iavf_set_itr_per_queue(struct iavf_adapter *adapter,
+static int iavf_set_itr_per_queue(struct iavf_adapter *adapter,
-				   struct ethtool_coalesce *ec, int queue)
+				  struct ethtool_coalesce *ec, int queue)
 {
 	struct iavf_ring *rx_ring = &adapter->rx_rings[queue];
 	struct iavf_ring *tx_ring = &adapter->tx_rings[queue];
 	struct iavf_q_vector *q_vector;
+	u16 itr_setting;
+
+	itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+
+	if (ec->rx_coalesce_usecs != itr_setting &&
+	    ec->use_adaptive_rx_coalesce) {
+		netif_info(adapter, drv, adapter->netdev,
+			   "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n");
+		return -EINVAL;
+	}
+
+	itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+
+	if (ec->tx_coalesce_usecs != itr_setting &&
+	    ec->use_adaptive_tx_coalesce) {
+		netif_info(adapter, drv, adapter->netdev,
+			   "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n");
+		return -EINVAL;
+	}
 
 	rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
 	tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
@@ -747,6 +766,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter,
 	 * the Tx and Rx ITR values based on the values we have entered
 	 * into the q_vector, no need to write the values now.
 	 */
+	return 0;
 }
 
 /**
@@ -788,9 +808,11 @@ static int __iavf_set_coalesce(struct net_device *netdev,
 	 */
 	if (queue < 0) {
 		for (i = 0; i < adapter->num_active_queues; i++)
-			iavf_set_itr_per_queue(adapter, ec, i);
+			if (iavf_set_itr_per_queue(adapter, ec, i))
+				return -EINVAL;
 	} else if (queue < adapter->num_active_queues) {
-		iavf_set_itr_per_queue(adapter, ec, queue);
+		if (iavf_set_itr_per_queue(adapter, ec, queue))
+			return -EINVAL;
 	} else {
 		netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n",
 			   adapter->num_active_queues - 1);

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -83,8 +83,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->rx_rings)
 		goto err_rings;
 
-	/* XDP will have vsi->alloc_txq Tx queues as well, so double the size */
+	/* txq_map needs to have enough space to track both Tx (stack) rings
-	vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq),
+	 * and XDP rings; at this point vsi->num_xdp_txq might not be set,
+	 * so use num_possible_cpus() as we want to always provide XDP ring
+	 * per CPU, regardless of queue count settings from user that might
+	 * have come from ethtool's set_channels() callback;
+	 */
+	vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()),
 				    sizeof(*vsi->txq_map), GFP_KERNEL);
 
 	if (!vsi->txq_map)

drivers/net/ethernet/intel/ice/ice_main.c

@@ -2397,7 +2397,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 			ice_stat_str(status));
 		goto clear_xdp_rings;
 	}
-	ice_vsi_assign_bpf_prog(vsi, prog);
+
+	/* assign the prog only when it's not already present on VSI;
+	 * this flow is a subject of both ethtool -L and ndo_bpf flows;
+	 * VSI rebuild that happens under ethtool -L can expose us to
+	 * the bpf_prog refcount issues as we would be swapping same
+	 * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put
+	 * on it as it would be treated as an 'old_prog'; for ndo_bpf
+	 * this is not harmful as dev_xdp_install bumps the refcount
+	 * before calling the op exposed by the driver;
+	 */
+	if (!ice_is_xdp_ena_vsi(vsi))
+		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
 clear_xdp_rings:
@@ -2527,6 +2538,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
 	} else {
+		/* safe to call even when prog == vsi->xdp_prog as
+		 * dev_xdp_install in net/core/dev.c incremented prog's
+		 * refcount so corresponding bpf_prog_put won't cause
+		 * underflow
+		 */
 		ice_vsi_assign_bpf_prog(vsi, prog);
 	}
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -8032,7 +8032,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	if (likely(napi_complete_done(napi, work_done)))
 		igb_ring_irq_enable(q_vector);
 
-	return min(work_done, budget - 1);
+	return work_done;
 }
 
 /**

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -4652,11 +4652,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 		mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8);
 	}
 
+	if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) {
+		netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n",
+			   mtu, (int)MVPP2_MAX_RX_BUF_SIZE);
+		return -EINVAL;
+	}
+
 	if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) {
-		if (port->xdp_prog) {
-			netdev_err(dev, "Jumbo frames are not supported with XDP\n");
-			return -EINVAL;
-		}
 		if (priv->percpu_pools) {
 			netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu);
 			mvpp2_bm_switch_buffers(priv, false);
@@ -4942,8 +4944,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf)
 	bool running = netif_running(port->dev);
 	bool reset = !prog != !port->xdp_prog;
 
-	if (port->dev->mtu > ETH_DATA_LEN) {
+	if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) {
-		NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled");
+		NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP");
 		return -EOPNOTSUPP;
 	}
 

drivers/net/ethernet/marvell/prestera/prestera_switchdev.c

@@ -439,8 +439,8 @@ static int prestera_port_bridge_join(struct prestera_port *port,
 
 	br_port = prestera_bridge_port_add(bridge, port->dev);
 	if (IS_ERR(br_port)) {
-		err = PTR_ERR(br_port);
+		prestera_bridge_put(bridge);
-		goto err_brport_create;
+		return PTR_ERR(br_port);
 	}
 
 	if (bridge->vlan_enabled)
@@ -454,8 +454,6 @@ static int prestera_port_bridge_join(struct prestera_port *port,
 
 err_port_join:
 	prestera_bridge_port_put(br_port);
-err_brport_create:
-	prestera_bridge_put(bridge);
 	return err;
 }
 

drivers/net/ethernet/mellanox/mlxsw/minimal.c

@@ -234,6 +234,7 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port)
 static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
 				   u8 *last_module)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core);
 	u8 module, width;
 	int err;
 
@@ -249,6 +250,9 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
 	if (module == *last_module)
 		return 0;
 	*last_module = module;
+
+	if (WARN_ON_ONCE(module >= max_ports))
+		return -EINVAL;
 	mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports;
 
 	return 0;

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -2052,9 +2052,14 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	enum mlxsw_reg_pude_oper_status status;
+	unsigned int max_ports;
 	u8 local_port;
 
+	max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
+
+	if (WARN_ON_ONCE(!local_port || local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port)
 		return;

drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c

@@ -568,10 +568,13 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 				 u8 domain_number, u16 sequence_id,
 				 u64 timestamp)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp1_ptp_key key;
 	u8 types;
 
+	if (WARN_ON_ONCE(local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port)
 		return;

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -2177,6 +2177,7 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 						   char *rauhtd_pl,
 						   int ent_index)
 {
+	u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
 	struct net_device *dev;
 	struct neighbour *n;
 	__be32 dipn;
@@ -2185,6 +2186,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip);
 
+	if (WARN_ON_ONCE(rif >= max_rifs))
+		return;
 	if (!mlxsw_sp->router->rifs[rif]) {
 		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n");
 		return;

drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c

@@ -2410,6 +2410,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 					    char *sfn_pl, int rec_index,
 					    bool adding)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	struct mlxsw_sp_bridge_device *bridge_device;
 	struct mlxsw_sp_bridge_port *bridge_port;
@@ -2422,6 +2423,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port);
+
+	if (WARN_ON_ONCE(local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
 		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n");

drivers/net/ethernet/microchip/lan743x_main.c

@@ -922,8 +922,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter)
 }
 
 static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter,
-					   u8 duplex, u16 local_adv,
+					   u16 local_adv, u16 remote_adv)
-					   u16 remote_adv)
 {
 	struct lan743x_phy *phy = &adapter->phy;
 	u8 cap;
@@ -951,7 +950,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 	phy_print_status(phydev);
 	if (phydev->state == PHY_RUNNING) {
-		struct ethtool_link_ksettings ksettings;
 		int remote_advertisement = 0;
 		int local_advertisement = 0;
 
@@ -988,18 +986,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 		}
 		lan743x_csr_write(adapter, MAC_CR, data);
 
-		memset(&ksettings, 0, sizeof(ksettings));
-		phy_ethtool_get_link_ksettings(netdev, &ksettings);
 		local_advertisement =
 			linkmode_adv_to_mii_adv_t(phydev->advertising);
 		remote_advertisement =
 			linkmode_adv_to_mii_adv_t(phydev->lp_advertising);
 
-		lan743x_phy_update_flowcontrol(adapter,
+		lan743x_phy_update_flowcontrol(adapter, local_advertisement,
-					       ksettings.base.duplex,
-					       local_advertisement,
 					       remote_advertisement);
-		lan743x_ptp_update_latency(adapter, ksettings.base.speed);
+		lan743x_ptp_update_latency(adapter, phydev->speed);
 	}
 }
 

drivers/net/ethernet/mscc/ocelot.c

@@ -811,12 +811,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
-	case HWTSTAMP_FILTER_ALL:
-	case HWTSTAMP_FILTER_SOME:
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
@@ -935,7 +929,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) |
 			 BIT(HWTSTAMP_TX_ONESTEP_SYNC);
-	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
 
 	return 0;
 }

drivers/net/ethernet/netronome/nfp/nfp_net.h

@@ -557,7 +557,6 @@ struct nfp_net_dp {
  * @exn_name:           Name for Exception interrupt
  * @shared_handler:     Handler for shared interrupts
  * @shared_name:        Name for shared interrupt
- * @me_freq_mhz:        ME clock_freq (MHz)
  * @reconfig_lock:	Protects @reconfig_posted, @reconfig_timer_active,
  *			@reconfig_sync_present and HW reconfiguration request
  *			regs/machinery from async requests (sync must take
@@ -640,8 +639,6 @@ struct nfp_net {
 	irq_handler_t shared_handler;
 	char shared_name[IFNAMSIZ + 8];
 
-	u32 me_freq_mhz;
-
 	bool link_up;
 	spinlock_t link_status_lock;
 

drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c

@@ -1347,7 +1347,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 	 * ME timestamp ticks.  There are 16 ME clock cycles for each timestamp
 	 * count.
 	 */
-	factor = nn->me_freq_mhz / 16;
+	factor = nn->tlv_caps.me_freq_mhz / 16;
 
 	/* Each pair of (usecs, max_frames) fields specifies that interrupts
 	 * should be coalesced until

drivers/net/ethernet/stmicro/stmmac/stmmac.h

@@ -258,6 +258,7 @@ int stmmac_mdio_register(struct net_device *ndev);
 int stmmac_mdio_reset(struct mii_bus *mii);
 void stmmac_set_ethtool_ops(struct net_device *netdev);
 
+int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags);
 void stmmac_ptp_register(struct stmmac_priv *priv);
 void stmmac_ptp_unregister(struct stmmac_priv *priv);
 int stmmac_resume(struct device *dev);

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -47,6 +47,13 @@
 #include "dwxgmac2.h"
 #include "hwif.h"
 
+/* As long as the interface is active, we keep the timestamping counter enabled
+ * with fine resolution and binary rollover. This avoid non-monotonic behavior
+ * (clock jumps) when changing timestamping settings at runtime.
+ */
+#define STMMAC_HWTS_ACTIVE	(PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \
+				 PTP_TCR_TSCTRLSSR)
+
 #define	STMMAC_ALIGN(x)		ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
@@ -508,8 +515,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
-	struct timespec64 now;
-	u64 temp = 0;
 	u32 ptp_v2 = 0;
 	u32 tstamp_all = 0;
 	u32 ptp_over_ipv4_udp = 0;
@@ -518,11 +523,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	u32 snap_type_sel = 0;
 	u32 ts_master_en = 0;
 	u32 ts_event_en = 0;
-	u32 sec_inc = 0;
-	u32 value = 0;
-	bool xmac;
-
-	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
 		netdev_alert(priv->dev, "No support for HW time stamping\n");
@@ -684,42 +684,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1);
 	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
 
-	if (!priv->hwts_tx_en && !priv->hwts_rx_en)
+	priv->systime_flags = STMMAC_HWTS_ACTIVE;
-		stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0);
-	else {
-		value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR |
-			 tstamp_all | ptp_v2 | ptp_over_ethernet |
-			 ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en |
-			 ts_master_en | snap_type_sel);
-		stmmac_config_hw_tstamping(priv, priv->ptpaddr, value);
 
-		/* program Sub Second Increment reg */
+	if (priv->hwts_tx_en || priv->hwts_rx_en) {
-		stmmac_config_sub_second_increment(priv,
+		priv->systime_flags |= tstamp_all | ptp_v2 |
-				priv->ptpaddr, priv->plat->clk_ptp_rate,
+				       ptp_over_ethernet | ptp_over_ipv6_udp |
-				xmac, &sec_inc);
+				       ptp_over_ipv4_udp | ts_event_en |
-		temp = div_u64(1000000000ULL, sec_inc);
+				       ts_master_en | snap_type_sel;
-
-		/* Store sub second increment and flags for later use */
-		priv->sub_second_inc = sec_inc;
-		priv->systime_flags = value;
-
-		/* calculate default added value:
-		 * formula is :
-		 * addend = (2^32)/freq_div_ratio;
-		 * where, freq_div_ratio = 1e9ns/sec_inc
-		 */
-		temp = (u64)(temp << 32);
-		priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate);
-		stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend);
-
-		/* initialize system time */
-		ktime_get_real_ts64(&now);
-
-		/* lower 32 bits of tv_sec are safe until y2106 */
-		stmmac_init_systime(priv, priv->ptpaddr,
-				(u32)now.tv_sec, now.tv_nsec);
 	}
 
+	stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags);
+
 	memcpy(&priv->tstamp_config, &config, sizeof(config));
 
 	return copy_to_user(ifr->ifr_data, &config,
@@ -747,6 +722,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 			    sizeof(*config)) ? -EFAULT : 0;
 }
 
+/**
+ * stmmac_init_tstamp_counter - init hardware timestamping counter
+ * @priv: driver private structure
+ * @systime_flags: timestamping flags
+ * Description:
+ * Initialize hardware counter for packet timestamping.
+ * This is valid as long as the interface is open and not suspended.
+ * Will be rerun after resuming from suspend, case in which the timestamping
+ * flags updated by stmmac_hwtstamp_set() also need to be restored.
+ */
+int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
+{
+	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+	struct timespec64 now;
+	u32 sec_inc = 0;
+	u64 temp = 0;
+	int ret;
+
+	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
+		return -EOPNOTSUPP;
+
+	ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+	if (ret < 0) {
+		netdev_warn(priv->dev,
+			    "failed to enable PTP reference clock: %pe\n",
+			    ERR_PTR(ret));
+		return ret;
+	}
+
+	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
+	priv->systime_flags = systime_flags;
+
+	/* program Sub Second Increment reg */
+	stmmac_config_sub_second_increment(priv, priv->ptpaddr,
+					   priv->plat->clk_ptp_rate,
+					   xmac, &sec_inc);
+	temp = div_u64(1000000000ULL, sec_inc);
+
+	/* Store sub second increment for later use */
+	priv->sub_second_inc = sec_inc;
+
+	/* calculate default added value:
+	 * formula is :
+	 * addend = (2^32)/freq_div_ratio;
+	 * where, freq_div_ratio = 1e9ns/sec_inc
+	 */
+	temp = (u64)(temp << 32);
+	priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate);
+	stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend);
+
+	/* initialize system time */
+	ktime_get_real_ts64(&now);
+
+	/* lower 32 bits of tv_sec are safe until y2106 */
+	stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter);
+
 /**
  * stmmac_init_ptp - init PTP
  * @priv: driver private structure
@@ -757,9 +792,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 static int stmmac_init_ptp(struct stmmac_priv *priv)
 {
 	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+	int ret;
 
-	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
+	ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE);
-		return -EOPNOTSUPP;
+	if (ret)
+		return ret;
 
 	priv->adv_ts = 0;
 	/* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */
@@ -2721,10 +2758,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	stmmac_mmc_setup(priv);
 
 	if (init_ptp) {
-		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
-		if (ret < 0)
-			netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
-
 		ret = stmmac_init_ptp(priv);
 		if (ret == -EOPNOTSUPP)
 			netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -5238,7 +5271,6 @@ int stmmac_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	u32 chan;
-	int ret;
 
 	if (!ndev || !netif_running(ndev))
 		return 0;
@@ -5280,13 +5312,6 @@ int stmmac_suspend(struct device *dev)
 
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
-		/* Disable clock in case of PWM is off */
-		clk_disable_unprepare(priv->plat->clk_ptp_ref);
-		ret = pm_runtime_force_suspend(dev);
-		if (ret) {
-			mutex_unlock(&priv->lock);
-			return ret;
-		}
 	}
 	mutex_unlock(&priv->lock);
 
@@ -5351,12 +5376,6 @@ int stmmac_resume(struct device *dev)
 		priv->irq_wake = 0;
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
-		/* enable the clk previously disabled */
-		ret = pm_runtime_force_resume(dev);
-		if (ret)
-			return ret;
-		if (priv->plat->clk_ptp_ref)
-			clk_prepare_enable(priv->plat->clk_ptp_ref);
 		/* reset the phy so that it's ready */
 		if (priv->mii)
 			stmmac_mdio_reset(priv->mii);

drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c

@@ -9,6 +9,7 @@
 *******************************************************************************/
 
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -778,9 +779,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
 	return stmmac_bus_clks_config(priv, true);
 }
 
+static int __maybe_unused stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	if (!netif_running(ndev))
+		return 0;
+
+	if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+		/* Disable clock in case of PWM is off */
+		clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+		ret = pm_runtime_force_suspend(dev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	if (!netif_running(ndev))
+		return 0;
+
+	if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+		/* enable the clk previously disabled */
+		ret = pm_runtime_force_resume(dev);
+		if (ret)
+			return ret;
+
+		stmmac_init_tstamp_counter(priv, priv->systime_flags);
+	}
+
+	return 0;
+}
+
 const struct dev_pm_ops stmmac_pltfr_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
 	SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
 };
 EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
 

drivers/net/mdio/mdio-aspeed.c

@@ -61,6 +61,13 @@ static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum)
 
 	iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL);
 
+	rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl,
+				!(ctrl & ASPEED_MDIO_CTRL_FIRE),
+				ASPEED_MDIO_INTERVAL_US,
+				ASPEED_MDIO_TIMEOUT_US);
+	if (rc < 0)
+		return rc;
+
 	rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data,
 				data & ASPEED_MDIO_DATA_IDLE,
 				ASPEED_MDIO_INTERVAL_US,

drivers/net/phy/phylink.c

@@ -644,6 +644,7 @@ static void phylink_resolve(struct work_struct *w)
 	struct phylink_link_state link_state;
 	struct net_device *ndev = pl->netdev;
 	bool mac_config = false;
+	bool retrigger = false;
 	bool cur_link_state;
 
 	mutex_lock(&pl->state_mutex);
@@ -657,6 +658,7 @@ static void phylink_resolve(struct work_struct *w)
 		link_state.link = false;
 	} else if (pl->mac_link_dropped) {
 		link_state.link = false;
+		retrigger = true;
 	} else {
 		switch (pl->cur_link_an_mode) {
 		case MLO_AN_PHY:
@@ -673,6 +675,19 @@ static void phylink_resolve(struct work_struct *w)
 		case MLO_AN_INBAND:
 			phylink_mac_pcs_get_state(pl, &link_state);
 
+			/* The PCS may have a latching link-fail indicator.
+			 * If the link was up, bring the link down and
+			 * re-trigger the resolve. Otherwise, re-read the
+			 * PCS state to get the current status of the link.
+			 */
+			if (!link_state.link) {
+				if (cur_link_state)
+					retrigger = true;
+				else
+					phylink_mac_pcs_get_state(pl,
+								  &link_state);
+			}
+
 			/* If we have a phy, the "up" state is the union of
 			 * both the PHY and the MAC */
 			if (pl->phydev)
@@ -680,6 +695,15 @@ static void phylink_resolve(struct work_struct *w)
 
 			/* Only update if the PHY link is up */
 			if (pl->phydev && pl->phy_state.link) {
+				/* If the interface has changed, force a
+				 * link down event if the link isn't already
+				 * down, and re-resolve.
+				 */
+				if (link_state.interface !=
+				    pl->phy_state.interface) {
+					retrigger = true;
+					link_state.link = false;
+				}
 				link_state.interface = pl->phy_state.interface;
 
 				/* If we have a PHY, we need to update with
@@ -721,7 +745,7 @@ static void phylink_resolve(struct work_struct *w)
 		else
 			phylink_link_up(pl, link_state);
 	}
-	if (!link_state.link && pl->mac_link_dropped) {
+	if (!link_state.link && retrigger) {
 		pl->mac_link_dropped = false;
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}

drivers/net/xen-netfront.c

@@ -126,21 +126,17 @@ struct netfront_queue {
 
 	/*
 	 * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
-	 * are linked from tx_skb_freelist through skb_entry.link.
+	 * are linked from tx_skb_freelist through tx_link.
-	 *
-	 *  NB. Freelist index entries are always going to be less than
-	 *  PAGE_OFFSET, whereas pointers to skbs will always be equal or
-	 *  greater than PAGE_OFFSET: we use this property to distinguish
-	 *  them.
 	 */
-	union skb_entry {
+	struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
-		struct sk_buff *skb;
+	unsigned short tx_link[NET_TX_RING_SIZE];
-		unsigned long link;
+#define TX_LINK_NONE 0xffff
-	} tx_skbs[NET_TX_RING_SIZE];
+#define TX_PENDING   0xfffe
 	grant_ref_t gref_tx_head;
 	grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
 	struct page *grant_tx_page[NET_TX_RING_SIZE];
 	unsigned tx_skb_freelist;
+	unsigned int tx_pend_queue;
 
 	spinlock_t   rx_lock ____cacheline_aligned_in_smp;
 	struct xen_netif_rx_front_ring rx;
@@ -173,6 +169,9 @@ struct netfront_info {
 	bool netback_has_xdp_headroom;
 	bool netfront_xdp_enabled;
 
+	/* Is device behaving sane? */
+	bool broken;
+
 	atomic_t rx_gso_checksum_fixup;
 };
 
@@ -181,33 +180,25 @@ struct netfront_rx_info {
 	struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
 };
 
-static void skb_entry_set_link(union skb_entry *list, unsigned short id)
-{
-	list->link = id;
-}
-
-static int skb_entry_is_link(const union skb_entry *list)
-{
-	BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
-	return (unsigned long)list->skb < PAGE_OFFSET;
-}
-
 /*
  * Access macros for acquiring freeing slots in tx_skbs[].
  */
 
-static void add_id_to_freelist(unsigned *head, union skb_entry *list,
+static void add_id_to_list(unsigned *head, unsigned short *list,
-			       unsigned short id)
+			   unsigned short id)
 {
-	skb_entry_set_link(&list[id], *head);
+	list[id] = *head;
 	*head = id;
 }
 
-static unsigned short get_id_from_freelist(unsigned *head,
+static unsigned short get_id_from_list(unsigned *head, unsigned short *list)
-					   union skb_entry *list)
 {
 	unsigned int id = *head;
-	*head = list[id].link;
+
+	if (id != TX_LINK_NONE) {
+		*head = list[id];
+		list[id] = TX_LINK_NONE;
+	}
 	return id;
 }
 
@@ -363,7 +354,7 @@ static int xennet_open(struct net_device *dev)
 	unsigned int i = 0;
 	struct netfront_queue *queue = NULL;
 
-	if (!np->queues)
+	if (!np->queues || np->broken)
 		return -ENODEV;
 
 	for (i = 0; i < num_queues; ++i) {
@@ -391,27 +382,47 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	unsigned short id;
 	struct sk_buff *skb;
 	bool more_to_do;
+	const struct device *dev = &queue->info->netdev->dev;
 
 	BUG_ON(!netif_carrier_ok(queue->info->netdev));
 
 	do {
 		prod = queue->tx.sring->rsp_prod;
+		if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) {
+			dev_alert(dev, "Illegal number of responses %u\n",
+				  prod - queue->tx.rsp_cons);
+			goto err;
+		}
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
 		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
-			struct xen_netif_tx_response *txrsp;
+			struct xen_netif_tx_response txrsp;
 
-			txrsp = RING_GET_RESPONSE(&queue->tx, cons);
+			RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
-			if (txrsp->status == XEN_NETIF_RSP_NULL)
+			if (txrsp.status == XEN_NETIF_RSP_NULL)
 				continue;
 
-			id  = txrsp->id;
+			id = txrsp.id;
-			skb = queue->tx_skbs[id].skb;
+			if (id >= RING_SIZE(&queue->tx)) {
+				dev_alert(dev,
+					  "Response has incorrect id (%u)\n",
+					  id);
+				goto err;
+			}
+			if (queue->tx_link[id] != TX_PENDING) {
+				dev_alert(dev,
+					  "Response for inactive request\n");
+				goto err;
+			}
+
+			queue->tx_link[id] = TX_LINK_NONE;
+			skb = queue->tx_skbs[id];
+			queue->tx_skbs[id] = NULL;
 			if (unlikely(gnttab_query_foreign_access(
 				queue->grant_tx_ref[id]) != 0)) {
-				pr_alert("%s: warning -- grant still in use by backend domain\n",
+				dev_alert(dev,
-					 __func__);
+					  "Grant still in use by backend domain\n");
-				BUG();
+				goto err;
 			}
 			gnttab_end_foreign_access_ref(
 				queue->grant_tx_ref[id], GNTMAP_readonly);
@@ -419,7 +430,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 				&queue->gref_tx_head, queue->grant_tx_ref[id]);
 			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
 			queue->grant_tx_page[id] = NULL;
-			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
+			add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id);
 			dev_kfree_skb_irq(skb);
 		}
 
@@ -429,13 +440,20 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	} while (more_to_do);
 
 	xennet_maybe_wake_tx(queue);
+
+	return;
+
+ err:
+	queue->info->broken = true;
+	dev_alert(dev, "Disabled for further use\n");
 }
 
 struct xennet_gnttab_make_txreq {
 	struct netfront_queue *queue;
 	struct sk_buff *skb;
 	struct page *page;
-	struct xen_netif_tx_request *tx; /* Last request */
+	struct xen_netif_tx_request *tx;      /* Last request on ring page */
+	struct xen_netif_tx_request tx_local; /* Last request local copy*/
 	unsigned int size;
 };
 
@@ -451,7 +469,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
 	struct netfront_queue *queue = info->queue;
 	struct sk_buff *skb = info->skb;
 
-	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link);
 	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
@@ -459,34 +477,37 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
 	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 					gfn, GNTMAP_readonly);
 
-	queue->tx_skbs[id].skb = skb;
+	queue->tx_skbs[id] = skb;
 	queue->grant_tx_page[id] = page;
 	queue->grant_tx_ref[id] = ref;
 
-	tx->id = id;
+	info->tx_local.id = id;
-	tx->gref = ref;
+	info->tx_local.gref = ref;
-	tx->offset = offset;
+	info->tx_local.offset = offset;
-	tx->size = len;
+	info->tx_local.size = len;
-	tx->flags = 0;
+	info->tx_local.flags = 0;
+
+	*tx = info->tx_local;
+
+	/*
+	 * Put the request in the pending queue, it will be set to be pending
+	 * when the producer index is about to be raised.
+	 */
+	add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id);
 
 	info->tx = tx;
-	info->size += tx->size;
+	info->size += info->tx_local.size;
 }
 
 static struct xen_netif_tx_request *xennet_make_first_txreq(
-	struct netfront_queue *queue, struct sk_buff *skb,
+	struct xennet_gnttab_make_txreq *info,
-	struct page *page, unsigned int offset, unsigned int len)
+	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
+	info->size = 0;
-		.queue = queue,
-		.skb = skb,
-		.page = page,
-		.size = 0,
-	};
 
-	gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info);
+	gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info);
 
-	return info.tx;
+	return info->tx;
 }
 
 static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
@@ -499,35 +520,27 @@ static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
 	xennet_tx_setup_grant(gfn, offset, len, data);
 }
 
-static struct xen_netif_tx_request *xennet_make_txreqs(
+static void xennet_make_txreqs(
-	struct netfront_queue *queue, struct xen_netif_tx_request *tx,
+	struct xennet_gnttab_make_txreq *info,
-	struct sk_buff *skb, struct page *page,
+	struct page *page,
 	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
-		.queue = queue,
-		.skb = skb,
-		.tx = tx,
-	};
-
 	/* Skip unused frames from start of page */
 	page += offset >> PAGE_SHIFT;
 	offset &= ~PAGE_MASK;
 
 	while (len) {
-		info.page = page;
+		info->page = page;
-		info.size = 0;
+		info->size = 0;
 
 		gnttab_foreach_grant_in_range(page, offset, len,
 					      xennet_make_one_txreq,
-					      &info);
+					      info);
 
 		page++;
 		offset = 0;
-		len -= info.size;
+		len -= info->size;
 	}
-
-	return info.tx;
 }
 
 /*
@@ -574,19 +587,34 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return queue_idx;
 }
 
+static void xennet_mark_tx_pending(struct netfront_queue *queue)
+{
+	unsigned int i;
+
+	while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) !=
+	       TX_LINK_NONE)
+		queue->tx_link[i] = TX_PENDING;
+}
+
 static int xennet_xdp_xmit_one(struct net_device *dev,
 			       struct netfront_queue *queue,
 			       struct xdp_frame *xdpf)
 {
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
+	struct xennet_gnttab_make_txreq info = {
+		.queue = queue,
+		.skb = NULL,
+		.page = virt_to_page(xdpf->data),
+	};
 	int notify;
 
-	xennet_make_first_txreq(queue, NULL,
+	xennet_make_first_txreq(&info,
-				virt_to_page(xdpf->data),
 				offset_in_page(xdpf->data),
 				xdpf->len);
 
+	xennet_mark_tx_pending(queue);
+
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);
@@ -611,6 +639,8 @@ static int xennet_xdp_xmit(struct net_device *dev, int n,
 	int drops = 0;
 	int i, err;
 
+	if (unlikely(np->broken))
+		return -ENODEV;
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -640,7 +670,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 {
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
-	struct xen_netif_tx_request *tx, *first_tx;
+	struct xen_netif_tx_request *first_tx;
 	unsigned int i;
 	int notify;
 	int slots;
@@ -649,6 +679,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	unsigned int len;
 	unsigned long flags;
 	struct netfront_queue *queue = NULL;
+	struct xennet_gnttab_make_txreq info = { };
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u16 queue_index;
 	struct sk_buff *nskb;
@@ -656,6 +687,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	/* Drop the packet if no queues are set up */
 	if (num_queues < 1)
 		goto drop;
+	if (unlikely(np->broken))
+		goto drop;
 	/* Determine which queue to transmit this SKB on */
 	queue_index = skb_get_queue_mapping(skb);
 	queue = &np->queues[queue_index];
@@ -706,21 +739,24 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	}
 
 	/* First request for the linear area. */
-	first_tx = tx = xennet_make_first_txreq(queue, skb,
+	info.queue = queue;
-						page, offset, len);
+	info.skb = skb;
-	offset += tx->size;
+	info.page = page;
+	first_tx = xennet_make_first_txreq(&info, offset, len);
+	offset += info.tx_local.size;
 	if (offset == PAGE_SIZE) {
 		page++;
 		offset = 0;
 	}
-	len -= tx->size;
+	len -= info.tx_local.size;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		/* local packet? */
-		tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_csum_blank |
+				   XEN_NETTXF_data_validated;
 	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
 		/* remote but checksummed. */
-		tx->flags |= XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_data_validated;
 
 	/* Optional extra info after the first request. */
 	if (skb_shinfo(skb)->gso_size) {
@@ -729,7 +765,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 		gso = (struct xen_netif_extra_info *)
 			RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 
-		tx->flags |= XEN_NETTXF_extra_info;
+		first_tx->flags |= XEN_NETTXF_extra_info;
 
 		gso->u.gso.size = skb_shinfo(skb)->gso_size;
 		gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
@@ -743,12 +779,12 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	}
 
 	/* Requests for the rest of the linear area. */
-	tx = xennet_make_txreqs(queue, tx, skb, page, offset, len);
+	xennet_make_txreqs(&info, page, offset, len);
 
 	/* Requests for all the frags. */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		tx = xennet_make_txreqs(queue, tx, skb, skb_frag_page(frag),
+		xennet_make_txreqs(&info, skb_frag_page(frag),
 					skb_frag_off(frag),
 					skb_frag_size(frag));
 	}
@@ -759,6 +795,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
+	xennet_mark_tx_pending(queue);
+
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);
@@ -816,7 +854,7 @@ static int xennet_get_extras(struct netfront_queue *queue,
 			     RING_IDX rp)
 
 {
-	struct xen_netif_extra_info *extra;
+	struct xen_netif_extra_info extra;
 	struct device *dev = &queue->info->netdev->dev;
 	RING_IDX cons = queue->rx.rsp_cons;
 	int err = 0;
@@ -832,24 +870,22 @@ static int xennet_get_extras(struct netfront_queue *queue,
 			break;
 		}
 
-		extra = (struct xen_netif_extra_info *)
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &extra);
-			RING_GET_RESPONSE(&queue->rx, ++cons);
 
-		if (unlikely(!extra->type ||
+		if (unlikely(!extra.type ||
-			     extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
+			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			if (net_ratelimit())
 				dev_warn(dev, "Invalid extra type: %d\n",
-					extra->type);
+					 extra.type);
 			err = -EINVAL;
 		} else {
-			memcpy(&extras[extra->type - 1], extra,
+			extras[extra.type - 1] = extra;
-			       sizeof(*extra));
 		}
 
 		skb = xennet_get_rx_skb(queue, cons);
 		ref = xennet_get_rx_ref(queue, cons);
 		xennet_move_rx_slot(queue, skb, ref);
-	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
+	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
 	queue->rx.rsp_cons = cons;
 	return err;
@@ -907,7 +943,7 @@ static int xennet_get_responses(struct netfront_queue *queue,
 				struct sk_buff_head *list,
 				bool *need_xdp_flush)
 {
-	struct xen_netif_rx_response *rx = &rinfo->rx;
+	struct xen_netif_rx_response *rx = &rinfo->rx, rx_local;
 	int max = XEN_NETIF_NR_SLOTS_MIN + (rx->status <= RX_COPY_THRESHOLD);
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
@@ -991,7 +1027,8 @@ static int xennet_get_responses(struct netfront_queue *queue,
 			break;
 		}
 
-		rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+		RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local);
+		rx = &rx_local;
 		skb = xennet_get_rx_skb(queue, cons + slots);
 		ref = xennet_get_rx_ref(queue, cons + slots);
 		slots++;
@@ -1046,10 +1083,11 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 	struct sk_buff *nskb;
 
 	while ((nskb = __skb_dequeue(list))) {
-		struct xen_netif_rx_response *rx =
+		struct xen_netif_rx_response rx;
-			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &rx);
+
 		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
@@ -1064,7 +1102,7 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(nfrag),
-				rx->offset, rx->status, PAGE_SIZE);
+				rx.offset, rx.status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
 		kfree_skb(nskb);
@@ -1158,12 +1196,19 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 	skb_queue_head_init(&tmpq);
 
 	rp = queue->rx.sring->rsp_prod;
+	if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) {
+		dev_alert(&dev->dev, "Illegal number of responses %u\n",
+			  rp - queue->rx.rsp_cons);
+		queue->info->broken = true;
+		spin_unlock(&queue->rx_lock);
+		return 0;
+	}
 	rmb(); /* Ensure we see queued responses up to 'rp'. */
 
 	i = queue->rx.rsp_cons;
 	work_done = 0;
 	while ((i != rp) && (work_done < budget)) {
-		memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
+		RING_COPY_RESPONSE(&queue->rx, i, rx);
 		memset(extras, 0, sizeof(rinfo.extras));
 
 		err = xennet_get_responses(queue, &rinfo, rp, &tmpq,
@@ -1288,17 +1333,18 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue)
 
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		/* Skip over entries which are actually freelist references */
-		if (skb_entry_is_link(&queue->tx_skbs[i]))
+		if (!queue->tx_skbs[i])
 			continue;
 
-		skb = queue->tx_skbs[i].skb;
+		skb = queue->tx_skbs[i];
+		queue->tx_skbs[i] = NULL;
 		get_page(queue->grant_tx_page[i]);
 		gnttab_end_foreign_access(queue->grant_tx_ref[i],
 					  GNTMAP_readonly,
 					  (unsigned long)page_address(queue->grant_tx_page[i]));
 		queue->grant_tx_page[i] = NULL;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
-		add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
+		add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i);
 		dev_kfree_skb_irq(skb);
 	}
 }
@@ -1378,6 +1424,9 @@ static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
 	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	spin_lock_irqsave(&queue->tx_lock, flags);
 	xennet_tx_buf_gc(queue);
 	spin_unlock_irqrestore(&queue->tx_lock, flags);
@@ -1390,6 +1439,9 @@ static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
 	struct netfront_queue *queue = dev_id;
 	struct net_device *dev = queue->info->netdev;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	if (likely(netif_carrier_ok(dev) &&
 		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
 		napi_schedule(&queue->napi);
@@ -1411,6 +1463,10 @@ static void xennet_poll_controller(struct net_device *dev)
 	struct netfront_info *info = netdev_priv(dev);
 	unsigned int num_queues = dev->real_num_tx_queues;
 	unsigned int i;
+
+	if (info->broken)
+		return;
+
 	for (i = 0; i < num_queues; ++i)
 		xennet_interrupt(0, &info->queues[i]);
 }
@@ -1482,6 +1538,11 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
+	struct netfront_info *np = netdev_priv(dev);
+
+	if (np->broken)
+		return -ENODEV;
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return xennet_xdp_set(dev, xdp->prog, xdp->extack);
@@ -1859,13 +1920,15 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
 		 devid, queue->id);
 
-	/* Initialise tx_skbs as a free chain containing every entry. */
+	/* Initialise tx_skb_freelist as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
+	queue->tx_pend_queue = TX_LINK_NONE;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
-		skb_entry_set_link(&queue->tx_skbs[i], i+1);
+		queue->tx_link[i] = i + 1;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
 		queue->grant_tx_page[i] = NULL;
 	}
+	queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE;
 
 	/* Clear out rx_skbs */
 	for (i = 0; i < NET_RX_RING_SIZE; i++) {
@@ -2134,6 +2197,9 @@ static int talk_to_netback(struct xenbus_device *dev,
 	if (info->queues)
 		xennet_destroy_queues(info);
 
+	/* For the case of a reconnect reset the "broken" indicator. */
+	info->broken = false;
+
 	err = xennet_create_queues(info, &num_queues);
 	if (err < 0) {
 		xenbus_dev_fatal(dev, err, "creating queues");

drivers/nvme/target/io-cmd-file.c

@@ -8,6 +8,7 @@
 #include <linux/uio.h>
 #include <linux/falloc.h>
 #include <linux/file.h>
+#include <linux/fs.h>
 #include "nvmet.h"
 
 #define NVMET_MAX_MPOOL_BVEC		16
@@ -266,7 +267,8 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 
 	if (req->ns->buffered_io) {
 		if (likely(!req->f.mpool_alloc) &&
-				nvmet_file_execute_io(req, IOCB_NOWAIT))
+		    (req->ns->file->f_mode & FMODE_NOWAIT) &&
+		    nvmet_file_execute_io(req, IOCB_NOWAIT))
 			return;
 		nvmet_file_submit_buffered_io(req);
 	} else

drivers/nvme/target/tcp.c

@@ -688,10 +688,11 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
+	int left = NVME_TCP_DIGEST_LENGTH - cmd->offset;
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
 	struct kvec iov = {
 		.iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
-		.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
+		.iov_len = left
 	};
 	int ret;
 
@@ -705,6 +706,10 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 		return ret;
 
 	cmd->offset += ret;
+	left -= ret;
+
+	if (left)
+		return -EAGAIN;
 
 	if (queue->nvme_sq.sqhd_disabled) {
 		cmd->queue->snd_cmd = NULL;

drivers/pci/controller/pci-aardvark.c

@@ -306,11 +306,6 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg)
 	return readl(pcie->base + reg);
 }
 
-static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg)
-{
-	return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8);
-}
-
 static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie)
 {
 	u32 val;
@@ -384,16 +379,9 @@ static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie)
 
 static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 {
-	u32 reg;
-
 	if (!pcie->reset_gpio)
 		return;
 
-	/* PERST does not work for some cards when link training is enabled */
-	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
-	reg &= ~LINK_TRAINING_EN;
-	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
 	/* 10ms delay is needed for some cards */
 	dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
 	gpiod_set_value_cansleep(pcie->reset_gpio, 1);
@@ -401,53 +389,46 @@ static void advk_pcie_issue_perst(struct advk_pcie *pcie)
 	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
 }
 
-static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen)
+static void advk_pcie_train_link(struct advk_pcie *pcie)
 {
-	int ret, neg_gen;
+	struct device *dev = &pcie->pdev->dev;
 	u32 reg;
+	int ret;
 
-	/* Setup link speed */
+	/*
+	 * Setup PCIe rev / gen compliance based on device tree property
+	 * 'max-link-speed' which also forces maximal link speed.
+	 */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg &= ~PCIE_GEN_SEL_MSK;
-	if (gen == 3)
+	if (pcie->link_gen == 3)
 		reg |= SPEED_GEN_3;
-	else if (gen == 2)
+	else if (pcie->link_gen == 2)
 		reg |= SPEED_GEN_2;
 	else
 		reg |= SPEED_GEN_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
 	/*
-	 * Enable link training. This is not needed in every call to this
+	 * Set maximal link speed value also into PCIe Link Control 2 register.
-	 * function, just once suffices, but it does not break anything either.
+	 * Armada 3700 Functional Specification says that default value is based
+	 * on SPEED_GEN but tests showed that default value is always 8.0 GT/s.
 	 */
+	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+	reg &= ~PCI_EXP_LNKCTL2_TLS;
+	if (pcie->link_gen == 3)
+		reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+	else if (pcie->link_gen == 2)
+		reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+	else
+		reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+
+	/* Enable link training after selecting PCIe generation */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
 	reg |= LINK_TRAINING_EN;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
-	/*
-	 * Start link training immediately after enabling it.
-	 * This solves problems for some buggy cards.
-	 */
-	reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-	reg |= PCI_EXP_LNKCTL_RL;
-	advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL);
-
-	ret = advk_pcie_wait_for_link(pcie);
-	if (ret)
-		return ret;
-
-	reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA);
-	neg_gen = reg & PCI_EXP_LNKSTA_CLS;
-
-	return neg_gen;
-}
-
-static void advk_pcie_train_link(struct advk_pcie *pcie)
-{
-	struct device *dev = &pcie->pdev->dev;
-	int neg_gen = -1, gen;
-
 	/*
 	 * Reset PCIe card via PERST# signal. Some cards are not detected
 	 * during link training when they are in some non-initial state.
@@ -458,41 +439,18 @@ static void advk_pcie_train_link(struct advk_pcie *pcie)
 	 * PERST# signal could have been asserted by pinctrl subsystem before
 	 * probe() callback has been called or issued explicitly by reset gpio
 	 * function advk_pcie_issue_perst(), making the endpoint going into
-	 * fundamental reset. As required by PCI Express spec a delay for at
+	 * fundamental reset. As required by PCI Express spec (PCI Express
-	 * least 100ms after such a reset before link training is needed.
+	 * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1
+	 * Conventional Reset) a delay for at least 100ms after such a reset
+	 * before sending a Configuration Request to the device is needed.
+	 * So wait until PCIe link is up. Function advk_pcie_wait_for_link()
+	 * waits for link at least 900ms.
 	 */
-	msleep(PCI_PM_D3COLD_WAIT);
+	ret = advk_pcie_wait_for_link(pcie);
-
+	if (ret < 0)
-	/*
+		dev_err(dev, "link never came up\n");
-	 * Try link training at link gen specified by device tree property
+	else
-	 * 'max-link-speed'. If this fails, iteratively train at lower gen.
+		dev_info(dev, "link up\n");
-	 */
-	for (gen = pcie->link_gen; gen > 0; --gen) {
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-		if (neg_gen > 0)
-			break;
-	}
-
-	if (neg_gen < 0)
-		goto err;
-
-	/*
-	 * After successful training if negotiated gen is lower than requested,
-	 * train again on negotiated gen. This solves some stability issues for
-	 * some buggy gen1 cards.
-	 */
-	if (neg_gen < gen) {
-		gen = neg_gen;
-		neg_gen = advk_pcie_train_at_gen(pcie, gen);
-	}
-
-	if (neg_gen == gen) {
-		dev_info(dev, "link up at gen %i\n", gen);
-		return;
-	}
-
-err:
-	dev_err(dev, "link never came up\n");
 }
 
 /*
@@ -692,6 +650,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 	u32 reg;
 	unsigned int status;
 	char *strcomp_status, *str_posted;
+	int ret;
 
 	reg = advk_readl(pcie, PIO_STAT);
 	status = (reg & PIO_COMPLETION_STATUS_MASK) >>
@@ -716,6 +675,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 	case PIO_COMPLETION_STATUS_OK:
 		if (reg & PIO_ERR_STATUS) {
 			strcomp_status = "COMP_ERR";
+			ret = -EFAULT;
 			break;
 		}
 		/* Get the read result */
@@ -723,9 +683,11 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 			*val = advk_readl(pcie, PIO_RD_DATA);
 		/* No error */
 		strcomp_status = NULL;
+		ret = 0;
 		break;
 	case PIO_COMPLETION_STATUS_UR:
 		strcomp_status = "UR";
+		ret = -EOPNOTSUPP;
 		break;
 	case PIO_COMPLETION_STATUS_CRS:
 		if (allow_crs && val) {
@@ -743,6 +705,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 			 */
 			*val = CFG_RD_CRS_VAL;
 			strcomp_status = NULL;
+			ret = 0;
 			break;
 		}
 		/* PCIe r4.0, sec 2.3.2, says:
@@ -758,21 +721,24 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 		 * Request and taking appropriate action, e.g., complete the
 		 * Request to the host as a failed transaction.
 		 *
-		 * To simplify implementation do not re-issue the Configuration
+		 * So return -EAGAIN and caller (pci-aardvark.c driver) will
-		 * Request and complete the Request as a failed transaction.
+		 * re-issue request again up to the PIO_RETRY_CNT retries.
 		 */
 		strcomp_status = "CRS";
+		ret = -EAGAIN;
 		break;
 	case PIO_COMPLETION_STATUS_CA:
 		strcomp_status = "CA";
+		ret = -ECANCELED;
 		break;
 	default:
 		strcomp_status = "Unknown";
+		ret = -EINVAL;
 		break;
 	}
 
 	if (!strcomp_status)
-		return 0;
+		return ret;
 
 	if (reg & PIO_NON_POSTED_REQ)
 		str_posted = "Non-posted";
@@ -782,7 +748,7 @@ static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u3
 	dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n",
 		str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS));
 
-	return -EFAULT;
+	return ret;
 }
 
 static int advk_pcie_wait_pio(struct advk_pcie *pcie)
@@ -790,13 +756,13 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 	struct device *dev = &pcie->pdev->dev;
 	int i;
 
-	for (i = 0; i < PIO_RETRY_CNT; i++) {
+	for (i = 1; i <= PIO_RETRY_CNT; i++) {
 		u32 start, isr;
 
 		start = advk_readl(pcie, PIO_START);
 		isr = advk_readl(pcie, PIO_ISR);
 		if (!start && isr)
-			return 0;
+			return i;
 		udelay(PIO_RETRY_DELAY);
 	}
 
@@ -984,7 +950,6 @@ static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
 static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 {
 	struct pci_bridge_emul *bridge = &pcie->bridge;
-	int ret;
 
 	bridge->conf.vendor =
 		cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff);
@@ -1004,19 +969,14 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 	/* Support interrupt A for MSI feature */
 	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
 
+	/* Indicates supports for Completion Retry Status */
+	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
+
 	bridge->has_pcie = true;
 	bridge->data = pcie;
 	bridge->ops = &advk_pci_bridge_emul_ops;
 
-	/* PCIe config space can be initialized after pci_bridge_emul_init() */
+	return pci_bridge_emul_init(bridge, 0);
-	ret = pci_bridge_emul_init(bridge, 0);
-	if (ret < 0)
-		return ret;
-
-	/* Indicates supports for Completion Retry Status */
-	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
-
-	return 0;
 }
 
 static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
@@ -1068,6 +1028,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
 	struct advk_pcie *pcie = bus->sysdata;
+	int retry_count;
 	bool allow_crs;
 	u32 reg;
 	int ret;
@@ -1090,18 +1051,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		    (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) &
 		     PCI_EXP_RTCTL_CRSSVE);
 
-	if (advk_pcie_pio_is_running(pcie)) {
+	if (advk_pcie_pio_is_running(pcie))
-		/*
+		goto try_crs;
-		 * If it is possible return Completion Retry Status so caller
-		 * tries to issue the request again instead of failing.
-		 */
-		if (allow_crs) {
-			*val = CFG_RD_CRS_VAL;
-			return PCIBIOS_SUCCESSFUL;
-		}
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -1120,30 +1071,24 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
+	retry_count = 0;
-	advk_writel(pcie, 1, PIO_ISR);
+	do {
-	advk_writel(pcie, 1, PIO_START);
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
+		ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0) {
+		if (ret < 0)
-		/*
+			goto try_crs;
-		 * If it is possible return Completion Retry Status so caller
-		 * tries to issue the request again instead of failing.
-		 */
-		if (allow_crs) {
-			*val = CFG_RD_CRS_VAL;
-			return PCIBIOS_SUCCESSFUL;
-		}
-		*val = 0xffffffff;
-		return PCIBIOS_SET_FAILED;
-	}
 
-	/* Check PIO status and get the read result */
+		retry_count += ret;
-	ret = advk_pcie_check_pio_status(pcie, allow_crs, val);
+
-	if (ret < 0) {
+		/* Check PIO status and get the read result */
-		*val = 0xffffffff;
+		ret = advk_pcie_check_pio_status(pcie, allow_crs, val);
-		return PCIBIOS_SET_FAILED;
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
-	}
+
+	if (ret < 0)
+		goto fail;
 
 	if (size == 1)
 		*val = (*val >> (8 * (where & 3))) & 0xff;
@@ -1151,6 +1096,20 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		*val = (*val >> (8 * (where & 3))) & 0xffff;
 
 	return PCIBIOS_SUCCESSFUL;
+
+try_crs:
+	/*
+	 * If it is possible, return Completion Retry Status so that caller
+	 * tries to issue the request again instead of failing.
+	 */
+	if (allow_crs) {
+		*val = CFG_RD_CRS_VAL;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+fail:
+	*val = 0xffffffff;
+	return PCIBIOS_SET_FAILED;
 }
 
 static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
@@ -1159,6 +1118,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	struct advk_pcie *pcie = bus->sysdata;
 	u32 reg;
 	u32 data_strobe = 0x0;
+	int retry_count;
 	int offset;
 	int ret;
 
@@ -1200,19 +1160,22 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
 
-	/* Clear PIO DONE ISR and start the transfer */
+	retry_count = 0;
-	advk_writel(pcie, 1, PIO_ISR);
+	do {
-	advk_writel(pcie, 1, PIO_START);
+		/* Clear PIO DONE ISR and start the transfer */
+		advk_writel(pcie, 1, PIO_ISR);
+		advk_writel(pcie, 1, PIO_START);
 
-	ret = advk_pcie_wait_pio(pcie);
+		ret = advk_pcie_wait_pio(pcie);
-	if (ret < 0)
+		if (ret < 0)
-		return PCIBIOS_SET_FAILED;
+			return PCIBIOS_SET_FAILED;
 
-	ret = advk_pcie_check_pio_status(pcie, false, NULL);
+		retry_count += ret;
-	if (ret < 0)
-		return PCIBIOS_SET_FAILED;
 
-	return PCIBIOS_SUCCESSFUL;
+		ret = advk_pcie_check_pio_status(pcie, false, NULL);
+	} while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT);
+
+	return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL;
 }
 
 static struct pci_ops advk_pcie_ops = {

drivers/scsi/mpt3sas/mpt3sas_scsih.c

@@ -3675,7 +3675,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
 
 	shost_for_each_device(sdev, ioc->shost) {
 		sas_device_priv_data = sdev->hostdata;
-		if (!sas_device_priv_data)
+		if (!sas_device_priv_data || !sas_device_priv_data->sas_target)
 			continue;
 		if (sas_device_priv_data->sas_target->sas_address
 		    != sas_address)

drivers/scsi/scsi_debug.c

@@ -4628,6 +4628,7 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip,
 			 struct sdeb_zone_state *zsp)
 {
 	enum sdebug_z_cond zc;
+	struct sdeb_store_info *sip = devip2sip(devip, false);
 
 	if (zbc_zone_is_conv(zsp))
 		return;
@@ -4639,6 +4640,10 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip,
 	if (zsp->z_cond == ZC4_CLOSED)
 		devip->nr_closed--;
 
+	if (zsp->z_wp > zsp->z_start)
+		memset(sip->storep + zsp->z_start * sdebug_sector_size, 0,
+		       (zsp->z_wp - zsp->z_start) * sdebug_sector_size);
+
 	zsp->z_non_seq_resource = false;
 	zsp->z_wp = zsp->z_start;
 	zsp->z_cond = ZC1_EMPTY;

drivers/scsi/scsi_sysfs.c

@@ -816,7 +816,7 @@ store_state_field(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&sdev->state_mutex);
 	if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) {
-		ret = count;
+		ret = 0;
 	} else {
 		ret = scsi_device_set_state(sdev, state);
 		if (ret == 0 && state == SDEV_RUNNING)

drivers/staging/fbtft/fb_ssd1351.c

@@ -187,7 +187,6 @@ static struct fbtft_display display = {
 	},
 };
 
-#ifdef CONFIG_FB_BACKLIGHT
 static int update_onboard_backlight(struct backlight_device *bd)
 {
 	struct fbtft_par *par = bl_get_data(bd);
@@ -231,9 +230,6 @@ static void register_onboard_backlight(struct fbtft_par *par)
 	if (!par->fbtftops.unregister_backlight)
 		par->fbtftops.unregister_backlight = fbtft_unregister_backlight;
 }
-#else
-static void register_onboard_backlight(struct fbtft_par *par) { };
-#endif
 
 FBTFT_REGISTER_DRIVER(DRVNAME, "solomon,ssd1351", &display);
 

drivers/staging/fbtft/fbtft-core.c

@@ -128,7 +128,6 @@ static int fbtft_request_gpios(struct fbtft_par *par)
 	return 0;
 }
 
-#ifdef CONFIG_FB_BACKLIGHT
 static int fbtft_backlight_update_status(struct backlight_device *bd)
 {
 	struct fbtft_par *par = bl_get_data(bd);
@@ -161,6 +160,7 @@ void fbtft_unregister_backlight(struct fbtft_par *par)
 		par->info->bl_dev = NULL;
 	}
 }
+EXPORT_SYMBOL(fbtft_unregister_backlight);
 
 static const struct backlight_ops fbtft_bl_ops = {
 	.get_brightness	= fbtft_backlight_get_brightness,
@@ -198,12 +198,7 @@ void fbtft_register_backlight(struct fbtft_par *par)
 	if (!par->fbtftops.unregister_backlight)
 		par->fbtftops.unregister_backlight = fbtft_unregister_backlight;
 }
-#else
-void fbtft_register_backlight(struct fbtft_par *par) { };
-void fbtft_unregister_backlight(struct fbtft_par *par) { };
-#endif
 EXPORT_SYMBOL(fbtft_register_backlight);
-EXPORT_SYMBOL(fbtft_unregister_backlight);
 
 static void fbtft_set_addr_win(struct fbtft_par *par, int xs, int ys, int xe,
 			       int ye)
@@ -853,13 +848,11 @@ int fbtft_register_framebuffer(struct fb_info *fb_info)
 		 fb_info->fix.smem_len >> 10, text1,
 		 HZ / fb_info->fbdefio->delay, text2);
 
-#ifdef CONFIG_FB_BACKLIGHT
 	/* Turn on backlight if available */
 	if (fb_info->bl_dev) {
 		fb_info->bl_dev->props.power = FB_BLANK_UNBLANK;
 		fb_info->bl_dev->ops->update_status(fb_info->bl_dev);
 	}
-#endif
 
 	return 0;
 

drivers/staging/greybus/audio_helper.c

@@ -192,7 +192,11 @@ int gbaudio_remove_component_controls(struct snd_soc_component *component,
 				      unsigned int num_controls)
 {
 	struct snd_card *card = component->card->snd_card;
+	int err;
 
-	return gbaudio_remove_controls(card, component->dev, controls,
+	down_write(&card->controls_rwsem);
-				       num_controls, component->name_prefix);
+	err = gbaudio_remove_controls(card, component->dev, controls,
+				      num_controls, component->name_prefix);
+	up_write(&card->controls_rwsem);
+	return err;
 }

drivers/staging/rtl8192e/rtl8192e/rtl_core.c

@@ -2551,13 +2551,14 @@ static void _rtl92e_pci_disconnect(struct pci_dev *pdev)
 			free_irq(dev->irq, dev);
 			priv->irq = 0;
 		}
-		free_rtllib(dev);
 
 		if (dev->mem_start != 0) {
 			iounmap((void __iomem *)dev->mem_start);
 			release_mem_region(pci_resource_start(pdev, 1),
 					pci_resource_len(pdev, 1));
 		}
+
+		free_rtllib(dev);
 	} else {
 		priv = rtllib_priv(dev);
 	}

drivers/tty/hvc/hvc_xen.c

@@ -86,7 +86,11 @@ static int __write_console(struct xencons_info *xencons,
 	cons = intf->out_cons;
 	prod = intf->out_prod;
 	mb();			/* update queue values before going on */
-	BUG_ON((prod - cons) > sizeof(intf->out));
+
+	if ((prod - cons) > sizeof(intf->out)) {
+		pr_err_once("xencons: Illegal ring page indices");
+		return -EINVAL;
+	}
 
 	while ((sent < len) && ((prod - cons) < sizeof(intf->out)))
 		intf->out[MASK_XENCONS_IDX(prod++, intf->out)] = data[sent++];
@@ -114,7 +118,10 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
 	 */
 	while (len) {
 		int sent = __write_console(cons, data, len);
-		
+
+		if (sent < 0)
+			return sent;
+
 		data += sent;
 		len -= sent;
 
@@ -138,7 +145,11 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len)
 	cons = intf->in_cons;
 	prod = intf->in_prod;
 	mb();			/* get pointers before reading ring */
-	BUG_ON((prod - cons) > sizeof(intf->in));
+
+	if ((prod - cons) > sizeof(intf->in)) {
+		pr_err_once("xencons: Illegal ring page indices");
+		return -EINVAL;
+	}
 
 	while (cons != prod && recv < len)
 		buf[recv++] = intf->in[MASK_XENCONS_IDX(cons++, intf->in)];

drivers/usb/chipidea/ci_hdrc_imx.c

@@ -425,15 +425,15 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0);
 	if (IS_ERR(data->phy)) {
 		ret = PTR_ERR(data->phy);
-		if (ret == -ENODEV) {
+		if (ret != -ENODEV)
-			data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0);
+			goto err_clk;
-			if (IS_ERR(data->phy)) {
+		data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0);
-				ret = PTR_ERR(data->phy);
+		if (IS_ERR(data->phy)) {
-				if (ret == -ENODEV)
+			ret = PTR_ERR(data->phy);
-					data->phy = NULL;
+			if (ret == -ENODEV)
-				else
+				data->phy = NULL;
-					goto err_clk;
+			else
-			}
+				goto err_clk;
 		}
 	}
 

drivers/usb/core/hub.c

@@ -4628,8 +4628,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	if (oldspeed == USB_SPEED_LOW)
 		delay = HUB_LONG_RESET_TIME;
 
-	mutex_lock(hcd->address0_mutex);
-
 	/* Reset the device; full speed may morph to high speed */
 	/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
 	retval = hub_port_reset(hub, port1, udev, delay, false);
@@ -4940,7 +4938,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 		hub_port_disable(hub, port1, 0);
 		update_devnum(udev, devnum);	/* for disconnect processing */
 	}
-	mutex_unlock(hcd->address0_mutex);
 	return retval;
 }
 
@@ -5115,6 +5112,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 	struct usb_port *port_dev = hub->ports[port1 - 1];
 	struct usb_device *udev = port_dev->child;
 	static int unreliable_port = -1;
+	bool retry_locked;
 
 	/* Disconnect any existing devices under this port */
 	if (udev) {
@@ -5170,8 +5168,11 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		unit_load = 100;
 
 	status = 0;
-	for (i = 0; i < PORT_INIT_TRIES; i++) {
 
+	for (i = 0; i < PORT_INIT_TRIES; i++) {
+		usb_lock_port(port_dev);
+		mutex_lock(hcd->address0_mutex);
+		retry_locked = true;
 		/* reallocate for each attempt, since references
 		 * to the previous one can escape in various ways
 		 */
@@ -5179,6 +5180,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		if (!udev) {
 			dev_err(&port_dev->dev,
 					"couldn't allocate usb_device\n");
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
 			goto done;
 		}
 
@@ -5200,12 +5203,14 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		}
 
 		/* reset (non-USB 3.0 devices) and get descriptor */
-		usb_lock_port(port_dev);
 		status = hub_port_init(hub, udev, port1, i);
-		usb_unlock_port(port_dev);
 		if (status < 0)
 			goto loop;
 
+		mutex_unlock(hcd->address0_mutex);
+		usb_unlock_port(port_dev);
+		retry_locked = false;
+
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
 			msleep(2000);
 
@@ -5298,6 +5303,10 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		usb_ep0_reinit(udev);
 		release_devnum(udev);
 		hub_free_dev(udev);
+		if (retry_locked) {
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
+		}
 		usb_put_dev(udev);
 		if ((status == -ENOTCONN) || (status == -ENOTSUPP))
 			break;
@@ -5839,6 +5848,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	mutex_lock(hcd->address0_mutex);
+
 	for (i = 0; i < PORT_INIT_TRIES; ++i) {
 
 		/* ep0 maxpacket size may change; let the HCD know about it.
@@ -5848,6 +5859,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 		if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV)
 			break;
 	}
+	mutex_unlock(hcd->address0_mutex);
 
 	if (ret < 0)
 		goto re_enumerate;

drivers/usb/dwc2/gadget.c

@@ -1198,6 +1198,8 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg,
 			}
 			ctrl |= DXEPCTL_CNAK;
 		} else {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA);
 			return;
 		}
@@ -2856,9 +2858,12 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep)
 
 	do {
 		hs_req = get_ep_head(hs_ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req,
 						    -ENODATA);
+		}
 		dwc2_gadget_incr_frame_num(hs_ep);
 		/* Update current frame number value. */
 		hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg);
@@ -2911,8 +2916,11 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep)
 
 	while (dwc2_gadget_target_frame_elapsed(ep)) {
 		hs_req = get_ep_head(ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, ep, hs_req, -ENODATA);
+		}
 
 		dwc2_gadget_incr_frame_num(ep);
 		/* Update current frame number value. */
@@ -3001,8 +3009,11 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep)
 
 	while (dwc2_gadget_target_frame_elapsed(hs_ep)) {
 		hs_req = get_ep_head(hs_ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA);
+		}
 
 		dwc2_gadget_incr_frame_num(hs_ep);
 		/* Update current frame number value. */

drivers/usb/dwc2/hcd_queue.c

@@ -59,7 +59,7 @@
 #define DWC2_UNRESERVE_DELAY (msecs_to_jiffies(5))
 
 /* If we get a NAK, wait this long before retrying */
-#define DWC2_RETRY_WAIT_DELAY 1*1E6L
+#define DWC2_RETRY_WAIT_DELAY (1 * NSEC_PER_MSEC)
 
 /**
  * dwc2_periodic_channel_available() - Checks that a channel is available for a

drivers/usb/dwc3/gadget.c

@@ -310,13 +310,24 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd,
 	if (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_STARTTRANSFER) {
 		int link_state;
 
+		/*
+		 * Initiate remote wakeup if the link state is in U3 when
+		 * operating in SS/SSP or L1/L2 when operating in HS/FS. If the
+		 * link state is in U1/U2, no remote wakeup is needed. The Start
+		 * Transfer command will initiate the link recovery.
+		 */
 		link_state = dwc3_gadget_get_link_state(dwc);
-		if (link_state == DWC3_LINK_STATE_U1 ||
+		switch (link_state) {
-		    link_state == DWC3_LINK_STATE_U2 ||
+		case DWC3_LINK_STATE_U2:
-		    link_state == DWC3_LINK_STATE_U3) {
+			if (dwc->gadget->speed >= USB_SPEED_SUPER)
+				break;
+
+			fallthrough;
+		case DWC3_LINK_STATE_U3:
 			ret = __dwc3_gadget_wakeup(dwc);
 			dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n",
 					ret);
+			break;
 		}
 	}
 
@@ -3370,6 +3381,14 @@ static void dwc3_gadget_endpoint_command_complete(struct dwc3_ep *dep,
 	if (cmd != DWC3_DEPCMD_ENDTRANSFER)
 		return;
 
+	/*
+	 * The END_TRANSFER command will cause the controller to generate a
+	 * NoStream Event, and it's not due to the host DP NoStream rejection.
+	 * Ignore the next NoStream event.
+	 */
+	if (dep->stream_capable)
+		dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM;
+
 	dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
 	dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 	dwc3_gadget_ep_cleanup_cancelled_requests(dep);
@@ -3592,14 +3611,6 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
 	WARN_ON_ONCE(ret);
 	dep->resource_index = 0;
 
-	/*
-	 * The END_TRANSFER command will cause the controller to generate a
-	 * NoStream Event, and it's not due to the host DP NoStream rejection.
-	 * Ignore the next NoStream event.
-	 */
-	if (dep->stream_capable)
-		dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM;
-
 	if (!interrupt)
 		dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 	else

drivers/usb/serial/option.c

@@ -1267,6 +1267,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9010),				/* Telit SBL FN980 flashing device */
 	  .driver_info = NCTRL(0) | ZLP },
+	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9200),				/* Telit LE910S1 flashing device */
+	  .driver_info = NCTRL(0) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) },
@@ -2094,6 +2096,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) },	/* Fibocom FG150 Diag */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) },		/* Fibocom FG150 AT */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */

drivers/usb/typec/tcpm/fusb302.c

@@ -665,18 +665,6 @@ static int tcpm_set_cc(struct tcpc_dev *dev, enum typec_cc_status cc)
 				    ret);
 			goto done;
 		}
-		ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK,
-					     FUSB_REG_MASK_BC_LVL |
-					     FUSB_REG_MASK_COMP_CHNG,
-					     FUSB_REG_MASK_COMP_CHNG);
-		if (ret < 0) {
-			fusb302_log(chip, "cannot set SRC interrupt, ret=%d",
-				    ret);
-			goto done;
-		}
-		chip->intr_comp_chng = true;
-		break;
-	case TYPEC_CC_RD:
 		ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK,
 					     FUSB_REG_MASK_BC_LVL |
 					     FUSB_REG_MASK_COMP_CHNG,
@@ -686,7 +674,21 @@ static int tcpm_set_cc(struct tcpc_dev *dev, enum typec_cc_status cc)
 				    ret);
 			goto done;
 		}
+		chip->intr_comp_chng = true;
+		chip->intr_bc_lvl = false;
+		break;
+	case TYPEC_CC_RD:
+		ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK,
+					     FUSB_REG_MASK_BC_LVL |
+					     FUSB_REG_MASK_COMP_CHNG,
+					     FUSB_REG_MASK_COMP_CHNG);
+		if (ret < 0) {
+			fusb302_log(chip, "cannot set SRC interrupt, ret=%d",
+				    ret);
+			goto done;
+		}
 		chip->intr_bc_lvl = true;
+		chip->intr_comp_chng = false;
 		break;
 	default:
 		break;

drivers/vhost/vsock.c

@@ -494,7 +494,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 			virtio_transport_free_pkt(pkt);
 
 		len += sizeof(pkt->hdr);
-		vhost_add_used(vq, head, len);
+		vhost_add_used(vq, head, 0);
 		total_len += len;
 		added = true;
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));

drivers/xen/xenbus/xenbus_probe.c

@@ -846,7 +846,7 @@ static struct notifier_block xenbus_resume_nb = {
 
 static int __init xenbus_init(void)
 {
-	int err = 0;
+	int err;
 	uint64_t v = 0;
 	xen_store_domain_type = XS_UNKNOWN;
 
@@ -886,6 +886,29 @@ static int __init xenbus_init(void)
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
+		/*
+		 * Uninitialized hvm_params are zero and return no error.
+		 * Although it is theoretically possible to have
+		 * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is
+		 * not zero when valid. If zero, it means that Xenstore hasn't
+		 * been properly initialized. Instead of attempting to map a
+		 * wrong guest physical address return error.
+		 *
+		 * Also recognize all bits set as an invalid value.
+		 */
+		if (!v || !~v) {
+			err = -ENOENT;
+			goto out_error;
+		}
+		/* Avoid truncation on 32-bit. */
+#if BITS_PER_LONG == 32
+		if (v > ULONG_MAX) {
+			pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n",
+			       __func__, v);
+			err = -EINVAL;
+			goto out_error;
+		}
+#endif
 		xen_store_gfn = (unsigned long)v;
 		xen_store_interface =
 			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
@@ -920,8 +943,10 @@ static int __init xenbus_init(void)
 	 */
 	proc_create_mount_point("xen");
 #endif
+	return 0;
 
 out_error:
+	xen_store_domain_type = XS_UNKNOWN;
 	return err;
 }
 

fs/ceph/super.c

@@ -52,8 +52,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry));
 	struct ceph_mon_client *monc = &fsc->client->monc;
 	struct ceph_statfs st;
-	u64 fsid;
+	int i, err;
-	int err;
 	u64 data_pool;
 
 	if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) {
@@ -99,12 +98,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = NAME_MAX;
 
 	/* Must convert the fsid, for consistent values across arches */
+	buf->f_fsid.val[0] = 0;
 	mutex_lock(&monc->mutex);
-	fsid = le64_to_cpu(*(__le64 *)(&monc->monmap->fsid)) ^
+	for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i)
-	       le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1));
+		buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]);
 	mutex_unlock(&monc->mutex);
 
-	buf->f_fsid = u64_to_fsid(fsid);
+	/* fold the fs_cluster_id into the upper bits */
+	buf->f_fsid.val[1] = monc->fs_cluster_id;
 
 	return 0;
 }

fs/cifs/file.c

@@ -2618,12 +2618,23 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
-		if (server->ops->flush)
+		if (server->ops->flush == NULL) {
-			rc = server->ops->flush(xid, tcon, &smbfile->fid);
-		else
 			rc = -ENOSYS;
+			goto strict_fsync_exit;
+		}
+
+		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
+			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			if (smbfile) {
+				rc = server->ops->flush(xid, tcon, &smbfile->fid);
+				cifsFileInfo_put(smbfile);
+			} else
+				cifs_dbg(FYI, "ignore fsync for file not open for write\n");
+		} else
+			rc = server->ops->flush(xid, tcon, &smbfile->fid);
 	}
 
+strict_fsync_exit:
 	free_xid(xid);
 	return rc;
 }
@@ -2635,6 +2646,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct cifs_tcon *tcon;
 	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);
 
 	rc = file_write_and_wait_range(file, start, end);
@@ -2651,12 +2663,23 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
-		if (server->ops->flush)
+		if (server->ops->flush == NULL) {
-			rc = server->ops->flush(xid, tcon, &smbfile->fid);
-		else
 			rc = -ENOSYS;
+			goto fsync_exit;
+		}
+
+		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
+			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			if (smbfile) {
+				rc = server->ops->flush(xid, tcon, &smbfile->fid);
+				cifsFileInfo_put(smbfile);
+			} else
+				cifs_dbg(FYI, "ignore fsync for file not open for write\n");
+		} else
+			rc = server->ops->flush(xid, tcon, &smbfile->fid);
 	}
 
+fsync_exit:
 	free_xid(xid);
 	return rc;
 }

fs/f2fs/node.c

@@ -1420,6 +1420,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 			  nid, nid_of_node(page), ino_of_node(page),
 			  ofs_of_node(page), cpver_of_node(page),
 			  next_blkaddr_of_node(page));
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		err = -EINVAL;
 out_err:
 		ClearPageUptodate(page);

fs/fuse/dev.c

@@ -856,17 +856,17 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 		goto out_put_old;
 	}
 
+	get_page(newpage);
+
+	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
+		lru_cache_add(newpage);
+
 	/*
 	 * Release while we have extra ref on stolen page.  Otherwise
 	 * anon_pipe_buf_release() might think the page can be reused.
 	 */
 	pipe_buf_release(cs->pipe, buf);
 
-	get_page(newpage);
-
-	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
-		lru_cache_add(newpage);
-
 	err = 0;
 	spin_lock(&cs->req->waitq.lock);
 	if (test_bit(FR_ABORTED, &cs->req->flags))

fs/nfs/nfs42xdr.c

@@ -1396,8 +1396,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
 	status = decode_clone(xdr);
 	if (status)
 		goto out;
-	status = decode_getfattr(xdr, res->dst_fattr, res->server);
+	decode_getfattr(xdr, res->dst_fattr, res->server);
-
 out:
 	res->rpc_status = status;
 	return status;

fs/proc/vmcore.c

@@ -124,9 +124,13 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			nr_bytes = count;
 
 		/* If pfn is not ram, return zeros for sparse dump files */
-		if (pfn_is_ram(pfn) == 0)
+		if (pfn_is_ram(pfn) == 0) {
-			memset(buf, 0, nr_bytes);
+			tmp = 0;
-		else {
+			if (!userbuf)
+				memset(buf, 0, nr_bytes);
+			else if (clear_user(buf, nr_bytes))
+				tmp = -EFAULT;
+		} else {
 			if (encrypted)
 				tmp = copy_oldmem_page_encrypted(pfn, buf,
 								 nr_bytes,
@@ -135,10 +139,10 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			else
 				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						       offset, userbuf);
-
-			if (tmp < 0)
-				return tmp;
 		}
+		if (tmp < 0)
+			return tmp;
+
 		*ppos += nr_bytes;
 		count -= nr_bytes;
 		buf += nr_bytes;

include/linux/bpf.h

@@ -177,7 +177,7 @@ struct bpf_map {
 	atomic64_t usercnt;
 	struct work_struct work;
 	struct mutex freeze_mutex;
-	u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
+	atomic64_t writecnt;
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -1260,6 +1260,7 @@ void bpf_map_charge_move(struct bpf_map_memory *dst,
 void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
+bool bpf_map_write_active(const struct bpf_map *map);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 int  generic_map_lookup_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,

include/linux/ipc_namespace.h

@@ -132,6 +132,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	if (ns) {
+		if (refcount_inc_not_zero(&ns->count))
+			return ns;
+	}
+
+	return NULL;
+}
+
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
@@ -148,6 +158,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	return ns;
+}
+
 static inline void put_ipc_ns(struct ipc_namespace *ns)
 {
 }

include/linux/sched/task.h

@@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
  * pins the final release of task.io_context.  Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),

include/net/ip6_fib.h

@@ -501,6 +501,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		 struct fib6_config *cfg, gfp_t gfp_flags,
 		 struct netlink_ext_ack *extack);
 void fib6_nh_release(struct fib6_nh *fib6_nh);
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh);
 
 int call_fib6_entry_notifiers(struct net *net,
 			      enum fib_event_type event_type,

include/net/ipv6_stubs.h

@@ -47,6 +47,7 @@ struct ipv6_stub {
 			    struct fib6_config *cfg, gfp_t gfp_flags,
 			    struct netlink_ext_ack *extack);
 	void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
+	void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh);
 	void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt);
 	int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify);
 	void (*fib6_rt_update)(struct net *net, struct fib6_info *rt,

include/net/nl802154.h

@@ -19,6 +19,8 @@
  *
  */
 
+#include <linux/types.h>
+
 #define NL802154_GENL_NAME "nl802154"
 
 enum nl802154_commands {
@@ -150,10 +152,9 @@ enum nl802154_attrs {
 };
 
 enum nl802154_iftype {
-	/* for backwards compatibility TODO */
+	NL802154_IFTYPE_UNSPEC = (~(__u32)0),
-	NL802154_IFTYPE_UNSPEC = -1,
 
-	NL802154_IFTYPE_NODE,
+	NL802154_IFTYPE_NODE = 0,
 	NL802154_IFTYPE_MONITOR,
 	NL802154_IFTYPE_COORD,
 

include/xen/interface/io/ring.h

@@ -1,21 +1,53 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 /******************************************************************************
  * ring.h
  *
  * Shared producer-consumer ring macros.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Tim Deegan and Andrew Warfield November 2004.
  */
 
 #ifndef __XEN_PUBLIC_IO_RING_H__
 #define __XEN_PUBLIC_IO_RING_H__
 
+/*
+ * When #include'ing this header, you need to provide the following
+ * declaration upfront:
+ * - standard integers types (uint8_t, uint16_t, etc)
+ * They are provided by stdint.h of the standard headers.
+ *
+ * In addition, if you intend to use the FLEX macros, you also need to
+ * provide the following, before invoking the FLEX macros:
+ * - size_t
+ * - memcpy
+ * - grant_ref_t
+ * These declarations are provided by string.h of the standard headers,
+ * and grant_table.h from the Xen public headers.
+ */
+
 #include <xen/interface/grant_table.h>
 
 typedef unsigned int RING_IDX;
 
 /* Round a 32-bit unsigned constant down to the nearest power of two. */
-#define __RD2(_x)  (((_x) & 0x00000002) ? 0x2		       : ((_x) & 0x1))
+#define __RD2(_x)  (((_x) & 0x00000002) ? 0x2                  : ((_x) & 0x1))
 #define __RD4(_x)  (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2    : __RD2(_x))
 #define __RD8(_x)  (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4    : __RD4(_x))
 #define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8    : __RD8(_x))
@@ -27,82 +59,79 @@ typedef unsigned int RING_IDX;
  * A ring contains as many entries as will fit, rounded down to the nearest
  * power of two (so we can mask with (size-1) to loop around).
  */
-#define __CONST_RING_SIZE(_s, _sz)				\
+#define __CONST_RING_SIZE(_s, _sz) \
-	(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) /	\
+    (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
-		sizeof(((struct _s##_sring *)0)->ring[0])))
+	    sizeof(((struct _s##_sring *)0)->ring[0])))
-
 /*
  * The same for passing in an actual pointer instead of a name tag.
  */
-#define __RING_SIZE(_s, _sz)						\
+#define __RING_SIZE(_s, _sz) \
-	(__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
+    (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
 
 /*
  * Macros to make the correct C datatypes for a new kind of ring.
  *
  * To make a new ring datatype, you need to have two message structures,
- * let's say struct request, and struct response already defined.
+ * let's say request_t, and response_t already defined.
  *
  * In a header where you want the ring datatype declared, you then do:
  *
- *     DEFINE_RING_TYPES(mytag, struct request, struct response);
+ *     DEFINE_RING_TYPES(mytag, request_t, response_t);
  *
  * These expand out to give you a set of types, as you can see below.
  * The most important of these are:
  *
- *     struct mytag_sring      - The shared ring.
+ *     mytag_sring_t      - The shared ring.
- *     struct mytag_front_ring - The 'front' half of the ring.
+ *     mytag_front_ring_t - The 'front' half of the ring.
- *     struct mytag_back_ring  - The 'back' half of the ring.
+ *     mytag_back_ring_t  - The 'back' half of the ring.
  *
  * To initialize a ring in your code you need to know the location and size
  * of the shared memory area (PAGE_SIZE, for instance). To initialise
  * the front half:
  *
- *     struct mytag_front_ring front_ring;
+ *     mytag_front_ring_t front_ring;
- *     SHARED_RING_INIT((struct mytag_sring *)shared_page);
+ *     SHARED_RING_INIT((mytag_sring_t *)shared_page);
- *     FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page,
+ *     FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
- *		       PAGE_SIZE);
  *
  * Initializing the back follows similarly (note that only the front
  * initializes the shared ring):
  *
- *     struct mytag_back_ring back_ring;
+ *     mytag_back_ring_t back_ring;
- *     BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page,
+ *     BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
- *		      PAGE_SIZE);
  */
 
-#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t)			\
+#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t)                     \
-									\
+                                                                        \
-/* Shared ring entry */							\
+/* Shared ring entry */                                                 \
-union __name##_sring_entry {						\
+union __name##_sring_entry {                                            \
-    __req_t req;							\
+    __req_t req;                                                        \
-    __rsp_t rsp;							\
+    __rsp_t rsp;                                                        \
-};									\
+};                                                                      \
-									\
+                                                                        \
-/* Shared ring page */							\
+/* Shared ring page */                                                  \
-struct __name##_sring {							\
+struct __name##_sring {                                                 \
-    RING_IDX req_prod, req_event;					\
+    RING_IDX req_prod, req_event;                                       \
-    RING_IDX rsp_prod, rsp_event;					\
+    RING_IDX rsp_prod, rsp_event;                                       \
-    uint8_t  pad[48];							\
+    uint8_t __pad[48];                                                  \
-    union __name##_sring_entry ring[1]; /* variable-length */		\
+    union __name##_sring_entry ring[1]; /* variable-length */           \
-};									\
+};                                                                      \
-									\
+                                                                        \
-/* "Front" end's private variables */					\
+/* "Front" end's private variables */                                   \
-struct __name##_front_ring {						\
+struct __name##_front_ring {                                            \
-    RING_IDX req_prod_pvt;						\
+    RING_IDX req_prod_pvt;                                              \
-    RING_IDX rsp_cons;							\
+    RING_IDX rsp_cons;                                                  \
-    unsigned int nr_ents;						\
+    unsigned int nr_ents;                                               \
-    struct __name##_sring *sring;					\
+    struct __name##_sring *sring;                                       \
-};									\
+};                                                                      \
-									\
+                                                                        \
-/* "Back" end's private variables */					\
+/* "Back" end's private variables */                                    \
-struct __name##_back_ring {						\
+struct __name##_back_ring {                                             \
-    RING_IDX rsp_prod_pvt;						\
+    RING_IDX rsp_prod_pvt;                                              \
-    RING_IDX req_cons;							\
+    RING_IDX req_cons;                                                  \
-    unsigned int nr_ents;						\
+    unsigned int nr_ents;                                               \
-    struct __name##_sring *sring;					\
+    struct __name##_sring *sring;                                       \
-};
+};                                                                      \
-
+                                                                        \
 /*
  * Macros for manipulating rings.
  *
@@ -119,94 +148,99 @@ struct __name##_back_ring {						\
  */
 
 /* Initialising empty rings */
-#define SHARED_RING_INIT(_s) do {					\
+#define SHARED_RING_INIT(_s) do {                                       \
-    (_s)->req_prod  = (_s)->rsp_prod  = 0;				\
+    (_s)->req_prod  = (_s)->rsp_prod  = 0;                              \
-    (_s)->req_event = (_s)->rsp_event = 1;				\
+    (_s)->req_event = (_s)->rsp_event = 1;                              \
-    memset((_s)->pad, 0, sizeof((_s)->pad));				\
+    (void)memset((_s)->__pad, 0, sizeof((_s)->__pad));                  \
 } while(0)
 
-#define FRONT_RING_ATTACH(_r, _s, _i, __size) do {			\
+#define FRONT_RING_ATTACH(_r, _s, _i, __size) do {                      \
-    (_r)->req_prod_pvt = (_i);						\
+    (_r)->req_prod_pvt = (_i);                                          \
-    (_r)->rsp_cons = (_i);						\
+    (_r)->rsp_cons = (_i);                                              \
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);                            \
-    (_r)->sring = (_s);							\
+    (_r)->sring = (_s);                                                 \
 } while (0)
 
 #define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size)
 
-#define BACK_RING_ATTACH(_r, _s, _i, __size) do {			\
+#define BACK_RING_ATTACH(_r, _s, _i, __size) do {                       \
-    (_r)->rsp_prod_pvt = (_i);						\
+    (_r)->rsp_prod_pvt = (_i);                                          \
-    (_r)->req_cons = (_i);						\
+    (_r)->req_cons = (_i);                                              \
-    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);                            \
-    (_r)->sring = (_s);							\
+    (_r)->sring = (_s);                                                 \
 } while (0)
 
 #define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size)
 
 /* How big is this ring? */
-#define RING_SIZE(_r)							\
+#define RING_SIZE(_r)                                                   \
     ((_r)->nr_ents)
 
 /* Number of free requests (for use on front side only). */
-#define RING_FREE_REQUESTS(_r)						\
+#define RING_FREE_REQUESTS(_r)                                          \
     (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons))
 
 /* Test if there is an empty slot available on the front ring.
  * (This is only meaningful from the front. )
  */
-#define RING_FULL(_r)							\
+#define RING_FULL(_r)                                                   \
     (RING_FREE_REQUESTS(_r) == 0)
 
 /* Test if there are outstanding messages to be processed on a ring. */
-#define RING_HAS_UNCONSUMED_RESPONSES(_r)				\
+#define RING_HAS_UNCONSUMED_RESPONSES(_r)                               \
     ((_r)->sring->rsp_prod - (_r)->rsp_cons)
 
-#define RING_HAS_UNCONSUMED_REQUESTS(_r)				\
+#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({                             \
-    ({									\
+    unsigned int req = (_r)->sring->req_prod - (_r)->req_cons;          \
-	unsigned int req = (_r)->sring->req_prod - (_r)->req_cons;	\
+    unsigned int rsp = RING_SIZE(_r) -                                  \
-	unsigned int rsp = RING_SIZE(_r) -				\
+        ((_r)->req_cons - (_r)->rsp_prod_pvt);                          \
-			   ((_r)->req_cons - (_r)->rsp_prod_pvt);	\
+    req < rsp ? req : rsp;                                              \
-	req < rsp ? req : rsp;						\
+})
-    })
 
 /* Direct access to individual ring elements, by index. */
-#define RING_GET_REQUEST(_r, _idx)					\
+#define RING_GET_REQUEST(_r, _idx)                                      \
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
 
+#define RING_GET_RESPONSE(_r, _idx)                                     \
+    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+
 /*
- * Get a local copy of a request.
+ * Get a local copy of a request/response.
  *
- * Use this in preference to RING_GET_REQUEST() so all processing is
+ * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is
  * done on a local copy that cannot be modified by the other end.
  *
  * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
- * to be ineffective where _req is a struct which consists of only bitfields.
+ * to be ineffective where dest is a struct which consists of only bitfields.
  */
-#define RING_COPY_REQUEST(_r, _idx, _req) do {				\
+#define RING_COPY_(type, r, idx, dest) do {				\
-	/* Use volatile to force the copy into _req. */			\
+	/* Use volatile to force the copy into dest. */			\
-	*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx);	\
+	*(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx);	\
 } while (0)
 
-#define RING_GET_RESPONSE(_r, _idx)					\
+#define RING_COPY_REQUEST(r, idx, req)  RING_COPY_(REQUEST, r, idx, req)
-    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp)
 
 /* Loop termination condition: Would the specified index overflow the ring? */
-#define RING_REQUEST_CONS_OVERFLOW(_r, _cons)				\
+#define RING_REQUEST_CONS_OVERFLOW(_r, _cons)                           \
     (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r))
 
 /* Ill-behaved frontend determination: Can there be this many requests? */
-#define RING_REQUEST_PROD_OVERFLOW(_r, _prod)               \
+#define RING_REQUEST_PROD_OVERFLOW(_r, _prod)                           \
     (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))
 
+/* Ill-behaved backend determination: Can there be this many responses? */
+#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod)                          \
+    (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r))
 
-#define RING_PUSH_REQUESTS(_r) do {					\
+#define RING_PUSH_REQUESTS(_r) do {                                     \
-    virt_wmb(); /* back sees requests /before/ updated producer index */	\
+    virt_wmb(); /* back sees requests /before/ updated producer index */\
-    (_r)->sring->req_prod = (_r)->req_prod_pvt;				\
+    (_r)->sring->req_prod = (_r)->req_prod_pvt;                         \
 } while (0)
 
-#define RING_PUSH_RESPONSES(_r) do {					\
+#define RING_PUSH_RESPONSES(_r) do {                                    \
-    virt_wmb(); /* front sees responses /before/ updated producer index */	\
+    virt_wmb(); /* front sees resps /before/ updated producer index */  \
-    (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt;				\
+    (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt;                         \
 } while (0)
 
 /*
@@ -239,40 +273,40 @@ struct __name##_back_ring {						\
  *  field appropriately.
  */
 
-#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do {		\
+#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do {           \
-    RING_IDX __old = (_r)->sring->req_prod;				\
+    RING_IDX __old = (_r)->sring->req_prod;                             \
-    RING_IDX __new = (_r)->req_prod_pvt;				\
+    RING_IDX __new = (_r)->req_prod_pvt;                                \
-    virt_wmb(); /* back sees requests /before/ updated producer index */	\
+    virt_wmb(); /* back sees requests /before/ updated producer index */\
-    (_r)->sring->req_prod = __new;					\
+    (_r)->sring->req_prod = __new;                                      \
-    virt_mb(); /* back sees new requests /before/ we check req_event */	\
+    virt_mb(); /* back sees new requests /before/ we check req_event */ \
-    (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) <		\
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) <           \
-		 (RING_IDX)(__new - __old));				\
+                 (RING_IDX)(__new - __old));                            \
 } while (0)
 
-#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do {		\
+#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do {          \
-    RING_IDX __old = (_r)->sring->rsp_prod;				\
+    RING_IDX __old = (_r)->sring->rsp_prod;                             \
-    RING_IDX __new = (_r)->rsp_prod_pvt;				\
+    RING_IDX __new = (_r)->rsp_prod_pvt;                                \
-    virt_wmb(); /* front sees responses /before/ updated producer index */	\
+    virt_wmb(); /* front sees resps /before/ updated producer index */  \
-    (_r)->sring->rsp_prod = __new;					\
+    (_r)->sring->rsp_prod = __new;                                      \
-    virt_mb(); /* front sees new responses /before/ we check rsp_event */	\
+    virt_mb(); /* front sees new resps /before/ we check rsp_event */   \
-    (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) <		\
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) <           \
-		 (RING_IDX)(__new - __old));				\
+                 (RING_IDX)(__new - __old));                            \
 } while (0)
 
-#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do {		\
+#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do {             \
-    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);                   \
-    if (_work_to_do) break;						\
+    if (_work_to_do) break;                                             \
-    (_r)->sring->req_event = (_r)->req_cons + 1;			\
+    (_r)->sring->req_event = (_r)->req_cons + 1;                        \
-    virt_mb();								\
+    virt_mb();                                                          \
-    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);                   \
 } while (0)
 
-#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do {		\
+#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do {            \
-    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);                  \
-    if (_work_to_do) break;						\
+    if (_work_to_do) break;                                             \
-    (_r)->sring->rsp_event = (_r)->rsp_cons + 1;			\
+    (_r)->sring->rsp_event = (_r)->rsp_cons + 1;                        \
-    virt_mb();								\
+    virt_mb();                                                          \
-    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);                  \
 } while (0)
 
 

ipc/shm.c

@@ -62,9 +62,18 @@ struct shmid_kernel /* private to the kernel */
 	struct pid		*shm_lprid;
 	struct user_struct	*mlock_user;
 
-	/* The task created the shm object.  NULL if the task is dead. */
+	/*
+	 * The task created the shm object, for
+	 * task_lock(shp->shm_creator)
+	 */
 	struct task_struct	*shm_creator;
-	struct list_head	shm_clist;	/* list by creator */
+
+	/*
+	 * List by creator. task_lock(->shm_creator) required for read/write.
+	 * If list_empty(), then the creator is dead already.
+	 */
+	struct list_head	shm_clist;
+	struct ipc_namespace	*ns;
 } __randomize_layout;
 
 /* shm_mode upper byte flags */
@@ -115,6 +124,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	struct shmid_kernel *shp;
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	WARN_ON(ns != shp->ns);
 
 	if (shp->shm_nattch) {
 		shp->shm_perm.mode |= SHM_DEST;
@@ -225,10 +235,43 @@ static void shm_rcu_free(struct rcu_head *head)
 	kvfree(shp);
 }
 
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
 {
-	list_del(&s->shm_clist);
+	struct task_struct *creator;
-	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+
+	/* ensure that shm_creator does not disappear */
+	rcu_read_lock();
+
+	/*
+	 * A concurrent exit_shm may do a list_del_init() as well.
+	 * Just do nothing if exit_shm already did the work
+	 */
+	if (!list_empty(&shp->shm_clist)) {
+		/*
+		 * shp->shm_creator is guaranteed to be valid *only*
+		 * if shp->shm_clist is not empty.
+		 */
+		creator = shp->shm_creator;
+
+		task_lock(creator);
+		/*
+		 * list_del_init() is a nop if the entry was already removed
+		 * from the list.
+		 */
+		list_del_init(&shp->shm_clist);
+		task_unlock(creator);
+	}
+	rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
+{
+	shm_clist_rm(s);
+	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
 }
 
 
@@ -283,7 +326,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_file = shp->shm_file;
 	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	shm_rmid(ns, shp);
+	shm_rmid(shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
 		shmem_lock(shm_file, 0, shp->mlock_user);
@@ -306,10 +349,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  *
  * 2) sysctl kernel.shm_rmid_forced is set to 1.
  */
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
 {
 	return (shp->shm_nattch == 0) &&
-	       (ns->shm_rmid_forced ||
+	       (shp->ns->shm_rmid_forced ||
 		(shp->shm_perm.mode & SHM_DEST));
 }
 
@@ -340,7 +383,7 @@ static void shm_close(struct vm_area_struct *vma)
 	ipc_update_pid(&shp->shm_lprid, task_tgid(current));
 	shp->shm_dtim = ktime_get_real_seconds();
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -361,10 +404,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 *
 	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
-	if (shp->shm_creator != NULL)
+	if (!list_empty(&shp->shm_clist))
 		return 0;
 
-	if (shm_may_destroy(ns, shp)) {
+	if (shm_may_destroy(shp)) {
 		shm_lock_by_ptr(shp);
 		shm_destroy(ns, shp);
 	}
@@ -382,48 +425,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 /* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
-	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
+	for (;;) {
-	struct shmid_kernel *shp, *n;
+		struct shmid_kernel *shp;
+		struct ipc_namespace *ns;
 
-	if (list_empty(&task->sysvshm.shm_clist))
+		task_lock(task);
-		return;
 
-	/*
+		if (list_empty(&task->sysvshm.shm_clist)) {
-	 * If kernel.shm_rmid_forced is not set then only keep track of
+			task_unlock(task);
-	 * which shmids are orphaned, so that a later set of the sysctl
+			break;
-	 * can clean them up.
-	 */
-	if (!ns->shm_rmid_forced) {
-		down_read(&shm_ids(ns).rwsem);
-		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
-			shp->shm_creator = NULL;
-		/*
-		 * Only under read lock but we are only called on current
-		 * so no entry on the list will be shared.
-		 */
-		list_del(&task->sysvshm.shm_clist);
-		up_read(&shm_ids(ns).rwsem);
-		return;
-	}
-
-	/*
-	 * Destroy all already created segments, that were not yet mapped,
-	 * and mark any mapped as orphan to cover the sysctl toggling.
-	 * Destroy is skipped if shm_may_destroy() returns false.
-	 */
-	down_write(&shm_ids(ns).rwsem);
-	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
-		shp->shm_creator = NULL;
-
-		if (shm_may_destroy(ns, shp)) {
-			shm_lock_by_ptr(shp);
-			shm_destroy(ns, shp);
 		}
-	}
 
-	/* Remove the list head from any segments still attached. */
+		shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
-	list_del(&task->sysvshm.shm_clist);
+				shm_clist);
-	up_write(&shm_ids(ns).rwsem);
+
+		/*
+		 * 1) Get pointer to the ipc namespace. It is worth to say
+		 * that this pointer is guaranteed to be valid because
+		 * shp lifetime is always shorter than namespace lifetime
+		 * in which shp lives.
+		 * We taken task_lock it means that shp won't be freed.
+		 */
+		ns = shp->ns;
+
+		/*
+		 * 2) If kernel.shm_rmid_forced is not set then only keep track of
+		 * which shmids are orphaned, so that a later set of the sysctl
+		 * can clean them up.
+		 */
+		if (!ns->shm_rmid_forced)
+			goto unlink_continue;
+
+		/*
+		 * 3) get a reference to the namespace.
+		 *    The refcount could be already 0. If it is 0, then
+		 *    the shm objects will be free by free_ipc_work().
+		 */
+		ns = get_ipc_ns_not_zero(ns);
+		if (!ns) {
+unlink_continue:
+			list_del_init(&shp->shm_clist);
+			task_unlock(task);
+			continue;
+		}
+
+		/*
+		 * 4) get a reference to shp.
+		 *   This cannot fail: shm_clist_rm() is called before
+		 *   ipc_rmid(), thus the refcount cannot be 0.
+		 */
+		WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+		/*
+		 * 5) unlink the shm segment from the list of segments
+		 *    created by current.
+		 *    This must be done last. After unlinking,
+		 *    only the refcounts obtained above prevent IPC_RMID
+		 *    from destroying the segment or the namespace.
+		 */
+		list_del_init(&shp->shm_clist);
+
+		task_unlock(task);
+
+		/*
+		 * 6) we have all references
+		 *    Thus lock & if needed destroy shp.
+		 */
+		down_write(&shm_ids(ns).rwsem);
+		shm_lock_by_ptr(shp);
+		/*
+		 * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+		 * safe to call ipc_rcu_putref here
+		 */
+		ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+		if (ipc_valid_object(&shp->shm_perm)) {
+			if (shm_may_destroy(shp))
+				shm_destroy(ns, shp);
+			else
+				shm_unlock(shp);
+		} else {
+			/*
+			 * Someone else deleted the shp from namespace
+			 * idr/kht while we have waited.
+			 * Just unlock and continue.
+			 */
+			shm_unlock(shp);
+		}
+
+		up_write(&shm_ids(ns).rwsem);
+		put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+	}
 }
 
 static vm_fault_t shm_fault(struct vm_fault *vmf)
@@ -680,7 +772,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (error < 0)
 		goto no_id;
 
+	shp->ns = ns;
+
+	task_lock(current);
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+	task_unlock(current);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1573,7 +1669,8 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);

kernel/bpf/syscall.c

@@ -129,6 +129,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+	atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+	atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+	return atomic64_read(&map->writecnt) != 0;
+}
+
 static u32 bpf_map_value_size(struct bpf_map *map)
 {
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -590,11 +605,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
+	if (vma->vm_flags & VM_MAYWRITE)
-		mutex_lock(&map->freeze_mutex);
+		bpf_map_write_active_inc(map);
-		map->writecnt++;
-		mutex_unlock(&map->freeze_mutex);
-	}
 }
 
 /* called for all unmapped memory region (including initial) */
@@ -602,11 +614,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
+	if (vma->vm_flags & VM_MAYWRITE)
-		mutex_lock(&map->freeze_mutex);
+		bpf_map_write_active_dec(map);
-		map->writecnt--;
-		mutex_unlock(&map->freeze_mutex);
-	}
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -656,7 +665,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 		goto out;
 
 	if (vma->vm_flags & VM_MAYWRITE)
-		map->writecnt++;
+		bpf_map_write_active_inc(map);
 out:
 	mutex_unlock(&map->freeze_mutex);
 	return err;
@@ -1088,6 +1097,7 @@ static int map_update_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1129,6 +1139,7 @@ static int map_update_elem(union bpf_attr *attr)
 free_key:
 	kfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1151,6 +1162,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1181,6 +1193,7 @@ static int map_delete_elem(union bpf_attr *attr)
 out:
 	kfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1485,6 +1498,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
 	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
@@ -1526,6 +1540,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 free_key:
 	kfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1552,8 +1567,7 @@ static int map_freeze(const union bpf_attr *attr)
 	}
 
 	mutex_lock(&map->freeze_mutex);
-
+	if (bpf_map_write_active(map)) {
-	if (map->writecnt) {
 		err = -EBUSY;
 		goto err_put;
 	}
@@ -3978,6 +3992,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr,
 			    int cmd)
 {
+	bool has_read  = cmd == BPF_MAP_LOOKUP_BATCH ||
+			 cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+	bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
 	struct bpf_map *map;
 	int err, ufd;
 	struct fd f;
@@ -3990,16 +4007,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
+	if (has_write)
-	if ((cmd == BPF_MAP_LOOKUP_BATCH ||
+		bpf_map_write_active_inc(map);
-	     cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
+	if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
-
+	if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
-	if (cmd != BPF_MAP_LOOKUP_BATCH &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -4012,8 +4026,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 		BPF_DO_BATCH(map->ops->map_update_batch);
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch);
-
 err_put:
+	if (has_write)
+		bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }

kernel/bpf/verifier.c

@@ -3486,7 +3486,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
-	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+	/* A map is considered read-only if the following condition are true:
+	 *
+	 * 1) BPF program side cannot change any of the map content. The
+	 *    BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+	 *    and was set at map creation time.
+	 * 2) The map value(s) have been initialized from user space by a
+	 *    loader and then "frozen", such that no new map update/delete
+	 *    operations from syscall side are possible for the rest of
+	 *    the map's lifetime from that point onwards.
+	 * 3) Any parallel/pending map update/delete operations from syscall
+	 *    side have been completed. Only after that point, it's safe to
+	 *    assume that map value(s) are immutable.
+	 */
+	return (map->map_flags & BPF_F_RDONLY_PROG) &&
+	       READ_ONCE(map->frozen) &&
+	       !bpf_map_write_active(map);
 }
 
 static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)

kernel/cpu.c

@@ -560,8 +560,8 @@ static int bringup_cpu(unsigned int cpu)
 	int ret;
 
 	/*
-	* Reset stale stack state from the last time this CPU was online.
+	 * Reset stale stack state from the last time this CPU was online.
-	*/
+	 */
 	scs_task_reset(idle);
 	kasan_unpoison_task_stack(idle);
 

kernel/power/hibernate.c

@@ -688,7 +688,7 @@ static int load_image_and_restore(void)
 		goto Unlock;
 
 	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	if (!error)
 		error = hibernation_restore(flags & SF_PLATFORM_MODE);
 
@@ -978,7 +978,7 @@ static int software_resume(void)
 	/* The snapshot device should not be opened while we're running */
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
-		swsusp_close(FMODE_READ);
+		swsusp_close(FMODE_READ | FMODE_EXCL);
 		goto Unlock;
 	}
 
@@ -1013,7 +1013,7 @@ static int software_resume(void)
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	goto Finish;
 }
 

kernel/trace/trace.h

@@ -1506,14 +1506,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
 	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
 		*tt = event_triggers_call(file, entry, event);
 
-	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
+	if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
-	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
+				    EVENT_FILE_FL_FILTERED |
-	     !filter_match_preds(file->filter, entry))) {
+				    EVENT_FILE_FL_PID_FILTER))))
-		__trace_event_discard_commit(buffer, event);
+		return false;
-		return true;
+
-	}
+	if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+		goto discard;
+
+	if (file->flags & EVENT_FILE_FL_FILTERED &&
+	    !filter_match_preds(file->filter, entry))
+		goto discard;
+
+	if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(file))
+		goto discard;
 
 	return false;
+ discard:
+	__trace_event_discard_commit(buffer, event);
+	return true;
 }
 
 /**

kernel/trace/trace_events.c

@@ -2462,12 +2462,22 @@ static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
 {
+	struct trace_pid_list *no_pid_list;
+	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
 
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
 		return NULL;
 
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     lockdep_is_held(&event_mutex));
+
+	if (pid_list || no_pid_list)
+		file->flags |= EVENT_FILE_FL_PID_FILTER;
+
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);

kernel/trace/trace_uprobe.c

@@ -1312,6 +1312,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+		tu = container_of(pos, struct trace_uprobe, tp);
 		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);

net/8021q/vlan.c

@@ -181,9 +181,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (err)
 		goto out_unregister_netdev;
 
-	/* Account for reference in struct vlan_dev_priv */
-	dev_hold(real_dev);
-
 	vlan_stacked_transfer_operstate(real_dev, dev, vlan);
 	linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */
 

net/8021q/vlan_dev.c

@@ -606,6 +606,9 @@ static int vlan_dev_init(struct net_device *dev)
 	if (!vlan->vlan_pcpu_stats)
 		return -ENOMEM;
 
+	/* Get vlan's reference to real_dev */
+	dev_hold(real_dev);
+
 	return 0;
 }
 

net/ipv4/nexthop.c

@@ -924,15 +924,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 /* if any FIB entries reference this nexthop, any dst entries
  * need to be regenerated
  */
-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh,
+			      struct nexthop *replaced_nh)
 {
 	struct fib6_info *f6i;
+	struct nh_group *nhg;
+	int i;
 
 	if (!list_empty(&nh->fi_list))
 		rt_cache_flush(net);
 
 	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
 		ipv6_stub->fib6_update_sernum(net, f6i);
+
+	/* if an IPv6 group was replaced, we have to release all old
+	 * dsts to make sure all refcounts are released
+	 */
+	if (!replaced_nh->is_group)
+		return;
+
+	/* new dsts must use only the new nexthop group */
+	synchronize_net();
+
+	nhg = rtnl_dereference(replaced_nh->nh_grp);
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+		struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info);
+
+		if (nhi->family == AF_INET6)
+			ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh);
+	}
 }
 
 static int replace_nexthop_grp(struct net *net, struct nexthop *old,
@@ -1111,7 +1132,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
 		err = replace_nexthop_single(net, old, new, extack);
 
 	if (!err) {
-		nh_rt_cache_flush(net, old);
+		nh_rt_cache_flush(net, old, new);
 
 		__remove_nexthop(net, new, NULL);
 		nexthop_put(new);
@@ -1355,11 +1376,15 @@ static int nh_create_ipv6(struct net *net,  struct nexthop *nh,
 	/* sets nh_dev if successful */
 	err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
 				      extack);
-	if (err)
+	if (err) {
+		/* IPv6 is not enabled, don't call fib6_nh_release */
+		if (err == -EAFNOSUPPORT)
+			goto out;
 		ipv6_stub->fib6_nh_release(fib6_nh);
-	else
+	} else {
 		nh->nh_flags = fib6_nh->fib_nh_flags;
-
+	}
+out:
 	return err;
 }
 

net/ipv4/tcp.c

@@ -3911,7 +3911,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	}
 #ifdef CONFIG_MMU
 	case TCP_ZEROCOPY_RECEIVE: {
-		struct tcp_zerocopy_receive zc;
+		struct tcp_zerocopy_receive zc = {};
 		int err;
 
 		if (get_user(len, optlen))
@@ -3929,7 +3929,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		lock_sock(sk);
 		err = tcp_zerocopy_receive(sk, &zc);
 		release_sock(sk);
-		if (len == sizeof(zc))
+		if (len >= offsetofend(struct tcp_zerocopy_receive, err))
 			goto zerocopy_rcv_sk_err;
 		switch (len) {
 		case offsetofend(struct tcp_zerocopy_receive, err):

net/ipv4/tcp_cubic.c

@@ -337,8 +337,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		return;
 
 	if (tcp_in_slow_start(tp)) {
-		if (hystart && after(ack, ca->end_seq))
-			bictcp_hystart_reset(sk);
 		acked = tcp_slow_start(tp, acked);
 		if (!acked)
 			return;
@@ -398,6 +396,9 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 threshold;
 
+	if (after(tp->snd_una, ca->end_seq))
+		bictcp_hystart_reset(sk);
+
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock_us(sk);
 

net/ipv6/af_inet6.c

@@ -1018,6 +1018,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
 	.fib6_nh_init	   = fib6_nh_init,
 	.fib6_nh_release   = fib6_nh_release,
+	.fib6_nh_release_dsts = fib6_nh_release_dsts,
 	.fib6_update_sernum = fib6_update_sernum_stub,
 	.fib6_rt_update	   = fib6_rt_update,
 	.ip6_del_rt	   = ip6_del_rt,

net/ipv6/ip6_output.c

@@ -193,7 +193,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
 		return dst_output(net, sk, skb);
 	}
 #endif

net/ipv6/route.c

@@ -3570,6 +3570,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh)
 	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
+{
+	int cpu;
+
+	if (!fib6_nh->rt6i_pcpu)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct rt6_info *pcpu_rt, **ppcpu_rt;
+
+		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+		pcpu_rt = xchg(ppcpu_rt, NULL);
+		if (pcpu_rt) {
+			dst_dev_put(&pcpu_rt->dst);
+			dst_release(&pcpu_rt->dst);
+		}
+	}
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)

net/mptcp/options.c

@@ -368,9 +368,10 @@ static void schedule_3rdack_retransmission(struct sock *sk)
 
 	/* reschedule with a timeout above RTT, as we must look only for drop */
 	if (tp->srtt_us)
-		timeout = tp->srtt_us << 1;
+		timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1));
 	else
 		timeout = TCP_TIMEOUT_INIT;
+	timeout += jiffies;
 
 	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
 	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;