Linux 6.1-rc2

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmNVv9UeHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGInQH/0YTqoWH4mYpBSgy
 KLOaLxs3fRY0B0EmSItcQfish1GuE0wsNClm6us4+CxcHIQPGnhoPdjobAp+W9X1
 JkBpxs+WbozGf23IGiVV8cFRXvpLL5TmiB5IeXo3kzvqGG2yvgEZ2uvclDeRN8bj
 Z0DlcPGG1Of9Fhmj+CsEwu0YOJ4o5kPNtuXrp1YVyiLlmyrGN68cb0vzZuEMQ6mg
 D7BkseqfE0lblKQCTyt1Uwxc08YR/LmmdkZ4d206NpKmJZaSFKhnfeXteljnvw/u
 vi3Rl1SKRxRsqZheJYSTGOmw0a6vu/6LDrsS3IVr1A54oS6tM77Y2WVbE+msyFaw
 R7EkOVc=
 =RQLk
 -----END PGP SIGNATURE-----

Merge tag 'v6.1-rc2' into android-mainline

Linux 6.1-rc2

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ib5212f4a6567c2452e703b52a9b7b0b6394bc6c7
This commit is contained in:
Greg Kroah-Hartman 2022-10-25 16:07:10 +02:00
commit 429562c3d3
27 changed files with 359 additions and 151 deletions

View File

@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 1
SUBLEVEL = 0
EXTRAVERSION = -rc1
EXTRAVERSION = -rc2
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*

View File

@ -13,6 +13,18 @@
#define KVM_PGTABLE_MAX_LEVELS 4U
/*
* The largest supported block sizes for KVM (no 52-bit PA support):
* - 4K (level 1): 1GB
* - 16K (level 2): 32MB
* - 64K (level 2): 512MB
*/
#ifdef CONFIG_ARM64_4K_PAGES
#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U
#else
#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U
#endif
static inline u64 kvm_get_parange(u64 mmfr0)
{
u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level)
static inline bool kvm_level_supports_block_mapping(u32 level)
{
/*
* Reject invalid block mappings and don't bother with 4TB mappings for
* 52-bit PAs.
*/
return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1));
return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
}
/**

View File

@ -10,13 +10,6 @@
#include <linux/pgtable.h>
/*
* PGDIR_SHIFT determines the size a top-level page table entry can map
* and depends on the number of levels in the page table. Compute the
* PGDIR_SHIFT for a given number of levels.
*/
#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
/*
* The hardware supports concatenation of up to 16 tables at stage2 entry
* level and we use the feature whenever possible, which means we resolve 4
@ -30,11 +23,6 @@
#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */
#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm))
#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm))
#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1)
/*
* kvm_mmmu_cache_min_pages() is the number of pages required to install
* a stage-2 translation. We pre-allocate the entry level page table at
@ -42,12 +30,4 @@
*/
#define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1)
static inline phys_addr_t
stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm);
return (boundary - 1 < end - 1) ? boundary : end;
}
#endif /* __ARM64_S2_PGTABLE_H_ */

View File

@ -5,9 +5,6 @@
incdir := $(srctree)/$(src)/include
subdir-asflags-y := -I$(incdir)
subdir-ccflags-y := -I$(incdir) \
-fno-stack-protector \
-DDISABLE_BRANCH_PROFILING \
$(DISABLE_STACKLEAK_PLUGIN)
subdir-ccflags-y := -I$(incdir)
obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o

View File

@ -10,6 +10,9 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
# will explode instantly (Words of Marc Zyngier). So introduce a generic flag
# __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM.
ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__
ccflags-y += -fno-stack-protector \
-DDISABLE_BRANCH_PROFILING \
$(DISABLE_STACKLEAK_PLUGIN)
hostprogs := gen-hyprel
HOST_EXTRACFLAGS += -I$(objtree)/include
@ -89,6 +92,10 @@ quiet_cmd_hypcopy = HYPCOPY $@
# Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
# This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
# Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
# when profile optimization is applied. gen-hyprel does not support SHT_REL and
# causes a build failure. Remove profile optimization flags.
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
# KVM nVHE code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may

View File

@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector;
static unsigned long io_map_base;
static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
{
phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
return (boundary - 1 < end - 1) ? boundary : end;
}
/*
* Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
if (!pgt)
return -EINVAL;
next = stage2_pgd_addr_end(kvm, addr, end);
next = stage2_range_addr_end(addr, end);
ret = fn(pgt, addr, next - addr);
if (ret)
break;

View File

@ -2149,7 +2149,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
memset(entry, 0, esz);
while (len > 0) {
while (true) {
int next_offset;
size_t byte_offset;
@ -2162,6 +2162,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
return next_offset;
byte_offset = next_offset * esz;
if (byte_offset >= len)
break;
id += next_offset;
gpa += byte_offset;
len -= byte_offset;

View File

@ -42,16 +42,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
/*
* The T-Head CMO errata internally probe the CBOM block size, but otherwise
* don't depend on Zicbom.
*/
extern unsigned int riscv_cbom_block_size;
#ifdef CONFIG_RISCV_ISA_ZICBOM
void riscv_init_cbom_blocksize(void);
#else
static inline void riscv_init_cbom_blocksize(void) { }
#endif
#ifdef CONFIG_RISCV_DMA_NONCOHERENT
void riscv_noncoherent_supported(void);

View File

@ -45,6 +45,7 @@ int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu);
int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
void kvm_riscv_guest_timer_init(struct kvm *kvm);
void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu);
bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu);

View File

@ -708,6 +708,9 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
}
}
/* Sync-up timer CSRs */
kvm_riscv_vcpu_timer_sync(vcpu);
}
int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)

View File

@ -320,6 +320,21 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
kvm_riscv_vcpu_timer_unblocking(vcpu);
}
void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_timer *t = &vcpu->arch.timer;
if (!t->sstc_enabled)
return;
#if defined(CONFIG_32BIT)
t->next_cycles = csr_read(CSR_VSTIMECMP);
t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
#else
t->next_cycles = csr_read(CSR_VSTIMECMP);
#endif
}
void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_timer *t = &vcpu->arch.timer;
@ -327,13 +342,11 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
if (!t->sstc_enabled)
return;
t = &vcpu->arch.timer;
#if defined(CONFIG_32BIT)
t->next_cycles = csr_read(CSR_VSTIMECMP);
t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
#else
t->next_cycles = csr_read(CSR_VSTIMECMP);
#endif
/*
* The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
* upon every VM exit so no need to save here.
*/
/* timer should be enabled for the remaining operations */
if (unlikely(!t->init_done))
return;

View File

@ -3,6 +3,7 @@
* Copyright (C) 2017 SiFive
*/
#include <linux/of.h>
#include <asm/cacheflush.h>
#ifdef CONFIG_SMP
@ -86,3 +87,40 @@ void flush_icache_pte(pte_t pte)
flush_icache_all();
}
#endif /* CONFIG_MMU */
unsigned int riscv_cbom_block_size;
EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
void riscv_init_cbom_blocksize(void)
{
struct device_node *node;
unsigned long cbom_hartid;
u32 val, probed_block_size;
int ret;
probed_block_size = 0;
for_each_of_cpu_node(node) {
unsigned long hartid;
ret = riscv_of_processor_hartid(node, &hartid);
if (ret)
continue;
/* set block-size for cbom extension if available */
ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
if (ret)
continue;
if (!probed_block_size) {
probed_block_size = val;
cbom_hartid = hartid;
} else {
if (probed_block_size != val)
pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
cbom_hartid, hartid);
}
}
if (probed_block_size)
riscv_cbom_block_size = probed_block_size;
}

View File

@ -8,13 +8,8 @@
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/mm.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <asm/cacheflush.h>
unsigned int riscv_cbom_block_size;
EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
static bool noncoherent_supported;
void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
@ -77,42 +72,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
dev->dma_coherent = coherent;
}
#ifdef CONFIG_RISCV_ISA_ZICBOM
void riscv_init_cbom_blocksize(void)
{
struct device_node *node;
unsigned long cbom_hartid;
u32 val, probed_block_size;
int ret;
probed_block_size = 0;
for_each_of_cpu_node(node) {
unsigned long hartid;
ret = riscv_of_processor_hartid(node, &hartid);
if (ret)
continue;
/* set block-size for cbom extension if available */
ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
if (ret)
continue;
if (!probed_block_size) {
probed_block_size = val;
cbom_hartid = hartid;
} else {
if (probed_block_size != val)
pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
cbom_hartid, hartid);
}
}
if (probed_block_size)
riscv_cbom_block_size = probed_block_size;
}
#endif
void riscv_noncoherent_supported(void)
{
WARN(!riscv_cbom_block_size,

View File

@ -6442,26 +6442,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
return 0;
}
static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
struct kvm_msr_filter *filter)
{
struct kvm_msr_filter __user *user_msr_filter = argp;
struct kvm_x86_msr_filter *new_filter, *old_filter;
struct kvm_msr_filter filter;
bool default_allow;
bool empty = true;
int r = 0;
u32 i;
if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
return -EFAULT;
if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++)
empty &= !filter.ranges[i].nmsrs;
for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
empty &= !filter->ranges[i].nmsrs;
default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY);
if (empty && !default_allow)
return -EINVAL;
@ -6469,8 +6465,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
if (!new_filter)
return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) {
r = kvm_add_msr_filter(new_filter, &filter->ranges[i]);
if (r) {
kvm_free_msr_filter(new_filter);
return r;
@ -6493,6 +6489,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
return 0;
}
#ifdef CONFIG_KVM_COMPAT
/* for KVM_X86_SET_MSR_FILTER */
struct kvm_msr_filter_range_compat {
__u32 flags;
__u32 nmsrs;
__u32 base;
__u32 bitmap;
};
struct kvm_msr_filter_compat {
__u32 flags;
struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES];
};
#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat)
long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct kvm *kvm = filp->private_data;
long r = -ENOTTY;
switch (ioctl) {
case KVM_X86_SET_MSR_FILTER_COMPAT: {
struct kvm_msr_filter __user *user_msr_filter = argp;
struct kvm_msr_filter_compat filter_compat;
struct kvm_msr_filter filter;
int i;
if (copy_from_user(&filter_compat, user_msr_filter,
sizeof(filter_compat)))
return -EFAULT;
filter.flags = filter_compat.flags;
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
struct kvm_msr_filter_range_compat *cr;
cr = &filter_compat.ranges[i];
filter.ranges[i] = (struct kvm_msr_filter_range) {
.flags = cr->flags,
.nmsrs = cr->nmsrs,
.base = cr->base,
.bitmap = (__u8 *)(ulong)cr->bitmap,
};
}
r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
break;
}
}
return r;
}
#endif
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
static int kvm_arch_suspend_notifier(struct kvm *kvm)
{
@ -6915,9 +6967,16 @@ long kvm_arch_vm_ioctl(struct file *filp,
case KVM_SET_PMU_EVENT_FILTER:
r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
break;
case KVM_X86_SET_MSR_FILTER:
r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
case KVM_X86_SET_MSR_FILTER: {
struct kvm_msr_filter __user *user_msr_filter = argp;
struct kvm_msr_filter filter;
if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
return -EFAULT;
r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
break;
}
default:
r = -ENOTTY;
}

View File

@ -66,6 +66,14 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_clk)
goto err_map;
}
/* Parse the device's DT node for an endianness specification */
if (of_property_read_bool(np, "big-endian"))
syscon_config.val_format_endian = REGMAP_ENDIAN_BIG;
else if (of_property_read_bool(np, "little-endian"))
syscon_config.val_format_endian = REGMAP_ENDIAN_LITTLE;
else if (of_property_read_bool(np, "native-endian"))
syscon_config.val_format_endian = REGMAP_ENDIAN_NATIVE;
/*
* search for reg-io-width property in DT. If it is not provided,
* default to 4 bytes. regmap_init_mmio will return an error if values

View File

@ -1390,6 +1390,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap);
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg);
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);

View File

@ -756,11 +756,14 @@ struct perf_event {
struct fasync_struct *fasync;
/* delayed work for NMIs and such */
int pending_wakeup;
int pending_kill;
int pending_disable;
unsigned int pending_wakeup;
unsigned int pending_kill;
unsigned int pending_disable;
unsigned int pending_sigtrap;
unsigned long pending_addr; /* SIGTRAP */
struct irq_work pending;
struct irq_work pending_irq;
struct callback_head pending_task;
unsigned int pending_work;
atomic_t event_limit;
@ -877,6 +880,14 @@ struct perf_event_context {
#endif
void *task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
/*
* Sum (event->pending_sigtrap + event->pending_work)
*
* The SIGTRAP is targeted at ctx->task, as such it won't do changing
* that until the signal is delivered.
*/
local_t nr_pending;
};
/*

View File

@ -10,6 +10,7 @@
#include <uapi/linux/utsname.h>
enum uts_proc {
UTS_PROC_ARCH,
UTS_PROC_OSTYPE,
UTS_PROC_OSRELEASE,
UTS_PROC_VERSION,

View File

@ -54,6 +54,7 @@
#include <linux/highmem.h>
#include <linux/pgtable.h>
#include <linux/buildid.h>
#include <linux/task_work.h>
#include "internal.h"
@ -2276,11 +2277,26 @@ event_sched_out(struct perf_event *event,
event->pmu->del(event, 0);
event->oncpu = -1;
if (READ_ONCE(event->pending_disable) >= 0) {
WRITE_ONCE(event->pending_disable, -1);
if (event->pending_disable) {
event->pending_disable = 0;
perf_cgroup_event_disable(event, ctx);
state = PERF_EVENT_STATE_OFF;
}
if (event->pending_sigtrap) {
bool dec = true;
event->pending_sigtrap = 0;
if (state != PERF_EVENT_STATE_OFF &&
!event->pending_work) {
event->pending_work = 1;
dec = false;
task_work_add(current, &event->pending_task, TWA_RESUME);
}
if (dec)
local_dec(&event->ctx->nr_pending);
}
perf_event_set_state(event, state);
if (!is_software_event(event))
@ -2432,7 +2448,7 @@ static void __perf_event_disable(struct perf_event *event,
* hold the top-level event's child_mutex, so any descendant that
* goes to exit will block in perf_event_exit_event().
*
* When called from perf_pending_event it's OK because event->ctx
* When called from perf_pending_irq it's OK because event->ctx
* is the current context on this CPU and preemption is disabled,
* hence we can't get into perf_event_task_sched_out for this context.
*/
@ -2471,9 +2487,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
void perf_event_disable_inatomic(struct perf_event *event)
{
WRITE_ONCE(event->pending_disable, smp_processor_id());
/* can fail, see perf_pending_event_disable() */
irq_work_queue(&event->pending);
event->pending_disable = 1;
irq_work_queue(&event->pending_irq);
}
#define MAX_INTERRUPTS (~0ULL)
@ -3428,11 +3443,23 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
perf_pmu_disable(pmu);
/* PMIs are disabled; ctx->nr_pending is stable. */
if (local_read(&ctx->nr_pending) ||
local_read(&next_ctx->nr_pending)) {
/*
* Must not swap out ctx when there's pending
* events that rely on the ctx->task relation.
*/
raw_spin_unlock(&next_ctx->lock);
rcu_read_unlock();
goto inside_switch;
}
WRITE_ONCE(ctx->task, next);
WRITE_ONCE(next_ctx->task, task);
perf_pmu_disable(pmu);
if (cpuctx->sched_cb_usage && pmu->sched_task)
pmu->sched_task(ctx, false);
@ -3473,6 +3500,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
raw_spin_lock(&ctx->lock);
perf_pmu_disable(pmu);
inside_switch:
if (cpuctx->sched_cb_usage && pmu->sched_task)
pmu->sched_task(ctx, false);
task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
@ -4940,7 +4968,7 @@ static void perf_addr_filters_splice(struct perf_event *event,
static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
irq_work_sync(&event->pending_irq);
unaccount_event(event);
@ -6440,7 +6468,8 @@ static void perf_sigtrap(struct perf_event *event)
return;
/*
* perf_pending_event() can race with the task exiting.
* Both perf_pending_task() and perf_pending_irq() can race with the
* task exiting.
*/
if (current->flags & PF_EXITING)
return;
@ -6449,23 +6478,33 @@ static void perf_sigtrap(struct perf_event *event)
event->attr.type, event->attr.sig_data);
}
static void perf_pending_event_disable(struct perf_event *event)
/*
* Deliver the pending work in-event-context or follow the context.
*/
static void __perf_pending_irq(struct perf_event *event)
{
int cpu = READ_ONCE(event->pending_disable);
int cpu = READ_ONCE(event->oncpu);
/*
* If the event isn't running; we done. event_sched_out() will have
* taken care of things.
*/
if (cpu < 0)
return;
/*
* Yay, we hit home and are in the context of the event.
*/
if (cpu == smp_processor_id()) {
WRITE_ONCE(event->pending_disable, -1);
if (event->attr.sigtrap) {
if (event->pending_sigtrap) {
event->pending_sigtrap = 0;
perf_sigtrap(event);
atomic_set_release(&event->event_limit, 1); /* rearm event */
return;
local_dec(&event->ctx->nr_pending);
}
if (event->pending_disable) {
event->pending_disable = 0;
perf_event_disable_local(event);
}
perf_event_disable_local(event);
return;
}
@ -6485,35 +6524,62 @@ static void perf_pending_event_disable(struct perf_event *event)
* irq_work_queue(); // FAILS
*
* irq_work_run()
* perf_pending_event()
* perf_pending_irq()
*
* But the event runs on CPU-B and wants disabling there.
*/
irq_work_queue_on(&event->pending, cpu);
irq_work_queue_on(&event->pending_irq, cpu);
}
static void perf_pending_event(struct irq_work *entry)
static void perf_pending_irq(struct irq_work *entry)
{
struct perf_event *event = container_of(entry, struct perf_event, pending);
struct perf_event *event = container_of(entry, struct perf_event, pending_irq);
int rctx;
rctx = perf_swevent_get_recursion_context();
/*
* If we 'fail' here, that's OK, it means recursion is already disabled
* and we won't recurse 'further'.
*/
rctx = perf_swevent_get_recursion_context();
perf_pending_event_disable(event);
/*
* The wakeup isn't bound to the context of the event -- it can happen
* irrespective of where the event is.
*/
if (event->pending_wakeup) {
event->pending_wakeup = 0;
perf_event_wakeup(event);
}
__perf_pending_irq(event);
if (rctx >= 0)
perf_swevent_put_recursion_context(rctx);
}
static void perf_pending_task(struct callback_head *head)
{
struct perf_event *event = container_of(head, struct perf_event, pending_task);
int rctx;
/*
* If we 'fail' here, that's OK, it means recursion is already disabled
* and we won't recurse 'further'.
*/
preempt_disable_notrace();
rctx = perf_swevent_get_recursion_context();
if (event->pending_work) {
event->pending_work = 0;
perf_sigtrap(event);
local_dec(&event->ctx->nr_pending);
}
if (rctx >= 0)
perf_swevent_put_recursion_context(rctx);
preempt_enable_notrace();
}
#ifdef CONFIG_GUEST_PERF_EVENTS
struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
@ -9198,8 +9264,8 @@ int perf_event_account_interrupt(struct perf_event *event)
*/
static int __perf_event_overflow(struct perf_event *event,
int throttle, struct perf_sample_data *data,
struct pt_regs *regs)
int throttle, struct perf_sample_data *data,
struct pt_regs *regs)
{
int events = atomic_read(&event->event_limit);
int ret = 0;
@ -9222,24 +9288,36 @@ static int __perf_event_overflow(struct perf_event *event,
if (events && atomic_dec_and_test(&event->event_limit)) {
ret = 1;
event->pending_kill = POLL_HUP;
event->pending_addr = data->addr;
perf_event_disable_inatomic(event);
}
if (event->attr.sigtrap) {
/*
* Should not be able to return to user space without processing
* pending_sigtrap (kernel events can overflow multiple times).
*/
WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel);
if (!event->pending_sigtrap) {
event->pending_sigtrap = 1;
local_inc(&event->ctx->nr_pending);
}
event->pending_addr = data->addr;
irq_work_queue(&event->pending_irq);
}
READ_ONCE(event->overflow_handler)(event, data, regs);
if (*perf_event_fasync(event) && event->pending_kill) {
event->pending_wakeup = 1;
irq_work_queue(&event->pending);
irq_work_queue(&event->pending_irq);
}
return ret;
}
int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
struct perf_sample_data *data,
struct pt_regs *regs)
{
return __perf_event_overflow(event, 1, data, regs);
}
@ -11556,8 +11634,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
init_waitqueue_head(&event->waitq);
event->pending_disable = -1;
init_irq_work(&event->pending, perf_pending_event);
init_irq_work(&event->pending_irq, perf_pending_irq);
init_task_work(&event->pending_task, perf_pending_task);
mutex_init(&event->mmap_mutex);
raw_spin_lock_init(&event->addr_filters.lock);
@ -11579,9 +11657,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
if (parent_event)
event->event_caps = parent_event->event_caps;
if (event->attr.sigtrap)
atomic_set(&event->event_limit, 1);
if (task) {
event->attach_state = PERF_ATTACH_TASK;
/*

View File

@ -22,7 +22,7 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
atomic_set(&handle->rb->poll, EPOLLIN);
handle->event->pending_wakeup = 1;
irq_work_queue(&handle->event->pending);
irq_work_queue(&handle->event->pending_irq);
}
/*

View File

@ -687,6 +687,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
perf_sample_data_init(sd, 0, 0);
sd->raw = &raw;
sd->sample_flags |= PERF_SAMPLE_RAW;
err = __bpf_perf_event_output(regs, map, flags, sd);
@ -745,6 +746,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
perf_fetch_caller_regs(regs);
perf_sample_data_init(sd, 0, 0);
sd->raw = &raw;
sd->sample_flags |= PERF_SAMPLE_RAW;
ret = __bpf_perf_event_output(regs, map, flags, sd);
out:

View File

@ -74,6 +74,7 @@ static int proc_do_uts_string(struct ctl_table *table, int write,
static DEFINE_CTL_TABLE_POLL(hostname_poll);
static DEFINE_CTL_TABLE_POLL(domainname_poll);
// Note: update 'enum uts_proc' to match any changes to this table
static struct ctl_table uts_kern_table[] = {
{
.procname = "arch",

View File

@ -1177,6 +1177,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
#define KVM_CAP_S390_ZPCI_OP 221
#define KVM_CAP_S390_CPU_TOPOLOGY 222
#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
#ifdef KVM_CAP_IRQ_ROUTING

View File

@ -662,8 +662,8 @@ int test_kvm_device(uint32_t gic_dev_type)
: KVM_DEV_TYPE_ARM_VGIC_V2;
if (!__kvm_test_create_device(v.vm, other)) {
ret = __kvm_test_create_device(v.vm, other);
TEST_ASSERT(ret && (errno == EINVAL || errno == EEXIST),
ret = __kvm_create_device(v.vm, other);
TEST_ASSERT(ret < 0 && (errno == EINVAL || errno == EEXIST),
"create GIC device while other version exists");
}

View File

@ -67,7 +67,7 @@ struct memslot_antagonist_args {
static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
uint64_t nr_modifications)
{
const uint64_t pages = 1;
uint64_t pages = max_t(int, vm->page_size, getpagesize()) / vm->page_size;
uint64_t gpa;
int i;

View File

@ -62,6 +62,8 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr,
.remove_on_exec = 1, /* Required by sigtrap. */
.sigtrap = 1, /* Request synchronous SIGTRAP on event. */
.sig_data = TEST_SIG_DATA(addr, id),
.exclude_kernel = 1, /* To allow */
.exclude_hv = 1, /* running as !root */
};
return attr;
}
@ -93,9 +95,13 @@ static void *test_thread(void *arg)
__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
iter = ctx.iterate_on; /* read */
for (i = 0; i < iter - 1; i++) {
__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
ctx.iterate_on = iter; /* idempotent write */
if (iter >= 0) {
for (i = 0; i < iter - 1; i++) {
__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
ctx.iterate_on = iter; /* idempotent write */
}
} else {
while (ctx.iterate_on);
}
return NULL;
@ -208,4 +214,27 @@ TEST_F(sigtrap_threads, signal_stress)
EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
}
TEST_F(sigtrap_threads, signal_stress_with_disable)
{
const int target_count = NUM_THREADS * 3000;
int i;
ctx.iterate_on = -1;
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
pthread_barrier_wait(&self->barrier);
while (__atomic_load_n(&ctx.signal_count, __ATOMIC_RELAXED) < target_count) {
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_DISABLE, 0), 0);
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
}
ctx.iterate_on = 0;
for (i = 0; i < NUM_THREADS; i++)
ASSERT_EQ(pthread_join(self->threads[i], NULL), 0);
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_DISABLE, 0), 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
}
TEST_HARNESS_MAIN

View File

@ -4839,6 +4839,12 @@ struct compat_kvm_clear_dirty_log {
};
};
long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
return -ENOTTY;
}
static long kvm_vm_compat_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@ -4847,6 +4853,11 @@ static long kvm_vm_compat_ioctl(struct file *filp,
if (kvm->mm != current->mm || kvm->vm_dead)
return -EIO;
r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg);
if (r != -ENOTTY)
return r;
switch (ioctl) {
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
case KVM_CLEAR_DIRTY_LOG: {