linux-yocto/kernel
Luo Gengkun fd199366bf perf/core: Fix WARN in perf_cgroup_switch()
[ Upstream commit 3172fb9866 ]

There may be concurrency between perf_cgroup_switch and
perf_cgroup_event_disable. Consider the following scenario: after a new
perf cgroup event is created on CPU0, the new event may not trigger
a reprogramming, causing ctx->is_active to be 0. In this case, when CPU1
disables this perf event, it executes __perf_remove_from_context->
list _del_event->perf_cgroup_event_disable on CPU1, which causes a race
with perf_cgroup_switch running on CPU0.

The following describes the details of this concurrency scenario:

CPU0						CPU1

perf_cgroup_switch:
   ...
   # cpuctx->cgrp is not NULL here
   if (READ_ONCE(cpuctx->cgrp) == NULL)
   	return;

						perf_remove_from_context:
						   ...
						   raw_spin_lock_irq(&ctx->lock);
						   ...
						   # ctx->is_active == 0 because reprogramm is not
						   # tigger, so CPU1 can do __perf_remove_from_context
						   # for CPU0
						   __perf_remove_from_context:
						         perf_cgroup_event_disable:
							    ...
							    if (--ctx->nr_cgroups)
							    ...

   # this warning will happened because CPU1 changed
   # ctx.nr_cgroups to 0.
   WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);

[peterz: use guard instead of goto unlock]
Fixes: db4a835601 ("perf/core: Set cgroup in CPU contexts for new cgroup events")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250604033924.3914647-3-luogengkun@huaweicloud.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
2025-06-27 11:11:45 +01:00
..
bpf bpf: Use proper type to calculate bpf_raw_tp_null_args.mask index 2025-06-27 11:11:33 +01:00
cgroup cgroup,freezer: fix incomplete freezing when attaching tasks 2025-06-27 11:11:19 +01:00
configs tinyconfig: remove unnecessary 'is not set' for choice blocks 2024-09-01 20:34:38 +09:00
debug move asm/unaligned.h to linux/unaligned.h 2024-10-02 17:23:23 -04:00
dma dma-mapping: Fix warning reported for missing prototype 2025-05-29 11:01:59 +02:00
entry treewide: context_tracking: Rename CONTEXT_* into CT_STATE_* 2024-07-29 07:33:10 +05:30
events perf/core: Fix WARN in perf_cgroup_switch() 2025-06-27 11:11:45 +01:00
futex futex: Pass in task to futex_queue() 2025-03-22 12:54:14 -07:00
gcov
irq PCI/MSI: Convert pci_msi_ignore_mask to per MSI domain flag 2025-05-02 07:58:56 +02:00
kcsan kcsan: Turn report_filterlist_lock into a raw_spinlock 2024-12-14 20:03:37 +01:00
livepatch
locking locking/lockdep: Decrease nr_unused_locks if lock unused in zap_class() 2025-04-20 10:15:45 +02:00
module module: sign with sha512 instead of sha1 by default 2025-05-02 07:58:51 +02:00
power PM: sleep: Print PM debug messages during hibernation 2025-06-19 15:31:32 +02:00
printk printk: Check CON_SUSPEND when unblanking a console 2025-05-29 11:02:22 +02:00
rcu rcu/cpu_stall_cputime: fix the hardirq count for x86 architecture 2025-06-19 15:31:30 +02:00
sched sched_ext, sched/core: Don't call scx_group_set_weight() prematurely from sched_create_group() 2025-06-27 11:11:38 +01:00
time clocksource: Fix the CPUs' choice in the watchdog per CPU verification 2025-06-27 11:11:26 +01:00
trace ftrace: Fix UAF when lookup kallsym after ftrace disabled 2025-06-27 11:11:23 +01:00
.gitignore
acct.c acct: block access to kernel internal filesystems 2025-02-27 04:30:23 -08:00
async.c
audit_fsnotify.c
audit_tree.c
audit_watch.c
audit.c audit: Make use of str_enabled_disabled() helper 2024-09-03 16:35:16 -04:00
audit.h
auditfilter.c audit: use task_tgid_nr() instead of task_pid_nr() 2024-08-28 16:48:28 -04:00
auditsc.c audit: use task_tgid_nr() instead of task_pid_nr() 2024-08-28 16:48:28 -04:00
backtracetest.c
bounds.c
capability.c
cfi.c
compat.c
configs.c
context_tracking.c context_tracking, rcu: Rename rcu_dyntick trace event into rcu_watching 2024-08-15 21:30:43 +05:30
cpu_pm.c
cpu.c watchdog/hardlockup/perf: Fix perf_event memory leak 2025-04-10 14:39:11 +02:00
crash_core.c Document/kexec: generalize crash hotplug description 2024-09-01 20:43:37 -07:00
crash_reserve.c crash: fix crash memory reserve exceed system memory bug 2024-09-01 20:43:30 -07:00
cred.c
delayacct.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
dma.c
elfcorehdr.c
exec_domain.c
exit.c perf: Fix sample vs do_exit() 2025-06-27 11:11:45 +01:00
exit.h
extable.c
fail_function.c
fork.c kernel/fork: only call untrack_pfn_clear() on VMAs duplicated for fork() 2025-05-29 11:03:14 +02:00
freezer.c sched/fair: Fix external p->on_rq users 2024-10-14 09:14:35 +02:00
gen_kheaders.sh kheaders: Ignore silly-rename files 2025-01-23 17:22:55 +01:00
groups.c
hung_task.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
iomem.c
irq_work.c
jump_label.c jump_label: Fix static_key_slow_dec() yet again 2024-09-10 11:57:27 +02:00
kallsyms_internal.h kallsyms: get rid of code for absolute kallsyms 2024-07-20 16:33:21 +09:00
kallsyms_selftest.c kallsyms: Match symbols exactly with CONFIG_LTO_CLANG 2024-08-15 09:33:35 -07:00
kallsyms_selftest.h
kallsyms.c kallsyms: Match symbols exactly with CONFIG_LTO_CLANG 2024-08-15 09:33:35 -07:00
kcmp.c
Kconfig.freezer
Kconfig.hz
Kconfig.kexec crash, powerpc: default to CRASH_DUMP=n on PPC_BOOK3S_32 2024-11-14 22:43:48 -08:00
Kconfig.locks
Kconfig.preempt sched_ext: Build fix on !CONFIG_STACKTRACE[_SUPPORT] 2024-08-01 07:08:01 -10:00
kcov.c kcov: mark in_softirq_really() as __always_inline 2025-01-09 13:33:49 +01:00
kexec_core.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
kexec_elf.c kexec: initialize ELF lowest address to ULONG_MAX 2025-04-10 14:39:24 +02:00
kexec_file.c kexec_file: fix elfcorehdr digest exclusion when CONFIG_CRASH_HOTPLUG=y 2024-09-01 17:59:01 -07:00
kexec_internal.h kexec: use atomic_try_cmpxchg_acquire() in kexec_trylock() 2024-09-01 20:43:23 -07:00
kexec.c
kheaders.c
kprobes.c kprobes: Fix to check symbol prefixes correctly 2024-08-05 14:04:03 +09:00
ksyms_common.c
ksysfs.c profiling: remove prof_cpu_mask 2024-07-29 10:45:54 -07:00
kthread.c kthread: unpark only parked kthread 2024-10-09 12:47:19 -07:00
latencytop.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
Makefile mm: move kernel/numa.c to mm/ 2024-09-03 21:15:26 -07:00
module_signature.c
notifier.c
nsproxy.c introduce fd_file(), convert all accessors to it. 2024-08-12 22:00:43 -04:00
padata.c padata: do not leak refcount in reorder_work 2025-05-29 11:03:19 +02:00
panic.c objtool, panic: Disable SMAP in __stack_chk_fail() 2025-05-02 07:59:19 +02:00
params.c module: ensure that kobject_put() is safe for module type kobjects 2025-05-18 08:24:54 +02:00
pid_namespace.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
pid_sysctl.h sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
pid.c introduce fd_file(), convert all accessors to it. 2024-08-12 22:00:43 -04:00
profile.c profiling: remove profile=sleep support 2024-08-04 13:36:28 -07:00
ptrace.c
range.c
reboot.c Flush console log from kernel_power_off() 2025-04-20 10:15:12 +02:00
regset.c
relay.c [tree-wide] finally take no_llseek out 2024-09-27 08:18:43 -07:00
resource_kunit.c resource, kunit: fix user-after-free in resource_test_region_intersects() 2024-10-09 12:47:19 -07:00
resource.c resource,kexec: walk_system_ram_res_rev must retain resource flags 2024-10-28 21:40:40 -07:00
rseq.c
scftorture.c
scs.c
seccomp.c seccomp: passthrough uretprobe systemcall without filtering 2025-02-17 10:05:12 +01:00
signal.c pidfs: improve multi-threaded exec and premature thread-group leader exit polling 2025-05-29 11:02:09 +02:00
smp.c smp: print only local CPU info when sched_clock goes backward 2024-08-15 00:06:48 +05:30
smpboot.c
smpboot.h
softirq.c lockdep: Fix wait context check on softirq for PREEMPT_RT 2025-05-29 11:02:08 +02:00
stackleak.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
stacktrace.c
static_call_inline.c x86/static-call: provide a way to do very early static-call updates 2024-12-19 18:13:23 +01:00
static_call.c
stop_machine.c rcu: Rename rcu_momentary_dyntick_idle() into rcu_momentary_eqs() 2024-08-15 21:30:42 +05:30
sys_ni.c Probes updates for v6.11: 2024-07-18 12:19:20 -07:00
sys.c struct fd layout change (and conversion to accessor helpers) 2024-09-23 09:35:36 -07:00
sysctl-test.c
sysctl.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
task_work.c sched/core: Disable page allocation in task_tick_mm_cid() 2024-10-11 10:49:32 +02:00
taskstats.c introduce fd_file(), convert all accessors to it. 2024-08-12 22:00:43 -04:00
torture.c
tracepoint.c tracepoint: Support iterating tracepoints in a loading module 2024-09-25 23:23:44 +09:00
tsacct.c tsacct: replace strncpy() with strscpy() 2024-07-12 16:39:53 -07:00
ucount.c signal: restore the override_rlimit logic 2024-11-07 14:14:59 -08:00
uid16.c
uid16.h
umh.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
up.c
user_namespace.c user_namespace: use kmemdup_array() instead of kmemdup() for multiple allocation 2024-09-09 16:47:42 -07:00
user-return-notifier.c
user.c uidgid: make sure we fit into one cacheline 2024-09-12 12:16:09 +02:00
usermode_driver.c
utsname_sysctl.c sysctl: treewide: constify the ctl_table argument of proc_handlers 2024-07-24 20:59:29 +02:00
utsname.c
vhost_task.c vhost_task: fix vhost_task_create() documentation 2025-05-29 11:01:59 +02:00
vmcore_info.c mm: support only one page_type per page 2024-09-03 21:15:43 -07:00
watch_queue.c watch_queue: fix pipe accounting mismatch 2025-04-10 14:39:10 +02:00
watchdog_buddy.c
watchdog_perf.c watchdog/hardlockup/perf: Fix perf_event memory leak 2025-04-10 14:39:11 +02:00
watchdog.c watchdog: fix watchdog may detect false positive of softlockup 2025-06-27 11:11:22 +01:00
workqueue_internal.h
workqueue.c workqueue: Initialize wq_isolated_cpumask in workqueue_init_early() 2025-06-27 11:11:42 +01:00