linux-kernel - [PATCH v3] perf/core: Fix WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0) in perf_cgroup

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [day] [month] [year] [list]

Message-Id: <20250609035316.250557-1-luogengkun@huaweicloud.com>
Date: Mon,  9 Jun 2025 03:53:16 +0000
From: Luo Gengkun <luogengkun@...weicloud.com>
To: peterz@...radead.org
Cc: mingo@...hat.com,
	acme@...nel.org,
	namhyung@...nel.org,
	mark.rutland@....com,
	alexander.shishkin@...ux.intel.com,
	jolsa@...nel.org,
	irogers@...gle.com,
	adrian.hunter@...el.com,
	kan.liang@...ux.intel.com,
	linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH v3] perf/core: Fix WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0) in perf_cgroup_switch

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);

To fix this problem, re-check the condition after hold the lock and take
this opportunity to convert to guard instead of adding goto unlock.

Fixes: db4a835601b7 ("perf/core: Set cgroup in CPU contexts for new cgroup events")
Signed-off-by: Luo Gengkun <luogengkun@...weicloud.com>
---
Changes in v3:
1. Using guard instead of adding goto unlock to make the code more robust.
2. Re-check the condition instead of expand the lock-holding critical
section.

Link to v2: https://lore.kernel.org/all/20250604033924.3914647-1-luogengkun@huaweicloud.com/
---
 kernel/events/core.c | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 280d42b40b34..4759a051459f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,25 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
 	__perf_ctx_unlock(&cpuctx->ctx);
 }
 
+typedef struct {
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+} class_perf_ctx_lock_t;
+
+static inline void
+class_perf_ctx_lock_destructor(class_perf_ctx_lock_t *_T)
+{
+	perf_ctx_unlock(_T->cpuctx, _T->ctx);
+}
+
+static inline class_perf_ctx_lock_t
+class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
+				struct perf_event_context *ctx)
+{
+	perf_ctx_lock(cpuctx, ctx);
+	return (class_perf_ctx_lock_t) {cpuctx, ctx};
+}
+
 #define TASK_TOMBSTONE ((void *)-1L)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -938,13 +957,19 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
-	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
-
 	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
 
-	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+	guard(perf_ctx_lock)(cpuctx, cpuctx->task_ctx);
+	/*
+	 * Re-check, could've raced vs perf_remove_from_context().
+	 */
+	if (READ_ONCE(cpuctx->cgrp) == NULL)
+		return;
+
+	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +987,6 @@ static void perf_cgroup_switch(struct task_struct *task)
 	ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
 
 	perf_ctx_enable(&cpuctx->ctx, true);
-	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
 static int perf_cgroup_ensure_storage(struct perf_event *event,
-- 
2.34.1