perf/core: Fix WARN 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);

[peterz: use guard instead of goto unlock]
Fixes: db4a835601b7 ("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

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d78608323916fa5d249948f07169cfb4f9371a50..d7cf008f3d7559d41c311c4a910170c9fd21d8ed 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,19 @@ 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)
@@ -944,7 +957,13 @@ static void perf_cgroup_switch(struct task_struct *task)
        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;
+
        perf_ctx_disable(&cpuctx->ctx, true);
 
        ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +981,6 @@ 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,