openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

perf: Fix lockdep warning on process exit 

Sasha Levin reported:

> While fuzzing with trinity inside a KVM tools guest running the latest -next
> kernel I've stumbled on the following spew:
>
> ======================================================
> [ INFO: possible circular locking dependency detected ]
> 3.15.0-next-20140613-sasha-00026-g6dd125d-dirty #654 Not tainted
> -------------------------------------------------------
> trinity-c578/9725 is trying to acquire lock:
> (&(&pool->lock)->rlock){-.-...}, at: __queue_work (kernel/workqueue.c:1346)
>
> but task is already holding lock:
> (&ctx->lock){-.....}, at: perf_event_exit_task (kernel/events/core.c:7471 kernel/events/core.c:7533)
>
> which lock already depends on the new lock.

> 1 lock held by trinity-c578/9725:
> #0: (&ctx->lock){-.....}, at: perf_event_exit_task (kernel/events/core.c:7471 kernel/events/core.c:7533)
>
>  Call Trace:
>  dump_stack (lib/dump_stack.c:52)
>  print_circular_bug (kernel/locking/lockdep.c:1216)
>  __lock_acquire (kernel/locking/lockdep.c:1840 kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131 kernel/locking/lockdep.c:3182)
>  lock_acquire (./arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602)
>  _raw_spin_lock (include/linux/spinlock_api_smp.h:143 kernel/locking/spinlock.c:151)
>  __queue_work (kernel/workqueue.c:1346)
>  queue_work_on (kernel/workqueue.c:1424)
>  free_object (lib/debugobjects.c:209)
>  __debug_check_no_obj_freed (lib/debugobjects.c:715)
>  debug_check_no_obj_freed (lib/debugobjects.c:727)
>  kmem_cache_free (mm/slub.c:2683 mm/slub.c:2711)
>  free_task (kernel/fork.c:221)
>  __put_task_struct (kernel/fork.c:250)
>  put_ctx (include/linux/sched.h:1855 kernel/events/core.c:898)
>  perf_event_exit_task (kernel/events/core.c:907 kernel/events/core.c:7478 kernel/events/core.c:7533)
>  do_exit (kernel/exit.c:766)
>  do_group_exit (kernel/exit.c:884)
>  get_signal_to_deliver (kernel/signal.c:2347)
>  do_signal (arch/x86/kernel/signal.c:698)
>  do_notify_resume (arch/x86/kernel/signal.c:751)
>  int_signal (arch/x86/kernel/entry_64.S:600)

Urgh.. so the only way I can make that happen is through:

  perf_event_exit_task_context()
    raw_spin_lock(&child_ctx->lock);
    unclone_ctx(child_ctx)
      put_ctx(ctx->parent_ctx);
    raw_spin_unlock_irqrestore(&child_ctx->lock);

And we can avoid this by doing the change below.

I can't immediately see how this changed recently, but given that you
say it's easy to reproduce, lets fix this.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140623141242.GB19860@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2014-06-23 16:12:42 +02:00 committed by Ingo Molnar
parent 7711fe4fc2
commit 4a1c0f262f
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
kernel/events/core.c
View File

@ -7486,7 +7486,7 @@ __perf_event_exit_task(struct perf_event *child_event,
static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
{
struct perf_event *child_event, *next;
struct perf_event_context *child_ctx;
struct perf_event_context *child_ctx, *parent_ctx;
unsigned long flags;
if (likely(!child->perf_event_ctxp[ctxn])) {
@ -7511,6 +7511,15 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
raw_spin_lock(&child_ctx->lock);
task_ctx_sched_out(child_ctx);
child->perf_event_ctxp[ctxn] = NULL;
/*
* In order to avoid freeing: child_ctx->parent_ctx->task
* under perf_event_context::lock, grab another reference.
*/
parent_ctx = child_ctx->parent_ctx;
if (parent_ctx)
get_ctx(parent_ctx);
/*
* If this context is a clone; unclone it so it can't get
* swapped to another process while we're removing all
@ -7520,6 +7529,13 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
update_context_time(child_ctx);
raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
/*
* Now that we no longer hold perf_event_context::lock, drop
* our extra child_ctx->parent_ctx reference.
*/
if (parent_ctx)
put_ctx(parent_ctx);
/*
* Report the task dead after unscheduling the events so that we
* won't get any samples after PERF_RECORD_EXIT. We can however still