On Mon, Jun 16, 2014 at 10:24:58AM -0400, Sasha Levin wrote:
> Hi all,
>
> While fuzzing with trinity inside a KVM tools guest running the latest -next
> kernel I've stumbled on the following spew:
>
> [ 430.429005] ======================================================
> [ 430.429005] [ INFO: possible circular locking dependency detected ]
> [ 430.429005] 3.15.0-next-20140613-sasha-00026-g6dd125d-dirty #654 Not
> tainted
> [ 430.429005] -------------------------------------------------------
> [ 430.429005] trinity-c578/9725 is trying to acquire lock:
> [ 430.429005] (&(&pool->lock)->rlock){-.-...}, at: __queue_work
> (kernel/workqueue.c:1346)
> [ 430.429005]
> [ 430.429005] but task is already holding lock:
> [ 430.429005] (&ctx->lock){-.....}, at: perf_event_exit_task
> (kernel/events/core.c:7471 kernel/events/core.c:7533)
> [ 430.439509]
> [ 430.439509] which lock already depends on the new lock.
> [ 430.450111] 1 lock held by trinity-c578/9725:
> [ 430.450111] #0: (&ctx->lock){-.....}, at: perf_event_exit_task
> (kernel/events/core.c:7471 kernel/events/core.c:7533)
> [ 430.450111]
> [ 430.450111] stack backtrace:
> [ 430.450111] CPU: 6 PID: 9725 Comm: trinity-c578 Not tainted
> 3.15.0-next-20140613-sasha-00026-g6dd125d-dirty #654
> [ 430.450111] ffffffffadb45840 ffff880101787848 ffffffffaa511b1c
> 0000000000000003
> [ 430.450111] ffffffffadb8a4c0 ffff880101787898 ffffffffaa5044e2
> 0000000000000001
> [ 430.450111] ffff880101787928 ffff880101787898 ffff8800aed98cf8
> ffff8800aed98000
> [ 430.450111] Call Trace:
> [ 430.450111] dump_stack (lib/dump_stack.c:52)
> [ 430.450111] print_circular_bug (kernel/locking/lockdep.c:1216)
> [ 430.450111] __lock_acquire (kernel/locking/lockdep.c:1840
> kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131
> kernel/locking/lockdep.c:3182)
> [ 430.450111] lock_acquire (./arch/x86/include/asm/current.h:14
> kernel/locking/lockdep.c:3602)
> [ 430.450111] _raw_spin_lock (include/linux/spinlock_api_smp.h:143
> kernel/locking/spinlock.c:151)
> [ 430.450111] __queue_work (kernel/workqueue.c:1346)
> [ 430.450111] queue_work_on (kernel/workqueue.c:1424)
> [ 430.450111] free_object (lib/debugobjects.c:209)
> [ 430.450111] __debug_check_no_obj_freed (lib/debugobjects.c:715)
> [ 430.450111] debug_check_no_obj_freed (lib/debugobjects.c:727)
> [ 430.450111] kmem_cache_free (mm/slub.c:2683 mm/slub.c:2711)
> [ 430.450111] free_task (kernel/fork.c:221)
> [ 430.450111] __put_task_struct (kernel/fork.c:250)
> [ 430.450111] put_ctx (include/linux/sched.h:1855 kernel/events/core.c:898)
> [ 430.450111] perf_event_exit_task (kernel/events/core.c:907
> kernel/events/core.c:7478 kernel/events/core.c:7533)
> [ 430.450111] do_exit (kernel/exit.c:766)
> [ 430.450111] do_group_exit (kernel/exit.c:884)
> [ 430.450111] get_signal_to_deliver (kernel/signal.c:2347)
> [ 430.450111] do_signal (arch/x86/kernel/signal.c:698)
> [ 430.450111] do_notify_resume (arch/x86/kernel/signal.c:751)
> [ 430.450111] 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 something like..
I can't immediately see how this changed recently, but given that you
say its easy to reproduce, can you give this a spin?
---
kernel/events/core.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a33d9a2bcbd7..5e90fa579055 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7474,7 +7474,7 @@ __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])) {
@@ -7499,6 +7499,15 @@ 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
@@ -7509,6 +7518,13 @@ static void perf_event_exit_task_context(struct
task_struct *child, int ctxn)
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
* get a few PERF_RECORD_READ events.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
