perf_counter: fix counter freeing logic

Fix counter lifetime bugs which explain the crashes reported by
Marcelo Tosatti and Arnaldo Carvalho de Melo.

The new rule is: flushing + freeing is only done for a task's
own counters, never for other tasks.

[ Impact: fix crashes/lockups with inherited counters ]

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reported-by: Marcelo Tosatti <mtosatti@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Ingo Molnar 2009-05-17 11:08:41 +02:00
parent b68f1d2e7a
commit 33b2fb303f
2 changed files with 9 additions and 12 deletions

View File

@ -178,12 +178,6 @@ repeat:
proc_flush_task(p);
/*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
perf_counter_exit_task(p);
write_lock_irq(&tasklist_lock);
tracehook_finish_release_task(p);
__exit_signal(p);
@ -985,6 +979,13 @@ NORET_TYPE void do_exit(long code)
module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
/*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
perf_counter_exit_task(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
mpol_put(tsk->mempolicy);
@ -1257,12 +1258,6 @@ static int wait_task_zombie(struct task_struct *p, int options,
*/
read_unlock(&tasklist_lock);
/*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
perf_counter_exit_task(p);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
? p->signal->group_exit_code : p->exit_code;

View File

@ -3299,6 +3299,8 @@ void perf_counter_exit_task(struct task_struct *child)
struct perf_counter *child_counter, *tmp;
struct perf_counter_context *child_ctx;
WARN_ON_ONCE(child != current);
child_ctx = &child->perf_counter_ctx;
if (likely(!child_ctx->nr_counters))