2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 13:13:57 +08:00

perf: Fix race in perf_event_exit_task_context()

There is a race between perf_event_exit_task_context() and
orphans_remove_work() which results in a use-after-free.

We mark ctx->task with TASK_TOMBSTONE to indicate a context is
'dead', under ctx->lock. After which point event_function_call()
on any event of that context will NOP

A concurrent orphans_remove_work() will only hold ctx->mutex for
the list iteration and not serialize against this. Therefore its
possible that orphans_remove_work()'s perf_remove_from_context()
call will fail, but we'll continue to free the event, with the
result of free'd memory still being on lists and everything.

Once perf_event_exit_task_context() gets around to acquiring
ctx->mutex it too will iterate the event list, encounter the
already free'd event and proceed to free it _again_. This fails
with the WARN in free_event().

Plug the race by having perf_event_exit_task_context() hold
ctx::mutex over the whole tear-down, thereby 'naturally'
serializing against all other sites, including the orphan work.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: alexander.shishkin@linux.intel.com
Cc: dsahern@gmail.com
Cc: namhyung@kernel.org
Link: http://lkml.kernel.org/r/20160125130954.GY6357@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2016-01-25 14:09:54 +01:00 committed by Ingo Molnar
parent 78cd2c748f
commit 6a3351b612

View File

@ -8748,14 +8748,40 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
{
struct perf_event_context *child_ctx, *clone_ctx = NULL;
struct perf_event *child_event, *next;
unsigned long flags;
WARN_ON_ONCE(child != current);
child_ctx = perf_lock_task_context(child, ctxn, &flags);
child_ctx = perf_pin_task_context(child, ctxn);
if (!child_ctx)
return;
/*
* In order to reduce the amount of tricky in ctx tear-down, we hold
* ctx::mutex over the entire thing. This serializes against almost
* everything that wants to access the ctx.
*
* The exception is sys_perf_event_open() /
* perf_event_create_kernel_count() which does find_get_context()
* without ctx::mutex (it cannot because of the move_group double mutex
* lock thing). See the comments in perf_install_in_context().
*
* We can recurse on the same lock type through:
*
* __perf_event_exit_task()
* sync_child_event()
* put_event()
* mutex_lock(&ctx->mutex)
*
* But since its the parent context it won't be the same instance.
*/
mutex_lock(&child_ctx->mutex);
/*
* In a single ctx::lock section, de-schedule the events and detach the
* context from the task such that we cannot ever get it scheduled back
* in.
*/
raw_spin_lock_irq(&child_ctx->lock);
task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
/*
@ -8767,14 +8793,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE);
put_task_struct(current); /* cannot be last */
/*
* If this context is a clone; unclone it so it can't get
* swapped to another process while we're removing all
* the events from it.
*/
clone_ctx = unclone_ctx(child_ctx);
update_context_time(child_ctx);
raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
raw_spin_unlock_irq(&child_ctx->lock);
if (clone_ctx)
put_ctx(clone_ctx);
@ -8786,18 +8806,6 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
*/
perf_event_task(child, child_ctx, 0);
/*
* We can recurse on the same lock type through:
*
* __perf_event_exit_task()
* sync_child_event()
* put_event()
* mutex_lock(&ctx->mutex)
*
* But since its the parent context it won't be the same instance.
*/
mutex_lock(&child_ctx->mutex);
list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
__perf_event_exit_task(child_event, child_ctx, child);