p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

perf: Untangle 'owner' confusion 

There are two concepts of owner wrt an event and they are conflated:

 - event::owner / event::owner_list,
   used by prctl(.option = PR_TASK_PERF_EVENTS_{EN,DIS}ABLE).

 - the 'owner' of the event object, typically the file descriptor.

Currently these two concepts are conflated, which gives trouble with
scm_rights passing of file descriptors. Passing the event and then
closing the creating task would render the event 'orphan' and would
have it cleared out. Unlikely what is expectd.

This patch untangles these two concepts by using PERF_EVENT_STATE_EXIT
to denote the second type.

Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.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>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2016-01-26 14:55:02 +01:00 committed by Ingo Molnar
parent 45a0e07abf
commit 60beda8493
1 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
kernel/events/core.c
View File

@ -1650,7 +1650,7 @@ static void perf_group_detach(struct perf_event *event)
*/
static bool is_orphaned_event(struct perf_event *event)
{
return event && !is_kernel_event(event) && !READ_ONCE(event->owner);
return event && event->state == PERF_EVENT_STATE_EXIT;
}
/*
@ -1771,6 +1771,7 @@ group_sched_out(struct perf_event *group_event,
}
#define DETACH_GROUP 0x01UL
#define DETACH_STATE 0x02UL
/*
* Cross CPU call to remove a performance event
@ -1790,6 +1791,8 @@ __perf_remove_from_context(struct perf_event *event,
if (flags & DETACH_GROUP)
perf_group_detach(event);
list_del_event(event, ctx);
if (flags & DETACH_STATE)
event->state = PERF_EVENT_STATE_EXIT;
if (!ctx->nr_events && ctx->is_active) {
ctx->is_active = 0;
@ -3801,9 +3804,16 @@ static void put_event(struct perf_event *event)
*/
ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
WARN_ON_ONCE(ctx->parent_ctx);
perf_remove_from_context(event, DETACH_GROUP);
perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
perf_event_ctx_unlock(event, ctx);
/*
* At this point we must have event->state == PERF_EVENT_STATE_EXIT,
* either from the above perf_remove_from_context() or through
* perf_event_exit_event().
*/
WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
_free_event(event);
}