linux/kernel/events
Peter Zijlstra 63b6da39bb perf: Fix perf_event_exit_task() race
There is a race against perf_event_exit_task() vs
event_function_call(),find_get_context(),perf_install_in_context()
(iow, everyone).

Since there is no permanent marker on a context that its dead, it is
quite possible that we access (and even modify) a context after its
passed through perf_event_exit_task().

For instance, find_get_context() might find the context still
installed, but by the time we get to perf_install_in_context() it
might already have passed through perf_event_exit_task() and be
considered dead, we will however still add the event to it.

Solve this by marking a ctx dead by setting its ctx->task value to -1,
it must be !0 so we still know its a (former) task context.

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>
2016-01-21 18:54:25 +01:00
..
callchain.c treewide: Remove old email address 2015-11-23 09:44:58 +01:00
core.c perf: Fix perf_event_exit_task() race 2016-01-21 18:54:25 +01:00
hw_breakpoint.c perf: Collapse and fix event_function_call() users 2016-01-21 18:54:24 +01:00
internal.h perf: Fix AUX buffer refcounting 2015-07-06 14:08:30 +02:00
Makefile ftrace: allow architectures to specify ftrace compile options 2015-01-29 09:19:19 +01:00
ring_buffer.c treewide: Remove old email address 2015-11-23 09:44:58 +01:00
uprobes.c treewide: Remove old email address 2015-11-23 09:44:58 +01:00