perf/ring_buffer: Fix exposing a temporarily decreased data_head
authorYabin Cui <yabinc@google.com>
Fri, 17 May 2019 11:52:31 +0000 (13:52 +0200)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Sat, 22 Jun 2019 06:16:16 +0000 (08:16 +0200)
commit9e2de43b538600df9a9bfffdb13730886aff5ceb
treecf163826cc09bae774f048b011b08513dfb073b3
parent746b9c0c3e59baacb180088b36424a39ffaf26bf
perf/ring_buffer: Fix exposing a temporarily decreased data_head

[ Upstream commit 1b038c6e05ff70a1e66e3e571c2e6106bdb75f53 ]

In perf_output_put_handle(), an IRQ/NMI can happen in below location and
write records to the same ring buffer:

...
local_dec_and_test(&rb->nest)
...                          <-- an IRQ/NMI can happen here
rb->user_page->data_head = head;
...

In this case, a value A is written to data_head in the IRQ, then a value
B is written to data_head after the IRQ. And A > B. As a result,
data_head is temporarily decreased from A to B. And a reader may see
data_head < data_tail if it read the buffer frequently enough, which
creates unexpected behaviors.

This can be fixed by moving dec(&rb->nest) to after updating data_head,
which prevents the IRQ/NMI above from updating data_head.

[ Split up by peterz. ]

Signed-off-by: Yabin Cui <yabinc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.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>
Cc: mark.rutland@arm.com
Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables")
Link: http://lkml.kernel.org/r/20190517115418.224478157@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
kernel/events/ring_buffer.c