From cca19ab29a1a52ebd37e68923ad3e409a0001c07 Mon Sep 17 00:00:00 2001 From: Yabin Cui Date: Fri, 17 May 2019 13:52:31 +0200 Subject: [PATCH] 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 Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver 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 Signed-off-by: Sasha Levin --- kernel/events/ring_buffer.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 99c7f199f2d4..31edf1f39cca 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -52,11 +52,18 @@ static void perf_output_put_handle(struct perf_output_handle *handle) head = local_read(&rb->head); /* - * IRQ/NMI can happen here, which means we can miss a head update. + * IRQ/NMI can happen here and advance @rb->head, causing our + * load above to be stale. */ - if (!local_dec_and_test(&rb->nest)) + /* + * If this isn't the outermost nesting, we don't have to update + * @rb->user_page->data_head. + */ + if (local_read(&rb->nest) > 1) { + local_dec(&rb->nest); goto out; + } /* * Since the mmap() consumer (userspace) can run on a different CPU: @@ -88,9 +95,18 @@ static void perf_output_put_handle(struct perf_output_handle *handle) rb->user_page->data_head = head; /* - * Now check if we missed an update -- rely on previous implied - * compiler barriers to force a re-read. + * We must publish the head before decrementing the nest count, + * otherwise an IRQ/NMI can publish a more recent head value and our + * write will (temporarily) publish a stale value. + */ + barrier(); + local_set(&rb->nest, 0); + + /* + * Ensure we decrement @rb->nest before we validate the @rb->head. + * Otherwise we cannot be sure we caught the 'last' nested update. */ + barrier(); if (unlikely(head != local_read(&rb->head))) { local_inc(&rb->nest); goto again; -- GitLab