From: Peter Zijlstra <peterz@infradead.org>
To: peterz@infradead.org, mingo@kernel.org
Cc: yabinc@google.com, acme@kernel.org,
alexander.shishkin@linux.intel.com, jolsa@redhat.com,
namhyung@kernel.org, mark.rutland@arm.com,
linux-kernel@vger.kernel.org
Subject: [PATCH 2/4] perf/ring_buffer: Add ordering to rb->nest increment
Date: Fri, 17 May 2019 13:52:32 +0200 [thread overview]
Message-ID: <20190517115418.309516009@infradead.org> (raw)
In-Reply-To: 20190517115230.437269790@infradead.org
Similar to how decrementing rb->next too early can cause data_head to
(temporarily) be observed to go backward, so too can this happen when
we increment too late.
This barrier() ensures the rb->head load happens after the increment,
both the one in the 'goto again' path, as the one from
perf_output_get_handle() -- albeit very unlikely to matter for the
latter.
Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables")
Suggested-by: Yabin Cui <yabinc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/events/ring_buffer.c | 9 +++++++++
1 file changed, 9 insertions(+)
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -48,6 +48,15 @@ static void perf_output_put_handle(struc
unsigned long head;
again:
+ /*
+ * In order to avoid publishing a head value that goes backwards,
+ * we must ensure the load of @rb->head happens after we've
+ * incremented @rb->nest.
+ *
+ * Otherwise we can observe a @rb->head value before one published
+ * by an IRQ/NMI happening between the load and the increment.
+ */
+ barrier();
head = local_read(&rb->head);
/*
next prev parent reply other threads:[~2019-05-17 11:55 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-17 11:52 [PATCH 0/4] perf ring-buffer fixes Peter Zijlstra
2019-05-17 11:52 ` [PATCH 1/4] perf/ring_buffer: Fix exposing a temporarily decreased data_head Peter Zijlstra
2019-05-17 13:05 ` Ingo Molnar
2019-05-17 14:26 ` Peter Zijlstra
2019-05-24 7:01 ` Ingo Molnar
2019-05-24 8:08 ` [tip:perf/urgent] " tip-bot for Yabin Cui
2019-05-17 11:52 ` Peter Zijlstra [this message]
2019-05-24 8:08 ` [tip:perf/urgent] perf/ring_buffer: Add ordering to rb->nest increment tip-bot for Peter Zijlstra
2019-05-17 11:52 ` [PATCH 3/4] perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data Peter Zijlstra
2019-05-24 8:09 ` [tip:perf/urgent] " tip-bot for Peter Zijlstra
2019-05-17 11:52 ` [PATCH 4/4] perf/ring-buffer: Use regular variables for nesting Peter Zijlstra
2019-05-24 8:10 ` [tip:perf/urgent] " tip-bot for Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190517115418.309516009@infradead.org \
--to=peterz@infradead.org \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=yabinc@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).