From: Mark Rutland <mark.rutland@arm.com>
To: linux-arm-kernel@lists.infradead.org
Cc: asahi@lists.linux.dev, ecurtin@redhat.com, j@jannau.net,
lina@asahilina.net, linux-kernel@vger.kernel.org,
mark.rutland@arm.com, peterz@infradead.org,
ravi.bangoria@amd.com, will@kernel.org
Subject: [PATCH 0/2] arm_pmu: fix fallout from context handling rewrite
Date: Thu, 16 Feb 2023 14:12:37 +0000 [thread overview]
Message-ID: <20230216141240.3833272-1-mark.rutland@arm.com> (raw)
Janne reports [1] that perf has been broken on Apple M1 as of commit:
bd27568117664b8b ("perf: Rewrite core context handling")
This is due to changes to pmu::filter_match() and
arm_pmu::filter_match(), which have been renamed and had their polarity
inverted, but the conversion was inconsistent, and so in some cases we
return the opposite result relative to what we had intended. This
results in consistently losing events on Apple M1.
That commit also (silently) removed the filtering of CHAIN events, which
is undesireable.
These patches fix and simplify the CPU filtering, and replace the CHAIN
event filtering with early rejection of CHAIN events, which is much
simpler.
Thanks,
Mark
[1] https://lore.kernel.org/asahi/20230215-arm_pmu_m1_regression-v1-1-f5a266577c8d@jannau.net/
Mark Rutland (2):
arm_pmu: fix event CPU filtering
arm64: perf: reject CHAIN events at creation time
arch/arm64/kernel/perf_event.c | 15 ++++++++-------
drivers/perf/arm_pmu.c | 8 +-------
include/linux/perf/arm_pmu.h | 1 -
3 files changed, 9 insertions(+), 15 deletions(-)
--
2.30.2
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next reply other threads:[~2023-02-16 14:13 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-16 14:12 Mark Rutland [this message]
2023-02-16 14:12 ` [PATCH 1/2] arm_pmu: fix event CPU filtering Mark Rutland
2023-02-16 14:35 ` Janne Grunau
2023-02-16 15:13 ` Mark Rutland
2023-02-16 15:17 ` Will Deacon
2023-02-16 14:12 ` [PATCH 2/2] arm64: perf: reject CHAIN events at creation time Mark Rutland
2023-02-16 22:14 ` [PATCH 0/2] arm_pmu: fix fallout from context handling rewrite Will Deacon
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=20230216141240.3833272-1-mark.rutland@arm.com \
--to=mark.rutland@arm.com \
--cc=asahi@lists.linux.dev \
--cc=ecurtin@redhat.com \
--cc=j@jannau.net \
--cc=lina@asahilina.net \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=will@kernel.org \
/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