From: Leo Yan <leo.yan@arm.com>
To: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: peterz@infradead.org, mingo@redhat.com, namhyung@kernel.org,
irogers@google.com, mark.rutland@arm.com,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
eranian@google.com, ctshao@google.com, tmricht@linux.ibm.com,
Aishwarya.TCV@arm.com
Subject: Re: [PATCH V4 01/16] perf: Fix the throttle logic for a group
Date: Wed, 28 May 2025 11:28:01 +0100 [thread overview]
Message-ID: <20250528102801.GK2566836@e132581.arm.com> (raw)
In-Reply-To: <44e1c864-a6e1-41a8-9f11-0ea25999131c@linux.intel.com>
On Tue, May 27, 2025 at 03:30:06PM -0400, Liang, Kan wrote:
[...]
> There may be two ways to fix it.
> - Add a check of MAX_INTERRUPTS in the event_stop. Return immediately if
> the stop is invoked by the throttle.
> - Introduce a PMU flag to track the case. Avoid the event_stop in
> perf_event_throttle() if the flag is detected.
>
> The latter looks more generic. It may be used if there are other cases
> that want to avoid the stop. So the latter is implemented as below.
Yes. I agreed the fix below is more general and confirmed it can fix
the observed issue.
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 947ad12dfdbe..66f02f46595c 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -303,6 +303,7 @@ struct perf_event_pmu_context;
> #define PERF_PMU_CAP_AUX_OUTPUT 0x0080
> #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
> #define PERF_PMU_CAP_AUX_PAUSE 0x0200
> +#define PERF_PMU_CAP_NO_THROTTLE_STOP 0x0400
>
> /**
> * pmu::scope
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 8327ab0ee641..596597886d96 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2655,7 +2655,8 @@ static void perf_event_unthrottle(struct
> perf_event *event, bool start)
>
> static void perf_event_throttle(struct perf_event *event)
> {
> - event->pmu->stop(event, 0);
> + if (!(event->pmu->capabilities & PERF_PMU_CAP_NO_THROTTLE_STOP))
> + event->pmu->stop(event, 0);
A background info is that even a PMU event is not stopped when
throttling, we still need to re-enable it. This is why we don't do
particualy handling for PERF_PMU_CAP_NO_THROTTLE_STOP in
perf_event_unthrottle().
Maybe it is deserved add a comment for easier understanding.
Thanks,
Leo
> event->hw.interrupts = MAX_INTERRUPTS;
> perf_log_throttle(event, 0);
> }
> @@ -11846,7 +11847,8 @@ static int cpu_clock_event_init(struct
> perf_event *event)
> static struct pmu perf_cpu_clock = {
> .task_ctx_nr = perf_sw_context,
>
> - .capabilities = PERF_PMU_CAP_NO_NMI,
> + .capabilities = PERF_PMU_CAP_NO_NMI |
> + PERF_PMU_CAP_NO_THROTTLE_STOP,
> .dev = PMU_NULL_DEV,
>
> .event_init = cpu_clock_event_init,
> @@ -11928,7 +11930,8 @@ static int task_clock_event_init(struct
> perf_event *event)
> static struct pmu perf_task_clock = {
> .task_ctx_nr = perf_sw_context,
>
> - .capabilities = PERF_PMU_CAP_NO_NMI,
> + .capabilities = PERF_PMU_CAP_NO_NMI |
> + PERF_PMU_CAP_NO_THROTTLE_STOP,
> .dev = PMU_NULL_DEV,
>
> .event_init = task_clock_event_init,
>
>
> Thanks,
> Kan
>
>
next prev parent reply other threads:[~2025-05-28 10:28 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-20 18:16 [PATCH V4 00/16] perf: Fix the throttle logic for group kan.liang
2025-05-20 18:16 ` [PATCH V4 01/16] perf: Fix the throttle logic for a group kan.liang
2025-05-20 22:02 ` Namhyung Kim
2025-05-27 16:16 ` Leo Yan
2025-05-27 19:30 ` Liang, Kan
2025-05-28 10:28 ` Leo Yan [this message]
2025-05-28 14:51 ` Liang, Kan
2025-06-02 0:30 ` perf regression. Was: " Alexei Starovoitov
2025-06-02 12:55 ` Liang, Kan
2025-06-02 16:24 ` Alexei Starovoitov
2025-06-02 17:51 ` Liang, Kan
2025-06-02 18:14 ` Alexei Starovoitov
2025-05-20 18:16 ` [PATCH V4 02/16] perf: Only dump the throttle log for the leader kan.liang
2025-05-20 22:02 ` Namhyung Kim
2025-05-21 12:05 ` Peter Zijlstra
2025-05-21 13:55 ` Liang, Kan
2025-05-20 18:16 ` [PATCH V4 03/16] perf/x86/intel: Remove driver-specific throttle support kan.liang
2025-05-20 18:16 ` [PATCH V4 04/16] perf/x86/amd: " kan.liang
2025-05-20 18:16 ` [PATCH V4 05/16] perf/x86/zhaoxin: " kan.liang
2025-05-20 18:16 ` [PATCH V4 06/16] powerpc/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 07/16] s390/perf: " kan.liang
2025-07-23 8:06 ` Sumanth Korikkar
2025-08-06 8:37 ` Sumanth Korikkar
2025-08-06 17:05 ` Liang, Kan
2025-08-11 14:02 ` Sumanth Korikkar
2025-05-20 18:16 ` [PATCH V4 08/16] perf/arm: " kan.liang
2025-05-20 18:16 ` [PATCH V4 09/16] perf/apple_m1: " kan.liang
2025-05-20 18:16 ` [PATCH V4 10/16] alpha/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 11/16] arc/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 12/16] csky/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 13/16] loongarch/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 14/16] sparc/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 15/16] xtensa/perf: " kan.liang
2025-05-20 18:16 ` [PATCH V4 16/16] mips/perf: " kan.liang
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=20250528102801.GK2566836@e132581.arm.com \
--to=leo.yan@arm.com \
--cc=Aishwarya.TCV@arm.com \
--cc=ctshao@google.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=tmricht@linux.ibm.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).