public inbox for linux-arm-kernel@lists.infradead.org
 help / color / mirror / Atom feed
From: Mark Rutland <mark.rutland@arm.com>
To: Yicong Yang <yangyicong@huawei.com>
Cc: will@kernel.org, linux-arm-kernel@lists.infradead.org,
	james.clark@linaro.org, robh@kernel.org,
	anshuman.khandual@arm.com, jonathan.cameron@huawei.com,
	hejunhao3@huawei.com, linuxarm@huawei.com,
	prime.zeng@hisilicon.com, xuwei5@huawei.com,
	wangyushan12@huawei.com, yangyicong@hisilicon.com
Subject: Re: [PATCH 1/2] perf: arm_pmuv3: Factor out PMCCNTR_EL0 use conditions
Date: Tue, 12 Aug 2025 11:25:07 +0100	[thread overview]
Message-ID: <aJsWg9g_Z9z-ejcL@J2N7QTR9R3> (raw)
In-Reply-To: <20250812080830.20796-2-yangyicong@huawei.com>

On Tue, Aug 12, 2025 at 04:08:29PM +0800, Yicong Yang wrote:
> From: Yicong Yang <yangyicong@hisilicon.com>
> 
> PMCCNTR_EL0 is preferred for counting CPU_CYCLES under certain
> conditions. Factor out the condition check to a separate function
> for further extension. Add documents for better understanding.
> No functional changes intended.
> 
> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>

FWIW, splitting this oudt looks fine to me (with one nit below), so:

Acked-by: Mark Rutland <mark.rutland@arm.com>

> ---
>  drivers/perf/arm_pmuv3.c | 30 ++++++++++++++++++++++++++++--
>  1 file changed, 28 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
> index f6d7bab5d555..95c899d07df5 100644
> --- a/drivers/perf/arm_pmuv3.c
> +++ b/drivers/perf/arm_pmuv3.c
> @@ -978,6 +978,33 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
>  	return -EAGAIN;
>  }
>  
> +static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc,
> +				     struct perf_event *event)
> +{
> +	struct hw_perf_event *hwc = &event->hw;
> +	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
> +
> +	/* PMCCNTR_EL0 can only be used for CPU_CYCLES event */
> +	if (evtype != ARMV8_PMUV3_PERFCTR_CPU_CYCLES)
> +		return false;

Nit: I don't think this comment is useful, and it could be deleted.

Mark.

> +
> +	/*
> +	 * A CPU_CYCLES event with threshold counting cannot use PMCCNTR_EL0
> +	 * since it lacks threshold support.
> +	 */
> +	if (armv8pmu_event_get_threshold(&event->attr))
> +		return false;
> +
> +	/*
> +	 * PMCCNTR_EL0 is not affected by BRBE controls like BRBCR_ELx.FZP.
> +	 * So don't use it for branch events.
> +	 */
> +	if (has_branch_stack(event))
> +		return false;
> +
> +	return true;
> +}
> +
>  static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
>  				  struct perf_event *event)
>  {
> @@ -986,8 +1013,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
>  	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
>  
>  	/* Always prefer to place a cycle counter into the cycle counter. */
> -	if ((evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
> -	    !armv8pmu_event_get_threshold(&event->attr) && !has_branch_stack(event)) {
> +	if (armv8pmu_can_use_pmccntr(cpuc, event)) {
>  		if (!test_and_set_bit(ARMV8_PMU_CYCLE_IDX, cpuc->used_mask))
>  			return ARMV8_PMU_CYCLE_IDX;
>  		else if (armv8pmu_event_is_64bit(event) &&
> -- 
> 2.24.0
> 


  parent reply	other threads:[~2025-08-12 16:19 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-12  8:08 [PATCH 0/2] perf: arm_pmuv3: Don't use PMCCNTR_EL0 on SMT cores Yicong Yang
2025-08-12  8:08 ` [PATCH 1/2] perf: arm_pmuv3: Factor out PMCCNTR_EL0 use conditions Yicong Yang
2025-08-12 10:02   ` James Clark
2025-08-12 10:25   ` Mark Rutland [this message]
2025-08-12  8:08 ` [PATCH 2/2] perf: arm_pmuv3: Don't use PMCCNTR_EL0 on SMT cores Yicong Yang
2025-08-12 10:00   ` James Clark
2025-08-12 10:14     ` Yicong Yang
2025-08-12 10:22       ` Mark Rutland
2025-08-13  8:17         ` Yicong Yang
2025-08-12 10:31       ` James Clark
2025-08-13  8:32         ` Yicong Yang
2025-08-12 10:33   ` Mark Rutland
2025-08-13  8:03     ` Yicong Yang

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=aJsWg9g_Z9z-ejcL@J2N7QTR9R3 \
    --to=mark.rutland@arm.com \
    --cc=anshuman.khandual@arm.com \
    --cc=hejunhao3@huawei.com \
    --cc=james.clark@linaro.org \
    --cc=jonathan.cameron@huawei.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linuxarm@huawei.com \
    --cc=prime.zeng@hisilicon.com \
    --cc=robh@kernel.org \
    --cc=wangyushan12@huawei.com \
    --cc=will@kernel.org \
    --cc=xuwei5@huawei.com \
    --cc=yangyicong@hisilicon.com \
    --cc=yangyicong@huawei.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