All of lore.kernel.org
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Vladimir Kondratiev" <vladimir.kondratiev@mobileye.com>
Cc: linux-rt-devel@lists.linux.dev, devicetree@vger.kernel.org,
	linux-perf-users@vger.kernel.org, robh@kernel.org,
	conor+dt@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 5/7] perf: add MIPS Coherence Manager 3 (CM3) PMU driver
Date: Thu, 19 Nov 2026 18:17:44 +0000	[thread overview]
Message-ID: <sashiko-outbox-223763@kernel.org> (raw)
In-Reply-To: <20261119-i6500-cm3-pmu-v3-5-c86410934b51@mobileye.com>

Thank you for your contribution! Sashiko AI review found 2 potential
issues to consider:
- [Medium] perf: mips_cm3_pmu: counter overflow double-counting in
  cm3_pmu_update()
- [Low] perf: mips_cm3_pmu: WARN_ON() in cm3_pmu_online_cpu() when
  !CONFIG_SMP
--

commit 51299d17e3e40c4c71d192990c0a48a22c2de2cb
Author: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>

perf: add MIPS Coherence Manager 3 (CM3) PMU driver

This commit adds an uncore PMU driver and documentation for the MIPS
Coherence Manager 3 (CM3) performance counters.

> diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
> index 245e7bb763b99..2dbed2fc7b030 100644
> --- a/drivers/perf/Kconfig
> +++ b/drivers/perf/Kconfig
> @@ -75,6 +75,18 @@ config ARM_XSCALE_PMU
>  	depends on ARM_PMU && CPU_XSCALE
>  	def_bool y
>  
> +config MIPS_CM3_PMU
> +	tristate "MIPS Coherence Manager 3 (CM3) PMU"
> +	depends on MIPS_CM

[Severity: Low]
Should MIPS_CM3_PMU depend on MIPS_CPS (or SMP) rather than just MIPS_CM?

MIPS_GIC selects MIPS_CM even when CONFIG_SMP=n and CONFIG_MIPS_CPS=n.
On a !CONFIG_SMP build, cpuhp_state_add_instance() still invokes
cm3_pmu_online_cpu() on the boot CPU, where the !CONFIG_SMP stub for
irq_set_affinity() returns -EINVAL and triggers WARN_ON() whenever an
overflow IRQ is present.  Without CONFIG_MIPS_CPS, cps_smp_setup() also
never populates the cluster ID in cpu_data[].globalnumber.

> diff --git a/drivers/perf/mips_cm3_pmu.c b/drivers/perf/mips_cm3_pmu.c
> new file mode 100644
> index 0000000000000..6d53535473b96
> --- /dev/null
> +++ b/drivers/perf/mips_cm3_pmu.c
[ ... ]
> +static void cm3_pmu_update(struct perf_event *event)
> +{
> +	struct cm3_pmu *cm3_pmu = to_cm3_pmu(event->pmu);
> +	struct hw_perf_event *hwc = &event->hw;
> +	u32 ov_bit = cm3_pmu_overflow_bit(hwc->idx);
> +	u64 delta, prev, new;
> +	bool overflowed = false;
> +
> +	/* Counts were harvested when the cluster went down, nothing since */
> +	if (READ_ONCE(cm3_pmu->paused))
> +		return;
> +
> +	/*
> +	 * When polling, the counter cannot wrap twice between two reads and
> +	 * the 32-bit difference tells the whole story. With the overflow
> +	 * interrupt the counter is only read on demand and may have made a
> +	 * full turn since the last read, which the overflow status tells.
> +	 * It is read and cleared before the counter so that a wrap seen
> +	 * here is also reflected in the counter value; a wrap happening in
> +	 * between is accounted by the next update, which the interrupt it
> +	 * raises makes sure happens. In interrupt mode every access to the
> +	 * event runs on cm3_pmu->on_cpu with interrupts disabled, so the
> +	 * status and the counter are read consistently.
> +	 */
> +	if (cm3_pmu->irq > 0) {
> +		overflowed = CM3_PMU_READ(cm3_pmu, pc_ov) & ov_bit;
> +		if (overflowed)
> +			CM3_PMU_WRITE(cm3_pmu, pc_ov, ov_bit);
> +	}
> +
> +	do {
> +		prev = local64_read(&hwc->prev_count);
> +		new = cm3_pmu_read_counter(cm3_pmu, hwc->idx);
> +	} while (local64_cmpxchg(&hwc->prev_count, prev, new) != prev);
> +
> +	/*
> +	 * If the counter wrapped and now shows a value not below the
> +	 * previous one, it made a full turn on top of the 32-bit difference.
> +	 */
> +	delta = (new - prev) & CM3_PMU_COUNTER_MASK;
> +	if (overflowed && new >= prev)
> +		delta += CM3_PMU_COUNTER_MASK + 1;
> +
> +	local64_add(delta, &event->count);
> +}

[Severity: Medium]
Can cm3_pmu_update() double-count a counter wrap in interrupt mode and
add an extra 2^32 to event->count?

If hwc->prev_count holds a non-zero value prev (from an earlier read) and
the counter wraps past 0xffffffff to a small value new < prev right after
pc_ov is read as 0 but before cm3_pmu_read_counter() runs, then:

1. This call sees overflowed == false and new < prev, so
   delta = (new - prev) & CM3_PMU_COUNTER_MASK already accounts for the
   wrap across 0xffffffff -> 0, and hwc->prev_count becomes new.
2. Because the wrap happened after reading pc_ov, ov_bit remains latched
   in pc_ov and the overflow interrupt fires next.
3. cm3_pmu_handle_irq() -> cm3_pmu_update() now sees overflowed == true
   and new >= prev (relative to the already post-wrap prev), so
   if (overflowed && new >= prev) adds CM3_PMU_COUNTER_MASK + 1 a second
   time for the same wrap.

Also, Documentation/admin-guide/perf/mips_cm3_pmu.rst notes that the CM3
asserts so_cm_perf_cnt_int when a counter reaches 0xffffffff.  If
cm3_pmu_update() reads the counter while it is still at 0xffffffff with
overflowed == true, new == 0xffffffff satisfies new >= prev for any
32-bit prev, adding 2^32 before the counter actually wraps to 0 on the
next event.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261119-i6500-cm3-pmu-v3-0-c86410934b51@mobileye.com?part=5

  reply	other threads:[~2026-11-19 18:17 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 17:51 [PATCH v3 0/7] perf: add PMU driver for the MIPS Coherence Manager 3 performance counters Vladimir Kondratiev
2026-11-19 17:51 ` [PATCH v3 1/7] mips: {cm,cpc}: Make cm_core_lock, cpc_core_lock raw spinlocks Vladimir Kondratiev
2026-11-19 18:02   ` sashiko-bot
2026-11-20 11:46   ` Sebastian Andrzej Siewior
2026-11-19 17:51 ` [PATCH v3 2/7] MIPS: CM: add CM3 performance counter GCR definitions Vladimir Kondratiev
2026-11-19 17:54   ` sashiko-bot
2026-11-19 17:51 ` [PATCH v3 3/7] MIPS: CM: export the symbols needed to access the GCRs from a module Vladimir Kondratiev
2026-11-19 17:54   ` sashiko-bot
2026-11-19 17:51 ` [PATCH v3 4/7] dt-bindings: mips: mti,mips-cm: add performance counter interrupt Vladimir Kondratiev
2026-11-19 17:53   ` sashiko-bot
2026-11-19 17:51 ` [PATCH v3 5/7] perf: add MIPS Coherence Manager 3 (CM3) PMU driver Vladimir Kondratiev
2026-11-19 18:17   ` sashiko-bot [this message]
2026-11-19 17:51 ` [PATCH v3 6/7] MIPS: eyeq6_defconfig: enable the CM3 PMU Vladimir Kondratiev
2026-11-19 17:56   ` sashiko-bot
2026-11-19 17:51 ` [PATCH v3 7/7] MAINTAINERS: Add entry for MIPS " Vladimir Kondratiev

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=sashiko-outbox-223763@kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=conor+dt@kernel.org \
    --cc=devicetree@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=robh@kernel.org \
    --cc=sashiko-reviews@lists.linux.dev \
    --cc=vladimir.kondratiev@mobileye.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.