From: Marc Zyngier <maz@kernel.org>
To: myrialsarvay@gmail.com
Cc: Will Deacon <will@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Rob Herring <robh@kernel.org>,
Krzysztof Kozlowski <krzk+dt@kernel.org>,
Conor Dooley <conor+dt@kernel.org>, Sven Peter <sven@kernel.org>,
Janne Grunau <j@jannau.net>, Neal Gompa <neal@gompa.dev>,
linux-arm-kernel@lists.infradead.org,
linux-perf-users@vger.kernel.org, devicetree@vger.kernel.org,
linux-kernel@vger.kernel.org, asahi@lists.linux.dev,
Yuvan Shen <yuvanshen09@gmail.com>,
Nick Chan <towinchenmi@gmail.com>
Subject: Re: [PATCH v2 03/15] drivers/perf: apple_m1: Support per-implementation event tables
Date: Wed, 18 Nov 2026 11:59:30 +0000 [thread overview]
Message-ID: <864ide1hb1.wl-maz@kernel.org> (raw)
In-Reply-To: <20261107-m3-plus-pmu-events-v2-3-acf1e78da039@gmail.com>
On Sat, 07 Nov 2026 10:48:50 +0000,
Myria Sarvay via B4 Relay <devnull+myrialsarvay.gmail.com@kernel.org> wrote:
>
> From: Nick Chan <towinchenmi@gmail.com>
>
> Use per-implementation event tables to allow supporting implementations
> with a different list of events and event affinities.
>
> Signed-off-by: Nick Chan <towinchenmi@gmail.com>
> Co-developed-by: Myria Sarvay <myrialsarvay@gmail.com>
> Signed-off-by: Myria Sarvay <myrialsarvay@gmail.com>
> ---
> drivers/perf/apple_m1_cpu_pmu.c | 113 ++++++++++++++++++++++++----------------
> 1 file changed, 69 insertions(+), 44 deletions(-)
>
> diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
> index de4026c63afd..2ff0c2e0b737 100644
> --- a/drivers/perf/apple_m1_cpu_pmu.c
> +++ b/drivers/perf/apple_m1_cpu_pmu.c
> @@ -43,9 +43,6 @@
> * moment, we don't really need to distinguish between the two because we
> * know next to nothing about the events themselves, and we already have
> * per cpu-type PMU abstractions.
> - *
> - * If we eventually find out that the events are different across
> - * implementations, we'll have to introduce per cpu-type tables.
> */
> enum m1_pmu_events {
> M1_PMU_PERFCTR_RETIRE_UOP = 0x1,
> @@ -167,7 +164,7 @@ static const u16 m1_pmu_event_affinity[M1_PMU_PERFCTR_LAST + 1] = {
> [M1_PMU_PERFCTR_UNKNOWN_fd] = ONLY_2_4_6,
> };
>
> -static const unsigned m1_pmu_perf_map[PERF_COUNT_HW_MAX] = {
> +static const unsigned int m1_pmu_perf_map[PERF_COUNT_HW_MAX] = {
> PERF_MAP_ALL_UNSUPPORTED,
> [PERF_COUNT_HW_CPU_CYCLES] = M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE,
> [PERF_COUNT_HW_INSTRUCTIONS] = M1_PMU_PERFCTR_INST_ALL,
> @@ -486,11 +483,12 @@ static void m1_pmu_write_counter(struct perf_event *event, u64 value)
> isb();
> }
>
> -static int m1_pmu_get_event_idx(struct pmu_hw_events *cpuc,
> - struct perf_event *event)
> +static int apple_pmu_get_event_idx(struct pmu_hw_events *cpuc,
> + struct perf_event *event,
> + const u16 event_affinities[])
> {
> unsigned long evtype = event->hw.config_base & M1_PMU_CFG_EVENT;
> - unsigned long affinity = m1_pmu_event_affinity[evtype];
> + unsigned long affinity = event_affinities[evtype];
> int idx;
>
> /*
> @@ -509,6 +507,12 @@ static int m1_pmu_get_event_idx(struct pmu_hw_events *cpuc,
> return -EAGAIN;
> }
>
> +static int m1_pmu_get_event_idx(struct pmu_hw_events *cpuc,
> + struct perf_event *event)
> +{
> + return apple_pmu_get_event_idx(cpuc, event, m1_pmu_event_affinity);
> +}
> +
> static void m1_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
> struct perf_event *event)
> {
> @@ -536,44 +540,52 @@ static void m1_pmu_stop(struct arm_pmu *cpu_pmu)
> __m1_pmu_set_mode(PMCR0_IMODE_OFF);
> }
>
> +static int apple_pmu_map_event(struct perf_event *event,
> + const unsigned int (*perf_map)[],
> + unsigned int flags)
> +{
> + event->hw.flags |= flags;
> + return armpmu_map_event(event, perf_map, NULL, M1_PMU_CFG_EVENT);
> +}
> +
> +/*
> + * Apple PMU counters have been observed to be either 48 or
> + * 64 bits wide, depending on the SoC. However, the MSB is
> + * what triggers an overflow interrupt, so we advertise the
> + * counters as being 1-bit smaller than hardware so as to
> + * mimick ARM PMU behaviour
> + */
> static int m1_pmu_map_event(struct perf_event *event)
> {
> - /*
> - * Although the counters are 48bit wide, bit 47 is what
> - * triggers the overflow interrupt. Advertise the counters
> - * being 47bit wide to mimick the behaviour of the ARM PMU.
> - */
> - event->hw.flags |= ARMPMU_EVT_47BIT;
> - return armpmu_map_event(event, &m1_pmu_perf_map, NULL, M1_PMU_CFG_EVENT);
> + return apple_pmu_map_event(event, &m1_pmu_perf_map, ARMPMU_EVT_47BIT);
> }
>
> static int m2_pmu_map_event(struct perf_event *event)
> {
> - /*
> - * Same deal as the above, except that M2 has 64bit counters.
> - * Which, as far as we're concerned, actually means 63 bits.
> - * Yes, this is getting awkward.
> - */
> - event->hw.flags |= ARMPMU_EVT_63BIT;
> - return armpmu_map_event(event, &m1_pmu_perf_map, NULL, M1_PMU_CFG_EVENT);
> + return apple_pmu_map_event(event, &m1_pmu_perf_map, ARMPMU_EVT_63BIT);
> }
>
> -static int m1_pmu_map_pmuv3_event(unsigned int eventsel)
> +static int apple_pmu_map_pmuv3_event(unsigned int eventsel, const u16 pmceid_map[])
> {
> - u16 m1_event = HW_OP_UNSUPPORTED;
> + u16 apple_event = HW_OP_UNSUPPORTED;
nit: s/apple_event/hw_event/.
>
> if (eventsel < ARMV8_PMUV3_MAX_COMMON_EVENTS)
> - m1_event = m1_pmu_pmceid_map[eventsel];
> + apple_event = pmceid_map[eventsel];
>
> - return m1_event == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : m1_event;
> + return apple_event == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : apple_event;
> }
>
> -static void m1_pmu_init_pmceid(struct arm_pmu *pmu)
> +static int m1_pmu_map_pmuv3_event(unsigned int eventsel)
> +{
> + return apple_pmu_map_pmuv3_event(eventsel, m1_pmu_pmceid_map);
> +}
> +
> +static void apple_pmu_init_pmceid(struct arm_pmu *pmu)
> {
> unsigned int event;
>
> for (event = 0; event < ARMV8_PMUV3_MAX_COMMON_EVENTS; event++) {
> - if (m1_pmu_map_pmuv3_event(event) >= 0)
> + if (pmu->map_pmuv3_event(event) >= 0)
> set_bit(event, pmu->pmceid_bitmap);
> }
> }
> @@ -616,33 +628,22 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event,
> return 0;
> }
>
> -static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags)
> +static int apple_pmu_init(struct arm_pmu *cpu_pmu)
> {
> cpu_pmu->handle_irq = m1_pmu_handle_irq;
> cpu_pmu->enable = m1_pmu_enable_event;
> cpu_pmu->disable = m1_pmu_disable_event;
> cpu_pmu->read_counter = m1_pmu_read_counter;
> cpu_pmu->write_counter = m1_pmu_write_counter;
> - cpu_pmu->get_event_idx = m1_pmu_get_event_idx;
> cpu_pmu->clear_event_idx = m1_pmu_clear_event_idx;
> cpu_pmu->start = m1_pmu_start;
> cpu_pmu->stop = m1_pmu_stop;
> -
> - if (flags & ARMPMU_EVT_47BIT)
> - cpu_pmu->map_event = m1_pmu_map_event;
> - else if (flags & ARMPMU_EVT_63BIT)
> - cpu_pmu->map_event = m2_pmu_map_event;
> - else
> - return WARN_ON(-EINVAL);
> -
> cpu_pmu->reset = m1_pmu_reset;
> cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
>
> - cpu_pmu->map_pmuv3_event = m1_pmu_map_pmuv3_event;
> - m1_pmu_init_pmceid(cpu_pmu);
> + apple_pmu_init_pmceid(cpu_pmu);
>
> bitmap_set(cpu_pmu->cntr_mask, 0, M1_PMU_NR_COUNTERS);
> - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
> cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &m1_pmu_format_attr_group;
> return 0;
> }
> @@ -651,25 +652,49 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags)
> static int m1_pmu_ice_init(struct arm_pmu *cpu_pmu)
> {
> cpu_pmu->name = "apple_icestorm_pmu";
> - return m1_pmu_init(cpu_pmu, ARMPMU_EVT_47BIT);
> + cpu_pmu->get_event_idx = m1_pmu_get_event_idx;
> + cpu_pmu->map_event = m1_pmu_map_event;
> +
> + cpu_pmu->map_pmuv3_event = m1_pmu_map_pmuv3_event;
> +
> + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
> + return apple_pmu_init(cpu_pmu);
> }
>
Looking at the following patches, I feel that this series is taking
the long route to get to a relatively clear point: most of the
invariant that we relied on for M1, slightly relaxed for M2 (counter
width), are even more relaxed for M3+ (event width). We therefore need
to indirect things. The way you do it is to mirror the current setup,
with a whole set of callbacks per implementation and a bunch of
additional helpers.
But instead of having a set of helper functions, one per
implementation, with an ever increasing set of parameters, it really
feels like we could do with a more data-centric approach where we have
a single data structure describing an implementation, containing all
the relevant data (pointer to the event mapping table, flags, bit
indices for the user/kernel/guest/host attributes, and so on. We could
then have a single set of callbacks that work on everything.
You could convert M1/M2 to that, then just add the relevant
descriptions for M3+, which should just add data and the init
functions, nothing else.
Does this make sense to you?
Thanks,
M.
--
Without deviation from the norm, progress is not possible.
next prev parent reply other threads:[~2026-11-18 11:59 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-07 10:48 [PATCH v2 00/15] drivers/perf: apple_m1: Add M3/M4/A18 Pro Support Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:48 ` [PATCH v2 01/15] dt-bindings: arm: pmu: Add Apple M3/M4/A18 Pro SoC CPU PMU compatibles Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:52 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 02/15] drivers/perf: apple_m1: Remove unused variables Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:54 ` sashiko-bot
2026-11-18 11:13 ` Marc Zyngier
2026-11-18 13:06 ` Myria Sarvay
2026-11-07 10:48 ` [PATCH v2 03/15] drivers/perf: apple_m1: Support per-implementation event tables Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:53 ` sashiko-bot
2026-11-18 11:59 ` Marc Zyngier [this message]
2026-11-18 13:36 ` Myria Sarvay
2026-11-18 15:35 ` Marc Zyngier
2026-11-07 10:48 ` [PATCH v2 04/15] drivers/perf: apple_m1: Support per-implementation event size Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:53 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 05/15] drivers/perf: apple_m1: Use macros for per-implementation init functions Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:52 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 06/15] drivers/perf: apple_m1: Add Apple M3 Series Support Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:53 ` sashiko-bot
2026-11-08 0:42 ` kernel test robot
2026-11-07 10:48 ` [PATCH v2 07/15] drivers/perf: apple_m1: Add Apple M4 " Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:55 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 08/15] drivers/perf: apple_m1: Add Apple A18 Support Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:53 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 09/15] arm64: dts: apple: t603*: Add core interrupt affinities Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:53 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 10/15] arm64: dts: apple: t8140: " Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:57 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 11/15] arm64: dts: apple: t603x: Add PMU Device Nodes Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:55 ` sashiko-bot
2026-11-07 10:48 ` [PATCH v2 12/15] arm64: dts: apple: t8122: " Myria Sarvay via B4 Relay
2026-11-07 10:48 ` Myria Sarvay
2026-11-07 10:54 ` sashiko-bot
2026-11-07 10:49 ` [PATCH v2 13/15] arm64: dts: apple: t604x: " Myria Sarvay via B4 Relay
2026-11-07 10:49 ` Myria Sarvay
2026-11-07 10:55 ` sashiko-bot
2026-11-07 10:49 ` [PATCH v2 14/15] arm64: dts: apple: t8132: " Myria Sarvay via B4 Relay
2026-11-07 10:49 ` Myria Sarvay
2026-11-07 10:56 ` sashiko-bot
2026-11-07 10:49 ` [PATCH v2 15/15] arm64: dts: apple: t8140: " Myria Sarvay via B4 Relay
2026-11-07 10:49 ` Myria Sarvay
2026-11-07 10:55 ` sashiko-bot
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=864ide1hb1.wl-maz@kernel.org \
--to=maz@kernel.org \
--cc=asahi@lists.linux.dev \
--cc=conor+dt@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=j@jannau.net \
--cc=krzk+dt@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=myrialsarvay@gmail.com \
--cc=neal@gompa.dev \
--cc=robh@kernel.org \
--cc=sven@kernel.org \
--cc=towinchenmi@gmail.com \
--cc=will@kernel.org \
--cc=yuvanshen09@gmail.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.