From: Anshuman Khandual <anshuman.khandual@arm.com>
To: Namhyung Kim <namhyung@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, will@kernel.org,
catalin.marinas@arm.com, mark.rutland@arm.com,
Mark Brown <broonie@kernel.org>,
James Clark <james.clark@arm.com>, Rob Herring <robh@kernel.org>,
Marc Zyngier <maz@kernel.org>,
Suzuki Poulose <suzuki.poulose@arm.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
linux-perf-users@vger.kernel.org
Subject: Re: [PATCH V11 05/10] arm64/perf: Add branch stack support in ARMV8 PMU
Date: Mon, 5 Jun 2023 08:13:08 +0530 [thread overview]
Message-ID: <58628cba-7ec4-b2b3-b993-14c2af1a67cb@arm.com> (raw)
In-Reply-To: <CAM9d7cioDUxzNos5b3ANkG-BkJUcROSGCG0gpLzSXnc-v6o9jw@mail.gmail.com>
Hello Namhyung,
On 6/2/23 08:03, Namhyung Kim wrote:
> On Tue, May 30, 2023 at 9:27 PM Anshuman Khandual
> <anshuman.khandual@arm.com> wrote:
>> This enables support for branch stack sampling event in ARMV8 PMU, checking
>> has_branch_stack() on the event inside 'struct arm_pmu' callbacks. Although
>> these branch stack helpers armv8pmu_branch_XXXXX() are just dummy functions
>> for now. While here, this also defines arm_pmu's sched_task() callback with
>> armv8pmu_sched_task(), which resets the branch record buffer on a sched_in.
>>
>> Cc: Catalin Marinas <catalin.marinas@arm.com>
>> Cc: Will Deacon <will@kernel.org>
>> Cc: Mark Rutland <mark.rutland@arm.com>
>> Cc: linux-arm-kernel@lists.infradead.org
>> Cc: linux-kernel@vger.kernel.org
>> Tested-by: James Clark <james.clark@arm.com>
>> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
>> ---
>> arch/arm64/include/asm/perf_event.h | 33 +++++++++++++
>> drivers/perf/arm_pmuv3.c | 76 ++++++++++++++++++++---------
>> 2 files changed, 86 insertions(+), 23 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
>> index eb7071c9eb34..7548813783ba 100644
>> --- a/arch/arm64/include/asm/perf_event.h
>> +++ b/arch/arm64/include/asm/perf_event.h
>> @@ -24,4 +24,37 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
>> (regs)->pstate = PSR_MODE_EL1h; \
>> }
>>
>> +struct pmu_hw_events;
>> +struct arm_pmu;
>> +struct perf_event;
>> +
>> +#ifdef CONFIG_PERF_EVENTS
>> +static inline bool has_branch_stack(struct perf_event *event);
>> +
>> +static inline void armv8pmu_branch_read(struct pmu_hw_events *cpuc, struct perf_event *event)
>> +{
>> + WARN_ON_ONCE(!has_branch_stack(event));
>> +}
>> +
>> +static inline bool armv8pmu_branch_valid(struct perf_event *event)
>> +{
>> + WARN_ON_ONCE(!has_branch_stack(event));
>> + return false;
>> +}
>> +
>> +static inline void armv8pmu_branch_enable(struct perf_event *event)
>> +{
>> + WARN_ON_ONCE(!has_branch_stack(event));
>> +}
>> +
>> +static inline void armv8pmu_branch_disable(struct perf_event *event)
>> +{
>> + WARN_ON_ONCE(!has_branch_stack(event));
>> +}
>> +
>> +static inline void armv8pmu_branch_probe(struct arm_pmu *arm_pmu) { }
>> +static inline void armv8pmu_branch_reset(void) { }
>> +static inline int armv8pmu_private_alloc(struct arm_pmu *arm_pmu) { return 0; }
>> +static inline void armv8pmu_private_free(struct arm_pmu *arm_pmu) { }
>> +#endif
>> #endif
>> diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
>> index c98e4039386d..86d803ff1ae3 100644
>> --- a/drivers/perf/arm_pmuv3.c
>> +++ b/drivers/perf/arm_pmuv3.c
>> @@ -705,38 +705,21 @@ static void armv8pmu_enable_event(struct perf_event *event)
>> * Enable counter and interrupt, and set the counter to count
>> * the event that we're interested in.
>> */
>> -
>> - /*
>> - * Disable counter
>> - */
>> armv8pmu_disable_event_counter(event);
>> -
>> - /*
>> - * Set event.
>> - */
>> armv8pmu_write_event_type(event);
>> -
>> - /*
>> - * Enable interrupt for this counter
>> - */
>> armv8pmu_enable_event_irq(event);
>> -
>> - /*
>> - * Enable counter
>> - */
>> armv8pmu_enable_event_counter(event);
>> +
>> + if (has_branch_stack(event))
>> + armv8pmu_branch_enable(event);
>> }
>>
>> static void armv8pmu_disable_event(struct perf_event *event)
>> {
>> - /*
>> - * Disable counter
>> - */
>> - armv8pmu_disable_event_counter(event);
>> + if (has_branch_stack(event))
>> + armv8pmu_branch_disable(event);
>>
>> - /*
>> - * Disable interrupt for this counter
>> - */
>> + armv8pmu_disable_event_counter(event);
>> armv8pmu_disable_event_irq(event);
>> }
>>
>> @@ -814,6 +797,11 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
>> if (!armpmu_event_set_period(event))
>> continue;
>>
>> + if (has_branch_stack(event) && !WARN_ON(!cpuc->branches)) {
>> + armv8pmu_branch_read(cpuc, event);
>> + perf_sample_save_brstack(&data, event, &cpuc->branches->branch_stack);
>> + }
>> +
>> /*
>> * Perf event overflow will queue the processing of the event as
>> * an irq_work which will be taken care of in the handling of
>> @@ -912,6 +900,14 @@ static int armv8pmu_user_event_idx(struct perf_event *event)
>> return event->hw.idx;
>> }
>>
>> +static void armv8pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
>> +{
>> + struct arm_pmu *armpmu = to_arm_pmu(pmu_ctx->pmu);
>> +
>> + if (sched_in && arm_pmu_branch_stack_supported(armpmu))
>> + armv8pmu_branch_reset();
>> +}
>> +
>> /*
>> * Add an event filter to a given event.
>> */
>> @@ -982,6 +978,9 @@ static void armv8pmu_reset(void *info)
>> pmcr |= ARMV8_PMU_PMCR_LP;
>>
>> armv8pmu_pmcr_write(pmcr);
>> +
>> + if (arm_pmu_branch_stack_supported(cpu_pmu))
>> + armv8pmu_branch_reset();
>> }
>>
>> static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu,
>> @@ -1019,6 +1018,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
>>
>> hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event);
>>
>> + if (has_branch_stack(event) && !armv8pmu_branch_valid(event))
>> + return -EOPNOTSUPP;
>> +
>> /*
>> * CHAIN events only work when paired with an adjacent counter, and it
>> * never makes sense for a user to open one in isolation, as they'll be
>> @@ -1135,6 +1137,21 @@ static void __armv8pmu_probe_pmu(void *info)
>> cpu_pmu->reg_pmmir = read_pmmir();
>> else
>> cpu_pmu->reg_pmmir = 0;
>> + armv8pmu_branch_probe(cpu_pmu);
>> +}
>> +
>> +static int branch_records_alloc(struct arm_pmu *armpmu)
>> +{
>> + struct pmu_hw_events *events;
>> + int cpu;
>> +
>> + for_each_possible_cpu(cpu) {
>> + events = per_cpu_ptr(armpmu->hw_events, cpu);
>> + events->branches = kzalloc(sizeof(struct branch_records), GFP_KERNEL);
>> + if (!events->branches)
>> + return -ENOMEM;
>> + }
>> + return 0;
>> }
>>
>> static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
>> @@ -1145,12 +1162,24 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
>> };
>> int ret;
>>
>> + ret = armv8pmu_private_alloc(cpu_pmu);
>> + if (ret)
>> + return ret;
> Wouldn't it be better to move it under the if statement below
> if it's only needed for branch stack?
armv8pmu_private_alloc() allocates arm_pmu's private structure which stores
the BRBE HW attributes during armv8pmu_branch_probe(), called from this SMP
callback __armv8pmu_probe_pmu(). Hence without the structure being allocated
and assigned, following smp_call_function_any() cannot execute successfully.
armv8pmu_private_alloc()
{
......
Allocates arm_pmu->private as single 'struct brbe_hw_attr'
Allocates arm_pmu->pmu.task_ctx_cache
......
}
__armv8pmu_probe_pmu()
armv8pmu_branch_probe()
brbe_attributes_probe()
{
......
brbe_attr->brbe_version = brbe;
brbe_attr->brbe_format = brbe_get_format(brbidr);
brbe_attr->brbe_cc = brbe_get_cc_bits(brbidr);
brbe_attr->brbe_nr = brbe_get_numrec(brbidr);
......
}
armv8pmu_private_alloc() cannot be moved inside armv8pmu_branch_probe(),
because there cannot be any allocation while being in a SMP call context.
>
>> +
>> ret = smp_call_function_any(&cpu_pmu->supported_cpus,
>> __armv8pmu_probe_pmu,
>> &probe, 1);
>> if (ret)
>> return ret;
> Otherwise you might need to free it here.
>
>> + if (arm_pmu_branch_stack_supported(cpu_pmu)) {
>> + ret = branch_records_alloc(cpu_pmu);
>> + if (ret)
>> + return ret;
> And here too.
Not freeing the arm_pmu's private data, might not be a problem in cases
where either pmu does not support BRBE or pmu probe itself fails. But for
completeness, will change as following.
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 9725a53d6799..fdbe52913cc7 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1198,13 +1198,17 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
ret = smp_call_function_any(&cpu_pmu->supported_cpus,
__armv8pmu_probe_pmu,
&probe, 1);
- if (ret)
+ if (ret) {
+ armv8pmu_private_free(cpu_pmu);
return ret;
+ }
if (arm_pmu_branch_stack_supported(cpu_pmu)) {
ret = branch_records_alloc(cpu_pmu);
- if (ret)
+ if (ret) {
+ armv8pmu_private_free(cpu_pmu);
return ret;
+ }
} else {
armv8pmu_private_free(cpu_pmu);
}
next prev parent reply other threads:[~2023-06-05 2:43 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-31 4:04 [PATCH V11 00/10] arm64/perf: Enable branch stack sampling Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 01/10] drivers: perf: arm_pmu: Add new sched_task() callback Anshuman Khandual
2023-06-05 7:26 ` Mark Rutland
2023-05-31 4:04 ` [PATCH V11 02/10] arm64/perf: Add BRBE registers and fields Anshuman Khandual
2023-06-05 7:55 ` Mark Rutland
2023-06-06 4:27 ` Anshuman Khandual
2023-06-13 16:27 ` Mark Rutland
2023-06-14 2:59 ` Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 03/10] arm64/perf: Add branch stack support in struct arm_pmu Anshuman Khandual
2023-06-05 7:58 ` Mark Rutland
2023-06-06 4:47 ` Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 04/10] arm64/perf: Add branch stack support in struct pmu_hw_events Anshuman Khandual
2023-06-05 8:00 ` Mark Rutland
2023-05-31 4:04 ` [PATCH V11 05/10] arm64/perf: Add branch stack support in ARMV8 PMU Anshuman Khandual
2023-06-02 2:33 ` Namhyung Kim
2023-06-05 2:43 ` Anshuman Khandual [this message]
2023-06-05 12:05 ` Mark Rutland
2023-06-06 10:34 ` Anshuman Khandual
2023-06-06 10:41 ` Mark Rutland
2023-06-08 10:13 ` Suzuki K Poulose
2023-06-09 4:00 ` Anshuman Khandual
2023-06-09 9:54 ` Suzuki K Poulose
2023-06-09 7:14 ` Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 06/10] arm64/perf: Enable branch stack events via FEAT_BRBE Anshuman Khandual
2023-06-02 1:45 ` Namhyung Kim
2023-06-05 3:00 ` Anshuman Khandual
2023-06-05 13:43 ` Mark Rutland
2023-06-09 4:30 ` Anshuman Khandual
2023-06-09 12:37 ` Mark Rutland
2023-06-09 4:47 ` Anshuman Khandual
2023-06-09 12:42 ` Mark Rutland
2023-06-09 5:22 ` Anshuman Khandual
2023-06-09 12:47 ` Mark Rutland
2023-06-09 13:15 ` Mark Rutland
2023-06-12 8:35 ` Anshuman Khandual
2023-06-09 13:34 ` James Clark
2023-06-12 10:12 ` Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 07/10] arm64/perf: Add PERF_ATTACH_TASK_DATA to events with has_branch_stack() Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 08/10] arm64/perf: Add struct brbe_regset helper functions Anshuman Khandual
2023-06-02 2:40 ` Namhyung Kim
2023-06-05 3:14 ` Anshuman Khandual
2023-06-05 23:49 ` Namhyung Kim
2023-06-13 17:17 ` Mark Rutland
2023-06-14 5:14 ` Anshuman Khandual
2023-06-14 10:59 ` Mark Rutland
2023-05-31 4:04 ` [PATCH V11 09/10] arm64/perf: Implement branch records save on task sched out Anshuman Khandual
2023-05-31 4:04 ` [PATCH V11 10/10] arm64/perf: Implement branch records save on PMU IRQ Anshuman Khandual
2023-06-09 11:13 ` [PATCH V11 00/10] arm64/perf: Enable branch stack sampling Anshuman Khandual
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=58628cba-7ec4-b2b3-b993-14c2af1a67cb@arm.com \
--to=anshuman.khandual@arm.com \
--cc=acme@kernel.org \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=james.clark@arm.com \
--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=maz@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=robh@kernel.org \
--cc=suzuki.poulose@arm.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;
as well as URLs for NNTP newsgroup(s).