| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAM9d7cioDUxzNos5b3ANkG-BkJUcROSGCG0gpLzSXnc-v6o9jw@mail.gmail.com>
Date: Thu, 1 Jun 2023 19:33:54 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Anshuman Khandual <anshuman.khandual@....com>
Cc: linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
will@...nel.org, catalin.marinas@....com, mark.rutland@....com,
Mark Brown <broonie@...nel.org>,
James Clark <james.clark@....com>,
Rob Herring <robh@...nel.org>, Marc Zyngier <maz@...nel.org>,
Suzuki Poulose <suzuki.poulose@....com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
linux-perf-users@...r.kernel.org
Subject: Re: [PATCH V11 05/10] arm64/perf: Add branch stack support in ARMV8 PMU
On Tue, May 30, 2023 at 9:27 PM Anshuman Khandual
<anshuman.khandual@....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@....com>
> Cc: Will Deacon <will@...nel.org>
> Cc: Mark Rutland <mark.rutland@....com>
> Cc: linux-arm-kernel@...ts.infradead.org
> Cc: linux-kernel@...r.kernel.org
> Tested-by: James Clark <james.clark@....com>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@....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?
> +
> 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.
Thanks,
Namhyung
> + } else {
> + armv8pmu_private_free(cpu_pmu);
> + }
> +
> return probe.present ? 0 : -ENODEV;
> }
>
> @@ -1214,6 +1243,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
> cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
>
> cpu_pmu->pmu.event_idx = armv8pmu_user_event_idx;
> + cpu_pmu->sched_task = armv8pmu_sched_task;
>
> cpu_pmu->name = name;
> cpu_pmu->map_event = map_event;
> --
> 2.25.1
>
Powered by blists - more mailing lists