The following commit has been merged into the perf/core branch of tip: Commit-ID: e1f13d813df8d83f13b9dcca02656e41b29b2167 Gitweb: https://git.kernel.org/tip/e1f13d813df8d83f13b9dcca02656e41b29b2167 Author: Sandipan Das <sandipan.das@xxxxxxx> AuthorDate: Thu, 21 Apr 2022 11:16:57 +05:30 Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx> CommitterDate: Fri, 29 Apr 2022 11:06:27 +02:00 perf/x86/amd/core: Add PerfMonV2 counter control If AMD Performance Monitoring Version 2 (PerfMonV2) is supported, use a new scheme to manage the Core PMCs using the new global control and status registers. This will be bypassed on unsupported hardware (x86_pmu.version < 2). Currently, all PMCs have dedicated control (PERF_CTL) and counter (PERF_CTR) registers. For a given PMC, the enable (En) bit of its PERF_CTL register is used to start or stop counting. The Performance Counter Global Control (PerfCntrGlobalCtl) register has enable (PerfCntrEn) bits for each PMC. For a PMC to start counting, both PERF_CTL and PerfCntrGlobalCtl enable bits must be set. If either of those are cleared, the PMC stops counting. In x86_pmu_{en,dis}able_all(), the PERF_CTL registers of all active PMCs are written to in a loop. Ideally, PMCs counting the same event that were started and stopped at the same time should record the same counts. Due to delays in between writes to the PERF_CTL registers across loop iterations, the PMCs cannot be enabled or disabled at the same instant and hence, record slightly different counts. This is fixed by enabling or disabling all active PMCs at the same time with a single write to the PerfCntrGlobalCtl register. Signed-off-by: Sandipan Das <sandipan.das@xxxxxxx> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Link: https://lkml.kernel.org/r/dfe8e934074aaabc6ba748dfaccd0a77c974bb82.1650515382.git.sandipan.das@xxxxxxx --- arch/x86/events/amd/core.c | 50 +++++++++++++++++++++++++++++++++---- 1 file changed, 45 insertions(+), 5 deletions(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 52fd794..a339c3e 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -664,6 +664,11 @@ static void amd_pmu_cpu_dead(int cpu) amd_pmu_cpu_reset(cpu); } +static inline void amd_pmu_set_global_ctl(u64 ctl) +{ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl); +} + /* * When a PMC counter overflows, an NMI is used to process the event and * reset the counter. NMI latency can result in the counter being updated @@ -693,15 +698,11 @@ static void amd_pmu_wait_on_overflow(int idx) } } -static void amd_pmu_disable_all(void) +static void amd_pmu_check_overflow(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; - amd_brs_disable_all(); - - x86_pmu_disable_all(); - /* * This shouldn't be called from NMI context, but add a safeguard here * to return, since if we're in NMI context we can't wait for an NMI @@ -748,6 +749,26 @@ static void amd_pmu_enable_all(int added) } } +static void amd_pmu_v2_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * Testing cpu_hw_events.enabled should be skipped in this case unlike + * in x86_pmu_enable_event(). + * + * Since cpu_hw_events.enabled is set only after returning from + * x86_pmu_start(), the PMCs must be programmed and kept ready. + * Counting starts only after x86_pmu_enable_all() is called. + */ + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); +} + +static void amd_pmu_v2_enable_all(int added) +{ + amd_pmu_set_global_ctl(amd_pmu_global_cntr_mask); +} + static void amd_pmu_disable_event(struct perf_event *event) { x86_pmu_disable_event(event); @@ -765,6 +786,20 @@ static void amd_pmu_disable_event(struct perf_event *event) amd_pmu_wait_on_overflow(event->hw.idx); } +static void amd_pmu_disable_all(void) +{ + amd_brs_disable_all(); + x86_pmu_disable_all(); + amd_pmu_check_overflow(); +} + +static void amd_pmu_v2_disable_all(void) +{ + /* Disable all PMCs */ + amd_pmu_set_global_ctl(0); + amd_pmu_check_overflow(); +} + static void amd_pmu_add_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -1216,6 +1251,11 @@ static int __init amd_core_pmu_init(void) x86_pmu.num_counters = ebx.split.num_core_pmc; amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1; + + /* Update PMC handling functions */ + x86_pmu.enable_all = amd_pmu_v2_enable_all; + x86_pmu.disable_all = amd_pmu_v2_disable_all; + x86_pmu.enable = amd_pmu_v2_enable_event; } /*
![]() |