diff options
| author | Stephane Eranian <eranian@google.com> | 2023-04-11 11:38:09 +0200 |
|---|---|---|
| committer | Will Deacon <will@kernel.org> | 2023-04-11 12:35:20 +0100 |
| commit | a30b87e6bd7db112deb1e3014b23fb90111bc6c4 (patch) | |
| tree | f1ac6d89b96d7155ea75efb56609caa979474800 /drivers/perf | |
| parent | 23b2fd83948952ffee2e96ce6a982be9d8e96f9f (diff) | |
arm64: pmuv3: dynamically map PERF_COUNT_HW_BRANCH_INSTRUCTIONS
The mapping of perf_events generic hardware events to actual PMU events on
ARM PMUv3 may not always be correct. This is in particular true for the
PERF_COUNT_HW_BRANCH_INSTRUCTIONS event. Although the mapping points to an
architected event, it may not always be available. This can be seen with a
simple:
$ perf stat -e branches sleep 0
Performance counter stats for 'sleep 0':
<not supported> branches
0.001401081 seconds time elapsed
Yet the hardware does have an event that could be used for branches.
Dynamically check for a supported hardware event which can be used for
PERF_COUNT_HW_BRANCH_INSTRUCTIONS at mapping time.
And with that:
$ perf stat -e branches sleep 0
Performance counter stats for 'sleep 0':
166,739 branches
0.000832163 seconds time elapsed
Co-developed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Co-developed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Co-developed-by: Peter Newman <peternewman@google.com>
Signed-off-by: Peter Newman <peternewman@google.com>
Link: https://lore.kernel.org/all/YvunKCJHSXKz%2FkZB@FVFF77S0Q05N
Link: https://lore.kernel.org/r/20230411093809.657501-1-peternewman@google.com
Signed-off-by: Will Deacon <will@kernel.org>
Diffstat (limited to 'drivers/perf')
| -rw-r--r-- | drivers/perf/arm_pmuv3.c | 27 |
1 files changed, 23 insertions, 4 deletions
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 34ed0d5d7898..c98e4039386d 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -46,7 +46,6 @@ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND, @@ -985,6 +984,28 @@ static void armv8pmu_reset(void *info) armv8pmu_pmcr_write(pmcr); } +static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu, + struct perf_event *event) +{ + if (event->attr.type == PERF_TYPE_HARDWARE && + event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) { + + if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, + armpmu->pmceid_bitmap)) + return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED; + + if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED, + armpmu->pmceid_bitmap)) + return ARMV8_PMUV3_PERFCTR_BR_RETIRED; + + return HW_OP_UNSUPPORTED; + } + + return armpmu_map_event(event, &armv8_pmuv3_perf_map, + &armv8_pmuv3_perf_cache_map, + ARMV8_PMU_EVTYPE_EVENT); +} + static int __armv8_pmuv3_map_event(struct perf_event *event, const unsigned (*extra_event_map) [PERF_COUNT_HW_MAX], @@ -996,9 +1017,7 @@ static int __armv8_pmuv3_map_event(struct perf_event *event, int hw_event_id; struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map, - &armv8_pmuv3_perf_cache_map, - ARMV8_PMU_EVTYPE_EVENT); + hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event); /* * CHAIN events only work when paired with an adjacent counter, and it |