This enables the sampling check in kernel/events/core.c's
perf_event_open, which returns the more appropriate -EOPNOTSUPP.
BEFORE:
$ sudo perf record -a -e instructions,l3_request_g1.caching_l3_cache_accesses true
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (l3_request_g1.caching_l3_cache_accesses).
/bin/dmesg | grep -i perf may provide additional information.
With nothing relevant in dmesg.
AFTER:
$ sudo perf record -a -e instructions,l3_request_g1.caching_l3_cache_accesses true
Error:
l3_request_g1.caching_l3_cache_accesses: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'
Signed-off-by: Kim Phillips <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Michael Petlan <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Fixes: c43ca5091a37 ("perf/x86/amd: Add support for AMD NB and L2I "uncore" counters")
---
arch/x86/events/amd/uncore.c | 17 +++++++----------
1 file changed, 7 insertions(+), 10 deletions(-)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a6ea07f2aa84..4d867a752f0e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event)
/*
* NB and Last level cache counters (MSRs) are shared across all cores
- * that share the same NB / Last level cache. Interrupts can be directed
- * to a single target core, however, event counts generated by processes
- * running on other cores cannot be masked out. So we do not support
- * sampling and per-thread events.
+ * that share the same NB / Last level cache. On family 16h and below,
+ * Interrupts can be directed to a single target core, however, event
+ * counts generated by processes running on other cores cannot be masked
+ * out. So we do not support sampling and per-thread events via
+ * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
*/
- if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
- return -EINVAL;
-
- /* and we do not enable counter overflow interrupts */
hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
hwc->idx = -1;
@@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = {
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
};
static struct pmu amd_llc_pmu = {
@@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = {
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
};
static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
--
2.25.0