perf: RISC-V: Check standard event availability
Commit Message
The RISC-V SBI PMU specification defines several standard hardware and
cache events. Currently, all of these events appear in the `perf list`
output, even if they are not actually implemented. Add logic to check
which events are supported by the hardware (i.e. can be mapped to some
counter), so only usable events are reported to userspace.
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
---
Before this patch:
$ perf list hw
List of pre-defined events (to be used in -e or -M):
branch-instructions OR branches [Hardware event]
branch-misses [Hardware event]
bus-cycles [Hardware event]
cache-misses [Hardware event]
cache-references [Hardware event]
cpu-cycles OR cycles [Hardware event]
instructions [Hardware event]
ref-cycles [Hardware event]
stalled-cycles-backend OR idle-cycles-backend [Hardware event]
stalled-cycles-frontend OR idle-cycles-frontend [Hardware event]
$ perf stat -ddd true
Performance counter stats for 'true':
4.36 msec task-clock # 0.744 CPUs utilized
1 context-switches # 229.325 /sec
0 cpu-migrations # 0.000 /sec
38 page-faults # 8.714 K/sec
4,375,694 cycles # 1.003 GHz (60.64%)
728,945 instructions # 0.17 insn per cycle
79,199 branches # 18.162 M/sec
17,709 branch-misses # 22.36% of all branches
181,734 L1-dcache-loads # 41.676 M/sec
5,547 L1-dcache-load-misses # 3.05% of all L1-dcache accesses
<not counted> LLC-loads (0.00%)
<not counted> LLC-load-misses (0.00%)
<not counted> L1-icache-loads (0.00%)
<not counted> L1-icache-load-misses (0.00%)
<not counted> dTLB-loads (0.00%)
<not counted> dTLB-load-misses (0.00%)
<not counted> iTLB-loads (0.00%)
<not counted> iTLB-load-misses (0.00%)
<not counted> L1-dcache-prefetches (0.00%)
<not counted> L1-dcache-prefetch-misses (0.00%)
0.005860375 seconds time elapsed
0.000000000 seconds user
0.010383000 seconds sys
After this patch:
$ perf list hw
List of pre-defined events (to be used in -e or -M):
branch-instructions OR branches [Hardware event]
branch-misses [Hardware event]
cache-misses [Hardware event]
cache-references [Hardware event]
cpu-cycles OR cycles [Hardware event]
instructions [Hardware event]
$ perf stat -ddd true
Performance counter stats for 'true':
5.16 msec task-clock # 0.848 CPUs utilized
1 context-switches # 193.817 /sec
0 cpu-migrations # 0.000 /sec
37 page-faults # 7.171 K/sec
5,183,625 cycles # 1.005 GHz
961,696 instructions # 0.19 insn per cycle
85,853 branches # 16.640 M/sec
20,462 branch-misses # 23.83% of all branches
243,545 L1-dcache-loads # 47.203 M/sec
5,974 L1-dcache-load-misses # 2.45% of all L1-dcache accesses
<not supported> LLC-loads
<not supported> LLC-load-misses
<not supported> L1-icache-loads
<not supported> L1-icache-load-misses
<not supported> dTLB-loads
19,619 dTLB-load-misses
<not supported> iTLB-loads
6,831 iTLB-load-misses
<not supported> L1-dcache-prefetches
<not supported> L1-dcache-prefetch-misses
0.006085625 seconds time elapsed
0.000000000 seconds user
0.013022000 seconds sys
drivers/perf/riscv_pmu_sbi.c | 37 ++++++++++++++++++++++++++++++++++--
1 file changed, 35 insertions(+), 2 deletions(-)
@@ -86,7 +86,7 @@ struct sbi_pmu_event_data {
};
};
-static const struct sbi_pmu_event_data pmu_hw_event_map[] = {
+static struct sbi_pmu_event_data pmu_hw_event_map[] = {
[PERF_COUNT_HW_CPU_CYCLES] = {.hw_gen_event = {
SBI_PMU_HW_CPU_CYCLES,
SBI_PMU_EVENT_TYPE_HW, 0}},
@@ -120,7 +120,7 @@ static const struct sbi_pmu_event_data pmu_hw_event_map[] = {
};
#define C(x) PERF_COUNT_HW_CACHE_##x
-static const struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
+static struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
@@ -265,6 +265,36 @@ static const struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_M
},
};
+static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH,
+ 0, cmask, 0, edata->event_idx, 0, 0);
+ if (!ret.error) {
+ sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
+ ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
+ } else if (ret.error == SBI_ERR_NOT_SUPPORTED) {
+ /* This event cannot be monitored by any counter */
+ edata->event_idx = -EINVAL;
+ }
+}
+
+static void pmu_sbi_update_events(void)
+{
+ /* Ensure events are not already mapped to a counter */
+ sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
+ 0, cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
+
+ for (int i = 0; i < ARRAY_SIZE(pmu_hw_event_map); i++)
+ pmu_sbi_check_event(&pmu_hw_event_map[i]);
+
+ for (int i = 0; i < ARRAY_SIZE(pmu_cache_event_map); i++)
+ for (int j = 0; j < ARRAY_SIZE(pmu_cache_event_map[i]); j++)
+ for (int k = 0; k < ARRAY_SIZE(pmu_cache_event_map[i][j]); k++)
+ pmu_sbi_check_event(&pmu_cache_event_map[i][j][k]);
+}
+
static int pmu_sbi_ctr_get_width(int idx)
{
return pmu_ctr_list[idx].width;
@@ -1046,6 +1076,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
if (pmu_sbi_get_ctrinfo(num_counters, &cmask))
goto out_free;
+ /* Check which standard events are available */
+ pmu_sbi_update_events();
+
ret = pmu_sbi_setup_irqs(pmu, pdev);
if (ret < 0) {
pr_info("Perf sampling/filtering is not supported as sscof extension is not available\n");