From: Like Xu <likexu@xxxxxxxxxxx>
Most invocation of start_event() and measure() first sets evt.count=0.
Instead of forcing each caller to ensure count is zeroed, optimize the
count to zero during start_event(), then drop all of the manual zeroing.
Accumulating counts can be handled by reading the current count before
start_event(), and doing something like stuffing a high count to test an
edge case could be handled by an inner helper, __start_event().
For overflow, just open code measure() for that one-off case. Requiring
callers to zero out a field in most common cases isn't exactly flexible.
Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
[sean: tag __measure() noinline so its count is stable]
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
x86/pmu.c | 31 ++++++++++++++++---------------
1 file changed, 16 insertions(+), 15 deletions(-)
diff --git a/x86/pmu.c b/x86/pmu.c
index 715b45a3..77e59c5c 100644
--- a/x86/pmu.c
+++ b/x86/pmu.c
@@ -137,9 +137,9 @@ static void global_disable(pmu_counter_t *cnt)
~(1ull << cnt->idx));
}
-
-static void start_event(pmu_counter_t *evt)
+static void __start_event(pmu_counter_t *evt, uint64_t count)
{
+ evt->count = count;
wrmsr(evt->ctr, evt->count);
if (is_gp(evt))
wrmsr(MSR_P6_EVNTSEL0 + event_to_global_idx(evt),
@@ -162,6 +162,11 @@ static void start_event(pmu_counter_t *evt)
apic_write(APIC_LVTPC, PC_VECTOR);
}
+static void start_event(pmu_counter_t *evt)
+{
+ __start_event(evt, 0);
+}
+
static void stop_event(pmu_counter_t *evt)
{
global_disable(evt);
@@ -186,6 +191,13 @@ static noinline void measure(pmu_counter_t *evt, int count)
stop_event(&evt[i]);
}
+static noinline void __measure(pmu_counter_t *evt, uint64_t count)
+{
+ __start_event(evt, count);
+ loop();
+ stop_event(evt);
+}
+
static bool verify_event(uint64_t count, struct pmu_event *e)
{
// printf("%d <= %ld <= %d\n", e->min, count, e->max);
@@ -208,7 +220,6 @@ static void check_gp_counter(struct pmu_event *evt)
int i;
for (i = 0; i < nr_gp_counters; i++, cnt.ctr++) {
- cnt.count = 0;
measure(&cnt, 1);
report(verify_event(cnt.count, evt), "%s-%d", evt->name, i);
}
@@ -235,7 +246,6 @@ static void check_fixed_counters(void)
int i;
for (i = 0; i < nr_fixed_counters; i++) {
- cnt.count = 0;
cnt.ctr = fixed_events[i].unit_sel;
measure(&cnt, 1);
report(verify_event(cnt.count, &fixed_events[i]), "fixed-%d", i);
@@ -253,14 +263,12 @@ static void check_counters_many(void)
if (!pmu_gp_counter_is_available(i))
continue;
- cnt[n].count = 0;
cnt[n].ctr = gp_counter_base + n;
cnt[n].config = EVNTSEL_OS | EVNTSEL_USR |
gp_events[i % ARRAY_SIZE(gp_events)].unit_sel;
n++;
}
for (i = 0; i < nr_fixed_counters; i++) {
- cnt[n].count = 0;
cnt[n].ctr = fixed_events[i].unit_sel;
cnt[n].config = EVNTSEL_OS | EVNTSEL_USR;
n++;
@@ -283,9 +291,8 @@ static void check_counter_overflow(void)
pmu_counter_t cnt = {
.ctr = gp_counter_base,
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[1].unit_sel /* instructions */,
- .count = 0,
};
- measure(&cnt, 1);
+ __measure(&cnt, 0);
count = cnt.count;
/* clear status before test */
@@ -311,7 +318,7 @@ static void check_counter_overflow(void)
else
cnt.config &= ~EVNTSEL_INT;
idx = event_to_global_idx(&cnt);
- measure(&cnt, 1);
+ __measure(&cnt, cnt.count);
report(cnt.count == 1, "cntr-%d", i);
status = rdmsr(MSR_CORE_PERF_GLOBAL_STATUS);
report(status & (1ull << idx), "status-%d", i);
@@ -329,7 +336,6 @@ static void check_gp_counter_cmask(void)
pmu_counter_t cnt = {
.ctr = gp_counter_base,
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[1].unit_sel /* instructions */,
- .count = 0,
};
cnt.config |= (0x2 << EVNTSEL_CMASK_SHIFT);
measure(&cnt, 1);
@@ -415,7 +421,6 @@ static void check_running_counter_wrmsr(void)
pmu_counter_t evt = {
.ctr = gp_counter_base,
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[1].unit_sel,
- .count = 0,
};
report_prefix_push("running counter wrmsr");
@@ -430,7 +435,6 @@ static void check_running_counter_wrmsr(void)
wrmsr(MSR_CORE_PERF_GLOBAL_OVF_CTRL,
rdmsr(MSR_CORE_PERF_GLOBAL_STATUS));
- evt.count = 0;
start_event(&evt);
count = -1;
@@ -454,13 +458,11 @@ static void check_emulated_instr(void)
.ctr = MSR_IA32_PERFCTR0,
/* branch instructions */
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[5].unit_sel,
- .count = 0,
};
pmu_counter_t instr_cnt = {
.ctr = MSR_IA32_PERFCTR0 + 1,
/* instructions */
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[1].unit_sel,
- .count = 0,
};
report_prefix_push("emulated instruction");
@@ -592,7 +594,6 @@ static void set_ref_cycle_expectations(void)
pmu_counter_t cnt = {
.ctr = MSR_IA32_PERFCTR0,
.config = EVNTSEL_OS | EVNTSEL_USR | gp_events[2].unit_sel,
- .count = 0,
};
uint64_t tsc_delta;
uint64_t t0, t1, t2, t3;
--
2.38.1.431.g37b22c650d-goog
