perf: Use sample_flags for weight

Use the new sample_flags to indicate whether the weight field is filled
by the PMU driver.

Remove the weight field from the perf_sample_data_init() to minimize the
number of cache lines touched.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220901130959.1285717-5-kan.liang@linux.intel.com
This commit is contained in:
Kan Liang 2022-09-01 06:09:57 -07:00 committed by Peter Zijlstra
parent a9a931e266
commit 2abe681da0
4 changed files with 14 additions and 7 deletions

View File

@ -2305,9 +2305,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
if (event->attr.sample_type & PERF_SAMPLE_WEIGHT_TYPE &&
ppmu->get_mem_weight)
ppmu->get_mem_weight) {
ppmu->get_mem_weight(&data.weight.full, event->attr.sample_type);
data.sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
}
if (perf_event_overflow(event, &data, regs))
power_pmu_stop(event, 0);
} else if (period) {

View File

@ -1527,8 +1527,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
/*
* Use latency for weight (only avail with PEBS-LL)
*/
if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE))
if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) {
data->weight.full = pebs->lat;
data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
}
/*
* data.data_src encodes the data source
@ -1620,9 +1622,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll)
if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) {
data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning);
data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
}
if (sample_type & PERF_SAMPLE_TRANSACTION)
data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
pebs->ax);
@ -1764,6 +1767,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
intel_get_tsx_weight(meminfo->tsx_tuning);
}
data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
}
if (sample_type & PERF_SAMPLE_DATA_SRC)

View File

@ -1012,7 +1012,6 @@ struct perf_sample_data {
u64 addr;
struct perf_raw_record *raw;
u64 period;
union perf_sample_weight weight;
u64 txn;
union perf_mem_data_src data_src;
@ -1021,6 +1020,7 @@ struct perf_sample_data {
* perf_{prepare,output}_sample().
*/
struct perf_branch_stack *br_stack;
union perf_sample_weight weight;
u64 type;
u64 ip;
@ -1063,7 +1063,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->addr = addr;
data->raw = NULL;
data->period = period;
data->weight.full = 0;
data->data_src.val = PERF_MEM_NA;
data->txn = 0;
}

View File

@ -7408,6 +7408,9 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
data->weight.full = 0;
if (sample_type & PERF_SAMPLE_REGS_INTR) {
/* regs dump ABI info */
int size = sizeof(u64);