perf: Use sample_flags for data_src

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

Remove the data_src 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/20220901130959.1285717-6-kan.liang@linux.intel.com

Author: Kan Liang

arch/powerpc/perf/core-book3s.c

@@ -2301,8 +2301,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
-						ppmu->get_mem_data_src)
+						ppmu->get_mem_data_src) {
 			ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
+			data.sample_flags |= PERF_SAMPLE_DATA_SRC;
+		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_WEIGHT_TYPE &&
 						ppmu->get_mem_weight) {

arch/x86/events/intel/ds.c

@@ -1535,8 +1535,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	/*
 	 * data.data_src encodes the data source
 	 */
-	if (sample_type & PERF_SAMPLE_DATA_SRC)
+	if (sample_type & PERF_SAMPLE_DATA_SRC) {
 		data->data_src.val = get_data_src(event, pebs->dse);
+		data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+	}
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1770,8 +1772,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
-		if (sample_type & PERF_SAMPLE_DATA_SRC)
+		if (sample_type & PERF_SAMPLE_DATA_SRC) {
 			data->data_src.val = get_data_src(event, meminfo->aux);
+			data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+		}
 
 		if (sample_type & PERF_SAMPLE_ADDR_TYPE)
 			data->addr = meminfo->address;

include/linux/perf_event.h

@@ -1013,14 +1013,14 @@ struct perf_sample_data {
 	struct perf_raw_record		*raw;
 	u64				period;
 	u64				txn;
-	union  perf_mem_data_src	data_src;
 
 	/*
 	 * The other fields, optionally {set,used} by
 	 * perf_{prepare,output}_sample().
 	 */
 	struct perf_branch_stack	*br_stack;
 	union perf_sample_weight	weight;
+	union  perf_mem_data_src	data_src;
 
 	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->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
 

kernel/events/core.c

@@ -7411,6 +7411,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
 		data->weight.full = 0;
 
+	if (filtered_sample_type & PERF_SAMPLE_DATA_SRC)
+		data->data_src.val = PERF_MEM_NA;
+
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);