perf: Use sample_flags for branch stack

Use the new sample_flags to indicate whether the branch stack is filled
by the PMU driver.

Remove the br_stack 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/20220901130959.1285717-4-kan.liang@linux.intel.com

arch/powerpc/perf/core-book3s.c

@@ -2297,6 +2297,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
 			power_pmu_bhrb_read(event, cpuhw);
 			data.br_stack = &cpuhw->bhrb_stack;
+			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&

arch/x86/events/amd/core.c

@@ -929,8 +929,10 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (has_branch_stack(event))
+		if (has_branch_stack(event)) {
 			data.br_stack = &cpuc->lbr_stack;
+			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+		}
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/core.c

@@ -1714,8 +1714,10 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
+		if (has_branch_stack(event)) {
 			data.br_stack = &cpuc->lbr_stack;
+			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+		}
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/intel/core.c

@@ -2995,8 +2995,10 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
+		if (has_branch_stack(event)) {
 			data.br_stack = &cpuc->lbr_stack;
+			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+		}
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/intel/ds.c

@@ -1640,8 +1640,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 		data->sample_flags |= PERF_SAMPLE_TIME;
 	}
 
-	if (has_branch_stack(event))
+	if (has_branch_stack(event)) {
 		data->br_stack = &cpuc->lbr_stack;
+		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+	}
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1791,6 +1793,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
 			data->br_stack = &cpuc->lbr_stack;
+			data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 		}
 	}
 

include/linux/perf_event.h

@@ -1011,7 +1011,6 @@ struct perf_sample_data {
 	u64				sample_flags;
 	u64				addr;
 	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
 	u64				period;
 	union perf_sample_weight	weight;
 	u64				txn;
@@ -1021,6 +1020,8 @@ struct perf_sample_data {
 	 * The other fields, optionally {set,used} by
 	 * perf_{prepare,output}_sample().
 	 */
+	struct perf_branch_stack	*br_stack;
+
 	u64				type;
 	u64				ip;
 	struct {
@@ -1061,7 +1062,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->sample_flags = 0;
 	data->addr = addr;
 	data->raw  = NULL;
-	data->br_stack = NULL;
 	data->period = period;
 	data->weight.full = 0;
 	data->data_src.val = PERF_MEM_NA;

kernel/events/core.c

@@ -7052,7 +7052,7 @@ void perf_output_sample(struct perf_output_handle *handle,
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
-		if (data->br_stack) {
+		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
 			size_t size;
 
 			size = data->br_stack->nr
@@ -7358,7 +7358,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
 		int size = sizeof(u64); /* nr */
-		if (data->br_stack) {
+		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
 			if (perf_sample_save_hw_index(event))
 				size += sizeof(u64);