perf: Add sample_flags to indicate the PMU-filled sample data

On some platforms, some data e.g., timestamps, can be retrieved from
the PMU driver. Usually, the data from the PMU driver is more accurate.
The current perf kernel should output the PMU-filled sample data if
it's available.

To check the availability of the PMU-filled sample data, the current
perf kernel initializes the related fields in the
perf_sample_data_init(). When outputting a sample, the perf checks
whether the field is updated by the PMU driver. If yes, the updated
value will be output. If not, the perf uses an SW way to calculate the
value or just outputs the initialized value if an SW way is unavailable
either.

With more and more data being provided by the PMU driver, more fields
has to be initialized in the perf_sample_data_init(). That will
increase the number of cache lines touched in perf_sample_data_init()
and be harmful to the performance.

Add new "sample_flags" to indicate the PMU-filled sample data. The PMU
driver should set the corresponding PERF_SAMPLE_ flag when the field is
updated. The initialization of the corresponding field is not required
anymore. The following patches will make use of it and remove the
corresponding fields from the perf_sample_data_init(), which will
further minimize the number of cache lines touched.

Only clear the sample flags that have already been done by the PMU
driver in the perf_prepare_sample() for the PERF_RECORD_SAMPLE. For the
other PERF_RECORD_ event type, the sample data is not available.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
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/20220901130959.1285717-2-kan.liang@linux.intel.com

include/linux/perf_event.h

@@ -1008,6 +1008,7 @@ struct perf_sample_data {
 	 * Fields set by perf_sample_data_init(), group so as to
 	 * minimize the cachelines touched.
 	 */
+	u64				sample_flags;
 	u64				addr;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
@@ -1057,6 +1058,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
 {
 	/* remaining struct members initialized in perf_prepare_sample() */
+	data->sample_flags = 0;
 	data->addr = addr;
 	data->raw  = NULL;
 	data->br_stack = NULL;

kernel/events/core.c

@@ -6794,11 +6794,10 @@ out_put:
 
 static void __perf_event_header__init_id(struct perf_event_header *header,
 					 struct perf_sample_data *data,
-					 struct perf_event *event)
+					 struct perf_event *event,
+					 u64 sample_type)
 {
-	u64 sample_type = event->attr.sample_type;
+	data->type = event->attr.sample_type;
-
-	data->type = sample_type;
 	header->size += event->id_header_size;
 
 	if (sample_type & PERF_SAMPLE_TID) {
@@ -6827,7 +6826,7 @@ void perf_event_header__init_id(struct perf_event_header *header,
 				struct perf_event *event)
 {
 	if (event->attr.sample_id_all)
-		__perf_event_header__init_id(header, data, event);
+		__perf_event_header__init_id(header, data, event, event->attr.sample_type);
 }
 
 static void __perf_event__output_id_sample(struct perf_output_handle *handle,
@@ -7303,6 +7302,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			 struct pt_regs *regs)
 {
 	u64 sample_type = event->attr.sample_type;
+	u64 filtered_sample_type;
 
 	header->type = PERF_RECORD_SAMPLE;
 	header->size = sizeof(*header) + event->header_size;
@@ -7310,7 +7310,12 @@ void perf_prepare_sample(struct perf_event_header *header,
 	header->misc = 0;
 	header->misc |= perf_misc_flags(regs);
 
-	__perf_event_header__init_id(header, data, event);
+	/*
+	 * Clear the sample flags that have already been done by the
+	 * PMU driver.
+	 */
+	filtered_sample_type = sample_type & ~data->sample_flags;
+	__perf_event_header__init_id(header, data, event, filtered_sample_type);
 
 	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);