perf/core: Save the dynamic parts of sample data size

The perf sample data can be divided into parts.  The event->header_size
and event->id_header_size keep the static part of the sample data which
is determined by the sample_type flags.

But other parts like CALLCHAIN and BRANCH_STACK are changing dynamically
so it needs to see the actual data.  In preparation of handling repeated
calls for perf_prepare_sample(), it can save the dynamic size to the
perf sample data to avoid the duplicate work.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230118060559.615653-2-namhyung@kernel.org

include/linux/perf_event.h

@@ -1103,6 +1103,7 @@ struct perf_sample_data {
 	 */
 	u64				sample_flags;
 	u64				period;
+	u64				dyn_size;
 
 	/*
 	 * Fields commonly set by __perf_event_header__init_id(),
@@ -1158,6 +1159,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	/* remaining struct members initialized in perf_prepare_sample() */
 	data->sample_flags = PERF_SAMPLE_PERIOD;
 	data->period = period;
+	data->dyn_size = 0;
 
 	if (addr) {
 		data->addr = addr;

kernel/events/core.c

@@ -7586,7 +7586,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 		size += data->callchain->nr;
 
-		header->size += size * sizeof(u64);
+		data->dyn_size += size * sizeof(u64);
 	}
 
 	if (sample_type & PERF_SAMPLE_RAW) {
@@ -7612,7 +7612,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			data->raw = NULL;
 		}
 
-		header->size += size;
+		data->dyn_size += size;
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -7624,7 +7624,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += data->br_stack->nr
 			      * sizeof(struct perf_branch_entry);
 		}
-		header->size += size;
+		data->dyn_size += size;
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
@@ -7639,7 +7639,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += hweight64(mask) * sizeof(u64);
 		}
 
-		header->size += size;
+		data->dyn_size += size;
 	}
 
 	if (sample_type & PERF_SAMPLE_STACK_USER) {
@@ -7664,7 +7664,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += sizeof(u64) + stack_size;
 
 		data->stack_user_size = stack_size;
-		header->size += size;
+		data->dyn_size += size;
 	}
 
 	if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
@@ -7693,7 +7693,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += hweight64(mask) * sizeof(u64);
 		}
 
-		header->size += size;
+		data->dyn_size += size;
 	}
 
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR &&
@@ -7738,8 +7738,11 @@ void perf_prepare_sample(struct perf_event_header *header,
 		size = perf_prepare_sample_aux(event, data, size);
 
 		WARN_ON_ONCE(size + header->size > U16_MAX);
-		header->size += size;
+		data->dyn_size += size + sizeof(u64); /* size above */
 	}
+
+	header->size += data->dyn_size;
+
 	/*
 	 * If you're adding more sample types here, you likely need to do
 	 * something about the overflowing header::size, like repurpose the