perf cpumap: Add range data encoding

Often cpumaps encode a range of all CPUs, add a compact encoding that
doesn't require a bit mask or list of all CPUs.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Colin Ian King <colin.king@intel.com>
Cc: Dave Marchevsky <davemarchevsky@fb.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20220614143353.1559597-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 75 insertions, 76 deletions

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 851d11a64b0d..289ea17ac5f7 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1195,93 +1195,97 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 	return err;
 }
 
-static void synthesize_cpus(struct perf_record_cpu_map_data *data,
-			    const struct perf_cpu_map *map)
-{
-	int i, map_nr = perf_cpu_map__nr(map);
-
-	data->cpus_data.nr = map_nr;
+struct synthesize_cpu_map_data {
+	const struct perf_cpu_map *map;
+	int nr;
+	int min_cpu;
+	int max_cpu;
+	int has_any_cpu;
+	int type;
+	size_t size;
+	struct perf_record_cpu_map_data *data;
+};
 
-	for (i = 0; i < map_nr; i++)
-		data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu;
+static void synthesize_cpus(struct synthesize_cpu_map_data *data)
+{
+	data->data->type = PERF_CPU_MAP__CPUS;
+	data->data->cpus_data.nr = data->nr;
+	for (int i = 0; i < data->nr; i++)
+		data->data->cpus_data.cpu[i] = perf_cpu_map__cpu(data->map, i).cpu;
 }
 
-static void synthesize_mask(struct perf_record_cpu_map_data *data,
-			    const struct perf_cpu_map *map, int max)
+static void synthesize_mask(struct synthesize_cpu_map_data *data)
 {
 	int idx;
 	struct perf_cpu cpu;
 
 	/* Due to padding, the 4bytes per entry mask variant is always smaller. */
-	data->mask32_data.nr = BITS_TO_U32(max);
-	data->mask32_data.long_size = 4;
+	data->data->type = PERF_CPU_MAP__MASK;
+	data->data->mask32_data.nr = BITS_TO_U32(data->max_cpu);
+	data->data->mask32_data.long_size = 4;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+	perf_cpu_map__for_each_cpu(cpu, idx, data->map) {
 		int bit_word = cpu.cpu / 32;
-		__u32 bit_mask = 1U << (cpu.cpu & 31);
+		u32 bit_mask = 1U << (cpu.cpu & 31);
 
-		data->mask32_data.mask[bit_word] |= bit_mask;
+		data->data->mask32_data.mask[bit_word] |= bit_mask;
 	}
 }
 
-static size_t cpus_size(const struct perf_cpu_map *map)
+static void synthesize_range_cpus(struct synthesize_cpu_map_data *data)
 {
-	return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
+	data->data->type = PERF_CPU_MAP__RANGE_CPUS;
+	data->data->range_cpu_data.any_cpu = data->has_any_cpu;
+	data->data->range_cpu_data.start_cpu = data->min_cpu;
+	data->data->range_cpu_data.end_cpu = data->max_cpu;
 }
 
-static size_t mask_size(const struct perf_cpu_map *map, int *max)
-{
-	*max = perf_cpu_map__max(map).cpu;
-	return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32);
-}
-
-static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size,
-				 u16 *type, int *max)
+static void *cpu_map_data__alloc(struct synthesize_cpu_map_data *syn_data,
+				 size_t header_size)
 {
 	size_t size_cpus, size_mask;
-	bool is_dummy = perf_cpu_map__empty(map);
 
-	/*
-	 * Both array and mask data have variable size based
-	 * on the number of cpus and their actual values.
-	 * The size of the 'struct perf_record_cpu_map_data' is:
-	 *
-	 *   array = size of 'struct cpu_map_entries' +
-	 *           number of cpus * sizeof(u64)
-	 *
-	 *   mask  = size of 'struct perf_record_record_cpu_map' +
-	 *           maximum cpu bit converted to size of longs
-	 *
-	 * and finally + the size of 'struct perf_record_cpu_map_data'.
-	 */
-	size_cpus = cpus_size(map);
-	size_mask = mask_size(map, max);
+	syn_data->nr = perf_cpu_map__nr(syn_data->map);
+	syn_data->has_any_cpu = (perf_cpu_map__cpu(syn_data->map, 0).cpu == -1) ? 1 : 0;
 
-	if (is_dummy || (size_cpus < size_mask)) {
-		*size += size_cpus;
-		*type  = PERF_CPU_MAP__CPUS;
-	} else {
-		*size += size_mask;
-		*type  = PERF_CPU_MAP__MASK;
+	syn_data->min_cpu = perf_cpu_map__cpu(syn_data->map, syn_data->has_any_cpu).cpu;
+	syn_data->max_cpu = perf_cpu_map__max(syn_data->map).cpu;
+	if (syn_data->max_cpu - syn_data->min_cpu + 1 == syn_data->nr - syn_data->has_any_cpu) {
+		/* A consecutive range of CPUs can be encoded using a range. */
+		assert(sizeof(u16) + sizeof(struct perf_record_range_cpu_map) == sizeof(u64));
+		syn_data->type = PERF_CPU_MAP__RANGE_CPUS;
+		syn_data->size = header_size + sizeof(u64);
+		return zalloc(syn_data->size);
 	}
 
-	*size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */
-	*size = PERF_ALIGN(*size, sizeof(u64));
-	return zalloc(*size);
+	size_cpus = sizeof(u16) + sizeof(struct cpu_map_entries) + syn_data->nr * sizeof(u16);
+	/* Due to padding, the 4bytes per entry mask variant is always smaller. */
+	size_mask = sizeof(u16) + sizeof(struct perf_record_mask_cpu_map32) +
+		BITS_TO_U32(syn_data->max_cpu) * sizeof(__u32);
+	if (syn_data->has_any_cpu || size_cpus < size_mask) {
+		/* Follow the CPU map encoding. */
+		syn_data->type = PERF_CPU_MAP__CPUS;
+		syn_data->size = header_size + PERF_ALIGN(size_cpus, sizeof(u64));
+		return zalloc(syn_data->size);
+	}
+	/* Encode using a bitmask. */
+	syn_data->type = PERF_CPU_MAP__MASK;
+	syn_data->size = header_size + PERF_ALIGN(size_mask, sizeof(u64));
+	return zalloc(syn_data->size);
 }
 
-static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
-				     const struct perf_cpu_map *map,
-				     u16 type, int max)
+static void cpu_map_data__synthesize(struct synthesize_cpu_map_data *data)
 {
-	data->type = type;
-
-	switch (type) {
+	switch (data->type) {
 	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus(data, map);
+		synthesize_cpus(data);
 		break;
 	case PERF_CPU_MAP__MASK:
-		synthesize_mask(data, map, max);
+		synthesize_mask(data);
+		break;
+	case PERF_CPU_MAP__RANGE_CPUS:
+		synthesize_range_cpus(data);
+		break;
 	default:
 		break;
 	}
@@ -1289,23 +1293,22 @@ static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
 
 static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map)
 {
-	size_t size = sizeof(struct perf_event_header);
+	struct synthesize_cpu_map_data syn_data = { .map = map };
 	struct perf_record_cpu_map *event;
-	int max;
-	u16 type;
 
-	event = cpu_map_data__alloc(map, &size, &type, &max);
+
+	event = cpu_map_data__alloc(&syn_data, sizeof(struct perf_event_header));
 	if (!event)
 		return NULL;
 
+	syn_data.data = &event->data;
 	event->header.type = PERF_RECORD_CPU_MAP;
-	event->header.size = size;
-	event->data.type   = type;
-
-	cpu_map_data__synthesize(&event->data, map, type, max);
+	event->header.size = syn_data.size;
+	cpu_map_data__synthesize(&syn_data);
 	return event;
 }
 
+
 int perf_event__synthesize_cpu_map(struct perf_tool *tool,
 				   const struct perf_cpu_map *map,
 				   perf_event__handler_t process,
@@ -1998,24 +2001,20 @@ int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evse
 int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel,
 					     perf_event__handler_t process)
 {
-	size_t size = sizeof(struct perf_event_header) + sizeof(u64) + sizeof(u64);
+	struct synthesize_cpu_map_data syn_data = { .map = evsel->core.own_cpus };
 	struct perf_record_event_update *ev;
-	int max, err;
-	u16 type;
-
-	if (!evsel->core.own_cpus)
-		return 0;
+	int err;
 
-	ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max);
+	ev = cpu_map_data__alloc(&syn_data, sizeof(struct perf_event_header) + 2 * sizeof(u64));
 	if (!ev)
 		return -ENOMEM;
 
+	syn_data.data = &ev->cpus.cpus;
 	ev->header.type = PERF_RECORD_EVENT_UPDATE;
-	ev->header.size = (u16)size;
+	ev->header.size = (u16)syn_data.size;
 	ev->type	= PERF_EVENT_UPDATE__CPUS;
 	ev->id		= evsel->core.id[0];
-
-	cpu_map_data__synthesize(&ev->cpus.cpus, evsel->core.own_cpus, type, max);
+	cpu_map_data__synthesize(&syn_data);
 
 	err = process(tool, (union perf_event *)ev, NULL, NULL);
 	free(ev);