perf tools: Factor stat reading and CQM changes

index f2dc91fb87fa..1c73bc4d57d3 100644
@@ -876,9 +876,8 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-static inline void compute_deltas(struct perf_evsel *evsel,
-				  int cpu,
-				  struct perf_counts_values *count)
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
 

@@ -913,7 +912,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, &count);
 
 	if (scale) {
 		if (count.run == 0)

@@ -956,7 +955,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 		}
 	}
 
-	compute_deltas(evsel, -1, aggr);
+	perf_evsel__compute_deltas(evsel, -1, aggr);
 
 	evsel->counts->scaled = 0;
 	if (scale) {

index 979790951bfb..746b7ea84589 100644
@@ -110,6 +110,9 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count);
+
 int perf_evsel__object_config(size_t object_size,
 			      int (*init)(struct perf_evsel *evsel),
 			      void (*fini)(struct perf_evsel *evsel));

index 1c73bc4d57d3..6dc7a67e6d35 100644
@@ -897,6 +897,26 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 	count->run = count->run - tmp.run;
 }
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+		}
+	} else
+		count->ena = count->run = 0;
+
+	if (pscaled)
+		*pscaled = scaled;
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {

@@ -913,15 +933,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 		return -errno;
 
 	perf_evsel__compute_deltas(evsel, cpu, &count);
-
-	if (scale) {
-		if (count.run == 0)
-			count.val = 0;
-		else if (count.run < count.ena)
-			count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
-	} else
-		count.ena = count.run = 0;
-
+	perf_counts_values__scale(&count, scale, NULL);
 	evsel->counts->cpu[cpu] = count;
 	return 0;
 }

@@ -956,22 +968,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	}
 
 	perf_evsel__compute_deltas(evsel, -1, aggr);
-
-	evsel->counts->scaled = 0;
-	if (scale) {
-		if (aggr->run == 0) {
-			evsel->counts->scaled = -1;
-			aggr->val = 0;
-			return 0;
-		}
-
-		if (aggr->run < aggr->ena) {
-			evsel->counts->scaled = 1;
-			aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
-		}
-	} else
-		aggr->ena = aggr->run = 0;
-
+	perf_counts_values__scale(aggr, scale, &evsel->counts->scaled);
 	return 0;
 }
 

index 746b7ea84589..7af0377ceb18 100644
@@ -110,6 +110,9 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled);
+
 void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 				struct perf_counts_values *count);
 

index 6dc7a67e6d35..2d26b7ad6fe0 100644
@@ -917,6 +917,22 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb)
+{
+	struct perf_counts_values count;
+
+	memset(&count, 0, sizeof(count));
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+		return -errno;
+
+	return cb(evsel, cpu, thread, &count);
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {

index 7af0377ceb18..5c93bed8e8d9 100644
@@ -233,6 +233,13 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
+typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
+				    int cpu, int thread,
+				    struct perf_counts_values *count);
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
 

index 055ce9232c9e..9cc0db1d7f06 100644
@@ -388,6 +388,26 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 		update_stats(&runtime_itlb_cache_stats[0], count[0]);
 }
 
+static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
+		   struct perf_counts_values *count)
+{
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+	case AGGR_NONE:
+		perf_evsel__compute_deltas(evsel, cpu, count);
+		perf_counts_values__scale(count, scale, NULL);
+		evsel->counts->cpu[cpu] = *count;
+		update_shadow_stats(evsel, count->values);
+		break;
+	case AGGR_GLOBAL:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode

@@ -424,16 +444,11 @@ static int read_counter_aggr(struct perf_evsel *counter)
  */
 static int read_counter(struct perf_evsel *counter)
 {
-	u64 *count;
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
+		if (perf_evsel__read_cb(counter, cpu, 0, read_cb))
 			return -1;
-
-		count = counter->counts->cpu[cpu].values;
-
-		update_shadow_stats(counter, count);
 	}
 
 	return 0;

index 9cc0db1d7f06..2511d3aae708 100644
@@ -444,11 +444,18 @@ static int read_counter_aggr(struct perf_evsel *counter)
  */
 static int read_counter(struct perf_evsel *counter)
 {
-	int cpu;
+	int nthreads = thread_map__nr(evsel_list->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		if (perf_evsel__read_cb(counter, cpu, 0, read_cb))
-			return -1;
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+				return -1;
+		}
 	}
 
 	return 0;

index 2511d3aae708..b24a7a08bd1d 100644
@@ -391,6 +391,8 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		   struct perf_counts_values *count)
 {
+	struct perf_counts_values *aggr = &evsel->counts->aggr;
+
 	switch (aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:

@@ -401,6 +403,11 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		update_shadow_stats(evsel, count->values);
 		break;
 	case AGGR_GLOBAL:
+		aggr->val += count->val;
+		if (scale) {
+			aggr->ena += count->ena;
+			aggr->run += count->run;
+		}
 	default:
 		break;
 	}

@@ -408,20 +415,27 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 	return 0;
 }
 
+static int read_counter(struct perf_evsel *counter);
+
 /*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode
  */
 static int read_counter_aggr(struct perf_evsel *counter)
 {
+	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
 	int i;
 
-	if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
-			       thread_map__nr(evsel_list->threads), scale) < 0)
+	aggr->val = aggr->ena = aggr->run = 0;
+
+	if (read_counter(counter))
 		return -1;
 
+	perf_evsel__compute_deltas(counter, -1, aggr);
+	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
+
 	for (i = 0; i < 3; i++)
 		update_stats(&ps->res_stats[i], count[i]);
 

index 2d26b7ad6fe0..1e90c8557ede 100644
@@ -954,40 +954,6 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	return 0;
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel,
-		       int ncpus, int nthreads, bool scale)
-{
-	size_t nv = scale ? 3 : 1;
-	int cpu, thread;
-	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
-
-	if (evsel->system_wide)
-		nthreads = 1;
-
-	aggr->val = aggr->ena = aggr->run = 0;
-
-	for (cpu = 0; cpu < ncpus; cpu++) {
-		for (thread = 0; thread < nthreads; thread++) {
-			if (FD(evsel, cpu, thread) < 0)
-				continue;
-
-			if (readn(FD(evsel, cpu, thread),
-				  &count, nv * sizeof(u64)) < 0)
-				return -errno;
-
-			aggr->val += count.val;
-			if (scale) {
-				aggr->ena += count.ena;
-				aggr->run += count.run;
-			}
-		}
-	}
-
-	perf_evsel__compute_deltas(evsel, -1, aggr);
-	perf_counts_values__scale(aggr, scale, &evsel->counts->scaled);
-	return 0;
-}
-
 static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
 {
 	struct perf_evsel *leader = evsel->leader;

index 5c93bed8e8d9..17da44de7339 100644
@@ -269,35 +269,6 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
-		       bool scale);
-
-/**
- * perf_evsel__read - Read the aggregate results on all CPUs
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read(struct perf_evsel *evsel,
-				    int ncpus, int nthreads)
-{
-	return __perf_evsel__read(evsel, ncpus, nthreads, false);
-}
-
-/**
- * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
-					  int ncpus, int nthreads)
-{
-	return __perf_evsel__read(evsel, ncpus, nthreads, true);
-}
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 

index 17da44de7339..be295f185c32 100644
@@ -91,6 +91,7 @@ struct perf_evsel {
 	bool			immediate;
 	bool			system_wide;
 	bool			tracking;
+	bool			per_pkg;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

index c659a3ca1283..5a373483f0e4 100644
@@ -681,6 +681,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
+		evsel->per_pkg = info.per_pkg;
 	}
 
 	return evsel ? 0 : -ENOMEM;

index 881b75490533..f003b5a9e059 100644
@@ -163,6 +163,24 @@ error:
 	return -1;
 }
 
+static int
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	close(fd);
+
+	alias->per_pkg = true;
+	return 0;
+}
+
 static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;

@@ -181,6 +199,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
+	alias->per_pkg = false;
 
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {

@@ -194,6 +213,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	 */
 	perf_pmu__parse_unit(alias, dir, name);
 	perf_pmu__parse_scale(alias, dir, name);
+	perf_pmu__parse_per_pkg(alias, dir, name);
 
 	list_add_tail(&alias->list, list);
 

@@ -209,6 +229,8 @@ static inline bool pmu_alias_info_file(char *name)
 		return true;
 	if (len > 6 && !strcmp(name + len - 6, ".scale"))
 		return true;
+	if (len > 8 && !strcmp(name + len - 8, ".per-pkg"))
+		return true;
 
 	return false;
 }

@@ -649,6 +671,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	info->per_pkg = false;
+
 	/*
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)

@@ -668,6 +692,9 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
+		if (alias->per_pkg)
+			info->per_pkg = true;
+
 		list_del(&term->list);
 		free(term);
 	}

index 8092de78e818..c3a74e0e17a2 100644
@@ -29,6 +29,7 @@ struct perf_pmu {
 struct perf_pmu_info {
 	const char *unit;
 	double scale;
+	bool per_pkg;
 };
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */

@@ -39,6 +40,7 @@ struct perf_pmu_alias {
 	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
+	bool per_pkg;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);

index be295f185c32..3207f4861038 100644
@@ -73,6 +73,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
+	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;

index 5a373483f0e4..77b43fe43d55 100644
@@ -682,6 +682,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
 		evsel->per_pkg = info.per_pkg;
+		evsel->snapshot = info.snapshot;
 	}
 
 	return evsel ? 0 : -ENOMEM;

92 lines not on this page · raw message

index c3a74e0e17a2..6b1249fbdb5f 100644
@@ -30,6 +30,7 @@ struct perf_pmu_info {
 	const char *unit;
 	double scale;
 	bool per_pkg;
+	bool snapshot;
 };
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */

@@ -41,6 +42,7 @@ struct perf_pmu_alias {
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
 	bool per_pkg;
+	bool snapshot;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);

index b24a7a08bd1d..860e8ad06616 100644
@@ -388,10 +388,56 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 		update_stats(&runtime_itlb_cache_stats[0], count[0]);
 }
 
+static void zero_per_pkg(struct perf_evsel *counter)
+{
+	if (counter->per_pkg_mask)
+		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+}
+
+static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+{
+	unsigned long *mask = counter->per_pkg_mask;
+	struct cpu_map *cpus = perf_evsel__cpus(counter);
+	int s;
+
+	*skip = false;
+
+	if (!counter->per_pkg)
+		return 0;
+
+	if (cpu_map__empty(cpus))
+		return 0;
+
+	if (!mask) {
+		mask = zalloc(MAX_NR_CPUS);
+		if (!mask)
+			return -ENOMEM;
+
+		counter->per_pkg_mask = mask;
+	}
+
+	s = cpu_map__get_socket(cpus, cpu);
+	if (s < 0)
+		return -1;
+
+	*skip = test_and_set_bit(s, mask) == 1;
+	return 0;
+}
+
 static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		   struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
+	static struct perf_counts_values zero;
+	bool skip = false;
+
+	if (check_per_pkg(evsel, cpu, &skip)) {
+		pr_err("failed to read per-pkg counter\n");
+		return -1;
+	}
+
+	if (skip)
+		count = &zero;
 
 	switch (aggr_mode) {
 	case AGGR_CORE:

@@ -465,6 +511,9 @@ static int read_counter(struct perf_evsel *counter)
 	if (counter->system_wide)
 		nthreads = 1;
 
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
+
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
 			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))

index 3207f4861038..38622747d130 100644
@@ -93,6 +93,7 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
+	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

index 860e8ad06616..891086376381 100644
@@ -443,7 +443,8 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
-		perf_evsel__compute_deltas(evsel, cpu, count);
+		if (!evsel->snapshot)
+			perf_evsel__compute_deltas(evsel, cpu, count);
 		perf_counts_values__scale(count, scale, NULL);
 		evsel->counts->cpu[cpu] = *count;
 		update_shadow_stats(evsel, count->values);

@@ -479,7 +480,8 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	if (read_counter(counter))
 		return -1;
 
-	perf_evsel__compute_deltas(counter, -1, aggr);
+	if (!counter->snapshot)
+		perf_evsel__compute_deltas(counter, -1, aggr);
 	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)