perf/core improvements and fixes

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/stat-shadow.c | 11 -----------
 tools/perf/util/stat.h        | 43 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 42 insertions(+), 12 deletions(-)

tools/perf/util/stat-shadow.c +0 ~~-11~~

index 57ec22513971..93aac2788056 100644
@@ -9,17 +9,6 @@
 #include "expr.h"
 #include "metricgroup.h"
 
-enum {
-	CTX_BIT_USER	= 1 << 0,
-	CTX_BIT_KERNEL	= 1 << 1,
-	CTX_BIT_HV	= 1 << 2,
-	CTX_BIT_HOST	= 1 << 3,
-	CTX_BIT_IDLE	= 1 << 4,
-	CTX_BIT_MAX	= 1 << 5,
-};
-
-#define NUM_CTX CTX_BIT_MAX
-
 /*
  * AGGR_GLOBAL: Use CPU 0
  * AGGR_SOCKET: Use first CPU of socket

tools/perf/util/stat.h +42 -1

61 lines not on this page · raw message

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:29 UTC #2 lore raw

PATCH 2/35 perf stat: Extend rbtree to support per-thread shadow stats

From: Jin Yao <[email protected]>

Previously the rbtree was used to link generic metrics.

This patches adds new ctx/type/stat into rbtree keys because we will use this rbtree to maintain shadow metrics to replace original a couple of static arrays for supporting per-thread shadow stats.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/stat-shadow.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

tools/perf/util/stat-shadow.c +27 -0

index 93aac2788056..528be3e8d13b 100644
@@ -45,7 +45,10 @@ struct stats walltime_nsecs_stats;
 struct saved_value {
 	struct rb_node rb_node;
 	struct perf_evsel *evsel;
+	enum stat_type type;
+	int ctx;
 	int cpu;
+	struct runtime_stat *stat;
 	struct stats stats;
 };

@@ -58,6 +61,30 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 
 	if (a->cpu != b->cpu)
 		return a->cpu - b->cpu;
+
+	/*
+	 * Previously the rbtree was used to link generic metrics.
+	 * The keys were evsel/cpu. Now the rbtree is extended to support
+	 * per-thread shadow stats. For shadow stats case, the keys
+	 * are cpu/type/ctx/stat (evsel is NULL). For generic metrics
+	 * case, the keys are still evsel/cpu (type/ctx/stat are 0 or NULL).
+	 */
+	if (a->type != b->type)
+		return a->type - b->type;
+
+	if (a->ctx != b->ctx)
+		return a->ctx - b->ctx;
+
+	if (a->evsel == NULL && b->evsel == NULL) {
+		if (a->stat == b->stat)
+			return 0;
+
+		if ((char *)a->stat < (char *)b->stat)
+			return -1;
+
+		return 1;
+	}
+
 	if (a->evsel == b->evsel)
 		return 0;
 	if ((char *)a->evsel < (char *)b->evsel)

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:29 UTC #3 lore raw

PATCH 3/35 perf stat: Create the runtime_stat init/exit function

From: Jin Yao <[email protected]>

It mainly initializes and releases the rblist which is defined in struct runtime_stat.

For the original rblist 'runtime_saved_values', it's still kept there for keeping the patch bisectable.

The rblist 'runtime_saved_values' will be removed in later patch at switching time.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/stat-shadow.c | 17 +++++++++++++++++
 tools/perf/util/stat.h        |  3 +++
 2 files changed, 20 insertions(+)

tools/perf/util/stat-shadow.c +17 -0

index 528be3e8d13b..07cfbf613bdc 100644
@@ -40,6 +40,7 @@ static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS];
 static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
+struct runtime_stat rt_stat;
 struct stats walltime_nsecs_stats;
 
 struct saved_value {

@@ -134,6 +135,21 @@ static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
 	return NULL;
 }
 
+void runtime_stat__init(struct runtime_stat *st)
+{
+	struct rblist *rblist = &st->value_list;
+
+	rblist__init(rblist);
+	rblist->node_cmp = saved_value_cmp;
+	rblist->node_new = saved_value_new;
+	rblist->node_delete = saved_value_delete;
+}
+
+void runtime_stat__exit(struct runtime_stat *st)
+{
+	rblist__exit(&st->value_list);
+}
+
 void perf_stat__init_shadow_stats(void)
 {
 	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");

@@ -141,6 +157,7 @@ void perf_stat__init_shadow_stats(void)
 	runtime_saved_values.node_cmp = saved_value_cmp;
 	runtime_saved_values.node_new = saved_value_new;
 	runtime_saved_values.node_delete = saved_value_delete;
+	runtime_stat__init(&rt_stat);
 }
 
 static int evsel_context(struct perf_evsel *evsel)

tools/perf/util/stat.h +3 -0

index c685c41f1fb9..f20240037377 100644
@@ -117,12 +117,15 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
+extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
 typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
 typedef void (*new_line_t )(void *ctx);
 
+void runtime_stat__init(struct runtime_stat *st);
+void runtime_stat__exit(struct runtime_stat *st);
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:29 UTC #4 lore raw

PATCH 4/35 perf stat: Update per-thread shadow stats

From: Jin Yao <[email protected]>

The functions perf_stat__update_shadow_stats() is called to update the shadow stats on a set of static variables.

But the static variables are the limitations to be extended to support per-thread shadow stats.

This patch lets the perf_stat__update_shadow_stats() support to update the shadow stats on a input parameter 'st' and uses update_runtime_stat() to update the stats. It will not directly update the static variables as before.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-script.c   |  3 +-
 tools/perf/builtin-stat.c     |  3 +-
 tools/perf/util/stat-shadow.c | 86 +++++++++++++++++++++++++++++--------------
 tools/perf/util/stat.c        |  8 ++--
 tools/perf/util/stat.h        |  2 +-
 5 files changed, 68 insertions(+), 34 deletions(-)

tools/perf/builtin-script.c +2 -1

index 39d8b55f0db3..81b395040298 100644
@@ -1548,7 +1548,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	val = sample->period * evsel->scale;
 	perf_stat__update_shadow_stats(evsel,
 				       val,
-				       sample->cpu);
+				       sample->cpu,
+				       &rt_stat);
 	evsel_script(evsel)->val = val;
 	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
 		for_each_group_member (ev2, evsel->leader) {

tools/perf/builtin-stat.c +2 -1

index a027b4712e48..3f4a2c21b824 100644
@@ -1214,7 +1214,8 @@ static void aggr_update_shadow(void)
 				val += perf_counts(counter->counts, cpu, 0)->val;
 			}
 			perf_stat__update_shadow_stats(counter, val,
-						       first_shadow_cpu(counter, id));
+					first_shadow_cpu(counter, id),
+					&rt_stat);
 		}
 	}
 }

tools/perf/util/stat-shadow.c +58 ~~-28~~

147 lines not on this page · raw message

tools/perf/util/stat.c +5 -3

index 151e9efd7286..78abfd40b135 100644
@@ -278,9 +278,11 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, config->scale, NULL);
 		if (config->aggr_mode == AGGR_NONE)
-			perf_stat__update_shadow_stats(evsel, count->val, cpu);
+			perf_stat__update_shadow_stats(evsel, count->val, cpu,
+						       &rt_stat);
 		if (config->aggr_mode == AGGR_THREAD)
-			perf_stat__update_shadow_stats(evsel, count->val, 0);
+			perf_stat__update_shadow_stats(evsel, count->val, 0,
+						       &rt_stat);
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;

@@ -362,7 +364,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	perf_stat__update_shadow_stats(counter, *count, 0);
+	perf_stat__update_shadow_stats(counter, *count, 0, &rt_stat);
 
 	return 0;
 }

tools/perf/util/stat.h +1 -1

index f20240037377..bb9902ad3a79 100644
@@ -129,7 +129,7 @@ void runtime_stat__exit(struct runtime_stat *st);
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
-				    int cpu);
+				    int cpu, struct runtime_stat *st);
 struct perf_stat_output_ctx {
 	void *ctx;
 	print_metric_t print_metric;

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:29 UTC #5 lore raw

PATCH 5/35 perf stat: Print per-thread shadow stats

From: Jin Yao <[email protected]>

The function perf_stat__print_shadow_stats() is called to print the shadow stats on a set of static variables.

But the static variables are the limitations to support per-thread shadow stats.

This patch lets the perf_stat__print_shadow_stats() support to print the shadow stats from a input parameter 'st'.

It will not directly get value from static variable. Instead, it now uses runtime_stat_avg() and runtime_stat_n() to get and compute the values.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-script.c   |   3 +-
 tools/perf/builtin-stat.c     |  23 +++--
 tools/perf/util/stat-shadow.c | 209 ++++++++++++++++++++++++++----------------
 tools/perf/util/stat.h        |   3 +-
 4 files changed, 151 insertions(+), 87 deletions(-)

tools/perf/builtin-script.c +2 -1

index 81b395040298..fac6f053e4da 100644
@@ -1557,7 +1557,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 						      evsel_script(ev2)->val,
 						      sample->cpu,
 						      &ctx,
-						      NULL);
+						      NULL,
+						      &rt_stat);
 		}
 		evsel_script(evsel->leader)->gnum = 0;
 	}

tools/perf/builtin-stat.c +15 -8

index 3f4a2c21b824..097a694d16f2 100644
@@ -1097,7 +1097,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 }
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-		     char *prefix, u64 run, u64 ena, double noise)
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
 {
 	struct perf_stat_output_ctx out;
 	struct outstate os = {

@@ -1190,7 +1191,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
-				&out, &metric_events);
+				&out, &metric_events, st);
 	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);

@@ -1335,7 +1336,8 @@ static void print_aggr(char *prefix)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
 			if (!metric_only)
 				fputc('\n', output);
 		}

@@ -1365,7 +1367,8 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
+		printout(thread, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
 		fputc('\n', output);
 	}
 }

@@ -1402,7 +1405,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		fprintf(output, "%s", prefix);
 
 	uval = cd.avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
+	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
 	if (!metric_only)
 		fprintf(output, "\n");
 }

@@ -1441,7 +1445,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
 
 		fputc('\n', output);
 	}

@@ -1473,7 +1478,8 @@ static void print_no_aggr_metric(char *prefix)
 			run = perf_counts(counter->counts, cpu, 0)->run;
 
 			uval = val * counter->scale;
-			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
 		}
 		fputc('\n', stat_config.output);
 	}

@@ -1529,7 +1535,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
 					      &out,
-					      &metric_events);
+					      &metric_events,
+					      &rt_stat);
 	}
 	fputc('\n', stat_config.output);
 }

tools/perf/util/stat-shadow.c +132 ~~-77~~

504 lines not on this page · raw message

tools/perf/util/stat.h +2 -1

index bb9902ad3a79..76b322a2d293 100644
@@ -140,7 +140,8 @@ struct perf_stat_output_ctx {
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
-				   struct rblist *metric_events);
+				   struct rblist *metric_events,
+				   struct runtime_stat *st);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:29 UTC #6 lore raw

PATCH 6/35 perf stat: Remove a set of shadow stats static variables

From: Jin Yao <[email protected]>

In previous patches, we have reconstructed the code and let it not access the static variables directly.

This patch removes these static variables.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/stat-shadow.c | 68 ++++++++++---------------------------------
 tools/perf/util/stat.h        |  1 +
 2 files changed, 16 insertions(+), 53 deletions(-)

tools/perf/util/stat-shadow.c +15 ~~-53~~

index a95c4fe991aa..594d14a02b67 100644
@@ -16,28 +16,6 @@
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
  */
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS];
-static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
 struct runtime_stat rt_stat;

@@ -163,10 +141,6 @@ void runtime_stat__exit(struct runtime_stat *st)
 void perf_stat__init_shadow_stats(void)
 {
 	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
-	rblist__init(&runtime_saved_values);
-	runtime_saved_values.node_cmp = saved_value_cmp;
-	runtime_saved_values.node_new = saved_value_new;
-	runtime_saved_values.node_delete = saved_value_delete;
 	runtime_stat__init(&rt_stat);
 }

@@ -188,36 +162,13 @@ static int evsel_context(struct perf_evsel *evsel)
 	return ctx;
 }
 
-void perf_stat__reset_shadow_stats(void)
+static void reset_stat(struct runtime_stat *st)
 {
+	struct rblist *rblist;
 	struct rb_node *pos, *next;
 
-	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
-	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
-	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
-	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
-	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
-	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
-	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
-	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
-	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
-	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
-	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
-	memset(runtime_cycles_in_tx_stats, 0,
-			sizeof(runtime_cycles_in_tx_stats));
-	memset(runtime_transaction_stats, 0,
-		sizeof(runtime_transaction_stats));
-	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
-	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
-	memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots));
-	memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired));
-	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
-	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
-	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
-	memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats));
-	memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats));
-
-	next = rb_first(&runtime_saved_values.entries);
+	rblist = &st->value_list;
+	next = rb_first(&rblist->entries);
 	while (next) {
 		pos = next;
 		next = rb_next(pos);

@@ -227,6 +178,17 @@ void perf_stat__reset_shadow_stats(void)
 	}
 }
 
+void perf_stat__reset_shadow_stats(void)
+{
+	reset_stat(&rt_stat);
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
+{
+	reset_stat(st);
+}
+
 static void update_runtime_stat(struct runtime_stat *st,
 				enum stat_type type,
 				int ctx, int cpu, u64 count)

tools/perf/util/stat.h +1 -0

index 76b322a2d293..cfe4fb899633 100644
@@ -128,6 +128,7 @@ void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
+void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
 				    int cpu, struct runtime_stat *st);
 struct perf_stat_output_ctx {

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:31 UTC #7 lore raw

PATCH 7/35 perf stat: Allocate shadow stats buffer for threads

From: Jin Yao <[email protected]>

After perf_evlist__create_maps() being executed, we can get all threads from /proc. And via thread_map__nr(), we can also get the number of threads.

With the number of threads, the patch allocates a buffer which will record the shadow stats for these threads.

The buffer pointer is saved in stat_config.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-stat.c | 46 +++++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/stat.h    |  2 ++
 2 files changed, 47 insertions(+), 1 deletion(-)

tools/perf/builtin-stat.c +45 -1

index 097a694d16f2..4c492ac3ac07 100644
@@ -214,8 +214,13 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 
 static void perf_stat__reset_stats(void)
 {
+	int i;
+
 	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
+
+	for (i = 0; i < stat_config.stats_num; i++)
+		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)

@@ -2495,6 +2500,35 @@ int process_cpu_map_event(struct perf_tool *tool,
 	return set_maps(st);
 }
 
+static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
+{
+	int i;
+
+	config->stats = calloc(nthreads, sizeof(struct runtime_stat));
+	if (!config->stats)
+		return -1;
+
+	config->stats_num = nthreads;
+
+	for (i = 0; i < nthreads; i++)
+		runtime_stat__init(&config->stats[i]);
+
+	return 0;
+}
+
+static void runtime_stat_delete(struct perf_stat_config *config)
+{
+	int i;
+
+	if (!config->stats)
+		return;
+
+	for (i = 0; i < config->stats_num; i++)
+		runtime_stat__exit(&config->stats[i]);
+
+	free(config->stats);
+}
+
 static const char * const stat_report_usage[] = {
 	"perf stat report [<options>]",
 	NULL,

@@ -2750,8 +2784,15 @@ int cmd_stat(int argc, const char **argv)
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.
 	 */
-	if (stat_config.aggr_mode == AGGR_THREAD)
+	if (stat_config.aggr_mode == AGGR_THREAD) {
 		thread_map__read_comms(evsel_list->threads);
+		if (target.system_wide) {
+			if (runtime_stat_new(&stat_config,
+				thread_map__nr(evsel_list->threads))) {
+				goto out;
+			}
+		}
+	}
 
 	if (interval && interval < 100) {
 		if (interval < 10) {

@@ -2841,5 +2882,8 @@ int cmd_stat(int argc, const char **argv)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
 
 	perf_evlist__delete(evsel_list);
+
+	runtime_stat_delete(&stat_config);
+
 	return status;
 }

tools/perf/util/stat.h +2 -0

index cfe4fb899633..2ed95dc72784 100644
@@ -90,6 +90,8 @@ struct perf_stat_config {
 	bool		scale;
 	FILE		*output;
 	unsigned int	interval;
+	struct runtime_stat *stats;
+	int		stats_num;
 };
 
 void update_stats(struct stats *stats, u64 val);

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #8 lore raw

PATCH 8/35 perf stat: Update or print per-thread stats

From: Jin Yao <[email protected]>

If the stats pointer in stat_config structure is not null, it will update the per-thread stats or print the per-thread stats on this buffer.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-stat.c |  9 +++++++--
 tools/perf/util/stat.c    | 11 ++++++++---
 2 files changed, 15 insertions(+), 5 deletions(-)

tools/perf/builtin-stat.c +7 -2

index 4c492ac3ac07..f4129a5fbb01 100644
@@ -1372,8 +1372,13 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval, prefix, run, ena, 1.0,
-			 &rt_stat);
+
+		if (stat_config.stats)
+			printout(thread, 0, counter, uval, prefix, run, ena,
+				 1.0, &stat_config.stats[thread]);
+		else
+			printout(thread, 0, counter, uval, prefix, run, ena,
+				 1.0, &rt_stat);
 		fputc('\n', output);
 	}
 }

tools/perf/util/stat.c +8 -3

index 78abfd40b135..32235657c1ac 100644
@@ -280,9 +280,14 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 		if (config->aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->val, cpu,
 						       &rt_stat);
-		if (config->aggr_mode == AGGR_THREAD)
-			perf_stat__update_shadow_stats(evsel, count->val, 0,
-						       &rt_stat);
+		if (config->aggr_mode == AGGR_THREAD) {
+			if (config->stats)
+				perf_stat__update_shadow_stats(evsel,
+					count->val, 0, &config->stats[thread]);
+			else
+				perf_stat__update_shadow_stats(evsel,
+					count->val, 0, &rt_stat);
+		}
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #9 lore raw

PATCH 9/35 perf thread_map: Enumerate all threads from /proc

From: Jin Yao <[email protected]>

This patch calls thread_map__new_all_cpus() to enumerate all threads from /proc if per-thread flag is enabled.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/tests/thread-map.c | 2 +-
 tools/perf/util/evlist.c      | 3 ++-
 tools/perf/util/thread_map.c  | 5 ++++-
 tools/perf/util/thread_map.h  | 2 +-
 4 files changed, 8 insertions(+), 4 deletions(-)

tools/perf/tests/thread-map.c +1 -1

index dbcb6a19b375..4de1939b58ba 100644
@@ -105,7 +105,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 	TEST_ASSERT_VAL("failed to allocate map string",
 			asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
 
-	threads = thread_map__new_str(str, NULL, 0);
+	threads = thread_map__new_str(str, NULL, 0, false);
 
 	TEST_ASSERT_VAL("failed to allocate thread_map",
 			threads);

tools/perf/util/evlist.c +2 -1

index 3570355bcf39..f0a5e09c4071 100644
@@ -1105,7 +1105,8 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 
-	threads = thread_map__new_str(target->pid, target->tid, target->uid);
+	threads = thread_map__new_str(target->pid, target->tid, target->uid,
+				      target->per_thread);
 
 	if (!threads)
 		return -1;

tools/perf/util/thread_map.c +4 -1

index 2b653853eec2..3e1038f6491c 100644
@@ -323,7 +323,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-				       uid_t uid)
+				       uid_t uid, bool per_thread)
 {
 	if (pid)
 		return thread_map__new_by_pid_str(pid);

@@ -331,6 +331,9 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	if (!tid && uid != UINT_MAX)
 		return thread_map__new_by_uid(uid);
 
+	if (per_thread)
+		return thread_map__new_all_cpus();
+
 	return thread_map__new_by_tid_str(tid);
 }

tools/perf/util/thread_map.h +1 -1

index 07a765fb22bb..0a806b99e73c 100644
@@ -31,7 +31,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-		const char *tid, uid_t uid);
+		const char *tid, uid_t uid, bool per_thread);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #10 lore raw

PATCH 10/35 perf stat: Remove --per-thread pid/tid limitation

From: Jin Yao <[email protected]>

Currently, if we execute 'perf stat --per-thread' without specifying pid/tid, perf will return error.

root@skl:/tmp# perf stat --per-thread
The --per-thread option is only available when monitoring via -p -t options.
    -p, --pid <pid>       stat events on existing process id
    -t, --tid <tid>       stat events on existing thread id

This patch removes this limitation. If no pid/tid specified, it returns all threads (get threads from /proc).

Note that it doesn't support cpu_list yet so if it's a cpu_list case, then skip.

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-stat.c | 23 +++++++++++++++--------
 tools/perf/util/target.h  |  7 +++++++
 2 files changed, 22 insertions(+), 8 deletions(-)

tools/perf/builtin-stat.c +15 -8

index f4129a5fbb01..ee708ba6f79a 100644
@@ -277,7 +277,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 			attr->enable_on_exec = 1;
 	}
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);

@@ -340,7 +340,7 @@ static int read_counter(struct perf_evsel *counter)
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		ncpus = perf_evsel__nr_cpus(counter);
 	else
 		ncpus = 1;

@@ -2743,12 +2743,16 @@ int cmd_stat(int argc, const char **argv)
 		run_count = 1;
 	}
 
-	if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
-		fprintf(stderr, "The --per-thread option is only available "
-			"when monitoring via -p -t options.\n");
-		parse_options_usage(NULL, stat_options, "p", 1);
-		parse_options_usage(NULL, stat_options, "t", 1);
-		goto out;
+	if ((stat_config.aggr_mode == AGGR_THREAD) &&
+		!target__has_task(&target)) {
+		if (!target.system_wide || target.cpu_list) {
+			fprintf(stderr, "The --per-thread option is only "
+				"available when monitoring via -p -t -a "
+				"options or only --per-thread.\n");
+			parse_options_usage(NULL, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
+			goto out;
+		}
 	}
 
 	/*

@@ -2772,6 +2776,9 @@ int cmd_stat(int argc, const char **argv)
 
 	target__validate(&target);
 
+	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+		target.per_thread = true;
+
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");

tools/perf/util/target.h +7 -0

index 446aa7a56f25..6ef01a83b24e 100644
@@ -64,6 +64,11 @@ static inline bool target__none(struct target *target)
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__has_per_thread(struct target *target)
+{
+	return target->system_wide && target->per_thread;
+}
+
 static inline bool target__uses_dummy_map(struct target *target)
 {
 	bool use_dummy = false;

@@ -73,6 +78,8 @@ static inline bool target__uses_dummy_map(struct target *target)
 	else if (target__has_task(target) ||
 	         (!target__has_cpu(target) && !target->uses_mmap))
 		use_dummy = true;
+	else if (target__has_per_thread(target))
+		use_dummy = true;
 
 	return use_dummy;
 }

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #11 lore raw

PATCH 11/35 perf stat: Resort '--per-thread' result

From: Jin Yao <[email protected]>

There are many threads reported if we enable '--per-thread' globally.

1. Most of the threads are not counted or counting value 0. This patch removes these threads.

2. We also resort the threads in display according to the counting value. It's useful for user to see the hottest threads easily.

For example, the new results would be:

root@skl:/tmp# perf stat --per-thread
^C
 Performance counter stats for 'system wide':

            perf-24165              4.302433      cpu-clock (msec)          #    0.001 CPUs utilized
          vmstat-23127              1.562215      cpu-clock (msec)          #    0.000 CPUs utilized
      irqbalance-2780               0.827851      cpu-clock (msec)          #    0.000 CPUs utilized
            sshd-23111              0.278308      cpu-clock (msec)          #    0.000 CPUs utilized
        thermald-2841               0.230880      cpu-clock (msec)          #    0.000 CPUs utilized
            sshd-23058              0.207306      cpu-clock (msec)          #    0.000 CPUs utilized
     kworker/0:2-19991              0.133983      cpu-clock (msec)          #    0.000 CPUs utilized
   kworker/u16:1-18249              0.125636      cpu-clock (msec)          #    0.000 CPUs utilized
       rcu_sched-8                  0.085533      cpu-clock (msec)          #    0.000 CPUs utilized
   kworker/u16:2-23146              0.077139      cpu-clock (msec)          #    0.000 CPUs utilized
           gmain-2700               0.041789      cpu-clock (msec)          #    0.000 CPUs utilized
     kworker/4:1-15354              0.028370      cpu-clock (msec)          #    0.000 CPUs utilized
     kworker/6:0-17528              0.023895      cpu-clock (msec)          #    0.000 CPUs utilized
    kworker/4:1H-1887               0.013209      cpu-clock (msec)          #    0.000 CPUs utilized
     kworker/5:2-31362              0.011627      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/0-11                 0.010892      cpu-clock (msec)          #    0.000 CPUs utilized
     kworker/3:2-12870              0.010220      cpu-clock (msec)          #    0.000 CPUs utilized
     ksoftirqd/0-7                  0.008869      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/1-14                 0.008476      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/7-50                 0.002944      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/3-26                 0.002893      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/4-32                 0.002759      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/2-20                 0.002429      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/6-44                 0.001491      cpu-clock (msec)          #    0.000 CPUs utilized
      watchdog/5-38                 0.001477      cpu-clock (msec)          #    0.000 CPUs utilized
       rcu_sched-8                        10      context-switches          #    0.117 M/sec
   kworker/u16:1-18249                     7      context-switches          #    0.056 M/sec
            sshd-23111                     4      context-switches          #    0.014 M/sec
          vmstat-23127                     4      context-switches          #    0.003 M/sec
            perf-24165                     4      context-switches          #    0.930 K/sec
     kworker/0:2-19991                     3      context-switches          #    0.022 M/sec
   kworker/u16:2-23146                     3      context-switches          #    0.039 M/sec
     kworker/4:1-15354                     2      context-switches          #    0.070 M/sec
     kworker/6:0-17528                     2      context-switches          #    0.084 M/sec
            sshd-23058                     2      context-switches          #    0.010 M/sec
     ksoftirqd/0-7                         1      context-switches          #    0.113 M/sec
      watchdog/0-11                        1      context-switches          #    0.092 M/sec
      watchdog/1-14                        1      context-switches          #    0.118 M/sec
      watchdog/2-20                        1      context-switches          #    0.412 M/sec
      watchdog/3-26                        1      context-switches          #    0.346 M/sec
      watchdog/4-32                        1      context-switches          #    0.362 M/sec
      watchdog/5-38                        1      context-switches          #    0.677 M/sec
      watchdog/6-44                        1      context-switches          #    0.671 M/sec
      watchdog/7-50                        1      context-switches          #    0.340 M/sec
    kworker/4:1H-1887                      1      context-switches          #    0.076 M/sec
        thermald-2841                      1      context-switches          #    0.004 M/sec
           gmain-2700                      1      context-switches          #    0.024 M/sec
      irqbalance-2780                      1      context-switches          #    0.001 M/sec
     kworker/3:2-12870                     1      context-switches          #    0.098 M/sec
     kworker/5:2-31362                     1      context-switches          #    0.086 M/sec
   kworker/u16:1-18249                     2      cpu-migrations            #    0.016 M/sec
   kworker/u16:2-23146                     2      cpu-migrations            #    0.026 M/sec
       rcu_sched-8                         1      cpu-migrations            #    0.012 M/sec
            sshd-23058                     1      cpu-migrations            #    0.005 M/sec
            perf-24165             8,833,385      cycles                    #    2.053 GHz
          vmstat-23127             1,702,699      cycles                    #    1.090 GHz
      irqbalance-2780                739,847      cycles                    #    0.894 GHz
            sshd-23111               269,506      cycles                    #    0.968 GHz
        thermald-2841                204,556      cycles                    #    0.886 GHz
            sshd-23058               158,780      cycles                    #    0.766 GHz
     kworker/0:2-19991               112,981      cycles                    #    0.843 GHz
   kworker/u16:1-18249               100,926      cycles                    #    0.803 GHz
       rcu_sched-8                    74,024      cycles                    #    0.865 GHz
   kworker/u16:2-23146                55,984      cycles                    #    0.726 GHz
           gmain-2700                 34,278      cycles                    #    0.820 GHz
     kworker/4:1-15354                20,665      cycles                    #    0.728 GHz
     kworker/6:0-17528                16,445      cycles                    #    0.688 GHz
     kworker/5:2-31362                 9,492      cycles                    #    0.816 GHz
      watchdog/3-26                    8,695      cycles                    #    3.006 GHz
    kworker/4:1H-1887                  8,238      cycles                    #    0.624 GHz
      watchdog/4-32                    7,580      cycles                    #    2.747 GHz
     kworker/3:2-12870                 7,306      cycles                    #    0.715 GHz
      watchdog/2-20                    7,274      cycles                    #    2.995 GHz
      watchdog/0-11                    6,988      cycles                    #    0.642 GHz
     ksoftirqd/0-7                     6,376      cycles                    #    0.719 GHz
      watchdog/1-14                    5,340      cycles                    #    0.630 GHz
      watchdog/5-38                    4,061      cycles                    #    2.749 GHz
      watchdog/6-44                    3,976      cycles                    #    2.667 GHz
      watchdog/7-50                    3,418      cycles                    #    1.161 GHz
          vmstat-23127             2,511,699      instructions              #    1.48  insn per cycle
            perf-24165             1,829,908      instructions              #    0.21  insn per cycle
      irqbalance-2780              1,190,204      instructions              #    1.61  insn per cycle
        thermald-2841                143,544      instructions              #    0.70  insn per cycle
            sshd-23111               128,138      instructions              #    0.48  insn per cycle
            sshd-23058                57,654      instructions              #    0.36  insn per cycle
       rcu_sched-8                    44,063      instructions              #    0.60  insn per cycle
   kworker/u16:1-18249                42,551      instructions              #    0.42  insn per cycle
     kworker/0:2-19991                25,873      instructions              #    0.23  insn per cycle
   kworker/u16:2-23146                21,407      instructions              #    0.38  insn per cycle
           gmain-2700                 13,691      instructions              #    0.40  insn per cycle
     kworker/4:1-15354                12,964      instructions              #    0.63  insn per cycle
     kworker/6:0-17528                10,034      instructions              #    0.61  insn per cycle
     kworker/5:2-31362                 5,203      instructions              #    0.55  insn per cycle
     kworker/3:2-12870                 4,866      instructions              #    0.67  insn per cycle
    kworker/4:1H-1887                  3,586      instructions              #    0.44  insn per cycle
     ksoftirqd/0-7                     3,463      instructions              #    0.54  insn per cycle
      watchdog/0-11                    3,135      instructions              #    0.45  insn per cycle
      watchdog/1-14                    3,135      instructions              #    0.59  insn per cycle
      watchdog/2-20                    3,135      instructions              #    0.43  insn per cycle
      watchdog/3-26                    3,135      instructions              #    0.36  insn per cycle
      watchdog/4-32                    3,135      instructions              #    0.41  insn per cycle
      watchdog/5-38                    3,135      instructions              #    0.77  insn per cycle
      watchdog/6-44                    3,135      instructions              #    0.79  insn per cycle
      watchdog/7-50                    3,135      instructions              #    0.92  insn per cycle
          vmstat-23127               539,181      branches                  #  345.139 M/sec
            perf-24165               375,364      branches                  #   87.245 M/sec
      irqbalance-2780                262,092      branches                  #  316.593 M/sec
        thermald-2841                 31,611      branches                  #  136.915 M/sec
            sshd-23111                21,874      branches                  #   78.596 M/sec
            sshd-23058                10,682      branches                  #   51.528 M/sec
       rcu_sched-8                     8,693      branches                  #  101.633 M/sec
   kworker/u16:1-18249                 7,891      branches                  #   62.808 M/sec
     kworker/0:2-19991                 5,761      branches                  #   42.998 M/sec
   kworker/u16:2-23146                 4,099      branches                  #   53.138 M/sec
     kworker/4:1-15354                 2,755      branches                  #   97.110 M/sec
           gmain-2700                  2,638      branches                  #   63.127 M/sec
     kworker/6:0-17528                 2,216      branches                  #   92.739 M/sec
     kworker/5:2-31362                 1,132      branches                  #   97.360 M/sec
     kworker/3:2-12870                 1,081      branches                  #  105.773 M/sec
    kworker/4:1H-1887                    725      branches                  #   54.887 M/sec
     ksoftirqd/0-7                       707      branches                  #   79.716 M/sec
      watchdog/0-11                      652      branches                  #   59.860 M/sec
      watchdog/1-14                      652      branches                  #   76.923 M/sec
      watchdog/2-20                      652      branches                  #  268.423 M/sec
      watchdog/3-26                      652      branches                  #  225.372 M/sec
      watchdog/4-32                      652      branches                  #  236.318 M/sec
      watchdog/5-38                      652      branches                  #  441.435 M/sec
      watchdog/6-44                      652      branches                  #  437.290 M/sec
      watchdog/7-50                      652      branches                  #  221.467 M/sec
          vmstat-23127                 8,960      branch-misses             #    1.66% of all branches
      irqbalance-2780                  3,047      branch-misses             #    1.16% of all branches
            perf-24165                 2,876      branch-misses             #    0.77% of all branches
            sshd-23111                 1,843      branch-misses             #    8.43% of all branches
        thermald-2841                  1,444      branch-misses             #    4.57% of all branches
            sshd-23058                 1,379      branch-misses             #   12.91% of all branches
   kworker/u16:1-18249                   982      branch-misses             #   12.44% of all branches
       rcu_sched-8                       893      branch-misses             #   10.27% of all branches
   kworker/u16:2-23146                   578      branch-misses             #   14.10% of all branches
     kworker/0:2-19991                   376      branch-misses             #    6.53% of all branches
           gmain-2700                    280      branch-misses             #   10.61% of all branches
     kworker/6:0-17528                   196      branch-misses             #    8.84% of all branches
     kworker/4:1-15354                   187      branch-misses             #    6.79% of all branches
     kworker/5:2-31362                   123      branch-misses             #   10.87% of all branches
      watchdog/0-11                       95      branch-misses             #   14.57% of all branches
      watchdog/4-32                       89      branch-misses             #   13.65% of all branches
     kworker/3:2-12870                    80      branch-misses             #    7.40% of all branches
      watchdog/3-26                       61      branch-misses             #    9.36% of all branches
    kworker/4:1H-1887                     60      branch-misses             #    8.28% of all branches
      watchdog/2-20                       52      branch-misses             #    7.98% of all branches
     ksoftirqd/0-7                        47      branch-misses             #    6.65% of all branches
      watchdog/1-14                       46      branch-misses             #    7.06% of all branches
      watchdog/7-50                       13      branch-misses             #    1.99% of all branches
      watchdog/5-38                        8      branch-misses             #    1.23% of all branches
      watchdog/6-44                        7      branch-misses             #    1.07% of all branches

       3.695150786 seconds time elapsed

root@skl:/tmp# perf stat --per-thread -M IPC,CPI
^C

Performance counter stats for 'system wide':

          vmstat-23127             2,000,783      inst_retired.any          #      1.5 IPC
        thermald-2841              1,472,670      inst_retired.any          #      1.3 IPC
            sshd-23111               977,374      inst_retired.any          #      1.2 IPC
            perf-24163               483,779      inst_retired.any          #      0.2 IPC
           gmain-2700                341,213      inst_retired.any          #      0.9 IPC
            sshd-23058               148,891      inst_retired.any          #      0.8 IPC
    rtkit-daemon-3288                 71,210      inst_retired.any          #      0.7 IPC
   kworker/u16:1-18249                39,562      inst_retired.any          #      0.3 IPC
       rcu_sched-8                    14,474      inst_retired.any          #      0.8 IPC
     kworker/0:2-19991                 7,659      inst_retired.any          #      0.2 IPC
     kworker/4:1-15354                 6,714      inst_retired.any          #      0.8 IPC
    rtkit-daemon-3289                  4,839      inst_retired.any          #      0.3 IPC
     kworker/6:0-17528                 3,321      inst_retired.any          #      0.6 IPC
     kworker/5:2-31362                 3,215      inst_retired.any          #      0.5 IPC
     kworker/7:2-23145                 3,173      inst_retired.any          #      0.7 IPC
    kworker/4:1H-1887                  1,719      inst_retired.any          #      0.3 IPC
      watchdog/0-11                    1,479      inst_retired.any          #      0.3 IPC
      watchdog/1-14                    1,479      inst_retired.any          #      0.3 IPC
      watchdog/2-20                    1,479      inst_retired.any          #      0.4 IPC
      watchdog/3-26                    1,479      inst_retired.any          #      0.4 IPC
      watchdog/4-32                    1,479      inst_retired.any          #      0.3 IPC
      watchdog/5-38                    1,479      inst_retired.any          #      0.3 IPC
      watchdog/6-44                    1,479      inst_retired.any          #      0.7 IPC
      watchdog/7-50                    1,479      inst_retired.any          #      0.7 IPC
   kworker/u16:2-23146                 1,408      inst_retired.any          #      0.5 IPC
            perf-24163             2,249,872      cpu_clk_unhalted.thread
          vmstat-23127             1,352,455      cpu_clk_unhalted.thread
        thermald-2841              1,161,140      cpu_clk_unhalted.thread
            sshd-23111               807,827      cpu_clk_unhalted.thread
           gmain-2700                375,535      cpu_clk_unhalted.thread
            sshd-23058               194,071      cpu_clk_unhalted.thread
   kworker/u16:1-18249               114,306      cpu_clk_unhalted.thread
    rtkit-daemon-3288                103,547      cpu_clk_unhalted.thread
     kworker/0:2-19991                46,550      cpu_clk_unhalted.thread
       rcu_sched-8                    18,855      cpu_clk_unhalted.thread
    rtkit-daemon-3289                 17,549      cpu_clk_unhalted.thread
     kworker/4:1-15354                 8,812      cpu_clk_unhalted.thread
     kworker/5:2-31362                 6,812      cpu_clk_unhalted.thread
    kworker/4:1H-1887                  5,270      cpu_clk_unhalted.thread
     kworker/6:0-17528                 5,111      cpu_clk_unhalted.thread
     kworker/7:2-23145                 4,667      cpu_clk_unhalted.thread
      watchdog/0-11                    4,663      cpu_clk_unhalted.thread
      watchdog/1-14                    4,663      cpu_clk_unhalted.thread
      watchdog/4-32                    4,626      cpu_clk_unhalted.thread
      watchdog/5-38                    4,403      cpu_clk_unhalted.thread
      watchdog/3-26                    3,936      cpu_clk_unhalted.thread
      watchdog/2-20                    3,850      cpu_clk_unhalted.thread
   kworker/u16:2-23146                 2,654      cpu_clk_unhalted.thread
      watchdog/6-44                    2,017      cpu_clk_unhalted.thread
      watchdog/7-50                    2,017      cpu_clk_unhalted.thread
          vmstat-23127             2,000,783      inst_retired.any          #      0.7 CPI
        thermald-2841              1,472,670      inst_retired.any          #      0.8 CPI
            sshd-23111               977,374      inst_retired.any          #      0.8 CPI
            perf-24163               495,037      inst_retired.any          #      4.7 CPI
           gmain-2700                341,213      inst_retired.any          #      1.1 CPI
            sshd-23058               148,891      inst_retired.any          #      1.3 CPI
    rtkit-daemon-3288                 71,210      inst_retired.any          #      1.5 CPI
   kworker/u16:1-18249                39,562      inst_retired.any          #      2.9 CPI
       rcu_sched-8                    14,474      inst_retired.any          #      1.3 CPI
     kworker/0:2-19991                 7,659      inst_retired.any          #      6.1 CPI
     kworker/4:1-15354                 6,714      inst_retired.any          #      1.3 CPI
    rtkit-daemon-3289                  4,839      inst_retired.any          #      3.6 CPI
     kworker/6:0-17528                 3,321      inst_retired.any          #      1.5 CPI
     kworker/5:2-31362                 3,215      inst_retired.any          #      2.1 CPI
     kworker/7:2-23145                 3,173      inst_retired.any          #      1.5 CPI
    kworker/4:1H-1887                  1,719      inst_retired.any          #      3.1 CPI
      watchdog/0-11                    1,479      inst_retired.any          #      3.2 CPI
      watchdog/1-14                    1,479      inst_retired.any          #      3.2 CPI
      watchdog/2-20                    1,479      inst_retired.any          #      2.6 CPI
      watchdog/3-26                    1,479      inst_retired.any          #      2.7 CPI
      watchdog/4-32                    1,479      inst_retired.any          #      3.1 CPI
      watchdog/5-38                    1,479      inst_retired.any          #      3.0 CPI
      watchdog/6-44                    1,479      inst_retired.any          #      1.4 CPI
      watchdog/7-50                    1,479      inst_retired.any          #      1.4 CPI
   kworker/u16:2-23146                 1,408      inst_retired.any          #      1.9 CPI
            perf-24163             2,302,323      cycles
          vmstat-23127             1,352,455      cycles
        thermald-2841              1,161,140      cycles
            sshd-23111               807,827      cycles
           gmain-2700                375,535      cycles
            sshd-23058               194,071      cycles
   kworker/u16:1-18249               114,306      cycles
    rtkit-daemon-3288                103,547      cycles
     kworker/0:2-19991                46,550      cycles
       rcu_sched-8                    18,855      cycles
    rtkit-daemon-3289                 17,549      cycles
     kworker/4:1-15354                 8,812      cycles
     kworker/5:2-31362                 6,812      cycles
    kworker/4:1H-1887                  5,270      cycles
     kworker/6:0-17528                 5,111      cycles
     kworker/7:2-23145                 4,667      cycles
      watchdog/0-11                    4,663      cycles
      watchdog/1-14                    4,663      cycles
      watchdog/4-32                    4,626      cycles
      watchdog/5-38                    4,403      cycles
      watchdog/3-26                    3,936      cycles
      watchdog/2-20                    3,850      cycles
   kworker/u16:2-23146                 2,654      cycles
      watchdog/6-44                    2,017      cycles
      watchdog/7-50                    2,017      cycles

       2.175726600 seconds time elapsed

Signed-off-by Jin Yao <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-stat.c | 77 ++++++++++++++++++++++++++++++++++++++++-------
 tools/perf/util/stat.h    |  9 ++++++
 2 files changed, 75 insertions(+), 11 deletions(-)

tools/perf/builtin-stat.c +66 ~~-11~~

index ee708ba6f79a..58d501d1f5fd 100644
@@ -1351,13 +1351,24 @@ static void print_aggr(char *prefix)
 	}
 }
 
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+static int cmp_val(const void *a, const void *b)
 {
-	FILE *output = stat_config.output;
-	int nthreads = thread_map__nr(counter->threads);
-	int ncpus = cpu_map__nr(counter->cpus);
-	int cpu, thread;
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret)
+{
+	int cpu, thread, i = 0;
 	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
 
 	for (thread = 0; thread < nthreads; thread++) {
 		u64 ena = 0, run = 0, val = 0;

@@ -1368,19 +1379,63 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			run += perf_counts(counter->counts, cpu, thread)->run;
 		}
 
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(&target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = stat_config.output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		uval = val * counter->scale;
-
+		id = buf[thread].id;
 		if (stat_config.stats)
-			printout(thread, 0, counter, uval, prefix, run, ena,
-				 1.0, &stat_config.stats[thread]);
+			printout(id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &stat_config.stats[id]);
 		else
-			printout(thread, 0, counter, uval, prefix, run, ena,
-				 1.0, &rt_stat);
+			printout(id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
 		fputc('\n', output);
 	}
+
+	free(buf);
 }
 
 struct caggr_data {

tools/perf/util/stat.h +9 -0

index 2ed95dc72784..dbc6f7134f61 100644
@@ -111,6 +111,15 @@ static inline void init_stats(struct stats *stats)
 struct perf_evsel;
 struct perf_evlist;
 
+struct perf_aggr_thread_value {
+	struct perf_evsel *counter;
+	int id;
+	double uval;
+	u64 val;
+	u64 run;
+	u64 ena;
+};
+
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 			   enum perf_stat_evsel_id id);

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #12 lore raw

PATCH 12/35 perf utils: Move is_directory() to path.h

From: Jiri Olsa <[email protected]>

So that it can be used more widely, like in the next patch, when it will be used to fix a bug in 'perf test' handling of dirent.d_type == DT_UNKNOWN.

Signed-off-by Jiri Olsa <[email protected]>

Cc David Ahern <[email protected]>

Cc Michael Petlan <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Split from a larger patch, removed needless includes in path.h ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-script.c | 14 +-------------
 tools/perf/util/path.c      | 14 ++++++++++++++
 tools/perf/util/path.h      |  3 +++
 3 files changed, 18 insertions(+), 13 deletions(-)

tools/perf/builtin-script.c +1 ~~-13~~

index fac6f053e4da..77e47cf39f2c 100644
@@ -26,6 +26,7 @@
 #include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
+#include "util/path.h"
 #include "print_binary.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>

@@ -2401,19 +2402,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 	return rc;
 }
 
-/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
-static int is_directory(const char *base_path, const struct dirent *dent)
-{
-	char path[PATH_MAX];
-	struct stat st;
-
-	sprintf(path, "%s/%s", base_path, dent->d_name);
-	if (stat(path, &st))
-		return 0;
-
-	return S_ISDIR(st.st_mode);
-}
-
 #define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
 	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
 		if ((lang_dirent->d_type == DT_DIR ||			\

tools/perf/util/path.c +14 -0

index 933f5c6bffb4..ca56ba2dd3da 100644
@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <dirent.h>
 #include <unistd.h>
 
 static char bad_path[] = "/bad-path/";

@@ -77,3 +78,16 @@ bool is_regular_file(const char *file)
 
 	return S_ISREG(st.st_mode);
 }
+
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+bool is_directory(const char *base_path, const struct dirent *dent)
+{
+	char path[PATH_MAX];
+	struct stat st;
+
+	sprintf(path, "%s/%s", base_path, dent->d_name);
+	if (stat(path, &st))
+		return false;
+
+	return S_ISDIR(st.st_mode);
+}

tools/perf/util/path.h +3 -0

index 14a254ada7eb..f014f905df50 100644
@@ -2,9 +2,12 @@
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
+struct dirent;
+
 int path__join(char *bf, size_t size, const char *path1, const char *path2);
 int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);
 
 bool is_regular_file(const char *file);
+bool is_directory(const char *base_path, const struct dirent *dent);
 
 #endif /* _PERF_PATH_H */

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #13 lore raw

PATCH 13/35 perf test: Handle properly readdir DT_UNKNOWN

From: Jiri Olsa <[email protected]>

Some system can return DT_UNKNOWN in readdir's struct dirent::d_type and we must handle it properly. In this case we can directly check if the entity we found is directory and skip it.

Reported-by Michael Petlan <[email protected]>

Signed-off-by Jiri Olsa <[email protected]>

Cc David Ahern <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Split from a larger patch ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/tests/builtin-test.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

tools/perf/tests/builtin-test.c +5 -5

index 766573e236e4..fafa014240cd 100644
@@ -411,9 +411,9 @@ static const char *shell_test__description(char *description, size_t size,
 	return description ? trim(description + 1) : NULL;
 }
 
-#define for_each_shell_test(dir, ent)		\
+#define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (ent->d_type == DT_REG && ent->d_name[0] != '.')
+		if (!is_directory(base, ent))
 
 static const char *shell_tests__dir(char *path, size_t size)
 {

@@ -452,7 +452,7 @@ static int shell_tests__max_desc_width(void)
 	if (!dir)
 		return -1;
 
-	for_each_shell_test(dir, ent) {
+	for_each_shell_test(dir, path, ent) {
 		char bf[256];
 		const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name);

@@ -504,7 +504,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width)
 	if (!dir)
 		return -1;
 
-	for_each_shell_test(dir, ent) {
+	for_each_shell_test(dir, st.dir, ent) {
 		int curr = i++;
 		char desc[256];
 		struct test test = {

@@ -614,7 +614,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
 	if (!dir)
 		return -1;
 
-	for_each_shell_test(dir, ent) {
+	for_each_shell_test(dir, path, ent) {
 		int curr = i++;
 		char bf[256];
 		struct test t = {

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #14 lore raw

PATCH 14/35 perf perf: Remove duplicate includes

From: Pravin Shedge <[email protected]>

These duplicate includes have been found with scripts/checkincludes.pl but they have been removed manually to avoid removing false positives.

Signed-off-by Pravin Shedge <[email protected]>

Cc David S. Miller <[email protected]>

Cc Greg Kroah-Hartman <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/bench/futex-hash.c                          | 1 -
 tools/perf/builtin-c2c.c                               | 3 ---
 tools/perf/builtin-record.c                            | 1 -
 tools/perf/builtin-stat.c                              | 1 -
 tools/perf/tests/parse-events.c                        | 1 -
 tools/perf/util/auxtrace.c                             | 3 ---
 tools/perf/util/header.c                               | 2 --
 tools/perf/util/metricgroup.c                          | 2 --
 tools/perf/util/scripting-engines/trace-event-python.c | 1 -
 9 files changed, 15 deletions(-)

tools/perf/bench/futex-hash.c +0 -1

index 2defb6df7fd0..9aa3a674829b 100644
@@ -27,7 +27,6 @@
 #include "cpumap.h"
 
 #include <err.h>
-#include <sys/time.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;

tools/perf/builtin-c2c.c +0 -3

index f1da9b0833c0..c0debc3f79b6 100644
@@ -27,13 +27,10 @@
 #include "sort.h"
 #include "tool.h"
 #include "data.h"
-#include "sort.h"
 #include "event.h"
 #include "evlist.h"
 #include "evsel.h"
-#include <asm/bug.h>
 #include "ui/browsers/hists.h"
-#include "evlist.h"
 #include "thread.h"
 
 struct c2c_hists {

tools/perf/builtin-record.c +0 -1

index 0a5749ef8b94..98da8cb8de93 100644
@@ -51,7 +51,6 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
-#include <asm/bug.h>
 #include <linux/time64.h>
 
 struct switch_output {

tools/perf/builtin-stat.c +0 -1

index 58d501d1f5fd..98bf9d32f222 100644
@@ -63,7 +63,6 @@
 #include "util/group.h"
 #include "util/session.h"
 #include "util/tool.h"
-#include "util/group.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
 #include "asm/bug.h"

tools/perf/tests/parse-events.c +0 -1

index f0679613bd18..18b06444f230 100644
@@ -13,7 +13,6 @@
 #include <unistd.h>
 #include <linux/kernel.h>
 #include <linux/hw_breakpoint.h>
-#include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \

tools/perf/util/auxtrace.c +0 -3

index a33491416400..c76687e42344 100644
@@ -31,9 +31,6 @@
 #include <sys/param.h>
 #include <stdlib.h>
 #include <stdio.h>
-#include <string.h>
-#include <limits.h>
-#include <errno.h>
 #include <linux/list.h>
 
 #include "../perf.h"

tools/perf/util/header.c +0 -2

index 5890e08e0754..ca73aa7be708 100644
@@ -15,9 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/stringify.h>
 #include <sys/stat.h>
-#include <sys/types.h>
 #include <sys/utsname.h>
-#include <unistd.h>
 
 #include "evlist.h"
 #include "evsel.h"

tools/perf/util/metricgroup.c +0 -2

index e48410c99b39..1ddc3d1d0147 100644
@@ -20,12 +20,10 @@
 #include "pmu.h"
 #include "expr.h"
 #include "rblist.h"
-#include "pmu.h"
 #include <string.h>
 #include <stdbool.h>
 #include <errno.h>
 #include "pmu-events/pmu-events.h"
-#include "strbuf.h"
 #include "strlist.h"
 #include <assert.h>
 #include <ctype.h>

tools/perf/util/scripting-engines/trace-event-python.c +0 -1

index c7187f067d31..c1848b543f27 100644
@@ -43,7 +43,6 @@
 #include "../db-export.h"
 #include "../thread-stack.h"
 #include "../trace-event.h"
-#include "../machine.h"
 #include "../call-path.h"
 #include "thread_map.h"
 #include "cpumap.h"

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #15 lore raw

PATCH 15/35 tools include s390: Grab a copy of arch/s390/include/uapi/asm/unistd.h

From: Hendrik Brueckner <[email protected]>

Will be used for generating the syscall id/string translation table.

Signed-off-by Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

LPU-Reference: [email protected]

Link https://lkml.kernel.org/n/[email protected] open here

[ split from a larger patch ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/arch/s390/include/uapi/asm/unistd.h | 412 ++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh               |   1 +
 2 files changed, 413 insertions(+)
 create mode 100644 tools/arch/s390/include/uapi/asm/unistd.h

tools/arch/s390/include/uapi/asm/unistd.h new file +412 -0

new file mode 100644
index 000000000000..725120939051
@@ -0,0 +1,412 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *  S390 version
+ *
+ *  Derived from "include/asm-i386/unistd.h"
+ */
+
+#ifndef _UAPI_ASM_S390_UNISTD_H_
+#define _UAPI_ASM_S390_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_exit                 1
+#define __NR_fork                 2
+#define __NR_read                 3
+#define __NR_write                4
+#define __NR_open                 5
+#define __NR_close                6
+#define __NR_restart_syscall	  7
+#define __NR_creat                8
+#define __NR_link                 9
+#define __NR_unlink              10
+#define __NR_execve              11
+#define __NR_chdir               12
+#define __NR_mknod               14
+#define __NR_chmod               15
+#define __NR_lseek               19
+#define __NR_getpid              20
+#define __NR_mount               21
+#define __NR_umount              22
+#define __NR_ptrace              26
+#define __NR_alarm               27
+#define __NR_pause               29
+#define __NR_utime               30
+#define __NR_access              33
+#define __NR_nice                34
+#define __NR_sync                36
+#define __NR_kill                37
+#define __NR_rename              38
+#define __NR_mkdir               39
+#define __NR_rmdir               40
+#define __NR_dup                 41
+#define __NR_pipe                42
+#define __NR_times               43
+#define __NR_brk                 45
+#define __NR_signal              48
+#define __NR_acct                51
+#define __NR_umount2             52
+#define __NR_ioctl               54
+#define __NR_fcntl               55
+#define __NR_setpgid             57
+#define __NR_umask               60
+#define __NR_chroot              61
+#define __NR_ustat               62
+#define __NR_dup2                63
+#define __NR_getppid             64
+#define __NR_getpgrp             65
+#define __NR_setsid              66
+#define __NR_sigaction           67
+#define __NR_sigsuspend          72
+#define __NR_sigpending          73
+#define __NR_sethostname         74
+#define __NR_setrlimit           75
+#define __NR_getrusage           77
+#define __NR_gettimeofday        78
+#define __NR_settimeofday        79
+#define __NR_symlink             83
+#define __NR_readlink            85
+#define __NR_uselib              86
+#define __NR_swapon              87
+#define __NR_reboot              88
+#define __NR_readdir             89
+#define __NR_mmap                90
+#define __NR_munmap              91
+#define __NR_truncate            92
+#define __NR_ftruncate           93
+#define __NR_fchmod              94
+#define __NR_getpriority         96
+#define __NR_setpriority         97
+#define __NR_statfs              99
+#define __NR_fstatfs            100
+#define __NR_socketcall         102
+#define __NR_syslog             103
+#define __NR_setitimer          104
+#define __NR_getitimer          105
+#define __NR_stat               106
+#define __NR_lstat              107
+#define __NR_fstat              108
+#define __NR_lookup_dcookie     110
+#define __NR_vhangup            111
+#define __NR_idle               112
+#define __NR_wait4              114
+#define __NR_swapoff            115
+#define __NR_sysinfo            116
+#define __NR_ipc                117
+#define __NR_fsync              118
+#define __NR_sigreturn          119
+#define __NR_clone              120
+#define __NR_setdomainname      121
+#define __NR_uname              122
+#define __NR_adjtimex           124
+#define __NR_mprotect           125
+#define __NR_sigprocmask        126
+#define __NR_create_module      127
+#define __NR_init_module        128
+#define __NR_delete_module      129
+#define __NR_get_kernel_syms    130
+#define __NR_quotactl           131
+#define __NR_getpgid            132
+#define __NR_fchdir             133
+#define __NR_bdflush            134
+#define __NR_sysfs              135
+#define __NR_personality        136
+#define __NR_afs_syscall        137 /* Syscall for Andrew File System */
+#define __NR_getdents           141
+#define __NR_flock              143
+#define __NR_msync              144
+#define __NR_readv              145
+#define __NR_writev             146
+#define __NR_getsid             147
+#define __NR_fdatasync          148
+#define __NR__sysctl            149
+#define __NR_mlock              150
+#define __NR_munlock            151
+#define __NR_mlockall           152
+#define __NR_munlockall         153
+#define __NR_sched_setparam             154
+#define __NR_sched_getparam             155
+#define __NR_sched_setscheduler         156
+#define __NR_sched_getscheduler         157
+#define __NR_sched_yield                158
+#define __NR_sched_get_priority_max     159
+#define __NR_sched_get_priority_min     160
+#define __NR_sched_rr_get_interval      161
+#define __NR_nanosleep          162
+#define __NR_mremap             163
+#define __NR_query_module       167
+#define __NR_poll               168
+#define __NR_nfsservctl         169
+#define __NR_prctl              172
+#define __NR_rt_sigreturn       173
+#define __NR_rt_sigaction       174
+#define __NR_rt_sigprocmask     175
+#define __NR_rt_sigpending      176
+#define __NR_rt_sigtimedwait    177
+#define __NR_rt_sigqueueinfo    178
+#define __NR_rt_sigsuspend      179
+#define __NR_pread64            180
+#define __NR_pwrite64           181
+#define __NR_getcwd             183
+#define __NR_capget             184
+#define __NR_capset             185
+#define __NR_sigaltstack        186
+#define __NR_sendfile           187
+#define __NR_getpmsg		188
+#define __NR_putpmsg		189
+#define __NR_vfork		190
+#define __NR_pivot_root         217
+#define __NR_mincore            218
+#define __NR_madvise            219
+#define __NR_getdents64		220
+#define __NR_readahead		222
+#define __NR_setxattr		224
+#define __NR_lsetxattr		225
+#define __NR_fsetxattr		226
+#define __NR_getxattr		227
+#define __NR_lgetxattr		228
+#define __NR_fgetxattr		229
+#define __NR_listxattr		230
+#define __NR_llistxattr		231
+#define __NR_flistxattr		232
+#define __NR_removexattr	233
+#define __NR_lremovexattr	234
+#define __NR_fremovexattr	235
+#define __NR_gettid		236
+#define __NR_tkill		237
+#define __NR_futex		238
+#define __NR_sched_setaffinity	239
+#define __NR_sched_getaffinity	240
+#define __NR_tgkill		241
+/* Number 242 is reserved for tux */
+#define __NR_io_setup		243
+#define __NR_io_destroy		244
+#define __NR_io_getevents	245
+#define __NR_io_submit		246
+#define __NR_io_cancel		247
+#define __NR_exit_group		248
+#define __NR_epoll_create	249
+#define __NR_epoll_ctl		250
+#define __NR_epoll_wait		251
+#define __NR_set_tid_address	252
+#define __NR_fadvise64		253
+#define __NR_timer_create	254
+#define __NR_timer_settime	255
+#define __NR_timer_gettime	256
+#define __NR_timer_getoverrun	257
+#define __NR_timer_delete	258
+#define __NR_clock_settime	259
+#define __NR_clock_gettime	260
+#define __NR_clock_getres	261
+#define __NR_clock_nanosleep	262
+/* Number 263 is reserved for vserver */
+#define __NR_statfs64		265
+#define __NR_fstatfs64		266
+#define __NR_remap_file_pages	267
+#define __NR_mbind		268
+#define __NR_get_mempolicy	269
+#define __NR_set_mempolicy	270
+#define __NR_mq_open		271
+#define __NR_mq_unlink		272
+#define __NR_mq_timedsend	273
+#define __NR_mq_timedreceive	274
+#define __NR_mq_notify		275
+#define __NR_mq_getsetattr	276
+#define __NR_kexec_load		277
+#define __NR_add_key		278
+#define __NR_request_key	279
+#define __NR_keyctl		280
+#define __NR_waitid		281
+#define __NR_ioprio_set		282
+#define __NR_ioprio_get		283
+#define __NR_inotify_init	284
+#define __NR_inotify_add_watch	285
+#define __NR_inotify_rm_watch	286
+#define __NR_migrate_pages	287
+#define __NR_openat		288
+#define __NR_mkdirat		289
+#define __NR_mknodat		290
+#define __NR_fchownat		291
+#define __NR_futimesat		292
+#define __NR_unlinkat		294
+#define __NR_renameat		295
+#define __NR_linkat		296
+#define __NR_symlinkat		297
+#define __NR_readlinkat		298
+#define __NR_fchmodat		299
+#define __NR_faccessat		300
+#define __NR_pselect6		301
+#define __NR_ppoll		302
+#define __NR_unshare		303
+#define __NR_set_robust_list	304
+#define __NR_get_robust_list	305
+#define __NR_splice		306
+#define __NR_sync_file_range	307
+#define __NR_tee		308
+#define __NR_vmsplice		309
+#define __NR_move_pages		310
+#define __NR_getcpu		311
+#define __NR_epoll_pwait	312
+#define __NR_utimes		313
+#define __NR_fallocate		314
+#define __NR_utimensat		315
+#define __NR_signalfd		316
+#define __NR_timerfd		317
+#define __NR_eventfd		318
+#define __NR_timerfd_create	319
+#define __NR_timerfd_settime	320
+#define __NR_timerfd_gettime	321
+#define __NR_signalfd4		322
+#define __NR_eventfd2		323
+#define __NR_inotify_init1	324
+#define __NR_pipe2		325
+#define __NR_dup3		326
+#define __NR_epoll_create1	327
+#define	__NR_preadv		328
+#define	__NR_pwritev		329
+#define __NR_rt_tgsigqueueinfo	330
+#define __NR_perf_event_open	331
+#define __NR_fanotify_init	332
+#define __NR_fanotify_mark	333
+#define __NR_prlimit64		334
+#define __NR_name_to_handle_at	335
+#define __NR_open_by_handle_at	336
+#define __NR_clock_adjtime	337
+#define __NR_syncfs		338
+#define __NR_setns		339
+#define __NR_process_vm_readv	340
+#define __NR_process_vm_writev	341
+#define __NR_s390_runtime_instr 342
+#define __NR_kcmp		343
+#define __NR_finit_module	344
+#define __NR_sched_setattr	345
+#define __NR_sched_getattr	346
+#define __NR_renameat2		347
+#define __NR_seccomp		348
+#define __NR_getrandom		349
+#define __NR_memfd_create	350
+#define __NR_bpf		351
+#define __NR_s390_pci_mmio_write	352
+#define __NR_s390_pci_mmio_read		353
+#define __NR_execveat		354
+#define __NR_userfaultfd	355
+#define __NR_membarrier		356
+#define __NR_recvmmsg		357
+#define __NR_sendmmsg		358
+#define __NR_socket		359
+#define __NR_socketpair		360
+#define __NR_bind		361
+#define __NR_connect		362
+#define __NR_listen		363
+#define __NR_accept4		364
+#define __NR_getsockopt		365
+#define __NR_setsockopt		366
+#define __NR_getsockname	367
+#define __NR_getpeername	368
+#define __NR_sendto		369
+#define __NR_sendmsg		370
+#define __NR_recvfrom		371
+#define __NR_recvmsg		372
+#define __NR_shutdown		373
+#define __NR_mlock2		374
+#define __NR_copy_file_range	375
+#define __NR_preadv2		376
+#define __NR_pwritev2		377
+#define __NR_s390_guarded_storage	378
+#define __NR_statx		379
+#define __NR_s390_sthyi		380
+#define NR_syscalls 381
+
+/* 
+ * There are some system calls that are not present on 64 bit, some
+ * have a different name although they do the same (e.g. __NR_chown32
+ * is __NR_chown on 64 bit).
+ */
+#ifndef __s390x__
+
+#define __NR_time		 13
+#define __NR_lchown		 16
+#define __NR_setuid		 23
+#define __NR_getuid		 24
+#define __NR_stime		 25
+#define __NR_setgid		 46
+#define __NR_getgid		 47
+#define __NR_geteuid		 49
+#define __NR_getegid		 50
+#define __NR_setreuid		 70
+#define __NR_setregid		 71
+#define __NR_getrlimit		 76
+#define __NR_getgroups		 80
+#define __NR_setgroups		 81
+#define __NR_fchown		 95
+#define __NR_ioperm		101
+#define __NR_setfsuid		138
+#define __NR_setfsgid		139
+#define __NR__llseek		140
+#define __NR__newselect 	142
+#define __NR_setresuid		164
+#define __NR_getresuid		165
+#define __NR_setresgid		170
+#define __NR_getresgid		171
+#define __NR_chown		182
+#define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
+#define __NR_mmap2		192
+#define __NR_truncate64		193
+#define __NR_ftruncate64	194
+#define __NR_stat64		195
+#define __NR_lstat64		196
+#define __NR_fstat64		197
+#define __NR_lchown32		198
+#define __NR_getuid32		199
+#define __NR_getgid32		200
+#define __NR_geteuid32		201
+#define __NR_getegid32		202
+#define __NR_setreuid32		203
+#define __NR_setregid32		204
+#define __NR_getgroups32	205
+#define __NR_setgroups32	206
+#define __NR_fchown32		207
+#define __NR_setresuid32	208
+#define __NR_getresuid32	209
+#define __NR_setresgid32	210
+#define __NR_getresgid32	211
+#define __NR_chown32		212
+#define __NR_setuid32		213
+#define __NR_setgid32		214
+#define __NR_setfsuid32		215
+#define __NR_setfsgid32		216
+#define __NR_fcntl64		221
+#define __NR_sendfile64		223
+#define __NR_fadvise64_64	264
+#define __NR_fstatat64		293
+
+#else
+
+#define __NR_select		142
+#define __NR_getrlimit		191	/* SuS compliant getrlimit */
+#define __NR_lchown  		198
+#define __NR_getuid  		199
+#define __NR_getgid  		200
+#define __NR_geteuid  		201
+#define __NR_getegid  		202
+#define __NR_setreuid  		203
+#define __NR_setregid  		204
+#define __NR_getgroups  	205
+#define __NR_setgroups  	206
+#define __NR_fchown  		207
+#define __NR_setresuid  	208
+#define __NR_getresuid  	209
+#define __NR_setresgid  	210
+#define __NR_getresgid  	211
+#define __NR_chown  		212
+#define __NR_setuid  		213
+#define __NR_setgid  		214
+#define __NR_setfsuid  		215
+#define __NR_setfsgid  		216
+#define __NR_newfstatat		293
+
+#endif
+
+#endif /* _UAPI_ASM_S390_UNISTD_H_ */

tools/perf/check-headers.sh +1 -0

index ea602cd1b43a..f81ca508700c 100755
@@ -33,6 +33,7 @@ arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
 arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
+arch/s390/include/uapi/asm/unistd.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
 include/asm-generic/bitops/arch_hweight.h

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #16 lore raw

PATCH 16/35 perf s390: Generate system call table from asm/unistd.h

From: Hendrik Brueckner <[email protected]>

This should speed up accessing new system calls introduced with the kernel rather than waiting for libaudit updates to include them.

Committer testing:

  $ rm -rf /tmp/build/perf
  $ mkdir /tmp/build/perf
  $ make srctree=/home/acme/git/perf -C tools/perf/arch/s390 OUTPUT=/tmp/build/perf/ archheaders
  make: Entering directory '/home/acme/git/perf/tools/perf/arch/s390'
  /bin/sh '/home/acme/git/perf/tools/perf/arch/s390/entry/syscalls//mksyscalltbl' 'cc' /home/acme/git/perf/tools/arch/s390/include/uapi/asm/unistd.h > /tmp/build/perf/arch/s390/include/generated/asm/syscalls_64.c
  make: Leaving directory '/home/acme/git/perf/tools/perf/arch/s390'
  $ head -5 /tmp/build/perf/arch/s390/include/generated/asm/syscalls_64.c
  static const char *syscalltbl_s390_64[] = {
	[1] = "exit",
	[2] = "fork",
	[3] = "read",
	[4] = "write",
  $ tail -5 /tmp/build/perf/arch/s390/include/generated/asm/syscalls_64.c
	[378] = "s390_guarded_storage",
	[379] = "statx",
	[380] = "s390_sthyi",
  };
  #define SYSCALLTBL_S390_64_MAX_ID 380
  $

Now to plug this into 'perf trace' proper.

Signed-off-by Hendrik Brueckner <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

LPU-Reference: [email protected]

Link https://lkml.kernel.org/n/[email protected] open here

[ split from a larger patch ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/arch/s390/Makefile                    | 21 ++++++++++++++
 tools/perf/arch/s390/entry/syscalls/mksyscalltbl | 36 ++++++++++++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100755 tools/perf/arch/s390/entry/syscalls/mksyscalltbl

tools/perf/arch/s390/Makefile +21 -0

index 09ba923debe8..48228de415d0 100644
@@ -3,3 +3,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/s390/include/generated/asm
+header := $(out)/syscalls_64.c
+sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, s390) $(RM) $(header)
+
+archheaders: $(header)

tools/perf/arch/s390/entry/syscalls/mksyscalltbl new file +36 -0

new file mode 100755
index 000000000000..7fa0d0abd419
@@ -0,0 +1,36 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf
+#
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <[email protected]>
+#
+
+gcc=$1
+input=$2
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table()
+{
+	local max_nr
+
+	echo 'static const char *syscalltbl_s390_64[] = {'
+	while read sc nr; do
+		printf '\t[%d] = "%s",\n' $nr $sc
+		max_nr=$nr
+	done
+	echo '};'
+	echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr"
+}
+
+
+$gcc -m64 -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #17 lore raw

PATCH 17/35 perf trace: Use generated syscall table on s390 too

From: Hendrik Brueckner <[email protected]>

This should speed up accessing new system calls introduced with the kernel rather than waiting for libaudit updates to include them.

It also enables users to specify wildcards, for example, perf trace -e 'open*', just like was already possible on x86.

Signed-off-by Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

LPU-Reference: [email protected]

Link https://lkml.kernel.org/n/[email protected] open here

[ split from a larger patch ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Makefile.config   | 10 +++++++++-
 tools/perf/util/syscalltbl.c |  4 ++++
 2 files changed, 13 insertions(+), 1 deletion(-)

tools/perf/Makefile.config +9 -1

index 79b117a03fd7..6f73c2316740 100644
@@ -22,6 +22,7 @@ include $(srctree)/tools/scripts/Makefile.arch
 $(call detected_var,SRCARCH)
 
 NO_PERF_REGS := 1
+NO_SYSCALL_TABLE := 1
 
 # Additional ARCH settings for ppc
 ifeq ($(SRCARCH),powerpc)

@@ -33,7 +34,8 @@ endif
 ifeq ($(SRCARCH),x86)
   $(call detected,CONFIG_X86)
   ifeq (${IS_64_BIT}, 1)
-    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
+    NO_SYSCALL_TABLE := 0
+    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -I$(OUTPUT)arch/x86/include/generated
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma
     $(call detected,CONFIG_X86_64)

@@ -56,12 +58,18 @@ endif
 
 ifeq ($(ARCH),s390)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/s390/include/generated
 endif
 
 ifeq ($(NO_PERF_REGS),0)
   $(call detected,CONFIG_PERF_REGS)
 endif
 
+ifneq ($(NO_SYSCALL_TABLE),1)
+  CFLAGS += -DHAVE_SYSCALL_TABLE
+endif
+
 # So far there's only x86 and arm libdw unwind support merged in perf.
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures

tools/perf/util/syscalltbl.c +4 -0

index 6eea7cff3d4e..303bdb84ab5a 100644
@@ -26,6 +26,10 @@
 #include <asm/syscalls_64.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_x86_64;
+#elif defined(__s390x__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_s390_64;
 #endif
 
 struct syscall {

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #18 lore raw

PATCH 18/35 perf annotate: Get the cpuid from evsel->evlist->env in symbol__annotate()

From: Arnaldo Carvalho de Melo <[email protected]>

To reduce its function signature, since we get this from 'evsel' which is already one of its arguments.

Cc Adrian Hunter <[email protected]>

Cc David Ahern <[email protected]>

Cc Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Thomas Richter <[email protected]>

Cc Wang Nan <[email protected]>

Link https://lkml.kernel.org/n/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-top.c          | 2 +-
 tools/perf/ui/browsers/annotate.c | 4 +---
 tools/perf/ui/gtk/annotate.c      | 2 +-
 tools/perf/util/annotate.c        | 7 ++++---
 tools/perf/util/annotate.h        | 2 +-
 tools/perf/util/evsel.c           | 6 +++---
 tools/perf/util/evsel.h           | 2 +-
 7 files changed, 12 insertions(+), 13 deletions(-)

tools/perf/builtin-top.c +1 -1

index 540461f5e345..c6ccda52117d 100644
@@ -138,7 +138,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(sym, map, evsel, 0, NULL, NULL);
+	err = symbol__annotate(sym, map, evsel, 0, NULL);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;

tools/perf/ui/browsers/annotate.c +1 -3

index 03b7363a49c9..286427975112 100644
@@ -1116,9 +1116,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->nr_members;
 
-	err = symbol__annotate(sym, map, evsel,
-			       sizeof(struct browser_line), &browser.arch,
-			       perf_evsel__env_cpuid(evsel));
+	err = symbol__annotate(sym, map, evsel, sizeof(struct browser_line), &browser.arch);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));

tools/perf/ui/gtk/annotate.c +1 -1

index cdb5ecf91666..aeeaf15029f0 100644
@@ -169,7 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(sym, map, evsel, 0, NULL, NULL);
+	err = symbol__annotate(sym, map, evsel, 0, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));

tools/perf/util/annotate.c +4 -3

index facad1e279a8..bc34b28373f4 100644
@@ -1622,13 +1622,14 @@ void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel)
 
 int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct perf_evsel *evsel, size_t privsize,
-		     struct arch **parch, char *cpuid)
+		     struct arch **parch)
 {
 	struct annotate_args args = {
 		.privsize	= privsize,
 		.map		= map,
 		.evsel		= evsel,
 	};
+	struct perf_env *env = perf_evsel__env(evsel);
 	const char *arch_name = NULL;
 	struct arch *arch;
 	int err;

@@ -1648,7 +1649,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 		*parch = arch;
 
 	if (arch->init) {
-		err = arch->init(arch, cpuid);
+		err = arch->init(arch, env ? env->cpuid : NULL);
 		if (err) {
 			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
 			return err;

@@ -1999,7 +2000,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
 
-	if (symbol__annotate(sym, map, evsel, 0, NULL, NULL) < 0)
+	if (symbol__annotate(sym, map, evsel, 0, NULL) < 0)
 		return -1;
 
 	symbol__calc_percent(sym, evsel);

tools/perf/util/annotate.h +1 -1

index 6d7289e88fa3..ce427445671f 100644
@@ -179,7 +179,7 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct perf_evsel *evsel, size_t privsize,
-		     struct arch **parch, char *cpuid);
+		     struct arch **parch);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,

tools/perf/util/evsel.c +3 -3

index 95853c51c0ca..541897049c6c 100644
@@ -2842,9 +2842,9 @@ char *perf_evsel__env_arch(struct perf_evsel *evsel)
 	return NULL;
 }
 
-char *perf_evsel__env_cpuid(struct perf_evsel *evsel)
+struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 {
-	if (evsel && evsel->evlist && evsel->evlist->env)
-		return evsel->evlist->env->cpuid;
+	if (evsel && evsel->evlist)
+		return evsel->evlist->env;
 	return NULL;
 }

tools/perf/util/evsel.h +1 -1

index c3663a70c9b9..0e961ce60a9c 100644
@@ -447,6 +447,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv);
 
 char *perf_evsel__env_arch(struct perf_evsel *evsel);
-char *perf_evsel__env_cpuid(struct perf_evsel *evsel);
+struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
 #endif /* __PERF_EVSEL_H */

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #19 lore raw

PATCH 19/35 perf annotate: Use perf_env when obtaining the arch name

From: Arnaldo Carvalho de Melo <[email protected]>

Paving the way to reuse these routines in other areas, like when generating errno tables.

Cc Adrian Hunter <[email protected]>

Cc David Ahern <[email protected]>

Cc Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Thomas Richter <[email protected]>

Cc Wang Nan <[email protected]>

Link https://lkml.kernel.org/n/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/annotate.c | 17 ++++++++---------
 tools/perf/util/evsel.c    |  7 -------
 tools/perf/util/evsel.h    |  1 -
 3 files changed, 8 insertions(+), 17 deletions(-)

tools/perf/util/annotate.c +8 -9

index bc34b28373f4..eac45ccd5c32 100644
@@ -1420,16 +1420,19 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	return 0;
 }
 
-static const char *annotate__norm_arch(const char *arch_name)
+static const char *perf_env__arch(struct perf_env *env)
 {
 	struct utsname uts;
+	char *arch_name;
 
-	if (!arch_name) { /* Assume we are annotating locally. */
+	if (!env) { /* Assume local operation */
 		if (uname(&uts) < 0)
 			return NULL;
 		arch_name = uts.machine;
-	}
-	return normalize_arch((char *)arch_name);
+	} else
+		arch_name = env->arch;
+
+	return normalize_arch(arch_name);
 }
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)

@@ -1630,14 +1633,10 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 		.evsel		= evsel,
 	};
 	struct perf_env *env = perf_evsel__env(evsel);
-	const char *arch_name = NULL;
+	const char *arch_name = perf_env__arch(env);
 	struct arch *arch;
 	int err;
 
-	if (evsel)
-		arch_name = perf_evsel__env_arch(evsel);
-
-	arch_name = annotate__norm_arch(arch_name);
 	if (!arch_name)
 		return -1;

tools/perf/util/evsel.c +0 -7

index 541897049c6c..4718f0a460df 100644
@@ -2835,13 +2835,6 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			 perf_evsel__name(evsel));
 }
 
-char *perf_evsel__env_arch(struct perf_evsel *evsel)
-{
-	if (evsel && evsel->evlist && evsel->evlist->env)
-		return evsel->evlist->env->arch;
-	return NULL;
-}
-
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 {
 	if (evsel && evsel->evlist)

tools/perf/util/evsel.h +0 -1

index 0e961ce60a9c..846e41644525 100644
@@ -446,7 +446,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv);
 
-char *perf_evsel__env_arch(struct perf_evsel *evsel);
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
 #endif /* __PERF_EVSEL_H */

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #20 lore raw

PATCH 20/35 perf env: Adopt perf_env__arch() from the annotate code

From: Arnaldo Carvalho de Melo <[email protected]>

And use it in the libunwind case, with both passing a valid perf_env to extract the arch to be normalized from and passing NULL with the same semantic as in the annotate code: to get it from uname() uts.machine.

Now the code to generate per arch errno translation tables (int/string) can use it to decode perf.data files recorded in a different arch than that where 'perf trace' (or any other analysis tool) runs.

Cc Adrian Hunter <[email protected]>

Cc David Ahern <[email protected]>

Cc Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Michael Petlan <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Thomas Richter <[email protected]>

Cc Wang Nan <[email protected]>

Link https://lkml.kernel.org/n/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/arch/common.c           | 44 +++--------------------------------
 tools/perf/arch/common.h           |  1 -
 tools/perf/util/annotate.c         | 16 -------------
 tools/perf/util/env.c              | 47 ++++++++++++++++++++++++++++++++++++++
 tools/perf/util/env.h              |  2 ++
 tools/perf/util/unwind-libunwind.c |  4 ++--
 6 files changed, 54 insertions(+), 60 deletions(-)

tools/perf/arch/common.c +3 ~~-41~~

index 8c0cfeb55f8e..c6f373508a4f 100644
@@ -1,12 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
-#include <sys/utsname.h>
 #include "common.h"
+#include "../util/env.h"
 #include "../util/util.h"
 #include "../util/debug.h"
 
-#include "sane_ctype.h"
-
 const char *const arm_triplets[] = {
 	"arm-eabi-",
 	"arm-linux-androideabi-",

@@ -120,55 +118,19 @@ static int lookup_triplets(const char *const *triplets, const char *name)
 	return -1;
 }
 
-/*
- * Return architecture name in a normalized form.
- * The conversion logic comes from the Makefile.
- */
-const char *normalize_arch(char *arch)
-{
-	if (!strcmp(arch, "x86_64"))
-		return "x86";
-	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
-		return "x86";
-	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
-		return "sparc";
-	if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
-		return "arm64";
-	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
-		return "arm";
-	if (!strncmp(arch, "s390", 4))
-		return "s390";
-	if (!strncmp(arch, "parisc", 6))
-		return "parisc";
-	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
-		return "powerpc";
-	if (!strncmp(arch, "mips", 4))
-		return "mips";
-	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
-		return "sh";
-
-	return arch;
-}
-
 static int perf_env__lookup_binutils_path(struct perf_env *env,
 					  const char *name, const char **path)
 {
 	int idx;
-	const char *arch, *cross_env;
-	struct utsname uts;
+	const char *arch = perf_env__arch(env), *cross_env;
 	const char *const *path_list;
 	char *buf = NULL;
 
-	arch = normalize_arch(env->arch);
-
-	if (uname(&uts) < 0)
-		goto out;
-
 	/*
 	 * We don't need to try to find objdump path for native system.
 	 * Just use default binutils path (e.g.: "objdump").
 	 */
-	if (!strcmp(normalize_arch(uts.machine), arch))
+	if (!strcmp(perf_env__arch(NULL), arch))
 		goto out;
 
 	cross_env = getenv("CROSS_COMPILE");

tools/perf/arch/common.h +0 -1

index a1546509ad24..2d875baa92e6 100644
@@ -7,6 +7,5 @@
 extern const char *objdump_path;
 
 int perf_env__lookup_objdump(struct perf_env *env);
-const char *normalize_arch(char *arch);
 
 #endif /* ARCH_PERF_COMMON_H */

tools/perf/util/annotate.c +0 ~~-16~~

index eac45ccd5c32..68e687d1bf99 100644
@@ -26,7 +26,6 @@
 #include <pthread.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
-#include <sys/utsname.h>
 
 #include "sane_ctype.h"

@@ -1420,21 +1419,6 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	return 0;
 }
 
-static const char *perf_env__arch(struct perf_env *env)
-{
-	struct utsname uts;
-	char *arch_name;
-
-	if (!env) { /* Assume local operation */
-		if (uname(&uts) < 0)
-			return NULL;
-		arch_name = uts.machine;
-	} else
-		arch_name = env->arch;
-
-	return normalize_arch(arch_name);
-}
-
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct map *map = args->map;

tools/perf/util/env.c +47 -0

58 lines not on this page · raw message

tools/perf/util/env.h +2 -0

index 1eb35b190b34..bf970f57dce0 100644
@@ -65,4 +65,6 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
 void cpu_cache_level__free(struct cpu_cache_level *cache);
+
+const char *perf_env__arch(struct perf_env *env);
 #endif /* __PERF_ENV_H */

tools/perf/util/unwind-libunwind.c +2 -2

index 647a1e6b4c7b..b029a5e9ae49 100644
@@ -3,7 +3,7 @@
 #include "thread.h"
 #include "session.h"
 #include "debug.h"
-#include "arch/common.h"
+#include "env.h"
 
 struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;

@@ -39,7 +39,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
 	if (dso_type == DSO__TYPE_UNKNOWN)
 		return 0;
 
-	arch = normalize_arch(thread->mg->machine->env->arch);
+	arch = perf_env__arch(thread->mg->machine->env);
 
 	if (!strcmp(arch, "x86")) {
 		if (dso_type != DSO__TYPE_64BIT)

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #21 lore raw

PATCH 21/35 perf probe: Add warning message if there is unexpected event name

From: Masami Hiramatsu <[email protected]>

This improve the error message so that user can know event-name error before writing new events to kprobe-events interface.

E.g.
======
#./perf probe -x /lib64/libc-2.25.so malloc_get_state*

   Internal error: "malloc_get_state@GLIBC_2" is an invalid event name.
     Error: Failed to add events.
   ======

Reported-by Arnaldo Carvalho de Melo <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Paul Clarke <[email protected]>

Cc bhargavb <[email protected]>

Link http://lkml.kernel.org/r/151275040665.24652.5188568529237584489.stgit@devbox open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/probe-event.c | 8 ++++++++
 1 file changed, 8 insertions(+)

tools/perf/util/probe-event.c +8 -0

index b7aaf9b2294d..262d5da86623 100644
@@ -2625,6 +2625,14 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 
 out:
 	free(nbase);
+
+	/* Final validation */
+	if (ret >= 0 && !is_c_func_name(buf)) {
+		pr_warning("Internal error: \"%s\" is an invalid event name.\n",
+			   buf);
+		ret = -EINVAL;
+	}
+
 	return ret;
 }

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #22 lore raw

PATCH 22/35 perf probe: Cut off the version suffix from event name

From: Masami Hiramatsu <[email protected]>

Cut off the version suffix (e.g. @GLIBC_2.2.5 etc.) from automatic generated event name. This fixes wildcard event adding like below case;

=====

  # perf probe -x /lib64/libc-2.25.so malloc*
  Internal error: "malloc_get_state@GLIBC_2" is wrong event name.
    Error: Failed to add events.
  =====

This failure was caused by a versioned suffix symbol.

With this fix, perf probe automatically cuts the suffix after @ as below.

=====

  # ./perf probe -x /lib64/libc-2.25.so malloc*
  Added new events:
    probe_libc:malloc_printerr (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_consolidate (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_check (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_hook_ini (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc    (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_trim (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_usable_size (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_stats (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_info (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:mallochook (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_get_state (on malloc* in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_set_state (on malloc* in /usr/lib64/libc-2.25.so)

You can now use it in all perf tools, such as:

perf record -e probe_libc:malloc_set_state -aR sleep 1

=====

Reported-by Arnaldo Carvalho de Melo <[email protected]>

Reported-by bhargavb <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Paul Clarke <[email protected]>

Link http://lkml.kernel.org/r/None

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/probe-event.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

tools/perf/util/probe-event.c +2 -2

index 262d5da86623..7e582547ac07 100644
@@ -2584,8 +2584,8 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	if (!nbase)
 		return -ENOMEM;
 
-	/* Cut off the dot suffixes (e.g. .const, .isra)*/
-	p = strchr(nbase, '.');
+	/* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */
+	p = strpbrk(nbase, ".@");
 	if (p && p != nbase)
 		*p = '\0';

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #23 lore raw

PATCH 23/35 perf probe: Add __return suffix for return events

From: Masami Hiramatsu <[email protected]>

Add __return suffix for function return events automatically. Without this, user have to give --force option and will see the number suffix for each event like "function_1", which is not easy to recognize. Instead, this adds __return suffix to it automatically. E.g.

=====

  # ./perf probe -x /lib64/libc-2.25.so 'malloc*%return'
  Added new events:
    probe_libc:malloc_printerr__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_consolidate__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_check__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_hook_ini__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_trim__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_usable_size__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_stats__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_info__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:mallochook__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_get_state__return (on malloc*%return in /usr/lib64/libc-2.25.so)
    probe_libc:malloc_set_state__return (on malloc*%return in /usr/lib64/libc-2.25.so)

You can now use it in all perf tools, such as:

perf record -e probe_libc:malloc_set_state__return -aR sleep 1

=====

Reported-by Arnaldo Carvalho de Melo <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Paul Clarke <[email protected]>

Cc bhargavb <[email protected]>

Link http://lkml.kernel.org/r/151275046418.24652.6696011972866498489.stgit@devbox open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Documentation/perf-probe.txt | 2 +-
 tools/perf/util/probe-event.c           | 9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

tools/perf/Documentation/perf-probe.txt +1 -1

index d7e4869905f1..f96382692f42 100644
@@ -170,7 +170,7 @@ Probe points are defined by following syntax.
      or,
      sdt_PROVIDER:SDTEVENT
 
-'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function, and for return probes, a "\_\_return" suffix is automatically added to the function name. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
 Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
 modules.
 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.

tools/perf/util/probe-event.c +5 -4

index 7e582547ac07..a68141d360b0 100644
@@ -2573,7 +2573,8 @@ int show_perf_probe_events(struct strfilter *filter)
 }
 
 static int get_new_event_name(char *buf, size_t len, const char *base,
-			      struct strlist *namelist, bool allow_suffix)
+			      struct strlist *namelist, bool ret_event,
+			      bool allow_suffix)
 {
 	int i, ret;
 	char *p, *nbase;

@@ -2590,7 +2591,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		*p = '\0';
 
 	/* Try no suffix number */
-	ret = e_snprintf(buf, len, "%s", nbase);
+	ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : "");
 	if (ret < 0) {
 		pr_debug("snprintf() failed: %d\n", ret);
 		goto out;

@@ -2689,8 +2690,8 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 		group = PERFPROBE_GROUP;
 
 	/* Get an unused new event name */
-	ret = get_new_event_name(buf, 64, event,
-				 namelist, allow_suffix);
+	ret = get_new_event_name(buf, 64, event, namelist,
+				 tev->point.retprobe, allow_suffix);
 	if (ret < 0)
 		return ret;

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #24 lore raw

PATCH 24/35 perf probe: Find versioned symbols from map

From: Masami Hiramatsu <[email protected]>

Commit d80406453ad4 ("perf symbols: Allow user probes on versioned symbols") allows user to find default versioned symbols (with "@@") in map. However, it did not enable normal versioned symbol (with "@") for perf-probe. E.g.

=====

  # ./perf probe -x /lib64/libc-2.25.so malloc_get_state
  Failed to find symbol malloc_get_state in /usr/lib64/libc-2.25.so
    Error: Failed to add events.
  =====

This solves above issue by improving perf-probe symbol search function, as below.

=====

  # ./perf probe -x /lib64/libc-2.25.so malloc_get_state
  Added new event:
    probe_libc:malloc_get_state (on malloc_get_state in /usr/lib64/libc-2.25.so)

You can now use it in all perf tools, such as:

perf record -e probe_libc:malloc_get_state -aR sleep 1

  # ./perf probe -l
    probe_libc:malloc_get_state (on malloc_get_state@GLIBC_2.2.5 in /usr/lib64/libc-2.25.so)
  =====

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Paul Clarke <[email protected]>

Cc bhargavb <[email protected]>

Link http://lkml.kernel.org/r/151275049269.24652.1639103455496216255.stgit@devbox open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/arch/powerpc/util/sym-handling.c |  8 ++++++++
 tools/perf/util/probe-event.c               | 20 ++++++++++++++++++--
 tools/perf/util/symbol.c                    |  5 +++++
 tools/perf/util/symbol.h                    |  1 +
 4 files changed, 32 insertions(+), 2 deletions(-)

tools/perf/arch/powerpc/util/sym-handling.c +8 -0

index 9c4e23d8c8ce..53d83d7e6a09 100644
@@ -64,6 +64,14 @@ int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 
 	return strncmp(namea, nameb, n);
 }
+
+const char *arch__normalize_symbol_name(const char *name)
+{
+	/* Skip over initial dot */
+	if (name && *name == '.')
+		name++;
+	return name;
+}
 #endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2

tools/perf/util/probe-event.c +18 -2

index a68141d360b0..0d6c66d51939 100644
@@ -2801,16 +2801,32 @@ static int find_probe_functions(struct map *map, char *name,
 	int found = 0;
 	struct symbol *sym;
 	struct rb_node *tmp;
+	const char *norm, *ver;
+	char *buf = NULL;
 
 	if (map__load(map) < 0)
 		return 0;
 
 	map__for_each_symbol(map, sym, tmp) {
-		if (strglobmatch(sym->name, name)) {
+		norm = arch__normalize_symbol_name(sym->name);
+		if (!norm)
+			continue;
+
+		/* We don't care about default symbol or not */
+		ver = strchr(norm, '@');
+		if (ver) {
+			buf = strndup(norm, ver - norm);
+			if (!buf)
+				return -ENOMEM;
+			norm = buf;
+		}
+		if (strglobmatch(norm, name)) {
 			found++;
 			if (syms && found < probe_conf.max_probes)
 				syms[found - 1] = sym;
 		}
+		if (buf)
+			zfree(&buf);
 	}
 
 	return found;

@@ -2856,7 +2872,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	 * same name but different addresses, this lists all the symbols.
 	 */
 	num_matched_functions = find_probe_functions(map, pp->function, syms);
-	if (num_matched_functions == 0) {
+	if (num_matched_functions <= 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
 			pev->target ? : "kernel");
 		ret = -ENOENT;

tools/perf/util/symbol.c +5 -0

index 1b67a8639dfe..cc065d4bfafc 100644
@@ -94,6 +94,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+const char * __weak arch__normalize_symbol_name(const char *name)
+{
+	return name;
+}
+
 int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
 {
 	return strcmp(namea, nameb);

tools/perf/util/symbol.h +1 -0

index a4f0075b4e5c..0563f33c1eb3 100644
@@ -349,6 +349,7 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 #endif
 
+const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #25 lore raw

PATCH 25/35 perf string: Add {strdup,strpbrk}_esc()

From: Masami Hiramatsu <[email protected]>

To support the special characters escaped by '\' in 'perf probe' event parser.

Cc Paul Clarke <[email protected]>

Cc bhargavb <[email protected]>

Link http://lkml.kernel.org/r/151275052163.24652.18205979384585484358.stgit@devbox open here

[ Split from a larger patch ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/string.c  | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/string2.h |  2 ++
 2 files changed, 48 insertions(+)

tools/perf/util/string.c +46 -0

index aaa08ee8c717..d8bfd0c4d2cb 100644
@@ -396,3 +396,49 @@ char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints
 	free(expr);
 	return NULL;
 }
+
+/* Like strpbrk(), but not break if it is right after a backslash (escaped) */
+char *strpbrk_esc(char *str, const char *stopset)
+{
+	char *ptr;
+
+	do {
+		ptr = strpbrk(str, stopset);
+		if (ptr == str ||
+		    (ptr == str + 1 && *(ptr - 1) != '\\'))
+			break;
+		str = ptr + 1;
+	} while (ptr && *(ptr - 1) == '\\' && *(ptr - 2) != '\\');
+
+	return ptr;
+}
+
+/* Like strdup, but do not copy a single backslash */
+char *strdup_esc(const char *str)
+{
+	char *s, *d, *p, *ret = strdup(str);
+
+	if (!ret)
+		return NULL;
+
+	d = strchr(ret, '\\');
+	if (!d)
+		return ret;
+
+	s = d + 1;
+	do {
+		if (*s == '\0') {
+			*d = '\0';
+			break;
+		}
+		p = strchr(s + 1, '\\');
+		if (p) {
+			memmove(d, s, p - s);
+			d += p - s;
+			s = p + 1;
+		} else
+			memmove(d, s, strlen(s) + 1);
+	} while (p);
+
+	return ret;
+}

tools/perf/util/string2.h +2 -0

index ee14ca5451ab..4c68a09b97e8 100644
@@ -39,5 +39,7 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 	return asprintf_expr_inout_ints(var, false, nints, ints);
 }
 
+char *strpbrk_esc(char *str, const char *stopset);
+char *strdup_esc(const char *str);
 
 #endif /* PERF_STRING_H */

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #26 lore raw

PATCH 26/35 perf probe: Support escaped character in parser

From: Masami Hiramatsu <[email protected]>

Support the special characters escaped by '\' in parser. This allows user to specify versions directly like below.

=====

  # ./perf probe -x /lib64/libc-2.25.so malloc_get_state\\@GLIBC_2.2.5
  Added new event:
    probe_libc:malloc_get_state (on malloc_get_state@GLIBC_2.2.5 in /usr/lib64/libc-2.25.so)

You can now use it in all perf tools, such as:

perf record -e probe_libc:malloc_get_state -aR sleep 1

=====

Or, you can use separators in source filename, e.g.

=====

  # ./perf probe -x /opt/test/a.out foo+bar.c:3
  Semantic error :There is non-digit character in offset.
    Error: Command Parse Error.
  =====

Usually "+" in source file cause parser error, but

=====

  # ./perf probe -x /opt/test/a.out foo\\+bar.c:4
  Added new event:
    probe_a:main         (on @foo+bar.c:4 in /opt/test/a.out)

You can now use it in all perf tools, such as:

perf record -e probe_a:main -aR sleep 1
=====

escaped "\+" allows you to specify that.

Cc Paul Clarke <[email protected]>

Cc bhargavb <[email protected]>

Link http://lkml.kernel.org/r/151309111236.18107.5634753157435343410.stgit@devbox open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Documentation/perf-probe.txt | 16 +++++++++
 tools/perf/util/probe-event.c           | 58 ++++++++++++++++++++-------------
 2 files changed, 51 insertions(+), 23 deletions(-)

tools/perf/Documentation/perf-probe.txt +16 -0

index f96382692f42..b6866a05edd2 100644
@@ -182,6 +182,14 @@ Note that before using the SDT event, the target binary (on which SDT events are
 For details of the SDT, see below.
 https://sourceware.org/gdb/onlinedocs/gdb/Static-Probe-Points.html
 
+ESCAPED CHARACTER
+-----------------
+
+In the probe syntax, '=', '@', '+', ':' and ';' are treated as a special character. You can use a backslash ('\') to escape the special characters.
+This is useful if you need to probe on a specific versioned symbols, like @GLIBC_... suffixes, or also you need to specify a source file which includes the special characters.
+Note that usually single backslash is consumed by shell, so you might need to pass double backslash (\\) or wrapping with single quotes (\'AAA\@BBB').
+See EXAMPLES how it is used.
+
 PROBE ARGUMENT
 --------------
 Each probe argument follows below syntax.

@@ -277,6 +285,14 @@ Add a USDT probe to a target process running in a different mount namespace
 
  ./perf probe --target-ns <target pid> -x /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.121-0.b13.el7_3.x86_64/jre/lib/amd64/server/libjvm.so %sdt_hotspot:thread__sleep__end
 
+Add a probe on specific versioned symbol by backslash escape
+
+ ./perf probe -x /lib64/libc-2.25.so 'malloc_get_state\@GLIBC_2.2.5'
+
+Add a probe in a source file using special characters by backslash escape
+
+ ./perf probe -x /opt/test/a.out 'foo\+bar.c:4'
+
 
 SEE ALSO
 --------

tools/perf/util/probe-event.c +35 ~~-23~~

138 lines not on this page · raw message

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #27 lore raw

PATCH 27/35 perf evsel: Fix swap for samples with raw data

From: Jiri Olsa <[email protected]>

When we detect a different endianity we swap event before processing. It's tricky for samples because we have no idea what's inside. We treat it as an array of u64s, swap them and later on we swap back parts which are different.

We mangle this way also the tracepoint raw data, which ends up in report showing wrong data:

1.95% comm=Q^B pid=29285 prio=16777216 target_cpu=000 1.67% comm=l^B pid=0 prio=16777216 target_cpu=000

Luckily the traceevent library handles the endianity by itself (thank you Steven!), so we can pass the RAW data directly in the other endianity.

2.51% comm=beah-rhts-task pid=1175 prio=120 target_cpu=002 2.23% comm=kworker/0:0 pid=11566 prio=120 target_cpu=000

The fix is basically to swap back the raw data if different endianity is detected.

Signed-off-by Jiri Olsa <[email protected]>

Cc David Ahern <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Steven Rostedt <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Add util/memswap.c to python-ext-sources to link missing mem_bswap_64() ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/util/evsel.c            | 20 +++++++++++++++++---
 tools/perf/util/python-ext-sources |  1 +
 2 files changed, 18 insertions(+), 3 deletions(-)

tools/perf/util/evsel.c +17 -3

index 4718f0a460df..1cf044cbae36 100644
@@ -36,6 +36,7 @@
 #include "debug.h"
 #include "trace-event.h"
 #include "stat.h"
+#include "memswap.h"
 #include "util/parse-branch-options.h"
 
 #include "sane_ctype.h"

@@ -2131,14 +2132,27 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (type & PERF_SAMPLE_RAW) {
 		OVERFLOW_CHECK_u64(array);
 		u.val64 = *array;
-		if (WARN_ONCE(swapped,
-			      "Endianness of raw data not corrected!\n")) {
-			/* undo swap of u64, then swap on individual u32s */
+
+		/*
+		 * Undo swap of u64, then swap on individual u32s,
+		 * get the size of the raw area and undo all of the
+		 * swap. The pevent interface handles endianity by
+		 * itself.
+		 */
+		if (swapped) {
 			u.val64 = bswap_64(u.val64);
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
 		}
 		data->raw_size = u.val32[0];
+
+		/*
+		 * The raw data is aligned on 64bits including the
+		 * u32 size, so it's safe to use mem_bswap_64.
+		 */
+		if (swapped)
+			mem_bswap_64((void *) array, data->raw_size);
+
 		array = (void *)array + sizeof(u32);
 
 		OVERFLOW_CHECK(array, data->raw_size, max_size);

tools/perf/util/python-ext-sources +1 -0

index b4f2f06722a7..7aa0ea64544e 100644
@@ -10,6 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/memswap.c
 util/mmap.c
 util/namespaces.c
 ../lib/bitmap.c

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:32 UTC #28 lore raw

PATCH 28/35 perf test shell: Fix check open filename arg using 'perf trace'

From: Michael Petlan <[email protected]>

Commit f231af789b11 ("perf test shell: Fix check open filename arg using 'perf trace' on s390x") added an exception for s390x to use openat() instead of open() in the test that intercepts a open syscall to look for the filename argument as obtained by the vfs_getname 'perf probe' it puts in place at the getname_flags kernel function.

Its not just s390x that uses openat() instead of open(), so use 'perf list' to look for the syscall:sys_enter_open(at)? present in the system being tested instead of checking if the system is s390x.

In fact Namhyung pointed out that glibc 2.26 changed this behaviour, as described in https://lwn.net/Articles/738694/, so systems where glibc is

Quoted 1 line

= 2.26 will need this patch for this test to work, which already took

place in some distros for architectures such as s390x, while Fedora 26 x86_64 is at glibc 2.25, i.e. still uses open().

Signed-off-by Michael Petlan <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Tested-by Thomas Richter <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Cc Adrian Hunter <[email protected]>

Cc David Ahern <[email protected]>

Cc Hendrik Brueckner <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Wang Nan <[email protected]>

LPU-Reference: [email protected]

Link https://lkml.kernel.org/n/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/tests/shell/trace+probe_vfs_getname.sh | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

tools/perf/tests/shell/trace+probe_vfs_getname.sh +3 -4

index 2a9ef080efd0..55ad9793d544 100755
@@ -17,10 +17,9 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
-
-	perf trace -e ${svc:-open} touch $file 2>&1 | \
-	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	perf trace -e $evts touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #29 lore raw

PATCH 29/35 Revert "perf s390: Always build with -fPIC"

From: Arnaldo Carvalho de Melo <[email protected]>

This one made x86 always build with -fPIC, when the intention was for s390 to be built that way, due to a rebase mistake.

Reported-by Hendrik Brueckner <[email protected]>

This reverts commit 1dc4ddf112a408e607a073d951b962b6c6e2bd6c.

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Makefile.config | 1 -
 1 file changed, 1 deletion(-)

tools/perf/Makefile.config +0 -1

index 6f73c2316740..eb6bd99be0bd 100644
@@ -43,7 +43,6 @@ ifeq ($(SRCARCH),x86)
     LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
   endif
   NO_PERF_REGS := 0
-  CFLAGS += -fPIC
 endif
 
 ifeq ($(SRCARCH),arm)

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #30 lore raw

PATCH 30/35 perf s390: Always build with -fPIC

From: Hendrik Brueckner <[email protected]>

On s390, object files must be compiled with position-indepedent code in order to be incrementally linked or linked to shared libraries.

Therefore, add -fPIC to the CFLAGS for s390 to ensure each object file is built properly.

Reported-by Jonathan Hermann <[email protected]>

Signed-off-by Hendrik Brueckner <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc Martin Schwidefsky <[email protected]>

Cc Thomas Richter <[email protected]>

Cc linux s390 list <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Makefile.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

tools/perf/Makefile.config +1 -1

index eb6bd99be0bd..f050f38d8fa3 100644
@@ -58,7 +58,7 @@ endif
 ifeq ($(ARCH),s390)
   NO_PERF_REGS := 0
   NO_SYSCALL_TABLE := 0
-  CFLAGS += -I$(OUTPUT)arch/s390/include/generated
+  CFLAGS += -fPIC -I$(OUTPUT)arch/s390/include/generated
 endif
 
 ifeq ($(NO_PERF_REGS),0)

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #31 lore raw

PATCH 31/35 perf evsel: Enable ignore_missing_thread for pid option

From: Mengting Zhang <[email protected]>

While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error.

Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups.

        sys_perf_event_open: pid 28960  cpu 40  group_fd 118202  flags 0x8
        sys_perf_event_open: pid 28961  cpu 40  group_fd 118203  flags 0x8

WARNING: Ignored open failure for pid 28962
sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22

That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22.

        sys_perf_event_open(){
           ...
           if (group_fd != -1)
               perf_fget_light()//to get corresponding group_leader by group_fd
           ...
           if (group_leader)
              if (group_leader->ctx->task != ctx->task)//should on the same task
                   goto err_context
           ...
        }

This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread.

Changes since v1:
- Change group_fd__remove() into a more genetic way without changing code logic
- Remove redundant condition

Changes since v2:
- Use a proper function name and add some comment.
- Multiline comment style fixes.

Committer testing:

Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc:

[root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory

Usage: perf stat [<options>] [<command>]

-C, --cpu <cpu> list of cpus to monitor in system-wide
-a, --all-cpus system-wide collection from all CPUs
[root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory

Usage: perf stat [<options>] [<command>]

-C, --cpu <cpu> list of cpus to monitor in system-wide
-a, --all-cpus system-wide collection from all CPUs
[root@jouet ~]#

When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen.

Signed-off-by Mengting Zhang <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Cheng Jian <[email protected]>

Cc Li Bin <[email protected]>

Cc Wang Nan <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

[ Remove one use 'evlist' alias variable ]

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/builtin-record.c |  4 ++--
 tools/perf/util/evsel.c     | 47 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 47 insertions(+), 4 deletions(-)

tools/perf/builtin-record.c +2 -2

index 98da8cb8de93..50385d89c497 100644
@@ -1804,8 +1804,8 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
-	/* Enable ignoring missing threads when -u option is defined. */
-	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+	/* Enable ignoring missing threads when -u/-p option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
 
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)

tools/perf/util/evsel.c +45 -2

73 lines not on this page · raw message

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #32 lore raw

PATCH 32/35 perf probe arm64: Fix symbol fixup issues due to ELF type

From: Kim Phillips <[email protected]>

On an arm64 machine running a CONFIG_RANDOMIZE_BASE=y kernel, perf kernel symbol resolution fails. Debugging saw symsrc_init calling the default elf__needs_adjust_symbols() where checks for an ET_DYN (3) ehdr.e_type failed when they should have succeeded.

Fix by adopting powerpc version of the weak elf__needs_adjust_symbols() function, as done in commit d2332098331f ("perf probe ppc: Fix symbol fixup issues due to ELF type").

Prior to this patch, perf test 1 would fail:

  $ sudo oldperf test -v 1 |& head
   1: vmlinux symtab matches kallsyms                       :
  test child forked, pid 33374
  Looking at the vmlinux_path (8 entries long)
  Using /usr/lib/debug/boot/vmlinux for symbols
  ERR : 0xfffe0000100f1000: do_undefinstr not on kallsyms
  ERR : 0xfffe0000100f1320: do_sysinstr not on kallsyms
  ERR : 0xfffe0000100f13b0: do_debug_exception not on kallsyms
  ERR : 0xfffe0000100f1498: do_mem_abort not on kallsyms
  ERR : 0xfffe0000100f1580: do_sp_pc_abort not on kallsyms
  ...

After applying this patch, perf test 1 now succeeds:

  $ sudo ./newperf test -v 1 |& head
   1: vmlinux symtab matches kallsyms                       :
  test child forked, pid 33378
  Looking at the vmlinux_path (8 entries long)
  Using /usr/lib/debug/boot/vmlinux for symbols
  WARN: 0xffff000008081000: diff name v: do_undefinstr k: __exception_text_start
  WARN: 0xffff0000080819e8: diff name v: __irqentry_text_end k: __softirqentry_text_start
  WARN: 0xffff000008081d08: diff name v: __entry_text_start k: __softirqentry_text_end
  WARN: 0xffff00000809db5c: diff name v: flush_icache_range k: __flush_cache_user_range
  WARN: 0xffff000008101908: diff name v: sys_ni_syscall k: sys_vm86old
  ...

Signed-off-by Kim Phillips <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Ganapatrao Kulkarni <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Naveen N. Rao <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Will Deacon <[email protected]>

Cc linux-arm-kernel at lists.infradead.org

Link http://lkml.kernel.org/r/20171214175242.e30450f17f93ad675d968fa3 at arm.com

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/arch/arm64/util/Build          |  1 +
 tools/perf/arch/arm64/util/sym-handling.c | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+)
 create mode 100644 tools/perf/arch/arm64/util/sym-handling.c

tools/perf/arch/arm64/util/Build +1 -0

index b1ab72d2a42e..e04f6cdd6f32 100644
@@ -1,4 +1,5 @@
 libperf-y += header.o
+libperf-y += sym-handling.o
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o

tools/perf/arch/arm64/util/sym-handling.c new file +22 -0

new file mode 100644
index 000000000000..0051b1ee8450
@@ -0,0 +1,22 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+#include "probe-file.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC ||
+	       ehdr.e_type == ET_REL ||
+	       ehdr.e_type == ET_DYN;
+}
+#endif

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #33 lore raw

PATCH 33/35 perf tool: Improve bash command line auto-complete for multiple events with comma

From: Jin Yao <[email protected]>

perf has perf-completion.sh to define command line auto-completion in bash/zsh.

For record/stat -e it works for single events, but isn't working when specifying multiple events with comma.

It would be very useful if it could be fixed to make it easier by supporting multiple events, comma separated.

With this patch, the result can be like this:

1. Support the events returned from 'perf list --raw-dump'

root@skl:/tmp# perf stat -e cpu/cache<TAB>
cpu/cache-misses/      cpu/cache-references/

root@skl:/tmp# perf stat -e cpu/cache-misses/,cpu/branch-<TAB>
cpu/branch-instructions/  cpu/branch-misses/

root@skl:/tmp# perf stat -e cpu/cache-misses/,cpu/branch-i<TAB>
root@skl:/tmp# perf stat -e cpu/cache-misses/,cpu/branch-instructions/

2. Support the events listed in /sys/bus/event_source/devices/cpu/events

root@skl:/tmp# perf stat -e cycle<TAB>
cycle_activity.cycles_l1d_miss  cycle_activity.stalls_l3_miss
cycle_activity.cycles_l2_miss   cycle_activity.stalls_mem_any
cycle_activity.cycles_l3_miss   cycle_activity.stalls_total
cycle_activity.cycles_mem_any   cycles-ct
cycle_activity.stalls_l1d_miss  cycles-t
cycle_activity.stalls_l2_miss

root@skl:/tmp# perf stat -e cycles-<TAB>
cycles-ct  cycles-t

root@skl:/tmp# perf stat -e cycles-t,cpu/c<TAB>
cpu/cache-misses/      cpu/cpu-cycles/        cpu/cycles-t/
cpu/cache-references/  cpu/cycles-ct/

root@skl:/tmp# perf stat -e cycles-t,cpu/cache-<TAB>
cpu/cache-misses/      cpu/cache-references/

root@skl:/tmp# perf stat -e cycles-t,cpu/cache-misses/

3. Support the uppercase event which is with prefix "cpu/"

root@skl:/tmp# perf stat -e cpu/c<TAB>
cpu/cache-misses/      cpu/cpu-cycles/        cpu/cycles-t/
cpu/cache-references/  cpu/cycles-ct/

root@skl:/tmp# perf stat -e cpu/cache-misses/,cpu/C<TAB>
cpu/CACHE-MISSES/      cpu/CPU-CYCLES/        cpu/CYCLES-T/
cpu/CACHE-REFERENCES/  cpu/CYCLES-CT/

root@skl:/tmp# perf stat -e cpu/cache-misses/,cpu/CACHE-REFERENCES/

Note that:

a) This patch only supports bash.

b) It doesn't support the cases like {},{} or {...,...}.

Signed-off-by Jin Yao <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/perf-completion.sh | 38 ++++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

tools/perf/perf-completion.sh +34 -4

index 345f5d6e9ed5..d8310830a18b 100644
@@ -162,8 +162,33 @@ __perf_main ()
 	# List possible events for -e option
 	elif [[ $prev == @("-e"|"--event") &&
 		$prev_skip_opts == @(record|stat|top) ]]; then
-		evts=$($cmd list --raw-dump)
-		__perfcomp_colon "$evts" "$cur"
+
+		local cur1=${COMP_WORDS[COMP_CWORD]}
+		local raw_evts=$($cmd list --raw-dump)
+		local arr s tmp result
+
+		if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then
+			OLD_IFS="$IFS"
+			IFS=" "
+			arr=($raw_evts)
+			IFS="$OLD_IFS"
+
+			for s in ${arr[@]}
+			do
+				if [[ "$s" == *cpu/* ]]; then
+					tmp=${s#*cpu/}
+					result=$result" ""cpu/"${tmp^^}
+				else
+					result=$result" "$s
+				fi
+			done
+
+			evts=${result}+$(ls /sys/bus/event_source/devices/cpu/events)
+		else
+			evts=${raw_evts}+$(ls /sys/bus/event_source/devices/cpu/events)
+		fi
+
+		__perfcomp_colon "$evts" "$cur1"
 	else
 		# List subcommands for perf commands
 		if [[ $prev_skip_opts == @(kvm|kmem|mem|lock|sched|

@@ -246,11 +271,16 @@ fi
 type perf &>/dev/null &&
 _perf()
 {
+	if [[ "$COMP_WORDBREAKS" != *,* ]]; then
+		COMP_WORDBREAKS="${COMP_WORDBREAKS},"
+		export COMP_WORDBREAKS
+	fi
+
 	local cur words cword prev
 	if [ $preload_get_comp_words_by_ref = "true" ]; then
-		_get_comp_words_by_ref -n =: cur words cword prev
+		_get_comp_words_by_ref -n =:, cur words cword prev
 	else
-		__perf_get_comp_words_by_ref -n =: cur words cword prev
+		__perf_get_comp_words_by_ref -n =:, cur words cword prev
 	fi
 	__perf_main
 } &&

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #34 lore raw

PATCH 34/35 perf tools: Return all events as auto-completions after comma

From: Jin Yao <[email protected]>

It's a follow up for one previous patch "perf tool: Improve bash command line auto-complete for multiple events with comma."

It fixes an issue that no events are displayed when <TAB> is directly typed after comma.

With this patch, now the result is:

  root@skl:/tmp# perf stat -e cpu-cycles,<TAB>
  Display all 2389 possibilities? (y or n)
  alarmtimer:alarmtimer_cancel
  alarmtimer:alarmtimer_fired
  alarmtimer:alarmtimer_start
  alarmtimer:alarmtimer_suspend
  alignment-faults
  arith.divider_active
  BAClear_Cost
  baclears.any
  block:block_bio_backmerge
  block:block_bio_bounce
  block:block_bio_complete
  block:block_bio_frontmerge
  block:block_bio_queue
  block:block_bio_remap
  block:block_dirty_buffer
  block:block_getrq
  block:block_plug
  block:block_rq_complete
  block:block_rq_insert
  block:block_rq_issue
  block:block_rq_remap
  block:block_rq_requeue
  block:block_sleeprq
  --More--

One remaining issue is that the auto-completions doesn't work well for the event with ':'. For example, clk:clk_enable.

Because ':' is set as WORDBREAK by default in bash. Need more work for this case.

Reported-by Arnaldo Carvalho de Melo <[email protected]>

Signed-off-by Jin Yao <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/perf-completion.sh | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

tools/perf/perf-completion.sh +7 -3

index d8310830a18b..90206413f4d7 100644
@@ -183,12 +183,16 @@ __perf_main ()
 				fi
 			done
 
-			evts=${result}+$(ls /sys/bus/event_source/devices/cpu/events)
+			evts=${result}" "$(ls /sys/bus/event_source/devices/cpu/events)
 		else
-			evts=${raw_evts}+$(ls /sys/bus/event_source/devices/cpu/events)
+			evts=${raw_evts}" "$(ls /sys/bus/event_source/devices/cpu/events)
 		fi
 
-		__perfcomp_colon "$evts" "$cur1"
+		if [[ "$cur1" == , ]]; then
+			__perfcomp_colon "$evts" ""
+		else
+			__perfcomp_colon "$evts" "$cur1"
+		fi
 	else
 		# List subcommands for perf commands
 		if [[ $prev_skip_opts == @(kvm|kmem|mem|lock|sched|

Signature · 1 line

2.13.6

Arnaldo Carvalho de Melo

author maintainer

2017-12-28 14:30 UTC #35 lore raw

PATCH 35/35 perf tools: Auto-complete for events with ':'

From: Jin Yao <[email protected]>

It's a follow up patch for a previous patch "perf tool: Return all events as auto-completions after comma".

With this patch, auto-completion can work well for events with a ':'. For example:

  root@skl:/tmp# perf stat -e block:block_<TAB>
  block:block_bio_backmerge   block:block_rq_complete
  block:block_bio_bounce      block:block_rq_insert
  block:block_bio_complete    block:block_rq_issue
  block:block_bio_frontmerge  block:block_rq_remap
  block:block_bio_queue       block:block_rq_requeue
  block:block_bio_remap       block:block_sleeprq
  block:block_dirty_buffer    block:block_split
  block:block_getrq           block:block_touch_buffer
  block:block_plug            block:block_unplug

  root@skl:/tmp# perf stat -e block:block_rq_<TAB>
  block:block_rq_complete  block:block_rq_issue     block:block_rq_requeue
  block:block_rq_insert    block:block_rq_remap

  root@skl:/tmp# perf stat -e block:block_rq_complete<TAB>
  block:block_rq_complete

  root@skl:/tmp# perf stat -e block:block_rq_complete

Signed-off-by Jin Yao <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Kan Liang <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/perf-completion.sh | 5 +++++
 1 file changed, 5 insertions(+)

tools/perf/perf-completion.sh +5 -0

index 90206413f4d7..fdf75d45efff 100644
@@ -280,6 +280,11 @@ _perf()
 		export COMP_WORDBREAKS
 	fi
 
+	if [[ "$COMP_WORDBREAKS" == *:* ]]; then
+		COMP_WORDBREAKS="${COMP_WORDBREAKS/:/}"
+		export COMP_WORDBREAKS
+	fi
+
 	local cur words cword prev
 	if [ $preload_get_comp_words_by_ref = "true" ]; then
 		_get_comp_words_by_ref -n =:, cur words cword prev

Signature · 1 line

2.13.6

Ingo Molnar

2017-12-28 15:17 UTC #36 lore raw