perf/core improvements and fixes

index 5acf000939ea..138a0e3431fa 100644
@@ -20,6 +20,8 @@ int test__thread_map(void)
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "perf"));
+	TEST_ASSERT_VAL("wrong refcnt",
+			atomic_read(&map->refcnt) == 1);
 	thread_map__put(map);
 
 	/* test dummy pid */

@@ -33,6 +35,8 @@ int test__thread_map(void)
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "dummy"));
+	TEST_ASSERT_VAL("wrong refcnt",
+			atomic_read(&map->refcnt) == 1);
 	thread_map__put(map);
 	return 0;
 }

index f7d9c77ee31b..6bfcab9b7108 100644
@@ -1150,6 +1150,23 @@ out_delete_threads:
 	return -1;
 }
 
+int perf_evlist__set_maps(struct perf_evlist *evlist,
+			  struct cpu_map *cpus,
+			  struct thread_map *threads)
+{
+	if (evlist->cpus)
+		cpu_map__put(evlist->cpus);
+
+	evlist->cpus = cpus;
+
+	if (evlist->threads)
+		thread_map__put(evlist->threads);
+
+	evlist->threads = threads;
+
+	return perf_evlist__propagate_maps(evlist, false);
+}
+
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
 {
 	struct perf_evsel *evsel;

index 037633c1da9d..406a8216a51e 100644
@@ -152,14 +152,9 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 
-static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
-					 struct cpu_map *cpus,
-					 struct thread_map *threads)
-{
-	evlist->cpus	= cpus;
-	evlist->threads	= threads;
-}
-
+int perf_evlist__set_maps(struct perf_evlist *evlist,
+			  struct cpu_map *cpus,
+			  struct thread_map *threads);
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
 

index 6bfcab9b7108..80ab942afa8a 100644
@@ -1102,7 +1102,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 }
 
 static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
-				       struct target *target)
+				       bool has_user_cpus)
 {
 	struct perf_evsel *evsel;
 

@@ -1111,10 +1111,10 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		 * We already have cpus for evsel (via PMU sysfs) so
 		 * keep it, if there's no target cpu list defined.
 		 */
-		if (evsel->cpus && target->cpu_list)
+		if (evsel->cpus && has_user_cpus)
 			cpu_map__put(evsel->cpus);
 
-		if (!evsel->cpus || target->cpu_list)
+		if (!evsel->cpus || has_user_cpus)
 			evsel->cpus = cpu_map__get(evlist->cpus);
 
 		evsel->threads = thread_map__get(evlist->threads);

@@ -1142,7 +1142,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return perf_evlist__propagate_maps(evlist, target);
+	return perf_evlist__propagate_maps(evlist, !!target->cpu_list);
 
 out_delete_threads:
 	thread_map__put(evlist->threads);

index 80ab942afa8a..3b9f411a6b46 100644
@@ -1119,7 +1119,8 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
 		evsel->threads = thread_map__get(evlist->threads);
 
-		if (!evsel->cpus || !evsel->threads)
+		if ((evlist->cpus && !evsel->cpus) ||
+		    (evlist->threads && !evsel->threads))
 			return -ENOMEM;
 	}
 

index 03ace57a800c..179b2bdd157d 100644
@@ -923,17 +923,13 @@ static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
 			  FILE *fp)
 {
 	int nr, i;
-	char *str;
 
 	nr = ph->env.nr_cmdline;
-	str = ph->env.cmdline;
 
 	fprintf(fp, "# cmdline : ");
 
-	for (i = 0; i < nr; i++) {
-		fprintf(fp, "%s ", str);
-		str += strlen(str) + 1;
-	}
+	for (i = 0; i < nr; i++)
+		fprintf(fp, "%s ", ph->env.cmdline_argv[i]);
 	fputc('\n', fp);
 }
 

@@ -1541,14 +1537,13 @@ process_event_desc(struct perf_file_section *section __maybe_unused,
 	return 0;
 }
 
-static int process_cmdline(struct perf_file_section *section __maybe_unused,
+static int process_cmdline(struct perf_file_section *section,
 			   struct perf_header *ph, int fd,
 			   void *data __maybe_unused)
 {
 	ssize_t ret;
-	char *str;
-	u32 nr, i;
-	struct strbuf sb;
+	char *str, *cmdline = NULL, **argv = NULL;
+	u32 nr, i, len = 0;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))

@@ -1558,22 +1553,32 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
 		nr = bswap_32(nr);
 
 	ph->env.nr_cmdline = nr;
-	strbuf_init(&sb, 128);
+
+	cmdline = zalloc(section->size + nr + 1);
+	if (!cmdline)
+		return -1;
+
+	argv = zalloc(sizeof(char *) * (nr + 1));
+	if (!argv)
+		goto error;
 
 	for (i = 0; i < nr; i++) {
 		str = do_read_string(fd, ph);
 		if (!str)
 			goto error;
 
-		/* include a NULL character at the end */
-		strbuf_add(&sb, str, strlen(str) + 1);
+		argv[i] = cmdline + len;
+		memcpy(argv[i], str, strlen(str) + 1);
+		len += strlen(str) + 1;
 		free(str);
 	}
-	ph->env.cmdline = strbuf_detach(&sb, NULL);
+	ph->env.cmdline = cmdline;
+	ph->env.cmdline_argv = (const char **) argv;
 	return 0;
 
 error:
-	strbuf_release(&sb);
+	free(argv);
+	free(cmdline);
 	return -1;
 }
 

index d4d57962c591..9b53b6525ce8 100644
@@ -84,6 +84,7 @@ struct perf_session_env {
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	char			*cmdline;
+	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_threads;
 	char			*numa_nodes;

index ed9dc2555ec7..fb1d525ca3d0 100644
@@ -180,6 +180,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
 	zfree(&env->cpuid);
 
 	zfree(&env->cmdline);
+	zfree(&env->cmdline_argv);
 	zfree(&env->sibling_cores);
 	zfree(&env->sibling_threads);
 	zfree(&env->numa_nodes);

index 2fe98bb0e95b..c73276db6d6f 100644
@@ -137,6 +137,10 @@ struct dso {
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct {
+		u64		addr;
+		struct symbol	*symbol;
+	} last_find_result[MAP__NR_TYPES];
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;

index 45c2e3a8316b..725640fd7cd8 100644
@@ -444,7 +444,12 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
-	return symbols__find(&dso->symbols[type], addr);
+	if (dso->last_find_result[type].addr != addr) {
+		dso->last_find_result[type].addr   = addr;
+		dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
+	}
+
+	return dso->last_find_result[type].symbol;
 }
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)

index b5a5e9c02437..ce37e95bc513 100644
@@ -224,6 +224,20 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
+/*
+ * Use this and __map__is_kmodule() for map instances that are in
+ * machine->kmaps, and thus have map->groups->machine all properly set, to
+ * disambiguate between the kernel and modules.
+ *
+ * When the need arises, introduce map__is_{kernel,kmodule)() that
+ * checks (map->groups != NULL && map->groups->machine != NULL &&
+ * map->dso->kernel) before calling __map__is_{kernel,kmodule}())
+ */
+bool __map__is_kernel(const struct map *map)
+{
+	return map->groups->machine->vmlinux_maps[map->type] == map;
+}
+
 static void map__exit(struct map *map)
 {
 	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));

index d73e687b224e..57829e89b78b 100644
@@ -256,4 +256,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
+bool __map__is_kernel(const struct map *map);
+
+static inline bool __map__is_kmodule(const struct map *map)
+{
+	return !__map__is_kernel(map);
+}
+
 #endif /* __PERF_MAP_H */

index cc25f059ab3d..fcd8a9e3d2e1 100644
@@ -418,7 +418,7 @@ static int func_map_init(struct pevent *pevent)
 }
 
 static struct func_map *
-find_func(struct pevent *pevent, unsigned long long addr)
+__find_func(struct pevent *pevent, unsigned long long addr)
 {
 	struct func_map *func;
 	struct func_map key;

@@ -434,6 +434,71 @@ find_func(struct pevent *pevent, unsigned long long addr)
 	return func;
 }
 
+struct func_resolver {
+	pevent_func_resolver_t *func;
+	void		       *priv;
+	struct func_map	       map;
+};
+
+/**
+ * pevent_set_function_resolver - set an alternative function resolver
+ * @pevent: handle for the pevent
+ * @resolver: function to be used
+ * @priv: resolver function private state.
+ *
+ * Some tools may have already a way to resolve kernel functions, allow them to
+ * keep using it instead of duplicating all the entries inside
+ * pevent->funclist.
+ */
+int pevent_set_function_resolver(struct pevent *pevent,
+				 pevent_func_resolver_t *func, void *priv)
+{
+	struct func_resolver *resolver = malloc(sizeof(*resolver));
+
+	if (resolver == NULL)
+		return -1;
+
+	resolver->func = func;
+	resolver->priv = priv;
+
+	free(pevent->func_resolver);
+	pevent->func_resolver = resolver;
+
+	return 0;
+}
+
+/**
+ * pevent_reset_function_resolver - reset alternative function resolver
+ * @pevent: handle for the pevent
+ *
+ * Stop using whatever alternative resolver was set, use the default
+ * one instead.
+ */
+void pevent_reset_function_resolver(struct pevent *pevent)
+{
+	free(pevent->func_resolver);
+	pevent->func_resolver = NULL;
+}
+
+static struct func_map *
+find_func(struct pevent *pevent, unsigned long long addr)
+{
+	struct func_map *map;
+
+	if (!pevent->func_resolver)
+		return __find_func(pevent, addr);
+
+	map = &pevent->func_resolver->map;
+	map->mod  = NULL;
+	map->addr = addr;
+	map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
+						&map->addr, &map->mod);
+	if (map->func == NULL)
+		return NULL;
+
+	return map;
+}
+
 /**
  * pevent_find_function - find a function by a given address
  * @pevent: handle for the pevent

@@ -6564,6 +6629,7 @@ void pevent_free(struct pevent *pevent)
 	free(pevent->trace_clock);
 	free(pevent->events);
 	free(pevent->sort_events);
+	free(pevent->func_resolver);
 
 	free(pevent);
 }

index 063b1971eb35..204befb05a17 100644
@@ -453,6 +453,10 @@ struct cmdline_list;
 struct func_map;
 struct func_list;
 struct event_handler;
+struct func_resolver;
+
+typedef char *(pevent_func_resolver_t)(void *priv,
+				       unsigned long long *addrp, char **modp);
 
 struct pevent {
 	int ref_count;

@@ -481,6 +485,7 @@ struct pevent {
 	int cmdline_count;
 
 	struct func_map *func_map;
+	struct func_resolver *func_resolver;
 	struct func_list *funclist;
 	unsigned int func_count;
 

@@ -611,6 +616,9 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 };
 
+int pevent_set_function_resolver(struct pevent *pevent,
+				 pevent_func_resolver_t *func, void *priv);
+void pevent_reset_function_resolver(struct pevent *pevent);
 int pevent_register_comm(struct pevent *pevent, const char *comm, int pid);
 int pevent_register_trace_clock(struct pevent *pevent, const char *trace_clock);
 int pevent_register_function(struct pevent *pevent, char *name,

index d0bf1e590479..22006c15edf4 100644
@@ -1993,3 +1993,17 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
 {
 	return dsos__findnew(&machine->dsos, filename);
 }
+
+char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+	struct machine *machine = vmachine;
+	struct map *map;
+	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map,  NULL);
+
+	if (sym == NULL)
+		return NULL;
+
+	*modp = __map__is_kmodule(map) ? (char *)map->dso->short_name : NULL;
+	*addrp = map->unmap_ip(map, sym->start);
+	return sym->name;
+}

index 887798e511e9..ff5f78c886e0 100644
@@ -237,5 +237,9 @@ int machine__synthesize_threads(struct machine *machine, struct target *target,
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
+/*
+ * For use with libtraceevent's pevent_set_function_resolver()
+ */
+char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
 #endif /* __PERF_MACHINE_H */

69 lines not on this page · raw message

index d5168f0be4ec..568128c3284a 100644
@@ -18,6 +18,7 @@ struct trace_event {
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
+int trace_event__register_resolver(struct machine *machine);
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);
 

index 32b4d280af4f..282841b10f24 100644
@@ -1489,6 +1489,9 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
+	if (trace_event__register_resolver(trace->host) < 0)
+		return -errno;
+
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout);

index 24809787369f..2777c6444bc3 100644
@@ -1830,6 +1830,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	else
 		symbol_conf.use_callchain = false;
 
+	if (pevent_set_function_resolver(session->tevent.pevent,
+					 machine__resolve_kernel_addr,
+					 &session->machines.host) < 0) {
+		pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
+		return -1;
+	}
+
 	if (generate_script_lang) {
 		struct stat perf_stat;
 		int input;

index bd31380122f9..7912feb9a024 100644
@@ -1861,7 +1861,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	else
 		symbol_conf.use_callchain = false;
 
-	if (pevent_set_function_resolver(session->tevent.pevent,
+	if (session->tevent.pevent &&
+	    pevent_set_function_resolver(session->tevent.pevent,
 					 machine__resolve_kernel_addr,
 					 &session->machines.host) < 0) {
 		pr_err("%s: failed to set libtraceevent function resolver\n", __func__);

index d4957418657e..8ff7d620d942 100644
@@ -135,36 +135,6 @@ void event_format__print(struct event_format *event,
 	return event_format__fprintf(event, cpu, data, size, stdout);
 }
 
-void parse_proc_kallsyms(struct pevent *pevent,
-			 char *file, unsigned int size __maybe_unused)
-{
-	unsigned long long addr;
-	char *func;
-	char *line;
-	char *next = NULL;
-	char *addr_str;
-	char *mod;
-	char *fmt = NULL;
-
-	line = strtok_r(file, "\n", &next);
-	while (line) {
-		mod = NULL;
-		addr_str = strtok_r(line, " ", &fmt);
-		addr = strtoull(addr_str, NULL, 16);
-		/* skip character */
-		strtok_r(NULL, " ", &fmt);
-		func = strtok_r(NULL, "\t", &fmt);
-		mod = strtok_r(NULL, "]", &fmt);
-		/* truncate the extra '[' */
-		if (mod)
-			mod = mod + 1;
-
-		pevent_register_function(pevent, func, addr, mod);
-
-		line = strtok_r(NULL, "\n", &next);
-	}
-}
-
 void parse_ftrace_printk(struct pevent *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {

index 54d9e9b548a8..b67a0ccf5ab9 100644
@@ -162,25 +162,23 @@ out:
 static int read_proc_kallsyms(struct pevent *pevent)
 {
 	unsigned int size;
-	char *buf;
 
 	size = read4(pevent);
 	if (!size)
 		return 0;
-
-	buf = malloc(size + 1);
-	if (buf == NULL)
-		return -1;
-
-	if (do_read(buf, size) < 0) {
-		free(buf);
-		return -1;
-	}
-	buf[size] = '\0';
-
-	parse_proc_kallsyms(pevent, buf, size);
-
-	free(buf);
+	/*
+	 * Just skip it, now that we configure libtraceevent to use the
+	 * tools/perf/ symbol resolver.
+	 *
+	 * We need to skip it so that we can continue parsing old perf.data
+	 * files, that contains this /proc/kallsyms payload.
+	 *
+	 * Newer perf.data files will have just the 4-bytes zeros "kallsyms
+	 * payload", so that older tools can continue reading it and interpret
+	 * it as "no kallsyms payload is present".
+	 */
+	lseek(input_fd, size, SEEK_CUR);
+	trace_data_size += size;
 	return 0;
 }
 

index eb72716017ac..22245986e59e 100644
@@ -341,20 +341,14 @@ out:
 
 static int record_proc_kallsyms(void)
 {
-	unsigned int size;
-	const char *path = "/proc/kallsyms";
-	struct stat st;
-	int ret, err = 0;
-
-	ret = stat(path, &st);
-	if (ret < 0) {
-		/* not found */
-		size = 0;
-		if (write(output_fd, &size, 4) != 4)
-			err = -EIO;
-		return err;
-	}
-	return record_file(path, 4);
+	unsigned long long size = 0;
+	/*
+	 * Just to keep older perf.data file parsers happy, record a zero
+	 * sized kallsyms file, i.e. do the same thing that was done when
+	 * /proc/kallsyms (or something specified via --kallsyms, in a
+	 * different path) couldn't be read.
+	 */
+	return write(output_fd, &size, 4) != 4 ? -EIO : 0;
 }
 
 static int record_ftrace_printk(void)

index d97f84c080da..022d0acf7df0 100644
@@ -330,7 +330,8 @@ struct perf_event_attr {
 				mmap2          :  1, /* include mmap with inode data     */
 				comm_exec      :  1, /* flag comm events that are due to an exec */
 				use_clockid    :  1, /* use @clockid for time fields */
-				__reserved_1   : 38;
+				context_switch :  1, /* context switch data */
+				__reserved_1   : 37;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */

@@ -572,9 +573,11 @@ struct perf_event_mmap_page {
 /*
  * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
  * different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * Indicates that the content of PERF_SAMPLE_IP points to
  * the actual instruction that triggered the event. See also

@@ -818,6 +821,32 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_LOST_SAMPLES		= 13,
 
+	/*
+	 * Records a context switch in or out (flagged by
+	 * PERF_RECORD_MISC_SWITCH_OUT). See also
+	 * PERF_RECORD_SWITCH_CPU_WIDE.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH			= 14,
+
+	/*
+	 * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+	 * next_prev_tid that are the next (switching out) or previous
+	 * (switching in) pid/tid.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				next_prev_pid;
+	 *	u32				next_prev_tid;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

145 lines not on this page · raw message

index 01b06492bd6a..f62c49b35be0 100644
@@ -561,6 +561,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__repipe,
 			.aux		= perf_event__repipe,
 			.itrace_start	= perf_event__repipe,
+			.context_switch	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,

index 67a977e5d0ab..7ff61274ed57 100644
@@ -26,6 +26,8 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_AUX]			= "AUX",
 	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
+	[PERF_RECORD_SWITCH]			= "SWITCH",
+	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",

@@ -749,6 +751,14 @@ int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_samples_event(machine, event, sample);
 }
 
+int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine)
+{
+	return machine__process_switch_event(machine, event);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",

@@ -827,6 +837,20 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 		       event->itrace_start.pid, event->itrace_start.tid);
 }
 
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	const char *in_out = out ? "OUT" : "IN ";
+
+	if (event->header.type == PERF_RECORD_SWITCH)
+		return fprintf(fp, " %s\n", in_out);
+
+	return fprintf(fp, " %s  %s pid/tid: %5u/%-5u\n",
+		       in_out, out ? "next" : "prev",
+		       event->context_switch.next_prev_pid,
+		       event->context_switch.next_prev_tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",

@@ -852,6 +876,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_ITRACE_START:
 		ret += perf_event__fprintf_itrace_start(event, fp);
 		break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret += perf_event__fprintf_switch(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}

index c53f36384b64..4bb2ae894c78 100644
@@ -348,6 +348,12 @@ struct itrace_start_event {
 	u32 pid, tid;
 };
 
+struct context_switch_event {
+	struct perf_event_header header;
+	u32 next_prev_pid;
+	u32 next_prev_tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;

@@ -369,6 +375,7 @@ union perf_event {
 	struct auxtrace_error_event	auxtrace_error;
 	struct aux_event		aux;
 	struct itrace_start_event	itrace_start;
+	struct context_switch_event	context_switch;
 };
 
 void perf_event__print_totals(void);

@@ -418,6 +425,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample,
 				     struct machine *machine);
+int perf_event__process_switch(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,

@@ -480,6 +491,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,

index 49fb7b5feb09..9e6e6f40b787 100644
@@ -1127,6 +1127,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(mmap2, p_unsigned);
 	PRINT_ATTRf(comm_exec, p_unsigned);
 	PRINT_ATTRf(use_clockid, p_unsigned);
+	PRINT_ATTRf(context_switch, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);

index 22006c15edf4..be3e00891d22 100644
@@ -550,6 +550,14 @@ int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_switch(event, stdout);
+	return 0;
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {

@@ -1451,6 +1459,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_itrace_start_event(machine, event); break;
 	case PERF_RECORD_LOST_SAMPLES:
 		ret = machine__process_lost_samples_event(machine, event, sample); break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret = machine__process_switch_event(machine, event); break;
 	default:
 		ret = -1;
 		break;

index ff5f78c886e0..ea5cb4a621db 100644
@@ -87,6 +87,8 @@ int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
 int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,

index fb1d525ca3d0..2d9574710543 100644
@@ -333,6 +333,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->aux = perf_event__process_aux;
 	if (tool->itrace_start == NULL)
 		tool->itrace_start = perf_event__process_itrace_start;
+	if (tool->context_switch == NULL)
+		tool->context_switch = perf_event__process_switch;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)

@@ -471,6 +473,19 @@ static void perf_event__itrace_start_swap(union perf_event *event,
 		swap_sample_id_all(event, &event->itrace_start + 1);
 }
 
+static void perf_event__switch_swap(union perf_event *event, bool sample_id_all)
+{
+	if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+		event->context_switch.next_prev_pid =
+				bswap_32(event->context_switch.next_prev_pid);
+		event->context_switch.next_prev_tid =
+				bswap_32(event->context_switch.next_prev_tid);
+	}
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->context_switch + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {

@@ -633,6 +648,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
 	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
 	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
+	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
+	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,

@@ -1094,6 +1111,9 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		return tool->context_switch(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;

index c307dd438286..cab8cc24831b 100644
@@ -46,6 +46,7 @@ struct perf_tool {
 			lost_samples,
 			aux,
 			itrace_start,
+			context_switch,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;

index 1932e27c00d8..445a64d19625 100644
@@ -1075,6 +1075,8 @@ struct option __record_options[] = {
 			  "opts", "AUX area tracing Snapshot Mode", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
+		    "Record context switch events"),
 	OPT_END()
 };
 

@@ -1102,6 +1104,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 			  " system-wide mode\n");
 		usage_with_options(record_usage, record_options);
 	}
+	if (rec->opts.record_switch_events &&
+	    !perf_can_record_switch_events()) {
+		ui__error("kernel does not support recording context switch events (--switch-events option)\n");
+		usage_with_options(record_usage, record_options);
+	}
 
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);

index 937b16aa0300..cf459f89fc9b 100644
@@ -57,6 +57,7 @@ struct record_opts {
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
+	bool	     record_switch_events;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

index 406a8216a51e..a8930b68456b 100644
@@ -114,6 +114,7 @@ void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
+bool perf_can_record_switch_events(void);
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
 int record_opts__config(struct record_opts *opts);
 

index 9e6e6f40b787..71f6905c7cb9 100644
@@ -738,6 +738,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
+	if (opts->record_switch_events)
+		attr->context_switch = track;
+
 	if (opts->sample_transaction)
 		perf_evsel__set_sample_bit(evsel, TRANSACTION);
 

index 1f7becbe5e18..0d228a29526d 100644
@@ -85,6 +85,11 @@ static void perf_probe_comm_exec(struct perf_evsel *evsel)
 	evsel->attr.comm_exec = 1;
 }
 
+static void perf_probe_context_switch(struct perf_evsel *evsel)
+{
+	evsel->attr.context_switch = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
 	return perf_probe_api(perf_probe_sample_identifier);

@@ -95,6 +100,11 @@ static bool perf_can_comm_exec(void)
 	return perf_probe_api(perf_probe_comm_exec);
 }
 
+bool perf_can_record_switch_events(void)
+{
+	return perf_probe_api(perf_probe_context_switch);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;

index 2777c6444bc3..8a8e2ead6382 100644
@@ -661,7 +661,7 @@ static int process_comm_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 	int ret = -1;
 
 	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);

@@ -695,7 +695,7 @@ static int process_fork_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_fork(tool, event, sample, machine) < 0)
 		return -1;

@@ -727,7 +727,7 @@ static int process_exit_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
 	if (thread == NULL) {

@@ -759,7 +759,7 @@ static int process_mmap_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
 		return -1;

@@ -790,7 +790,7 @@ static int process_mmap2_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
 		return -1;

index 8a8e2ead6382..bd31380122f9 100644
@@ -623,6 +623,7 @@ struct perf_script {
 	struct perf_session	*session;
 	bool			show_task_events;
 	bool			show_mmap_events;
+	bool			show_switch_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,

@@ -813,6 +814,32 @@ static int process_mmap2_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int process_switch_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+
+	if (perf_event__process_switch(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, sample->pid,
+					 sample->tid);
+	if (thread == NULL) {
+		pr_debug("problem processing SWITCH event, skipping it.\n");
+		return -1;
+	}
+
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	thread__put(thread);
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;

@@ -834,6 +861,8 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.mmap = process_mmap_event;
 		script->tool.mmap2 = process_mmap2_event;
 	}
+	if (script->show_switch_events)
+		script->tool.context_switch = process_switch_event;
 
 	ret = perf_session__process_events(script->session);
 

@@ -1618,6 +1647,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the fork/comm/exit events"),
 	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
 		    "Show the mmap events"),
+	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
+		    "Show context switch events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options",