perf sched: Add timehist subcommand

index 6fcc358..7784a9d 100644
@@ -1011,11 +1011,27 @@ out_problem:
 	return 0;
 }
 
+static void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
 int machine__process_fork_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+	struct thread *thread = machine__find_thread(machine, event->fork.tid);
 	struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
 
+	/* if a thread currently exists for the thread id remove it */
+	if (thread != NULL)
+		machine__remove_thread(machine, thread);
+
+	thread = machine__findnew_thread(machine, event->fork.tid);
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 

@@ -1028,27 +1044,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	return 0;
 }
 
-static void machine__remove_thread(struct machine *machine, struct thread *th)
-{
-	machine->last_match = NULL;
-	rb_erase(&th->rb_node, &machine->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &machine->dead_threads);
-}
-
-int machine__process_exit_event(struct machine *machine, union perf_event *event)
+int machine__process_exit_event(struct machine *machine __maybe_unused,
+				union perf_event *event)
 {
-	struct thread *thread = machine__find_thread(machine, event->fork.tid);
-
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
-		machine__remove_thread(machine, thread);
-
 	return 0;
 }
 

index 948183a..34ce57d 100644
@@ -1445,7 +1445,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	return err;
 }
 
-static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
+static int perf_sched__read_events(struct perf_sched *sched,
 				   struct perf_session **psession)
 {
 	const struct perf_evsel_str_handler handlers[] = {

@@ -1480,11 +1480,10 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
 		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
 	}
 
-	if (destroy)
-		perf_session__delete(session);
-
 	if (psession)
 		*psession = session;
+	else
+		perf_session__delete(session);
 
 	return 0;
 

@@ -1529,8 +1528,11 @@ static int perf_sched__lat(struct perf_sched *sched)
 	struct perf_session *session;
 
 	setup_pager();
-	if (perf_sched__read_events(sched, false, &session))
+
+	/* save session -- references to threads are held in work_list */
+	if (perf_sched__read_events(sched, &session))
 		return -1;
+
 	perf_sched__sort_lat(sched);
 
 	printf("\n ---------------------------------------------------------------------------------------------------------------\n");

@@ -1565,7 +1567,7 @@ static int perf_sched__map(struct perf_sched *sched)
 	sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
 	setup_pager();
-	if (perf_sched__read_events(sched, true, NULL))
+	if (perf_sched__read_events(sched, NULL))
 		return -1;
 	print_bad_events(sched);
 	return 0;

@@ -1580,7 +1582,7 @@ static int perf_sched__replay(struct perf_sched *sched)
 
 	test_calibrations(sched);
 
-	if (perf_sched__read_events(sched, true, NULL))
+	if (perf_sched__read_events(sched, NULL))
 		return -1;
 
 	printf("nr_run_events:        %ld\n", sched->nr_run_events);

index 34ce57d..5285024 100644
@@ -1425,15 +1425,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 						 struct perf_evsel *evsel,
 						 struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, sample->tid);
 	int err = 0;
 
-	if (thread == NULL) {
-		pr_debug("problem processing %s event, skipping it.\n",
-			 perf_evsel__name(evsel));
-		return -1;
-	}
-
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 

index 5285024..42f4587 100644
@@ -1392,15 +1392,6 @@ static int process_sched_fork_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int process_sched_exit_event(struct perf_tool *tool __maybe_unused,
-				    struct perf_evsel *evsel,
-				    struct perf_sample *sample __maybe_unused,
-				    struct machine *machine __maybe_unused)
-{
-	pr_debug("sched_exit event %p\n", evsel);
-	return 0;
-}
-
 static int process_sched_migrate_task_event(struct perf_tool *tool,
 					    struct perf_evsel *evsel,
 					    struct perf_sample *sample,

@@ -1447,7 +1438,6 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		{ "sched:sched_wakeup",	      process_sched_wakeup_event, },
 		{ "sched:sched_wakeup_new",   process_sched_wakeup_event, },
 		{ "sched:sched_process_fork", process_sched_fork_event, },
-		{ "sched:sched_process_exit", process_sched_exit_event, },
 		{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
 	};
 	struct perf_session *session;

@@ -1634,7 +1624,6 @@ static int __cmd_record(int argc, const char **argv)
 		"-e", "sched:sched_stat_sleep",
 		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
-		"-e", "sched:sched_process_exit",
 		"-e", "sched:sched_process_fork",
 		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_migrate_task",

index 42f4587..f809cc7 100644
@@ -109,8 +109,9 @@ struct trace_sched_handler {
 	int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine);
 
-	int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel,
-			  struct perf_sample *sample);
+	/* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
+	int (*fork_event)(struct perf_sched *sched, union perf_event *event,
+			  struct machine *machine);
 
 	int (*migrate_task_event)(struct perf_sched *sched,
 				  struct perf_evsel *evsel,

@@ -717,22 +718,29 @@ static int replay_switch_event(struct perf_sched *sched,
 	return 0;
 }
 
-static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel,
-			     struct perf_sample *sample)
+static int replay_fork_event(struct perf_sched *sched,
+			     union perf_event *event,
+			     struct machine *machine)
 {
-	const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"),
-		   *child_comm  = perf_evsel__strval(evsel, sample, "child_comm");
-	const u32 parent_pid  = perf_evsel__intval(evsel, sample, "parent_pid"),
-		  child_pid  = perf_evsel__intval(evsel, sample, "child_pid");
+	struct thread *child, *parent;
+
+	child = machine__findnew_thread(machine, event->fork.tid);
+	parent = machine__findnew_thread(machine, event->fork.ptid);
+
+	if (child == NULL || parent == NULL) {
+		pr_debug("thread does not exist on fork event: child %p, parent %p\n",
+				 child, parent);
+		return 0;
+	}
 
 	if (verbose) {
-		printf("sched_fork event %p\n", evsel);
-		printf("... parent: %s/%d\n", parent_comm, parent_pid);
-		printf("...  child: %s/%d\n", child_comm, child_pid);
+		printf("fork event\n");
+		printf("... parent: %s/%d\n", parent->comm, parent->tid);
+		printf("...  child: %s/%d\n", child->comm, child->tid);
 	}
 
-	register_pid(sched, parent_pid, parent_comm);
-	register_pid(sched, child_pid, child_comm);
+	register_pid(sched, parent->tid, parent->comm);
+	register_pid(sched, child->tid, child->comm);
 	return 0;
 }
 

@@ -824,14 +832,6 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
 	return 0;
 }
 
-static int latency_fork_event(struct perf_sched *sched __maybe_unused,
-			      struct perf_evsel *evsel __maybe_unused,
-			      struct perf_sample *sample __maybe_unused)
-{
-	/* should insert the newcomer */
-	return 0;
-}
-
 static char sched_out_state(u64 prev_state)
 {
 	const char *str = TASK_STATE_TO_CHAR_STR;

@@ -1379,15 +1379,19 @@ static int process_sched_runtime_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int process_sched_fork_event(struct perf_tool *tool,
-				    struct perf_evsel *evsel,
-				    struct perf_sample *sample,
-				    struct machine *machine __maybe_unused)
+static int perf_sched__process_fork_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct perf_sample *sample,
+					  struct machine *machine)
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
+	/* run the fork event through the perf machineruy */
+	perf_event__process_fork(tool, event, sample, machine);
+
+	/* and then run additional processing needed for this command */
 	if (sched->tp_handler->fork_event)
-		return sched->tp_handler->fork_event(sched, evsel, sample);
+		return sched->tp_handler->fork_event(sched, event, machine);
 
 	return 0;
 }

@@ -1437,7 +1441,6 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		{ "sched:sched_stat_runtime", process_sched_runtime_event, },
 		{ "sched:sched_wakeup",	      process_sched_wakeup_event, },
 		{ "sched:sched_wakeup_new",   process_sched_wakeup_event, },
-		{ "sched:sched_process_fork", process_sched_fork_event, },
 		{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
 	};
 	struct perf_session *session;

@@ -1652,7 +1655,7 @@ static struct perf_sched sched = {
 		.sample		 = perf_sched__process_tracepoint_sample,
 		.comm		 = perf_event__process_comm,
 		.lost		 = perf_event__process_lost,
-		.fork		 = perf_event__process_fork,
+		.fork		 = perf_sched__process_fork_event,
 		.ordered_samples = true,
 	},
 	.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),

@@ -1714,7 +1717,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.wakeup_event	    = latency_wakeup_event,
 		.switch_event	    = latency_switch_event,
 		.runtime_event	    = latency_runtime_event,
-		.fork_event	    = latency_fork_event,
 		.migrate_task_event = latency_migrate_task_event,
 	};
 	struct trace_sched_handler map_ops  = {

index 77f3b95..c655b9e 100644
@@ -509,6 +509,46 @@ static u8 kallsyms2elf_type(char type)
 	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
 }
 
+static bool is_idle_sym(const char *name)
+{
+	static const char * const idle_symbols[] = {
+		"cpu_idle",
+		"intel_idle",
+		"default_idle",
+		"native_safe_halt",
+		"enter_idle",
+		"exit_idle",
+		"mwait_idle",
+		"mwait_idle_with_hints",
+		"poll_idle",
+		"ppc64_runlatch_off",
+		"pseries_dedicated_idle_sleep",
+		NULL
+	};
+
+	int i;
+
+	for (i = 0; idle_symbols[i]; i++) {
+		if (!strcmp(idle_symbols[i], name))
+			return true;
+	}
+
+	return false;
+}
+
+bool symbol__is_idle(struct symbol *sym)
+{
+	if (!sym)
+		return false;
+
+	if (!sym->idle_checked) {
+		sym->is_idle = is_idle_sym(sym->name);
+		sym->idle_checked = true;
+	}
+
+	return sym->is_idle;
+}
+
 static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {

@@ -527,6 +567,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
+
+	sym->is_idle = is_idle_sym(name);
+	sym->idle_checked = true;
+
 	/*
 	 * We will pass the symbols to the filter later, in
 	 * map__split_kallsyms, when we have split the maps per module

index fd5b70e..c163ba9 100644
@@ -59,7 +59,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 
 /** struct symbol - symtab entry
  *
- * @ignore - resolvable but tools ignore it (e.g. idle routines)
+ * @ignore - resolvable but perf-top ignores it (e.g. idle routines)
  */
 struct symbol {
 	struct rb_node	rb_node;

@@ -68,6 +68,8 @@ struct symbol {
 	u16		namelen;
 	u8		binding;
 	bool		ignore;
+	bool		is_idle;  /* pertains to kernel symbols only */
+	bool		idle_checked;
 	char		name[0];
 };
 

@@ -236,6 +238,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,

index 440c3b3..8eb0e3a 100644
@@ -634,26 +634,9 @@ repeat:
 	return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-	"intel_idle",
-	"default_idle",
-	"native_safe_halt",
-	"cpu_idle",
-	"enter_idle",
-	"exit_idle",
-	"mwait_idle",
-	"mwait_idle_with_hints",
-	"poll_idle",
-	"ppc64_runlatch_off",
-	"pseries_dedicated_idle_sleep",
-	NULL
-};
-
 static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
 	const char *name = sym->name;
-	int i;
 
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the

@@ -671,12 +654,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	    strstr(name, "_text_end"))
 		return 1;
 
-	for (i = 0; skip_symbols[i]; i++) {
-		if (!strcmp(skip_symbols[i], name)) {
-			sym->ignore = true;
-			break;
-		}
-	}
+	if (symbol__is_idle(sym))
+		sym->ignore = true;
 
 	return 0;
 }

index c655b9e..1f777f9 100644
@@ -1192,6 +1192,8 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
 		dso__set_long_name(dso, (char *)vmlinux);
 		dso__set_loaded(dso, map->type);
+		if (symbol_conf.vmlinux_name == NULL)
+			symbol_conf.vmlinux_name = strdup(symfs_vmlinux);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
 

@@ -1325,8 +1327,11 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 
 do_kallsyms:
 	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
-	if (err > 0)
+	if (err > 0) {
+		if (symbol_conf.kallsyms_name == NULL)
+			symbol_conf.kallsyms_name = strdup(kallsyms_filename);
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
+	}
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {

index cd616ff..ee5d6f8 100644
@@ -66,6 +66,7 @@ struct output_option {
 static struct {
 	bool user_set;
 	bool wildcard_set;
+	unsigned int print_ip_opts;
 	u64 fields;
 	u64 invalid_fields;
 } output[PERF_TYPE_MAX] = {

@@ -235,6 +236,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 {
 	int j;
 	struct perf_evsel *evsel;
+	struct perf_event_attr *attr;
 
 	for (j = 0; j < PERF_TYPE_MAX; ++j) {
 		evsel = perf_session__find_first_evtype(session, j);

@@ -253,6 +255,24 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		if (evsel && output[j].fields &&
 			perf_evsel__check_attr(evsel, session))
 			return -1;
+
+		if (evsel == NULL)
+			continue;
+
+		attr = &evsel->attr;
+
+		output[j].print_ip_opts = 0;
+		if (PRINT_FIELD(IP))
+			output[j].print_ip_opts |= PRINT_IP_OPT_IP;
+
+		if (PRINT_FIELD(SYM))
+			output[j].print_ip_opts |= PRINT_IP_OPT_SYM;
+
+		if (PRINT_FIELD(DSO))
+			output[j].print_ip_opts |= PRINT_IP_OPT_DSO;
+
+		if (PRINT_FIELD(SYMOFFSET))
+			output[j].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
 	}
 
 	return 0;

@@ -382,8 +402,7 @@ static void print_sample_bts(union perf_event *event,
 		else
 			printf("\n");
 		perf_evsel__print_ip(evsel, event, sample, machine,
-				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
-				     PRINT_FIELD(SYMOFFSET));
+				     output[attr->type].print_ip_opts);
 	}
 
 	printf(" => ");

@@ -423,9 +442,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 			printf(" ");
 		else
 			printf("\n");
+
 		perf_evsel__print_ip(evsel, event, sample, machine,
-				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
-				     PRINT_FIELD(SYMOFFSET));
+				     output[attr->type].print_ip_opts);
 	}
 
 	printf("\n");

index dedaeb2..e5fd658 100644
@@ -1489,10 +1489,14 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			  struct perf_sample *sample, struct machine *machine,
-			  int print_sym, int print_dso, int print_symoffset)
+			  unsigned int print_opts)
 {
 	struct addr_location al;
 	struct callchain_cursor_node *node;
+	int print_ip = print_opts & PRINT_IP_OPT_IP;
+	int print_sym = print_opts & PRINT_IP_OPT_SYM;
+	int print_dso = print_opts & PRINT_IP_OPT_DSO;
+	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample,
 					  NULL) < 0) {

@@ -1516,7 +1520,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!node)
 				break;
 
-			printf("\t%16" PRIx64, node->ip);
+			if (print_ip)
+				printf("%16" PRIx64, node->ip);
+
 			if (print_sym) {
 				printf(" ");
 				if (print_symoffset) {

@@ -1537,7 +1543,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 		}
 
 	} else {
-		printf("%16" PRIx64, sample->ip);
+		if (print_ip)
+			printf("%16" PRIx64, sample->ip);
+
 		if (print_sym) {
 			printf(" ");
 			if (print_symoffset)

index 8bed17e..69e554a 100644
@@ -41,6 +41,11 @@ struct perf_session {
 	char			filename[1];
 };
 
+#define PRINT_IP_OPT_IP		(1<<0)
+#define PRINT_IP_OPT_SYM		(1<<1)
+#define PRINT_IP_OPT_DSO		(1<<2)
+#define PRINT_IP_OPT_SYMOFFSET	(1<<3)
+
 struct perf_tool;
 
 struct perf_session *perf_session__new(const char *filename, int mode,

@@ -103,7 +108,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			  struct perf_sample *sample, struct machine *machine,
-			  int print_sym, int print_dso, int print_symoffset);
+			  unsigned int print_opts);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);

index e5fd658..0d895e7 100644
@@ -1497,6 +1497,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 	int print_sym = print_opts & PRINT_IP_OPT_SYM;
 	int print_dso = print_opts & PRINT_IP_OPT_DSO;
 	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
+	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+	char s = print_oneline ? ' ' : '\t';
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample,
 					  NULL) < 0) {

@@ -1521,7 +1523,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 				break;
 
 			if (print_ip)
-				printf("%16" PRIx64, node->ip);
+				printf("%c%16" PRIx64, s, node->ip);
 
 			if (print_sym) {
 				printf(" ");

@@ -1537,7 +1539,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 				map__fprintf_dsoname(node->map, stdout);
 				printf(")");
 			}
-			printf("\n");
+
+			if (!print_oneline)
+				printf("\n");
 
 			callchain_cursor_advance(&callchain_cursor);
 		}

index 69e554a..7c00ccb 100644
@@ -45,6 +45,7 @@ struct perf_session {
 #define PRINT_IP_OPT_SYM		(1<<1)
 #define PRINT_IP_OPT_DSO		(1<<2)
 #define PRINT_IP_OPT_SYMOFFSET	(1<<3)
+#define PRINT_IP_OPT_ONELINE	(1<<4)
 
 struct perf_tool;
 

index ee5d6f8..33b2d83 100644
@@ -402,7 +402,8 @@ static void print_sample_bts(union perf_event *event,
 		else
 			printf("\n");
 		perf_evsel__print_ip(evsel, event, sample, machine,
-				     output[attr->type].print_ip_opts);
+				     output[attr->type].print_ip_opts,
+				     PERF_MAX_STACK_DEPTH);
 	}
 
 	printf(" => ");

@@ -444,7 +445,8 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 			printf("\n");
 
 		perf_evsel__print_ip(evsel, event, sample, machine,
-				     output[attr->type].print_ip_opts);
+				     output[attr->type].print_ip_opts,
+				     PERF_MAX_STACK_DEPTH);
 	}
 
 	printf("\n");

index 0d895e7..5a89964 100644
@@ -1489,7 +1489,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			  struct perf_sample *sample, struct machine *machine,
-			  unsigned int print_opts)
+			  unsigned int print_opts, unsigned int stack_depth)
 {
 	struct addr_location al;
 	struct callchain_cursor_node *node;

@@ -1517,7 +1517,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 		}
 		callchain_cursor_commit(&callchain_cursor);
 
-		while (1) {
+		while (stack_depth) {
 			node = callchain_cursor_current(&callchain_cursor);
 			if (!node)
 				break;

@@ -1544,6 +1544,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 				printf("\n");
 
 			callchain_cursor_advance(&callchain_cursor);
+
+			stack_depth--;
 		}
 
 	} else {

index 7c00ccb..3aa75fb 100644
@@ -109,7 +109,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			  struct perf_sample *sample, struct machine *machine,
-			  unsigned int print_opts);
+			  unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);

index 1f777f9..4c90a7a 100644
@@ -549,6 +549,18 @@ bool symbol__is_idle(struct symbol *sym)
 	return sym->is_idle;
 }
 
+bool symbol__is_excluded(struct symbol *sym)
+{
+	if (sym == NULL)
+		return false;
+
+	if (symbol_conf.excl_sym_list &&
+	    strlist__has_entry(symbol_conf.excl_sym_list, sym->name))
+		return true;
+
+	return false;
+}
+
 static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {

@@ -1518,6 +1530,10 @@ int symbol__init(void)
 		       symbol_conf.sym_list_str, "symbol") < 0)
 		goto out_free_comm_list;
 
+	if (setup_list(&symbol_conf.excl_sym_list,
+		       symbol_conf.excl_sym_list_str, "exclude symbol") < 0)
+		goto out_free_sym_list;
+
 	/*
 	 * A path to symbols of "/" is identical to ""
 	 * reset here for simplicity.

@@ -1535,6 +1551,8 @@ int symbol__init(void)
 	symbol_conf.initialized = true;
 	return 0;
 
+out_free_sym_list:
+	strlist__delete(symbol_conf.sym_list);
 out_free_comm_list:
 	strlist__delete(symbol_conf.comm_list);
 out_free_dso_list:

@@ -1546,10 +1564,12 @@ void symbol__exit(void)
 {
 	if (!symbol_conf.initialized)
 		return;
+	strlist__delete(symbol_conf.excl_sym_list);
 	strlist__delete(symbol_conf.sym_list);
 	strlist__delete(symbol_conf.dso_list);
 	strlist__delete(symbol_conf.comm_list);
 	vmlinux_path__exit();
+	symbol_conf.excl_sym_list = NULL;
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }

index c163ba9..9501213 100644
@@ -112,10 +112,12 @@ struct symbol_conf {
 	const char	*dso_list_str,
 			*comm_list_str,
 			*sym_list_str,
+			*excl_sym_list_str,
 			*col_width_list_str;
        struct strlist	*dso_list,
 			*comm_list,
 			*sym_list,
+			*excl_sym_list,
 			*dso_from_list,
 			*dso_to_list,
 			*sym_from_list,

@@ -239,6 +241,7 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 bool symbol__is_idle(struct symbol *sym);
+bool symbol__is_excluded(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,

index 5a89964..0eada12 100644
@@ -1522,6 +1522,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!node)
 				break;
 
+			if (symbol__is_excluded(node->sym))
+				goto next;
+
 			if (print_ip)
 				printf("%c%16" PRIx64, s, node->ip);
 

@@ -1543,9 +1546,10 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!print_oneline)
 				printf("\n");
 
-			callchain_cursor_advance(&callchain_cursor);
-
 			stack_depth--;
+
+next:
+			callchain_cursor_advance(&callchain_cursor);
 		}
 
 	} else {

index f809cc7..1ec1ff4 100644
@@ -1415,7 +1415,7 @@ typedef int (*tracepoint_handler)(struct perf_tool *tool,
 				  struct machine *machine);
 
 static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
-						 union perf_event *event __maybe_unused,
+						 union perf_event *event,
 						 struct perf_sample *sample,
 						 struct perf_evsel *evsel,
 						 struct machine *machine)

@@ -1427,6 +1427,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;
+		evsel->handler.data = event;
 		err = f(tool, evsel, sample, machine);
 	}
 

index 1ec1ff4..a45a40f 100644
@@ -16,6 +16,8 @@
 
 #include "util/debug.h"
 
+#include "util/strlist.h"
+#include "asm/bug.h"
 #include <sys/prctl.h>
 #include <sys/resource.h>
 

@@ -169,8 +171,39 @@ struct perf_sched {
 	u64		 cpu_last_switched[MAX_CPUS];
 	struct rb_root	 atom_root, sorted_atom_root;
 	struct list_head sort_list, cmp_pid;
+
+	/* options for timehist command */
+	bool		show_events;
+	bool		no_callchain;
+	unsigned int	max_stack_depth;
+	bool		show_cpu_visual;
+};
+
+/* per thread run time data */
+struct thread_runtime {
+	u64 dt_run;
+	u64 dt_between;
+	u64 last_time;
+
+	u64 count;
+	u64 total_run_time;
+	u64 min_run_time;
+	u64 max_run_time;
+	double mean, M2;
+	char commstr[32];
+};
+
+/* per event run time data */
+struct evsel_runtime {
+	u64 *last_time; /* time this event was last seen per cpu */
+	u32 ncpu;       /* highest cpu slot allocated */
 };
 
+/* track idle times per cpu */
+static struct thread **idle_threads;
+static int idle_max_cpu;
+static char idle_comm[] = "<idle>";
+
 static u64 get_nsecs(void)
 {
 	struct timespec ts;

@@ -1479,6 +1512,652 @@ out_delete:
 	return -1;
 }
 
+static inline void printf_nsecs(unsigned long long nsecs, int width_sec)
+{
+	unsigned long secs;
+	unsigned long usecs;
+
+	secs = nsecs / NSECS_PER_SEC;
+	nsecs -= secs * NSECS_PER_SEC;
+	usecs = nsecs / NSECS_PER_USEC;
+	printf("%*lu.%06lu ", width_sec, secs, usecs);
+}
+
+static struct evsel_runtime *perf_evsel__get_runtime(struct perf_evsel *evsel)
+{
+	struct evsel_runtime *r = evsel->priv;
+
+	if (r == NULL) {
+		r = zalloc(sizeof(struct evsel_runtime));
+		evsel->priv = r;
+	}
+
+	return r;
+}
+
+static void perf_evsel__save_time(struct perf_evsel *evsel,
+				  u64 timestamp, u32 cpu)
+{
+	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+
+	if (r == NULL)
+		return;
+
+	if ((cpu > r->ncpu) || (r->last_time == NULL)) {
+		unsigned int i;
+		void *p = r->last_time;
+
+		r->last_time = realloc(r->last_time, (cpu+1) * sizeof(u64));
+		if (!r->last_time) {
+			free(p);
+			return;
+		}
+
+		i = r->ncpu ? r->ncpu + 1 : 0;
+		for (; i <= cpu; ++i)
+			r->last_time[i] = (u64) 0;
+
+		r->ncpu = cpu;
+	}
+
+	r->last_time[cpu] = timestamp;
+}
+
+static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu)
+{
+	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+
+	if (r == NULL)
+		return 0;
+
+	if (!r->last_time)
+		return 0;
+
+	if ((cpu > r->ncpu) || (r->last_time == NULL))
+		return 0;
+
+	return r->last_time[cpu];
+}
+
+static void timehist_header(struct perf_sched *sched)
+{
+	u32 max_cpus = sched->max_cpu;
+	u32 i, j;
+
+	printf("%-15s %-4s", "time", "cpu");
+
+	if (sched->show_cpu_visual && max_cpus) {
+		printf(" ");
+		for (i = 0, j = 0; i < max_cpus; ++i) {
+			printf("%x", j++);
+			if (j > 15)
+				j = 0;
+		}
+		printf(" ");
+	}
+
+	printf(" %-20s %9s %9s",
+		"task name[tid/pid]", "b/n time", "run time");
+
+	printf("\n");
+
+	printf("%15s %4s", "---------------", "----");
+
+	if (sched->show_cpu_visual && max_cpus) {
+		printf(" ");
+		for (i = 0; i < max_cpus; ++i)
+			printf("-");
+		printf(" ");
+	}
+
+	printf(" %20s %9s %9s",
+		"--------------------", "---------", "---------");
+
+	printf("\n");
+}
+
+static char *timehist_time_str(char *tstr, int len, u64 t)
+{
+	unsigned long secs, usecs;
+	unsigned long long nsecs;
+
+	nsecs = t;
+	secs = nsecs / NSECS_PER_SEC;
+	nsecs -= secs * NSECS_PER_SEC;
+	usecs = nsecs / NSECS_PER_USEC;
+	snprintf(tstr, len, "%5lu.%06lu", secs, usecs);
+
+	return tstr;
+}
+
+static unsigned int comm_width = 20;
+
+static void timehist_print_sample(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  struct thread *thread,
+				  struct machine *machine)
+{
+	struct thread_runtime *tr = thread__priv(thread);
+	union perf_event *event = evsel->handler.data;
+	char tstr[64];
+	u32 max_cpus = sched->max_cpu;
+
+	printf("%15s ", timehist_time_str(tstr, sizeof(tstr), sample->time));
+
+	printf("[%02d] ", sample->cpu);
+
+	if (sched->show_cpu_visual && max_cpus) {
+		u32 i;
+		char c;
+		for (i = 0; i < max_cpus; ++i) {
+			c = i == sample->cpu ? 's' : ' ';
+			printf("%c", c);
+		}
+		printf("  ");
+	}
+
+	printf("%-*s ", comm_width, tr->commstr);
+
+	printf_nsecs(tr->dt_between, 2);
+	printf_nsecs(tr->dt_run, 2);
+
+	perf_evsel__print_ip(evsel, event, sample, machine,
+			     PRINT_IP_OPT_SYM | PRINT_IP_OPT_ONELINE,
+			     sched->max_stack_depth);
+
+	printf("\n");
+}
+
+static int timehist_check_attr(struct perf_sched *sched,
+			       struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct evsel_runtime *er;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		er = perf_evsel__get_runtime(evsel);
+		if (er == NULL) {
+			pr_err("Failed to allocate memory for evsel runtime data\n");
+			return -1;
+		}
+
+		if (!sched->no_callchain &&
+		    !(evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			sched->no_callchain = 1;
+			symbol_conf.use_callchain = 0;
+		}
+	}
+
+	return 0;
+}
+
+static bool is_idle_sample(struct perf_sample *sample,
+			   struct perf_evsel *evsel,
+			   struct machine *machine)
+{
+	struct thread *thread;
+	struct callchain_cursor *cursor = &callchain_cursor;
+	struct callchain_cursor_node *node;
+	struct addr_location al;
+	int iter = 5;
+
+	/* pid 0 == swapper == idle task */
+	if (sample->pid == 0)
+		return true;
+
+	/* want main thread for process - has maps */
+	thread = machine__findnew_thread(machine, sample->pid);
+	if (thread == NULL) {
+		pr_debug("Failed to get thread for pid %d.\n", sample->pid);
+		return false;
+	}
+
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
+		return false;
+
+	if (machine__resolve_callchain(machine, evsel, thread,
+					sample, NULL, &al) != 0) {
+		if (verbose)
+			error("Failed to resolve callchain. Skipping\n");
+
+		return false;
+	}
+	callchain_cursor_commit(cursor);
+
+	/* idle symbol should be early in the stack */
+	while (iter) {
+		node = callchain_cursor_current(cursor);
+		if (!node)
+			break;
+
+		if (symbol__is_idle(node->sym))
+			return true;
+
+		callchain_cursor_advance(cursor);
+
+		iter--;
+	}
+
+	return false;
+}
+
+static void timehist_update_thread_stats(struct thread_runtime *r,
+					 u64 t, u64 dt_run)
+{
+	u64 dt_task = 0;
+	double delta;
+
+	r->count++;
+
+	/* current run time and total run time */
+	r->dt_run = dt_run;
+	r->total_run_time += dt_run;
+
+	/* time b/n sched events for task */
+	if (r->last_time)
+		dt_task = t - r->last_time;
+
+	/* subtract run time for this event to get time between
+	 * sched in events - i.e., how long between accesses to CPU
+	 */
+	if (dt_task > dt_run)
+		r->dt_between = dt_task - dt_run;
+
+	/*
+	 * update average and stddev stats
+	 */
+	delta    = dt_run - r->mean;
+	r->mean += delta / r->count;
+	r->M2   += delta * (dt_run - r->mean);
+
+	if (dt_run > r->max_run_time)
+		r->max_run_time = dt_run;
+
+	if (dt_run < r->min_run_time)
+		r->min_run_time = dt_run;
+}
+
+static struct thread *get_idle_thread(int cpu)
+{
+	/* expand/allocate array of pointers to local thread
+	 * structs if needed
+	 */
+	if ((cpu > idle_max_cpu) || (idle_threads == NULL)) {
+		int i, j = 15;
+		void *p;
+
+		if (cpu > j)
+			j = cpu;
+		p = realloc(idle_threads, (j+1) * sizeof(struct thread *));
+		if (!p)
+			return NULL;
+
+		idle_threads = (struct thread **) p;
+		i = idle_max_cpu ? idle_max_cpu + 1 : 0;
+		for (; i <= cpu; ++i)
+			idle_threads[i] = NULL;
+
+		idle_max_cpu = cpu;
+	}
+
+	/* allocate the actual thread struct if needed */
+	if (idle_threads[cpu] == NULL) {
+		idle_threads[cpu] = zalloc(sizeof(struct thread));
+		if (idle_threads[cpu]) {
+			idle_threads[cpu]->tid = 0;
+			idle_threads[cpu]->comm = idle_comm;
+		}
+	}
+
+	return idle_threads[cpu];
+}
+
+static void timehist_set_commstr(struct thread_runtime *r,
+				 const char *comm,
+				 pid_t pid, pid_t tid)
+{
+	unsigned int i, n;
+
+	if ((r == NULL) || (*r->commstr != '\0'))
+		return;
+
+	if (pid == 0) {
+		snprintf(r->commstr, sizeof(r->commstr)-1, "%s", comm);
+
+	} else if (tid != pid) {
+		snprintf(r->commstr, sizeof(r->commstr)-1, "%s[%d/%d]",
+			 comm, tid, pid);
+	} else {
+		snprintf(r->commstr, sizeof(r->commstr)-1, "%s[%d]",
+			 comm, tid);
+	}
+
+	for (i = 0; i < strlen(r->commstr); ++i) {
+		if (r->commstr[i] == ' ')
+			r->commstr[i] = '-';
+	}
+
+	n = strlen(r->commstr);
+	if (n > comm_width)
+		comm_width = n;
+}
+
+static struct thread_runtime *thread__init_runtime(struct thread *thread, pid_t pid)
+{
+	struct thread_runtime *r;
+
+	r = zalloc(sizeof(struct thread_runtime));
+	if (!r)
+		return NULL;
+
+	r->min_run_time = (u64) -1;
+	thread__set_priv(thread, r);
+
+	/* optimization - saving comm string used in stack dump */
+	timehist_set_commstr(r, thread->comm, pid, thread->tid);
+
+	return r;
+}
+
+static struct thread *timehist_get_thread(struct perf_evsel *evsel,
+					  struct perf_sample *sample,
+					  struct machine *machine)
+{
+	struct thread *thread;
+
+	if (is_idle_sample(sample, evsel, machine)) {
+		thread = get_idle_thread(sample->cpu);
+		if (thread == NULL)
+			pr_err("failed to get idle thread for cpu %d.\n", sample->cpu);
+
+	} else {
+		thread = machine__findnew_thread(machine, sample->tid);
+		if (thread == NULL) {
+			pr_debug("Failed to get thread for tid %d. skipping sample.\n",
+				 sample->tid);
+		}
+	}
+
+	return thread;
+}
+
+static int timehist_sched_change_event(struct perf_tool *tool,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       struct machine *machine)
+{
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	struct thread *thread;
+	struct thread_runtime *tr = NULL;
+	u64 dt_run = 0, tprev;
+	int rc = 0;
+
+	thread = timehist_get_thread(evsel, sample, machine);
+	if (thread == NULL) {
+		rc = -1;
+		goto out;
+	}
+
+	tr = thread__priv(thread);
+	if (tr == NULL) {
+		/* pid argument is not needed once Adrian's patch is picked up */
+		tr = thread__init_runtime(thread, sample->pid);
+		if (tr == NULL) {
+			pr_debug("failed to malloc memory for runtime data.\n");
+			rc = -1;
+			goto out;
+		}
+	}
+
+	tprev = perf_evsel__get_time(evsel, sample->cpu);
+	if (tprev)
+		dt_run = sample->time - tprev;
+
+	timehist_update_thread_stats(tr, sample->time, dt_run);
+	if (sched->show_events)
+		timehist_print_sample(sched, evsel, sample, thread, machine);
+
+out:
+	if (tr)
+		tr->last_time = sample->time;
+	perf_evsel__save_time(evsel, sample->time, sample->cpu);
+
+	return rc;
+}
+
+static int timehist_sched_switch_event(struct perf_tool *tool,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct machine *machine)
+{
+	return timehist_sched_change_event(tool, evsel, sample, machine);
+}
+
+static int process_lost(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine __maybe_unused)
+{
+	char tstr[64];
+
+	printf("%15s ", timehist_time_str(tstr, sizeof(tstr), sample->time));
+	printf("lost %" PRIu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
+
+	return 0;
+}
+
+
+static void print_thread_runtime(struct thread *t, struct thread_runtime *r)
+{
+	double variance;
+	float stddev;
+
+	printf("    %*s  %5d  %6" PRIu64 "  ",
+	       comm_width, r->commstr, t->ppid, r->count);
+
+	printf_nsecs(r->total_run_time, 2);
+	if (r->count > 1) {
+		variance = r->M2 / (r->count - 1);
+		stddev = 100.0 * sqrt(variance / r->count) / r->mean;
+
+		printf(" ");
+		printf_nsecs(r->min_run_time, 2);
+		printf(" ");
+		printf_nsecs(r->max_run_time, 2);
+		printf(" ");
+		printf_nsecs((u64) r->mean, 2);
+		printf(" ");
+		printf("%5.2f", stddev);
+	}
+	printf("\n");
+}
+
+static void timehist_print_summary(struct perf_session *session)
+{
+	struct machine *m = &session->machines.host;
+	struct rb_node *nd;
+	struct thread *t;
+	struct thread_runtime *r;
+	u64 total_run_time = 0;
+	u64 total_count = 0;
+	int i, total_task = 0;
+
+	printf("\nRuntime summary (times are in seconds)\n");
+	printf("    %*s  parent  number  ", comm_width, "comm");
+	printf("run-time    min-run    max-run   avg-run  stddev(%%)\n");
+
+	nd = rb_first(&m->threads);
+	while (nd) {
+		t = rb_entry(nd, struct thread, rb_node);
+
+		r = thread__priv(t);
+		if (r && r->count) {
+			total_count += r->count;
+			total_run_time += r->total_run_time;
+			total_task++;
+			print_thread_runtime(t, r);
+		}
+
+		nd = rb_next(nd);
+	}
+
+	printf("\nTerminated tasks:\n");
+	list_for_each_entry(t, &m->dead_threads, node) {
+		r = thread__priv(t);
+		if (r && r->count) {
+			total_count += r->count;
+			total_run_time += r->total_run_time;
+			total_task++;
+
+			print_thread_runtime(t, r);
+		}
+	}
+
+	printf("\nIdle stats:\n");
+	for (i = 0; i <= idle_max_cpu; ++i) {
+		t = idle_threads[i];
+		if (!t)
+			continue;
+
+		r = thread__priv(t);
+		if (r && r->count) {
+			total_count += r->count;
+			printf("    CPU %d idle for ", i);
+			printf_nsecs(r->total_run_time, 2);
+			printf("\n");
+		}
+	}
+
+	WARN_ONCE(!symbol_conf.vmlinux_name && !symbol_conf.kallsyms_name,
+		  "kernel symbols not given. If this is an offline analysis idle time computations will be wrong\n");
+
+	printf("\n"
+	       "    Total number of unique tasks: %d\n"
+	       "Total number of context switches: %" PRIu64 "\n"
+	       "            Total run time (sec): ",
+	       total_task, total_count);
+	printf_nsecs(total_run_time, 2);
+	printf("\n");
+}
+static int perf_timehist__process_sample(struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct perf_evsel *evsel,
+					 struct machine *machine)
+{
+	int err = 0;
+
+	evsel->hists.stats.total_period += sample->period;
+	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+
+	if (evsel->handler.func != NULL || verbose) {
+		tracepoint_handler f = evsel->handler.func;
+		evsel->handler.data = event;
+
+		if (f)
+			err = f(tool, evsel, sample, machine);
+	}
+
+	return err;
+}
+
+/* list of symbols to exclude from stack dump */
+static int setup_excl_sym(void)
+{
+	char buf[4096];
+
+	snprintf(buf, sizeof(buf),
+			"schedule,__schedule,"
+			"schedule_timeout,schedule_timeout_interruptible,"
+			"schedule_hrtimeout_range_clock,schedule_hrtimeout_range,"
+			"syscall,system_call_done,ia32_syscall_done,%s",
+			symbol_conf.excl_sym_list_str ? symbol_conf.excl_sym_list_str : "");
+
+	symbol_conf.excl_sym_list_str = strdup(buf);
+
+	return 0;
+}
+
+static int perf_sched__timehist(struct perf_sched *sched)
+{
+	const struct perf_evsel_str_handler handlers[] = {
+		{ "sched:sched_switch",       timehist_sched_switch_event, },
+	};
+
+	struct perf_session *session;
+	int err = -1;
+
+	/*
+	 * event handlers for timehist option
+	 */
+	sched->tool.sample	 = perf_timehist__process_sample;
+	sched->tool.mmap	 = perf_event__process_mmap;
+	sched->tool.comm	 = perf_event__process_comm;
+	sched->tool.exit	 = perf_event__process_exit;
+	sched->tool.fork	 = perf_event__process_fork;
+	sched->tool.lost	 = process_lost;
+	sched->tool.attr	 = perf_event__process_attr;
+	sched->tool.tracing_data = perf_event__process_tracing_data;
+	sched->tool.build_id	 = perf_event__process_build_id;
+
+	sched->tool.ordered_samples = true;
+	sched->tool.ordering_requires_timestamps = true;
+
+	/* if not given default to stack depth of 5 */
+	if (sched->max_stack_depth == 0)
+		sched->max_stack_depth = 5;
+
+	symbol_conf.use_callchain = !sched->no_callchain;
+	setup_excl_sym();
+	if (symbol__init() < 0)
+		return -1;
+
+	session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool);
+	if (session == NULL)
+		return -ENOMEM;
+
+	setup_pager();
+
+	if (timehist_check_attr(sched, session->evlist) != 0)
+		return -ENOMEM;
+
+	perf_session__fprintf_info(session, stdout, true);
+
+	/* pre-allocate struct for per-CPU idle stats */
+	sched->max_cpu = session->header.env.nr_cpus_online;
+	if (sched->max_cpu > 0) {
+		idle_max_cpu = sched->max_cpu - 1;
+		idle_threads = zalloc(sched->max_cpu * sizeof(struct thread *));
+	}
+
+	/* setup per-evsel handlers */
+	if (perf_session__set_tracepoints_handlers(session, handlers))
+		goto out;
+
+	if (perf_session__has_traces(session, "record -R")) {
+		if (sched->show_events)
+			timehist_header(sched);
+
+		err = perf_session__process_events(session, &sched->tool);
+		if (err) {
+			pr_err("Failed to process events, error %d", err);
+			goto out;
+		}
+
+		sched->nr_events      = session->stats.nr_events[0];
+		sched->nr_lost_events = session->stats.total_lost;
+		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
+	}
+
+	timehist_print_summary(session);
+
+out:
+	perf_session__delete(session);
+
+	return err;
+}
+
 static void print_bad_events(struct perf_sched *sched)
 {
 	if (sched->nr_unordered_timestamps && sched->nr_timestamps) {

@@ -1702,6 +2381,36 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "dump raw trace in ASCII"),
 	OPT_END()
 	};
+	const struct option timehist_options[] = {
+	OPT_STRING('i', "input", &input_name, "file",
+		    "input file name"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
+	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+		   "file", "kallsyms pathname"),
+	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+		   "only display events for these comms"),
+	OPT_UINTEGER('s', "stack-depth", &sched.max_stack_depth,
+		   "Maximum number of functions to display backtrace."),
+	OPT_STRING('x', "excl", &symbol_conf.excl_sym_list_str, "sym[,sym...]",
+		   "symbols to skip in backtrace"),
+	OPT_BOOLEAN('G', "hide-call-graph", &sched.no_callchain,
+		    "When printing symbols do not display call chain"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
+	OPT_BOOLEAN(0, "cpu-visual", &sched.show_cpu_visual, "Show CPU visual"),
+	OPT_BOOLEAN(0, "events", &sched.show_events, "show all events"),
+	OPT_END()
+	};
+	const char * const timehist_usage[] = {
+		"perf sched timehist [<options>]",
+		NULL
+	};
+
 	const char * const latency_usage[] = {
 		"perf sched latency [<options>]",
 		NULL

@@ -1740,7 +2449,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!strcmp(argv[0], "script"))
 		return cmd_script(argc, argv, prefix);
 
-	symbol__init();
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strncmp(argv[0], "lat", 3)) {

@@ -1751,10 +2459,12 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 				usage_with_options(latency_usage, latency_options);
 		}
 		setup_sorting(&sched, latency_options, latency_usage);
+		symbol__init();
 		return perf_sched__lat(&sched);
 	} else if (!strcmp(argv[0], "map")) {
 		sched.tp_handler = &map_ops;
 		setup_sorting(&sched, latency_options, latency_usage);
+		symbol__init();
 		return perf_sched__map(&sched);
 	} else if (!strncmp(argv[0], "rep", 3)) {
 		sched.tp_handler = &replay_ops;

@@ -1763,7 +2473,17 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (argc)
 				usage_with_options(replay_usage, replay_options);
 		}
+		symbol__init();
 		return perf_sched__replay(&sched);
+	} else if (!strcmp(argv[0], "timehist")) {
+		if (argc) {
+			argc = parse_options(argc, argv, timehist_options,
+					     timehist_usage, 0);
+			if (argc)
+				usage_with_options(timehist_usage, timehist_options);
+		}
+
+		return perf_sched__timehist(&sched);
 	} else {
 		usage_with_options(sched_usage, sched_options);
 	}

index 0eada12..83bdcfa 100644
@@ -1401,12 +1401,15 @@ int perf_session__process_events(struct perf_session *self,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
-		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
-		return false;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
+			return true;
 	}
 
-	return true;
+	pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
+	return false;
 }
 
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps,

index a45a40f..f5e98f1 100644
@@ -177,6 +177,7 @@ struct perf_sched {
 	bool		no_callchain;
 	unsigned int	max_stack_depth;
 	bool		show_cpu_visual;
+	bool		skip_cs;
 };
 
 /* per thread run time data */

@@ -1674,8 +1675,17 @@ static int timehist_check_attr(struct perf_sched *sched,
 {
 	struct perf_evsel *evsel;
 	struct evsel_runtime *er;
+	const char *evname;
+	bool have_cs_event = false, have_sched_event = false;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
+		evname = perf_evsel__name(evsel);
+		if (strcmp(evname, "cs") == 0 ||
+		    strcmp(evname, "context-switch") == 0)
+			have_cs_event = true;
+		else if (strcmp(evname, "sched:sched_switch") == 0)
+			have_sched_event = true;
+
 		er = perf_evsel__get_runtime(evsel);
 		if (er == NULL) {
 			pr_err("Failed to allocate memory for evsel runtime data\n");

@@ -1689,6 +1699,11 @@ static int timehist_check_attr(struct perf_sched *sched,
 		}
 	}
 
+	if (have_cs_event && have_sched_event) {
+		pr_debug("Both schedule change events exist. Ignoring context-switch event\n");
+		sched->skip_cs = true;
+	}
+
 	return 0;
 }
 

@@ -1926,6 +1941,30 @@ out:
 	return rc;
 }
 
+static int timehist_cs_event(struct perf_tool *tool __maybe_unused,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct machine *machine __maybe_unused)
+{
+	return timehist_sched_change_event(tool, evsel, sample, machine);
+}
+
+static void timehist_set_cs_handler(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	const char *evname;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		evname = perf_evsel__name(evsel);
+		if (strcmp(evname, "cs") == 0 ||
+		    strcmp(evname, "context-switch") == 0) {
+			evsel->handler.func = timehist_cs_event;
+		}
+	}
+
+	return;
+}
+
 static int timehist_sched_switch_event(struct perf_tool *tool,
 			       struct perf_evsel *evsel,
 			       struct perf_sample *sample,

@@ -2132,24 +2171,26 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	}
 
 	/* setup per-evsel handlers */
-	if (perf_session__set_tracepoints_handlers(session, handlers))
-		goto out;
+	if (!sched->skip_cs)
+		timehist_set_cs_handler(session->evlist);
 
-	if (perf_session__has_traces(session, "record -R")) {
-		if (sched->show_events)
-			timehist_header(sched);
+	if (perf_session__has_traces(session, "sched record") &&
+	    perf_session__set_tracepoints_handlers(session, handlers))
+		goto out;
 
-		err = perf_session__process_events(session, &sched->tool);
-		if (err) {
-			pr_err("Failed to process events, error %d", err);
-			goto out;
-		}
+	if (sched->show_events)
+		timehist_header(sched);
 
-		sched->nr_events      = session->stats.nr_events[0];
-		sched->nr_lost_events = session->stats.total_lost;
-		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
+	err = perf_session__process_events(session, &sched->tool);
+	if (err) {
+		pr_err("Failed to process events, error %d", err);
+		goto out;
 	}
 
+	sched->nr_events      = session->stats.nr_events[0];
+	sched->nr_lost_events = session->stats.total_lost;
+	sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
+
 	timehist_print_summary(session);
 
 out:

index f5e98f1..1be9081 100644
@@ -1897,6 +1897,50 @@ static struct thread *timehist_get_thread(struct perf_evsel *evsel,
 	return thread;
 }
 
+static void timehist_print_sched_event(struct perf_tool *tool,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct machine *machine)
+{
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	struct thread *thread;
+	struct thread_runtime *tr;
+	const char *evname;
+	char tstr[64];
+
+	thread = machine__findnew_thread(machine, sample->tid);
+	if (thread == NULL)
+		return;
+
+	tr = thread__priv(thread);
+	if (tr == NULL) {
+		tr = thread__init_runtime(thread, sample->pid);
+		if (tr == NULL)
+			return;
+	}
+
+	printf("%15s ", timehist_time_str(tstr, sizeof(tstr), sample->time));
+	printf("[%02d] ", sample->cpu);
+	if (sched->show_cpu_visual && sched->max_cpu)
+		printf("%*s  ", sched->max_cpu, "");
+
+	printf("%-*s ", comm_width, tr->commstr);
+
+	/* dt spacer */
+	printf(" %9s %9s ", "", "");
+
+	evname = perf_evsel__name(evsel);
+	printf("%s ", evname ? evname : "[unknown]");
+	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+		event_format__print(evsel->tp_format, sample->cpu,
+				    sample->raw_data, sample->raw_size);
+	}
+
+	printf("\n");
+
+	return;
+}
+
 static int timehist_sched_change_event(struct perf_tool *tool,
 				       struct perf_evsel *evsel,
 				       struct perf_sample *sample,

@@ -2079,12 +2123,14 @@ static void timehist_print_summary(struct perf_session *session)
 	printf_nsecs(total_run_time, 2);
 	printf("\n");
 }
+
 static int perf_timehist__process_sample(struct perf_tool *tool,
-					 union perf_event *event,
-					 struct perf_sample *sample,
-					 struct perf_evsel *evsel,
-					 struct machine *machine)
+						 union perf_event *event,
+						 struct perf_sample *sample,
+						 struct perf_evsel *evsel,
+						 struct machine *machine)
 {
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 	int err = 0;
 
 	evsel->hists.stats.total_period += sample->period;

@@ -2094,6 +2140,9 @@ static int perf_timehist__process_sample(struct perf_tool *tool,
 		tracepoint_handler f = evsel->handler.func;
 		evsel->handler.data = event;
 
+		if (sched->show_events && verbose)
+			timehist_print_sched_event(tool, evsel, sample, machine);
+
 		if (f)
 			err = f(tool, evsel, sample, machine);
 	}

index 1be9081..8e6ceee 100644
@@ -17,6 +17,7 @@
 #include "util/debug.h"
 
 #include "util/strlist.h"
+#include "util/intlist.h"
 #include "asm/bug.h"
 #include <sys/prctl.h>
 #include <sys/resource.h>

@@ -178,6 +179,9 @@ struct perf_sched {
 	unsigned int	max_stack_depth;
 	bool		show_cpu_visual;
 	bool		skip_cs;
+	/* process and task id's of interest */
+	struct perf_target target;
+	struct intlist	*pid, *tid;
 };
 
 /* per thread run time data */

@@ -1897,6 +1901,18 @@ static struct thread *timehist_get_thread(struct perf_evsel *evsel,
 	return thread;
 }
 
+static bool timehist_skip_sample(struct perf_sched *sched,
+				       struct perf_sample *sample)
+{
+	if (sched->pid && intlist__find(sched->pid, sample->pid) == NULL)
+		return true;
+
+	if (sched->tid && intlist__find(sched->tid, sample->tid) == NULL)
+		return true;
+
+	return false;
+}
+
 static void timehist_print_sched_event(struct perf_tool *tool,
 			       struct perf_evsel *evsel,
 			       struct perf_sample *sample,

@@ -1908,6 +1924,9 @@ static void timehist_print_sched_event(struct perf_tool *tool,
 	const char *evname;
 	char tstr[64];
 
+	if (timehist_skip_sample(sched, sample))
+		return;
+
 	thread = machine__findnew_thread(machine, sample->tid);
 	if (thread == NULL)
 		return;

@@ -1969,6 +1988,9 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		}
 	}
 
+	if (timehist_skip_sample(sched, sample))
+		goto out;
+
 	tprev = perf_evsel__get_time(evsel, sample->cpu);
 	if (tprev)
 		dt_run = sample->time - tprev;

@@ -2167,6 +2189,27 @@ static int setup_excl_sym(void)
 	return 0;
 }
 
+static int parse_target_str(struct perf_sched *sched)
+{
+	if (sched->target.pid) {
+		sched->pid = intlist__new(sched->target.pid);
+		if (sched->pid == NULL) {
+			pr_err("Error parsing process id string\n");
+			return -EINVAL;
+		}
+	}
+
+	if (sched->target.tid) {
+		sched->tid = intlist__new(sched->target.tid);
+		if (sched->tid == NULL) {
+			pr_err("Error parsing thread id string\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int perf_sched__timehist(struct perf_sched *sched)
 {
 	const struct perf_evsel_str_handler handlers[] = {

@@ -2205,6 +2248,9 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (parse_target_str(sched) != 0)
+		goto out;
+
 	setup_pager();
 
 	if (timehist_check_attr(sched, session->evlist) != 0)

@@ -2484,6 +2530,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "kallsyms pathname"),
 	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
 		   "only display events for these comms"),
+	OPT_STRING('p', "pid", &sched.target.pid, "pid",
+		   "analyze events only for given process id(s)"),
+	OPT_STRING('t', "tid", &sched.target.tid, "tid",
+		   "analyze events only for given thread id(s)"),
 	OPT_UINTEGER('s', "stack-depth", &sched.max_stack_depth,
 		   "Maximum number of functions to display backtrace."),
 	OPT_STRING('x', "excl", &symbol_conf.excl_sym_list_str, "sym[,sym...]",