Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf top: Fix live annotation in the --stdio interface
  perf top tui: Don't recalc column widths considering just the first page
  perf report: Add progress bar when processing time ordered events
  perf hists browser: Warn about lost events
  perf tools: Fix a typo of command name as trace-cmd
  perf hists: Fix recalculation of total_period when sorting entries
  perf header: Fix build on old systems
  perf ui browser: Handle K_RESIZE in dialog windows
  perf ui browser: No need to switch char sets that often
  perf hists browser: Use K_TIMER
  perf ui: Rename ui__warning_paranoid to ui__error_paranoid
  perf ui: Reimplement the popup windows using libslang
  perf ui: Reimplement ui__popup_menu using ui__browser
  perf ui: Reimplement ui_helpline using libslang
  perf ui: Improve handling sigwinch a bit
  perf ui progress: Reimplement using slang
  perf evlist: Fix grouping of multiple events

31 files changed, 624 insertions, 288 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f82480fa7f2..6ab58cc99d5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -262,13 +262,16 @@ static bool perf_evlist__equal(struct perf_evlist *evlist,
 
 static void open_counters(struct perf_evlist *evlist)
 {
-	struct perf_evsel *pos;
+	struct perf_evsel *pos, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
+		struct xyarray *group_fd = NULL;
 		/*
 		 * Check if parse_single_tracepoint_event has already asked for
 		 * PERF_SAMPLE_TIME.
@@ -283,15 +286,19 @@ static void open_counters(struct perf_evlist *evlist)
 		 */
 		bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
 
+		if (group && pos != first)
+			group_fd = first->fd;
+
 		config_attr(pos, evlist);
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
+				     group_fd) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
-				ui__warning_paranoid();
+				ui__error_paranoid();
 				exit(EXIT_FAILURE);
 			} else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7ce65f52415..7d98676808d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -278,9 +278,14 @@ struct stats			runtime_itlb_cache_stats[MAX_NR_CPUS];
 struct stats			runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats			walltime_nsecs_stats;
 
-static int create_perf_stat_counter(struct perf_evsel *evsel)
+static int create_perf_stat_counter(struct perf_evsel *evsel,
+				    struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	struct xyarray *group_fd = NULL;
+
+	if (group && evsel != first)
+		group_fd = first->fd;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -289,14 +294,15 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	attr->inherit = !no_inherit;
 
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, group);
-
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
+						group, group_fd);
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, group);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads,
+					   group, group_fd);
 }
 
 /*
@@ -396,7 +402,7 @@ static int read_counter(struct perf_evsel *counter)
 static int run_perf_stat(int argc __used, const char **argv)
 {
 	unsigned long long t0, t1;
-	struct perf_evsel *counter;
+	struct perf_evsel *counter, *first;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
@@ -453,8 +459,10 @@ static int run_perf_stat(int argc __used, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
+	first = list_entry(evsel_list->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(counter, &evsel_list->entries, node) {
-		if (create_perf_stat_counter(counter) < 0) {
+		if (create_perf_stat_counter(counter, first) < 0) {
 			if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index efe696f936e..831d1baeac3 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -291,7 +291,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false, NULL) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -366,7 +366,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false, NULL) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -531,7 +531,7 @@ static int test__basic_mmap(void)
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false, NULL) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7a871714d44..c9cdedb5813 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -89,6 +89,7 @@ static bool			vmlinux_warned;
 static bool			inherit				=  false;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
+static bool			sample_id_all_avail		=   true;
 static unsigned int		mmap_pages			=    128;
 
 static bool			dump_symtab                     =  false;
@@ -199,7 +200,8 @@ static void record_precise_ip(struct hist_entry *he, int counter, u64 ip)
 	struct symbol *sym;
 
 	if (he == NULL || he->ms.sym == NULL ||
-	    (he != top.sym_filter_entry && use_browser != 1))
+	    ((top.sym_filter_entry == NULL ||
+	      top.sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
 		return;
 
 	sym = he->ms.sym;
@@ -289,11 +291,13 @@ static void print_sym_table(void)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (top.total_lost_warned != top.session->hists.stats.total_lost) {
-		top.total_lost_warned = top.session->hists.stats.total_lost;
-		color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
-		printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
-		       top.total_lost_warned);
+	if (top.sym_evsel->hists.stats.nr_lost_warned !=
+	    top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
+		top.sym_evsel->hists.stats.nr_lost_warned =
+			top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+		color_fprintf(stdout, PERF_COLOR_RED,
+			      "WARNING: LOST %d chunks, Check IO/CPU overload",
+			      top.sym_evsel->hists.stats.nr_lost_warned);
 		++printed;
 	}
 
@@ -561,7 +565,6 @@ static void perf_top__sort_new_samples(void *arg)
 	hists__decay_entries_threaded(&t->sym_evsel->hists,
 				      top.hide_user_symbols,
 				      top.hide_kernel_symbols);
-	hists__output_recalc_col_len(&t->sym_evsel->hists, winsize.ws_row - 3);
 }
 
 static void *display_thread_tui(void *arg __used)
@@ -671,6 +674,7 @@ static int symbol_filter(struct map *map __used, struct symbol *sym)
 }
 
 static void perf_event__process_sample(const union perf_event *event,
+				       struct perf_evsel *evsel,
 				       struct perf_sample *sample,
 				       struct perf_session *session)
 {
@@ -770,12 +774,8 @@ static void perf_event__process_sample(const union perf_event *event,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
-		struct perf_evsel *evsel;
 		struct hist_entry *he;
 
-		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
-		assert(evsel != NULL);
-
 		if ((sort__has_parent || symbol_conf.use_callchain) &&
 		    sample->callchain) {
 			err = perf_session__resolve_callchain(session, al.thread,
@@ -807,6 +807,7 @@ static void perf_event__process_sample(const union perf_event *event,
 static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
 	struct perf_sample sample;
+	struct perf_evsel *evsel;
 	union perf_event *event;
 	int ret;
 
@@ -817,10 +818,16 @@ static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 			continue;
 		}
 
+		evsel = perf_evlist__id2evsel(self->evlist, sample.id);
+		assert(evsel != NULL);
+
 		if (event->header.type == PERF_RECORD_SAMPLE)
-			perf_event__process_sample(event, &sample, self);
-		else
+			perf_event__process_sample(event, evsel, &sample, self);
+		else if (event->header.type < PERF_RECORD_MAX) {
+			hists__inc_nr_events(&evsel->hists, event->header.type);
 			perf_event__process(event, &sample, self);
+		} else
+			++self->hists.stats.nr_unknown_events;
 	}
 }
 
@@ -834,10 +841,16 @@ static void perf_session__mmap_read(struct perf_session *self)
 
 static void start_counters(struct perf_evlist *evlist)
 {
-	struct perf_evsel *counter;
+	struct perf_evsel *counter, *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
 
 	list_for_each_entry(counter, &evlist->entries, node) {
 		struct perf_event_attr *attr = &counter->attr;
+		struct xyarray *group_fd = NULL;
+
+		if (group && counter != first)
+			group_fd = first->fd;
 
 		attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
@@ -858,14 +871,23 @@ static void start_counters(struct perf_evlist *evlist)
 		attr->mmap = 1;
 		attr->comm = 1;
 		attr->inherit = inherit;
+retry_sample_id:
+		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group) < 0) {
+				     top.evlist->threads, group,
+				     group_fd) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
-				ui__warning_paranoid();
+				ui__error_paranoid();
 				goto out_err;
+			} else if (err == EINVAL && sample_id_all_avail) {
+				/*
+				 * Old kernel, no attr->sample_id_type_all field
+				 */
+				sample_id_all_avail = false;
+				goto retry_sample_id;
 			}
 			/*
 			 * If it's cycles then fall back to hrtimer
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bc8f4773d4d..119e996035c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -310,9 +310,12 @@ fallback:
 		}
 		err = -ENOENT;
 		dso->annotate_warned = 1;
-		pr_err("Can't annotate %s: No vmlinux file%s was found in the "
-		       "path.\nPlease use 'perf buildid-cache -av vmlinux' or "
-		       "--vmlinux vmlinux.\n",
+		pr_err("Can't annotate %s:\n\n"
+		       "No vmlinux file%s\nwas found in the path.\n\n"
+		       "Please use:\n\n"
+		       "  perf buildid-cache -av vmlinux\n\n"
+		       "or:\n\n"
+		       "  --vmlinux vmlinux",
 		       sym->name, build_id_msg ?: "");
 		goto out_free_filename;
 	}
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 155749d7435..26817daa296 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -47,19 +47,20 @@ int dump_printf(const char *fmt, ...)
 }
 
 #ifdef NO_NEWT_SUPPORT
-void ui__warning(const char *format, ...)
+int ui__warning(const char *format, ...)
 {
 	va_list args;
 
 	va_start(args, format);
 	vfprintf(stderr, format, args);
 	va_end(args);
+	return 0;
 }
 #endif
 
-void ui__warning_paranoid(void)
+int ui__error_paranoid(void)
 {
-	ui__warning("Permission error - are you root?\n"
+	return ui__error("Permission error - are you root?\n"
 		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
 		    " -1 - Not paranoid at all\n"
 		    "  0 - Disallow raw tracepoint access for unpriv\n"
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index fd53db47e3d..f2ce88d04f5 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -19,23 +19,18 @@ static inline int ui_helpline__show_help(const char *format __used, va_list ap _
 	return 0;
 }
 
-static inline struct ui_progress *ui_progress__new(const char *title __used,
-						   u64 total __used)
-{
-	return (struct ui_progress *)1;
-}
-
-static inline void ui_progress__update(struct ui_progress *self __used,
-				       u64 curr __used) {}
+static inline void ui_progress__update(u64 curr __used, u64 total __used,
+				       const char *title __used) {}
 
-static inline void ui_progress__delete(struct ui_progress *self __used) {}
+#define ui__error(format, arg...) ui__warning(format, ##arg)
 #else
 extern char ui_helpline__last_msg[];
 int ui_helpline__show_help(const char *format, va_list ap);
 #include "ui/progress.h"
+int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 #endif
 
-void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
-void ui__warning_paranoid(void);
+int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+int ui__error_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2f6bc89027d..fbb4b4ab9cc 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -539,3 +539,33 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 {
 	evlist->selected = evsel;
 }
+
+int perf_evlist__open(struct perf_evlist *evlist, bool group)
+{
+	struct perf_evsel *evsel, *first;
+	int err, ncpus, nthreads;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		struct xyarray *group_fd = NULL;
+
+		if (group && evsel != first)
+			group_fd = first->fd;
+
+		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads,
+				       group, group_fd);
+		if (err < 0)
+			goto out_err;
+	}
+
+	return 0;
+out_err:
+	ncpus = evlist->cpus ? evlist->cpus->nr : 1;
+	nthreads = evlist->threads ? evlist->threads->nr : 1;
+
+	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+		perf_evsel__close(evsel, ncpus, nthreads);
+
+	return err;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6be71fc5779..1779ffef782 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -50,6 +50,8 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
+int perf_evlist__open(struct perf_evlist *evlist, bool group);
+
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b46f6e4bff3..e4262642258 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -16,6 +16,7 @@
 #include "thread_map.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
 int __perf_evsel__sample_size(u64 sample_type)
 {
@@ -204,15 +205,16 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group)
+			      struct thread_map *threads, bool group,
+			      struct xyarray *group_fds)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
-	int pid = -1;
+	int pid = -1, err;
 
 	if (evsel->fd == NULL &&
 	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
-		return -1;
+		return -ENOMEM;
 
 	if (evsel->cgrp) {
 		flags = PERF_FLAG_PID_CGROUP;
@@ -220,7 +222,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	}
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		int group_fd = -1;
+		int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -231,8 +233,10 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 								     pid,
 								     cpus->map[cpu],
 								     group_fd, flags);
-			if (FD(evsel, cpu, thread) < 0)
+			if (FD(evsel, cpu, thread) < 0) {
+				err = -errno;
 				goto out_close;
+			}
 
 			if (group && group_fd == -1)
 				group_fd = FD(evsel, cpu, thread);
@@ -249,7 +253,17 @@ out_close:
 		}
 		thread = threads->nr;
 	} while (--cpu >= 0);
-	return -1;
+	return err;
+}
+
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	if (evsel->fd == NULL)
+		return;
+
+	perf_evsel__close_fd(evsel, ncpus, nthreads);
+	perf_evsel__free_fd(evsel);
+	evsel->fd = NULL;
 }
 
 static struct {
@@ -269,7 +283,8 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group)
+		     struct thread_map *threads, bool group,
+		     struct xyarray *group_fd)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -279,19 +294,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group);
+	return __perf_evsel__open(evsel, cpus, threads, group, group_fd);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group)
+			     struct cpu_map *cpus, bool group,
+			     struct xyarray *group_fd)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group,
+				  group_fd);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group)
+				struct thread_map *threads, bool group,
+				struct xyarray *group_fd)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group,
+				  group_fd);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e9a31554e26..b1d15e6f7ae 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -82,11 +82,15 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group);
+			     struct cpu_map *cpus, bool group,
+			     struct xyarray *group_fds);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group);
+				struct thread_map *threads, bool group,
+				struct xyarray *group_fds);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group);
+		     struct thread_map *threads, bool group,
+		     struct xyarray *group_fds);
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 76c0b2c49eb..bcd05d05b4f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,5 +1,6 @@
 #define _FILE_OFFSET_BITS 64
 
+#include "util.h"
 #include <sys/types.h>
 #include <byteswap.h>
 #include <unistd.h>
@@ -11,7 +12,6 @@
 
 #include "evlist.h"
 #include "evsel.h"
-#include "util.h"
 #include "header.h"
 #include "../perf.h"
 #include "trace-event.h"
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f6a993963a1..a36a3fa81ff 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -365,7 +365,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 
 	root = hists__get_rotate_entries_in(hists);
 	next = rb_first(root);
-	hists->stats.total_period = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
@@ -379,7 +378,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 			 * been set by, say, the hist_browser.
 			 */
 			hists__apply_filters(hists, n);
-			hists__inc_nr_entries(hists, n);
 		}
 	}
 }
@@ -442,6 +440,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 	hists->entries = RB_ROOT;
 
 	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
 	hists__reset_col_len(hists);
 
 	while (next) {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ff93ddc91c5..c86c1d27bd1 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -28,6 +28,7 @@ struct events_stats {
 	u64 total_lost;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_lost_warned;
 	u32 nr_unknown_events;
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 7624324efad..9dd47a4f259 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -623,7 +623,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
 	evsel->attr.inherit = inherit;
-	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
+	/*
+	 * This will group just the fds for this single evsel, to group
+	 * multiple events, use evlist.open().
+	 */
+	if (perf_evsel__open(evsel, cpus, threads, group, NULL) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -814,6 +818,25 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	return Py_None;
 }
 
+static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	int group = 0;
+	static char *kwlist[] = { "group", NULL };
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group))
+		return NULL;
+
+	if (perf_evlist__open(evlist, group) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
 static PyMethodDef pyrf_evlist__methods[] = {
 	{
 		.ml_name  = "mmap",
@@ -822,6 +845,12 @@ static PyMethodDef pyrf_evlist__methods[] = {
 		.ml_doc	  = PyDoc_STR("mmap the file descriptor table.")
 	},
 	{
+		.ml_name  = "open",
+		.ml_meth  = (PyCFunction)pyrf_evlist__open,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("open the file descriptors.")
+	},
+	{
 		.ml_name  = "poll",
 		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
 		.ml_flags = METH_VARARGS | METH_KEYWORDS,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 20e011c99a9..85c1e6b76f0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -502,6 +502,7 @@ static void flush_sample_queue(struct perf_session *s,
 	struct perf_sample sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+	unsigned idx = 0, progress_next = os->nr_samples / 16;
 	int ret;
 
 	if (!ops->ordered_samples || !limit)
@@ -521,6 +522,11 @@ static void flush_sample_queue(struct perf_session *s,
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
 		list_add(&iter->list, &os->sample_cache);
+		if (++idx >= progress_next) {
+			progress_next += os->nr_samples / 16;
+			ui_progress__update(idx, os->nr_samples,
+					    "Processing time ordered events...");
+		}
 	}
 
 	if (list_empty(head)) {
@@ -529,6 +535,8 @@ static void flush_sample_queue(struct perf_session *s,
 		os->last_sample =
 			list_entry(head->prev, struct sample_queue, list);
 	}
+
+	os->nr_samples = 0;
 }
 
 /*
@@ -588,6 +596,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s)
 	u64 timestamp = new->timestamp;
 	struct list_head *p;
 
+	++os->nr_samples;
 	os->last_sample = new;
 
 	if (!sample) {
@@ -738,10 +747,27 @@ static int perf_session_deliver_event(struct perf_session *session,
 
 	dump_event(session, event, file_offset, sample);
 
+	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
+		/*
+		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
+		 * because the tools right now may apply filters, discarding
+		 * some of the samples. For consistency, in the future we
+		 * should have something like nr_filtered_samples and remove
+		 * the sample->period from total_sample_period, etc, KISS for
+		 * now tho.
+		 *
+		 * Also testing against NULL allows us to handle files without
+		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
+		 * future probably it'll be a good idea to restrict event
+		 * processing via perf_session to files with both set.
+		 */
+		hists__inc_nr_events(&evsel->hists, event->header.type);
+	}
+
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(session, event, sample);
-		evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 		if (evsel == NULL) {
 			++session->hists.stats.nr_unknown_id;
 			return -1;
@@ -874,11 +900,11 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 					    const struct perf_event_ops *ops)
 {
 	if (ops->lost == perf_event__process_lost &&
-	    session->hists.stats.total_lost != 0) {
-		ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
-			    "!\n\nCheck IO/CPU overload!\n\n",
-			    session->hists.stats.total_period,
-			    session->hists.stats.total_lost);
+	    session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) {
+		ui__warning("Processed %d events and lost %d chunks!\n\n"
+			    "Check IO/CPU overload!\n\n",
+			    session->hists.stats.nr_events[0],
+			    session->hists.stats.nr_events[PERF_RECORD_LOST]);
 	}
 
 	if (session->hists.stats.nr_unknown_events != 0) {
@@ -1012,7 +1038,6 @@ int __perf_session__process_events(struct perf_session *session,
 {
 	u64 head, page_offset, file_offset, file_pos, progress_next;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
-	struct ui_progress *progress;
 	size_t	page_size, mmap_size;
 	cha