Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

 - Add 'perf record' --all-user/--all-kernel options, so that one can tell
   that all the events in the command line should be restricted to the user
   or kernel levels (Jiri Olsa), i.e.:

	perf record -e cycles:u,instructions:u

   is equivalent to:

        perf record --all-user -e cycles,instructions

 - Fix percentage update on key press, due to the buffering code
   (that creates hist_entries that will later be consumed) touching
   per hists state that is used by the display thread (Namhyung Kim)

 - Bail out when event modifiers not supported by 'perf stat' are
   specified, i.e.: (Wang Nan)

   # perf stat -e cycles/no-inherit/ usleep 1
   event syntax error: 'cycles/no-inherit/'
                        \___ 'no-inherit' is not usable in 'perf stat'
   # perf stat -e cycles/foo/ usleep 1
   event syntax error: 'cycles/foo/'
                               \___ unknown term

   valid terms: config,config1,config2,name
   #

 - Enable setting names for legacy cache, raw and numeric events, e.g: (Wang Nan)

   # perf record -e cycles -e 4:0x6530160/name=evtx,call-graph=fp/ -a sleep 1
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 1.659 MB perf.data (844 samples) ]
   # perf evlist
   cycles
   evtx
   #

Miscelaneous/Infrastructure changes:

 - Handled scaled == -1 case for counters in 'perf stat', fixing
   recent, only in perf/core, regression (Andi Kleen)

 - Reference count the cpu and thread maps at set_maps(), fixing the
   'object code reading' 'perf test' entry when it was requesting a
   perf_event_attr.sample_freq > /proc/sys/kernel/perf_event_max_sample_rate
   (Arnaldo Carvalho de Melo)

 - Improve perf_evlist__strerror_open() to provide hints for -EINVAL due
   to perf_event_attr.sample_freq > /proc/sys/kernel/perf_event_max_sample_rate
   (Arnaldo Carvalho de Melo)

 - Add checks to various callchain and histogram routines (Namhyung Kim)

 - Fix checking asprintf return value when parsing additional event config terms (Wang Nan)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/Documentation/perf-record.txt

@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/builtin-record.c

@@ -1140,6 +1140,12 @@ struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
+	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
+			 "Configure all used events to run in kernel space.",
+			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
+			 "Configure all used events to run in user space.",
+			 PARSE_OPT_EXCLUSIVE),
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",

tools/perf/builtin-report.c

@@ -469,10 +469,11 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
-static void report__collapse_hists(struct report *rep)
+static int report__collapse_hists(struct report *rep)
 {
 	struct ui_progress prog;
 	struct perf_evsel *pos;
+	int ret = 0;
 
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
@@ -484,7 +485,9 @@ static void report__collapse_hists(struct report *rep)
 
 		hists->socket_filter = rep->socket_filter;
 
-		hists__collapse_resort(hists, &prog);
+		ret = hists__collapse_resort(hists, &prog);
+		if (ret < 0)
+			break;
 
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
@@ -497,6 +500,7 @@ static void report__collapse_hists(struct report *rep)
 	}
 
 	ui_progress__finish();
+	return ret;
 }
 
 static void report__output_resort(struct report *rep)
@@ -564,7 +568,11 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	report__collapse_hists(rep);
+	ret = report__collapse_hists(rep);
+	if (ret) {
+		ui__error("failed to process hist entry\n");
+		return ret;
+	}
 
 	if (session_done())
 		return 0;

tools/perf/builtin-stat.c

@@ -860,7 +860,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	nl = new_line_std;
 
-	if (run == 0 || ena == 0) {
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
 		aggr_printout(counter, id, nr);
 
 		fprintf(stat_config.output, "%*s%s",
@@ -1831,6 +1831,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
+	parse_events__shrink_config_terms();
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);

tools/perf/perf.h

@@ -58,6 +58,8 @@ struct record_opts {
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
 	bool	     record_switch_events;
+	bool	     all_kernel;
+	bool	     all_user;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

tools/perf/tests/code-reading.c

@@ -439,7 +439,7 @@ static int do_test_code_reading(bool try_kcore)
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
-		.freq		     = 4000,
+		.freq		     = 500,
 		.target		     = {
 			.uses_mmap   = true,
 		},
@@ -559,7 +559,13 @@ static int do_test_code_reading(bool try_kcore)
 				evlist = NULL;
 				continue;
 			}
-			pr_debug("perf_evlist__open failed\n");
+
+			if (verbose) {
+				char errbuf[512];
+				perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
+			}
+
 			goto out_put;
 		}
 		break;

tools/perf/tests/parse-events.c

@@ -1271,6 +1271,38 @@ static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_config_symbol(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_raw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_num(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_cache(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1579,6 +1611,26 @@ static struct evlist_test test__events[] = {
 		.check = test__checkevent_precise_max_modifier,
 		.id    = 47,
 	},
+	{
+		.name  = "instructions/name=insn/",
+		.check = test__checkevent_config_symbol,
+		.id    = 48,
+	},
+	{
+		.name  = "r1234/name=rawpmu/",
+		.check = test__checkevent_config_raw,
+		.id    = 49,
+	},
+	{
+		.name  = "4:0x6530160/name=numpmu/",
+		.check = test__checkevent_config_num,
+		.id    = 50,
+	},
+	{
+		.name  = "L1-dcache-misses/name=cachepmu/",
+		.check = test__checkevent_config_cache,
+		.id    = 51,
+	},
 };
 
 static struct evlist_test test__events_pmu[] = {

tools/perf/util/bpf-loader.c

@@ -108,8 +108,8 @@ void bpf__clear(void)
 }
 
 static void
-bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
-		     void *_priv)
+clear_prog_priv(struct bpf_program *prog __maybe_unused,
+		void *_priv)
 {
 	struct bpf_prog_priv *priv = _priv;
 
@@ -337,7 +337,7 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
-	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	err = bpf_program__set_private(prog, priv, clear_prog_priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;

tools/perf/util/callchain.c

@@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 /*
  * Fill the node with callchain values
  */
-static void
+static int
 fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
 	struct callchain_cursor_node *cursor_node;
@@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
-			return;
+			return -1;
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
@@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		callchain_cursor_advance(cursor);
 		cursor_node = callchain_cursor_current(cursor);
 	}
+	return 0;
 }
 
 static struct callchain_node *
@@ -453,7 +454,19 @@ add_child(struct callchain_node *parent,
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, cursor);
+	if (new == NULL)
+		return NULL;
+
+	if (fill_node(new, cursor) < 0) {
+		struct callchain_list *call, *tmp;
+
+		list_for_each_entry_safe(call, tmp, &new->val, list) {
+			list_del(&call->list);
+			free(call);
+		}
+		free(new);
+		return NULL;
+	}
 
 	new->children_hit = 0;
 	new->hit = period;
@@ -462,16 +475,32 @@ add_child(struct callchain_node *parent,
 	return new;
 }
 
-static s64 match_chain(struct callchain_cursor_node *node,
-		      struct callchain_list *cnode)
+enum match_result {
+	MATCH_ERROR  = -1,
+	MATCH_EQ,
+	MATCH_LT,
+	MATCH_GT,
+};
+
+static enum match_result match_chain(struct callchain_cursor_node *node,
+				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
+	u64 left, right;
 
 	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION)
-		return cnode->ms.sym->start - sym->start;
-	else
-		return cnode->ip - node->ip;
+	    callchain_param.key == CCKEY_FUNCTION) {
+		left = cnode->ms.sym->start;
+		right = sym->start;
+	} else {
+		left = cnode->ip;
+		right = node->ip;
+	}
+
+	if (left == right)
+		return MATCH_EQ;
+
+	return left > right ? MATCH_GT : MATCH_LT;
 }
 
 /*
@@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node,
  * give a part of its callchain to the created child.
  * Then create another child to host the given callchain of new branch
  */
-static void
+static int
 split_add_child(struct callchain_node *parent,
 		struct callchain_cursor *cursor,
 		struct callchain_list *to_split,
@@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent,
 
 	/* split */
 	new = create_child(parent, true);
+	if (new == NULL)
+		return -1;
 
 	/* split the callchain and move a part to the new child */
 	old_tail = parent->val.prev;
@@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent,
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
+		if (new == NULL)
+			return -1;
 
 		/*
 		 * This is second child since we moved parent's children
@@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent,
 		cnode = list_first_entry(&first->val, struct callchain_list,
 					 list);
 
-		if (match_chain(node, cnode) < 0)
+		if (match_chain(node, cnode) == MATCH_LT)
 			pp = &p->rb_left;
 		else
 			pp = &p->rb_right;
@@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent,
 		parent->hit = period;
 		parent->count = 1;
 	}
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period);
 
-static void
+static int
 append_chain_children(struct callchain_node *root,
 		      struct callchain_cursor *cursor,
 		      u64 period)
@@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root,
 
 	node = callchain_cursor_current(cursor);
 	if (!node)
-		return;
+		return -1;
 
 	/* lookup in childrens */
 	while (*p) {
-		s64 ret;
+		enum match_result ret;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
 		/* If at least first entry matches, rely to children */
 		ret = append_chain(rnode, cursor, period);
-		if (ret == 0)
+		if (ret == MATCH_EQ)
 			goto inc_children_hit;
+		if (ret == MATCH_ERROR)
+			return -1;
 
-		if (ret < 0)
+		if (ret == MATCH_LT)
 			p = &parent->rb_left;
 		else
 			p = &parent->rb_right;
 	}
 	/* nothing in children, add to the current node */
 	rnode = add_child(root, cursor, period);
+	if (rnode == NULL)
+		return -1;
+
 	rb_link_node(&rnode->rb_node_in, parent, p);
 	rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
 	root->children_hit += period;
 	root->children_count++;
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period)
@@ -602,7 +642,7 @@ append_chain(struct callchain_node *root,
 	u64 start = cursor->pos;
 	bool found = false;
 	u64 matches;
-	int cmp = 0;
+	enum match_result cmp = MATCH_ERROR;
 
 	/*
 	 * Lookup in the current node
@@ -618,7 +658,7 @@ append_chain(struct callchain_node *root,
 			break;
 
 		cmp = match_chain(node, cnode);
-		if (cmp)
+		if (cmp != MATCH_EQ)
 			break;
 
 		found = true;
@@ -628,7 +668,7 @@ append_chain(struct callchain_node *root,
 
 	/* matches not, relay no the parent */
 	if (!found) {
-		WARN_ONCE(!cmp, "Chain comparison error\n");
+		WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
 		return cmp;
 	}
 
@@ -636,21 +676,25 @@ append_chain(struct callchain_node *root,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (matches < root->val_nr) {
-		split_add_child(root, cursor, cnode, start, matches, period);
-		return 0;
+		if (split_add_child(root, cursor, cnode, start, matches,
+				    period) < 0)
+			return MATCH_ERROR;
+
+		return MATCH_EQ;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
 		root->count++;
-		return 0;
+		return MATCH_EQ;
 	}
 
 	/* We match the node and still have a part remaining */
-	append_chain_children(root, cursor, period);
+	if (append_chain_children(root, cursor, period) < 0)
+		return MATCH_ERROR;
 
-	return 0;
+	return MATCH_EQ;
 }
 
 int callchain_append(struct callchain_root *root,
@@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root,
 
 	callchain_cursor_commit(cursor);
 
-	append_chain_children(&root->node, cursor, period);
+	if (append_chain_children(&root->node, cursor, period) < 0)
+		return -1;
 
 	if (cursor->nr > root->max_depth)
 		root->max_depth = cursor->nr;
@@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor,
 
 	if (src->hit) {
 		callchain_cursor_commit(cursor);
-		append_chain_children(dst, cursor, src->hit);
+		if (append_chain_children(dst, cursor, src->hit) < 0)
+			return -1;
 	}
 
 	n = rb_first(&src->rb_root_in);

tools/perf/util/evlist.c

@@ -1181,12 +1181,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
 	 */
 	if (cpus != evlist->cpus) {
 		cpu_map__put(evlist->cpus);
-		evlist->cpus = cpus;
+		evlist->cpus = cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
 		thread_map__put(evlist->threads);
-		evlist->threads = threads;
+		evlist->threads = thread_map__get(threads);
 	}
 
 	perf_evlist__propagate_maps(evlist);
@@ -1624,7 +1624,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
@@ -1652,7 +1652,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
 				    "Hint:\tThe current value is %d.", value);
 		break;
+	case EINVAL: {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+		int max_freq;
+
+		if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
+			goto out_default;
+
+		if (first->attr.sample_freq < (u64)max_freq)
+			goto out_default;
+
+		printed = scnprintf(buf, size,
+				    "Error:\t%s.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
+				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
+				    emsg, max_freq, first->attr.sample_freq);
+		break;
+	}
 	default:
+out_default:
 		scnprintf(buf, size, "%s", emsg);
 		break;
 	}

tools/perf/util/evsel.c

@@ -898,6 +898,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.

tools/perf/util/hist.c

@@ -405,6 +405,16 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
+static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	he->hists->callchain_period += period;
+	if (!he->filtered)
+		he->hists->callchain_non_filtered_period += period;
+}
+
 static struct hist_entry *hists__findnew_entry(struct hists *hists,
 					       struct hist_entry *entry,
 					       struct addr_location *al,
@@ -434,9 +444,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		if (!cmp) {
 			if (sample_self) {
 				he_stat__add_period(&he->stat, period, weight);
-				hists->stats.total_period += period;
-				if (!he->filtered)
-					hists->stats.total_non_filtered_period += period;
+				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
@@ -471,9 +479,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		return NULL;
 
 	if (sample_self)
-		hists__inc_stats(hists, he);
-	else
-		hists->nr_entries++;
+		hist_entry__add_callchain_period(he, period);
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
@@ -1039,8 +1046,8 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
  * collapse the histogram
  */
 
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-				  struct rb_root *root, struct hist_entry *he)
+int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
+				 struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -1054,18 +1061,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
+			int ret = 0;
+
 			he_stat__add_stat(&iter->stat, &he->stat);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
-				callchain_merge(&callchain_cursor,
-						iter->callchain,
-						he->callchain);
+				if (callchain_merge(&callchain_cursor,
+						    iter->callchain,
+						    he->callchain) < 0)
+					ret = -1;
 			}
 			hist_entry__delete(he);
-			return false;
+			return ret;
 		}
 
 		if (cmp < 0)
@@ -1077,7 +1087,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
-	return true;
+	return 1;
 }
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
@@ -1103,14 +1113,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_socket(hists, he);
 }
 
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	int ret;
 
 	if (!sort__need_collapse)
-		return;
+		return 0;
 
 	hists->nr_entries = 0;
 
@@ -1125,7 +1136,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		next = rb_next(&n->rb_node_in);
 
 		rb_erase(&n->rb_node_in, root);
-		if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
+		if (ret < 0)
+			return -1;
+
+		if (ret) {
 			/*
 			 * If it wasn't combined with one of the entries already
 			 * collapsed, we need to apply the filters that may have
@@ -1136,6 +1151,7 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		if (prog)
 			ui_progress__update(prog, 1);
 	}
+	return 0;
 }
 
 static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
@@ -1227,9 +1243,14 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	u64 callchain_total;
 	u64 min_callchain_hits;
 
-	min_callchain_hits = hists__total_period(hists) * (callchain_param.min_percent / 100);
+	callchain_total = hists->callchain_period;
+	if (symbol_conf.filter_relative)
+		callchain_total = hists->callchain_non_filtered_period;
+
+	min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;

tools/perf/util/hist.h

@@ -66,6 +66,8 @@ struct hists {
 	struct rb_root		entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
+	u64			callchain_period;
+	u64			callchain_non_filtered_period;
 	struct thread		*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
@@ -136,7 +138,7 @@ void hist_entry__delete(struct hist_entry *he);
 
 void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
@@ -195,7 +197,7 @@ int hists__init(void);
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+int hists__collapse_insert_entry(struct hists *hists,
 				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {

tools/perf/util/parse-events.c

@@ -279,7 +279,24 @@ const char *event_type(int type)
 	return "unknown";
 }
 
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
+}
+
+static char *get_config_name(struct list_head *head_terms)
+{
+	struct parse_events_term *term;
+
+	if (!head_terms)
+		return NULL;
+
+	list_for_each_entry(term, head_terms, list)
+		if (parse_events__is_name_term(term))
+			return term->val.str;
 
+	return NULL;
+}
 
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
@@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
 	return -1;
 }
 
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err);
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head,
+		       struct parse_events_error *err,
+		       config_term_func_t config_term);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2)
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *error,
+			   struct list_head *head_config)
 {
 	struct perf_event_attr attr;
-	char name[MAX_NAME_LEN];
+	LIST_HEAD(config_terms);
+	char name[MAX_NAME_LEN], *config_name;
 	int cache_type = -1, cache_op = -1, cache_result = -1;
 	char *op_result[2] = { op_result1, op_result2 };
 	int i, n;
@@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	if (cache_type == -1)
 		return -EINVAL;
 
+	config_name = get_config_name(head_config);
 	n = snprintf(name, MAX_NAME_LEN, "%s", type);
 
 	for (i = 0; (i < 2) && (op_result[i]); i++) {
@@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	memset(&attr, 0, sizeof(attr));
 	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
 	attr.type = PERF_TYPE_HW_CACHE;
-	return add_event(list, idx, &attr, name, NULL);
+
+	if (head_config) {
+		if (config_attr(&attr, head_config, error,
+				config_term_common))
+			return -EINVAL;
+
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+	}
+	return add_event(list, idx, &attr, config_name ? : name, &config_terms);
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
@@ -746,6 +787,60 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
+/*
+ * Update according to parse-events.l
+ */
+static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+};
+
+static bool config_term_shrinked;
+
+static bool
+config_term_avail(int term_type, struct parse_events_error *err)
+{
+	if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) {
+		err->str = strdup("Invalid term_type");
+		return false;
+	}
+	if (!config_term_shrinked)
+		return true;
+
+	switch (term_type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+		return true;
+	default:
+		if (!err)
+			return false;
+
+		/* term_type is validated so indexing is safe */
+		if (asprintf(&err->str, "'%s' is not usable in 'perf stat'",
+			     config_term_names[term_type]) < 0)
+			err->str = NULL;
+		return false;
+	}
+}
+
+void parse_events__shrink_config_terms(void)
+{
+	config_term_shrinked = true;
+}
+
 typedef int config_term_func_t(struct perf_event_attr *attr,
 			       struct parse_events_term *term,
 			       struct parse_events_error *err);
@@ -815,6 +910,17 @@ do {									   \
 		return -EINVAL;
 	}
 
+	/*
+	 * Check term availbility after basic checking so
+	 * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered.
+	 *
+	 * If check availbility at the entry of this function,
+	 * user will see "'<sysfs term>' is not usable in 'perf stat'"
+	 * if an invalid config term is provided for legacy events
+	 * (for example, instructions/badterm/...), which is confusing.
+	 */
+	if (!config_term_avail(term->type_term, err))
+		return -EINVAL;
 	return 0;
 #undef CHECK_TYPE_VAL
 }
@@ -961,23 +1067,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 			return -ENOMEM;
 	}
 
-	return add_event(list, &data->idx, &attr, NULL, &config_terms);
-}
-
-static int parse_events__is_name_term(struct parse_events_term *term)
-{
-	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
-}
-
-static char *pmu_event_name(struct list_head *head_terms)
-{
-	struct parse_events_term *term;
-
-	list_for_each_entry(term, head_terms, list)
-		if (parse_events__is_name_term(term))
-			return term->val.str;
-
-	return NULL;
+	return add_event(list, &data->idx, &attr,
+			 get_config_name(head_config), &config_terms);
 }
 
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -1024,7 +1115,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		return -EINVAL;
 
 	evsel = __add_event(list, &data->idx, &attr,
-			    pmu_event_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu->cpus,
 			    &config_terms);
 	if (evsel) {
 		evsel->unit = info.unit;
@@ -2097,6 +2188,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
 
+static void config_terms_list(char *buf, size_t buf_sz)
+{
+	int i;
+	bool first = true;
+
+	buf[0] = '\0';
+	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
+		const char *name = config_term_names[i];
+
+		if (!config_term_avail(i, NULL))
+			continue;
+		if (!name)
+			continue;
+		if (name[0] == '<')
+			continue;
+
+		if (strlen(buf) + strlen(name) + 2 >= buf_sz)
+			return;
+
+		if (!first)
+			strcat(buf, ",");
+		else
+			first = false;
+		strcat(buf, name);
+	}
+}
+
 /*
  * Return string contains valid config terms of an event.
  * @additional_terms: For terms such as PMU sysfs terms.
@@ -2104,17 +2222,18 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	/* "branch_type" is the longest name */
+	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
+			  (sizeof("branch_type") - 1)];
 
+	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
 	if (additional_terms) {
-		if (!asprintf(&str, "valid terms: %s,%s",
-			      additional_terms, static_terms))
+		if (asprintf(&str, "valid terms: %s,%s",
+			     additional_terms, static_terms) < 0)
 			goto fail;
 	} else {
-		if (!asprintf(&str, "valid terms: %s", static_terms))
+		if (asprintf(&str, "valid terms: %s", static_terms) < 0)
 			goto fail;
 	}
 	return str;

tools/perf/util/parse-events.h

@@ -68,7 +68,8 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
-	PARSE_EVENTS__TERM_TYPE_INHERIT
+	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
 struct parse_events_term {
@@ -104,6 +105,7 @@ struct parse_events_terms {
 	struct list_head *terms;
 };
 
+void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
@@ -138,7 +140,9 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2);
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *error,
+			   struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_evlist *data,

tools/perf/util/parse-events.l

@@ -178,8 +178,7 @@ modifier_bp	[rwx]{1,3}
 
 <config>{
 	/*
-	 * Please update parse_events_formats_error_string any time
-	 * new static term is added.
+	 * Please update config_term_names when new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }

tools/perf/util/parse-events.y

@@ -64,6 +64,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> opt_event_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -222,16 +223,6 @@ PE_NAME '/' event_config '/'
 	$$ = list;
 }
 |
-PE_NAME '/' '/'
-{
-	struct parse_events_evlist *data = _data;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
-	$$ = list;
-}
-|
 PE_KERNEL_PMU_EVENT sep_dc
 {
 	struct parse_events_evlist *data = _data;
@@ -302,33 +293,39 @@ value_sym sep_slash_dc
 }
 
 event_legacy_cache:
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+	parse_events_terms__delete($6);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE
+PE_NAME_CACHE_TYPE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -378,24 +375,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-tracepoint_name
-{
-	struct parse_events_evlist *data = _data;
-	struct parse_events_error *error = data->error;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	if (error)
-		error->idx = @1.first_column;
-
-	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, NULL))
-		return -1;
-
-	$$ = list;
-}
-|
-tracepoint_name '/' event_config '/'
+tracepoint_name opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
@@ -406,7 +386,7 @@ tracepoint_name '/' event_config '/'
 		error->idx = @1.first_column;
 
 	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, $3))
+					error, $2))
 		return -1;
 
 	$$ = list;
@@ -433,24 +413,26 @@ PE_NAME ':' PE_NAME
 }
 
 event_legacy_numeric:
-PE_VALUE ':' PE_VALUE
+PE_VALUE ':' PE_VALUE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 
 event_legacy_raw:
-PE_RAW
+PE_RAW opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -476,6 +458,21 @@ PE_BPF_SOURCE
 	$$ = list;
 }
 
+opt_event_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+'/' '/'
+{
+	$$ = NULL;
+}
+|
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;