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:

User visible:

  * Fixup header alignment in 'perf sched latency' output (Ramkumar Ramachandra)

  * Fix off-by-one error in 'perf timechart record' argv handling (Ramkumar Ramachandra)

  * Print the evsel name in the annotate stdio output, prep to fix support
    outputting annotation for multiple events, not just for the first one
    (Arnaldo Carvalho de Melo)

Internals:

  * Use tid in mmap/mmap2 events to find maps (Don Zickus)

  * Record the reason for filtering an address_location (Namhyung Kim)

  * Apply all filters to an addr_location (Namhyung Kim)

  * Merge al->filtered with hist_entry->filtered in report/hists (Namhyung Kim)

  * Fix memory leak when synthesizing thread records (Namhyung Kim)

  * Use ui__has_annotation() in 'report' (Namhyung Kim)

Cleanups:

  * Remove unused thread__find_map function (Jiri Olsa)

  * Remove unused simple_strtoul() function (Ramkumar Ramachandra)

Documentation:

  * Update function names in debug messages (Ramkumar Ramachandra)

  * Update some code references in design.txt (Ramkumar Ramachandra)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/builtin-report.c

@@ -231,7 +231,7 @@ static int process_sample_event(struct perf_tool *tool,
 		return -1;
 	}
 
-	if (al.filtered || (rep->hide_unresolved && al.sym == NULL))
+	if (rep->hide_unresolved && al.sym == NULL)
 		return 0;
 
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
@@ -928,7 +928,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (use_browser == 1 && sort__has_sym) {
+	if (ui__has_annotation()) {
 		symbol_conf.priv_size = sizeof(struct annotation);
 		machines__set_symbol_filter(&session->machines,
 					    symbol__annotate_init);

tools/perf/builtin-sched.c

@@ -1124,7 +1124,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 	avg = work_list->total_lat / work_list->nb_atoms;
 
-	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n",
 	      (double)work_list->total_runtime / 1e6,
 		 work_list->nb_atoms, (double)avg / 1e6,
 		 (double)work_list->max_lat / 1e6,
@@ -1527,9 +1527,9 @@ static int perf_sched__lat(struct perf_sched *sched)
 
 	perf_sched__sort_lat(sched);
 
-	printf("\n ---------------------------------------------------------------------------------------------------------------\n");
-	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at     |\n");
-	printf(" ---------------------------------------------------------------------------------------------------------------\n");
+	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
+	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 
 	next = rb_first(&sched->sorted_atom_root);
 
@@ -1541,7 +1541,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 		next = rb_next(next);
 	}
 
-	printf(" -----------------------------------------------------------------------------------------\n");
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
 		(double)sched->all_runtime / 1e6, sched->all_count);
 

tools/perf/builtin-timechart.c

@@ -494,7 +494,7 @@ static const char *cat_backtrace(union perf_event *event,
 			continue;
 		}
 
-		tal.filtered = false;
+		tal.filtered = 0;
 		thread__find_addr_location(al.thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &tal);
 
@@ -1238,7 +1238,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
 	for (i = 0; i < old_power_args_nr; i++)
 		*p++ = strdup(old_power_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++)
+	for (j = 0; j < (unsigned int)argc; j++)
 		*p++ = argv[j];
 
 	return cmd_record(rec_argc, rec_argv, NULL);

tools/perf/design.txt

@@ -18,7 +18,7 @@ underlying hardware counters.
 Performance counters are accessed via special file descriptors.
 There's one file descriptor per virtual counter used.
 
-The special file descriptor is opened via the perf_event_open()
+The special file descriptor is opened via the sys_perf_event_open()
 system call:
 
    int sys_perf_event_open(struct perf_event_attr *hw_event_uptr,
@@ -82,7 +82,7 @@ machine-specific.
 If 'raw_type' is 0, then the 'type' field says what kind of counter
 this is, with the following encoding:
 
-enum perf_event_types {
+enum perf_type_id {
 	PERF_TYPE_HARDWARE		= 0,
 	PERF_TYPE_SOFTWARE		= 1,
 	PERF_TYPE_TRACEPOINT		= 2,
@@ -95,7 +95,7 @@ specified by 'event_id':
  * Generalized performance counter event types, used by the hw_event.event_id
  * parameter of the sys_perf_event_open() syscall:
  */
-enum hw_event_ids {
+enum perf_hw_id {
 	/*
 	 * Common hardware events, generalized by the kernel:
 	 */
@@ -129,7 +129,7 @@ software events, selected by 'event_id':
  * physical and sw events of the kernel (and allow the profiling of them as
  * well):
  */
-enum sw_event_ids {
+enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_CLOCK		= 0,
 	PERF_COUNT_SW_TASK_CLOCK	= 1,
 	PERF_COUNT_SW_PAGE_FAULTS	= 2,
@@ -230,7 +230,7 @@ these events are recorded in the ring-buffer (see below).
 The 'comm' bit allows tracking of process comm data on process creation.
 This too is recorded in the ring-buffer (see below).
 
-The 'pid' parameter to the perf_event_open() system call allows the
+The 'pid' parameter to the sys_perf_event_open() system call allows the
 counter to be specific to a task:
 
  pid == 0: if the pid parameter is zero, the counter is attached to the
@@ -260,7 +260,7 @@ The 'flags' parameter is currently unused and must be zero.
 
 The 'group_fd' parameter allows counter "groups" to be set up.  A
 counter group has one counter which is the group "leader".  The leader
-is created first, with group_fd = -1 in the perf_event_open call
+is created first, with group_fd = -1 in the sys_perf_event_open call
 that creates it.  The rest of the group members are created
 subsequently, with group_fd giving the fd of the group leader.
 (A single counter on its own is created with group_fd = -1 and is

tools/perf/tests/hists_link.c

@@ -101,6 +101,7 @@ static struct machine *setup_fake_machine(struct machines *machines)
 			.mmap = {
 				.header = { .misc = PERF_RECORD_MISC_USER, },
 				.pid = fake_mmap_info[i].pid,
+				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
 				.len = 0x1000ULL,
 				.pgoff = 0ULL,

tools/perf/util/annotate.c

@@ -1236,14 +1236,15 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	struct dso *dso = map->dso;
 	char *filename;
 	const char *d_filename;
+	const char *evsel_name = perf_evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *pos, *queue = NULL;
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0;
 	int more = 0;
 	u64 len;
 	int width = 8;
-	int namelen;
+	int namelen, evsel_name_len, graph_dotted_len;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1256,14 +1257,17 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 	len = symbol__size(sym);
 	namelen = strlen(d_filename);
+	evsel_name_len = strlen(evsel_name);
 
 	if (perf_evsel__is_group_event(evsel))
 		width *= evsel->nr_members;
 
-	printf(" %-*.*s|	Source code & Disassembly of %s\n",
-	       width, width, "Percent", d_filename);
-	printf("-%-*.*s-------------------------------------\n",
-	       width+namelen, width+namelen, graph_dotted_line);
+	printf(" %-*.*s|	Source code & Disassembly of %s for %s\n",
+	       width, width, "Percent", d_filename, evsel_name);
+
+	graph_dotted_len = width + namelen + evsel_name_len;
+	printf("-%-*.*s-----------------------------------------\n",
+	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
 	if (verbose)
 		symbol__annotate_hits(sym, evsel);

tools/perf/util/event.c

@@ -1,6 +1,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "debug.h"
+#include "hist.h"
 #include "machine.h"
 #include "sort.h"
 #include "string.h"
@@ -445,6 +446,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
 	if (comm_event == NULL)
 		goto out;
@@ -457,9 +461,6 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
-	if (machine__is_default_guest(machine))
-		return 0;
-
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
@@ -705,7 +706,7 @@ void thread__find_addr_map(struct thread *thread,
 	al->thread = thread;
 	al->addr = addr;
 	al->cpumode = cpumode;
-	al->filtered = false;
+	al->filtered = 0;
 
 	if (machine == NULL) {
 		al->map = NULL;
@@ -731,11 +732,11 @@ void thread__find_addr_map(struct thread *thread,
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
 			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
 			!perf_guest)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__GUEST);
 		if ((cpumode == PERF_RECORD_MISC_USER ||
 			cpumode == PERF_RECORD_MISC_KERNEL) &&
 			!perf_host)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__HOST);
 
 		return;
 	}
@@ -792,9 +793,6 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	if (thread == NULL)
 		return -1;
 
-	if (thread__is_filtered(thread))
-		goto out_filtered;
-
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
@@ -812,6 +810,10 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
+
+	if (thread__is_filtered(thread))
+		al->filtered |= (1 << HIST_FILTER__THREAD);
+
 	al->sym = NULL;
 	al->cpu = sample->cpu;
 
@@ -823,21 +825,19 @@ int perf_event__preprocess_sample(const union perf_event *event,
 						  dso->short_name) ||
 			       (dso->short_name != dso->long_name &&
 				strlist__has_entry(symbol_conf.dso_list,
-						   dso->long_name)))))
-			goto out_filtered;
+						   dso->long_name))))) {
+			al->filtered |= (1 << HIST_FILTER__DSO);
+		}
 
 		al->sym = map__find_symbol(al->map, al->addr,
 					   machine->symbol_filter);
 	}
 
 	if (symbol_conf.sym_list &&
 		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
-						al->sym->name)))
-		goto out_filtered;
-
-	return 0;
+						al->sym->name))) {
+		al->filtered |= (1 << HIST_FILTER__SYMBOL);
+	}
 
-out_filtered:
-	al->filtered = true;
 	return 0;
 }

tools/perf/util/evsel.c

@@ -1023,7 +1023,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
 				  pid, cpus->map[cpu], group_fd, flags);
 
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
@@ -1032,7 +1032,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
-				pr_debug2("perf_event_open failed, error %d\n",
+				pr_debug2("sys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}

tools/perf/util/hist.c

@@ -13,13 +13,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
 
-enum hist_filter {
-	HIST_FILTER__DSO,
-	HIST_FILTER__THREAD,
-	HIST_FILTER__PARENT,
-	HIST_FILTER__SYMBOL,
-};
-
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5,
@@ -429,7 +422,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.weight = weight,
 		},
 		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
+		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,

tools/perf/util/hist.h

@@ -14,6 +14,15 @@ struct hist_entry;
 struct addr_location;
 struct symbol;
 
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
+	HIST_FILTER__GUEST,
+	HIST_FILTER__HOST,
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of

tools/perf/util/include/linux/kernel.h

@@ -94,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-static inline unsigned long
-simple_strtoul(const char *nptr, char **endptr, int base)
-{
-	return strtoul(nptr, endptr, base);
-}
-
 int eprintf(int level,
 	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 

tools/perf/util/machine.c

@@ -1027,7 +1027,7 @@ int machine__process_mmap2_event(struct machine *machine,
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap2.pid,
-					event->mmap2.pid);
+					event->mmap2.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1075,7 +1075,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap.pid,
-					 event->mmap.pid);
+					 event->mmap.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1312,7 +1312,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 			continue;
 		}
 
-		al.filtered = false;
+		al.filtered = 0;
 		thread__find_addr_location(thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &al);
 		if (al.sym != NULL) {

tools/perf/util/symbol.h

@@ -186,7 +186,7 @@ struct addr_location {
 	struct symbol *sym;
 	u64	      addr;
 	char	      level;
-	bool	      filtered;
+	u8	      filtered;
 	u8	      cpumode;
 	s32	      cpu;
 };

tools/perf/util/thread.h

@@ -44,12 +44,6 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-static inline struct map *thread__find_map(struct thread *thread,
-					   enum map_type type, u64 addr)
-{
-	return thread ? map_groups__find(&thread->mg, type, addr) : NULL;
-}
-
 void thread__find_addr_map(struct thread *thread, struct machine *machine,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);