Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Conflicts:
	tools/perf/builtin-stat.c

8 files changed, 126 insertions, 66 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 85c5f026930d..98a31e3181a5 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -72,6 +72,17 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+--asm-raw::
+	Show raw instruction encoding of assembly instructions. They
+	are displayed by default, disable with --no-asm-raw.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 918cc38ee6d1..08394c4879a8 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -94,6 +94,13 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
 corresponding events, i.e., they always refer to events defined earlier on the command
 line.
 
+-o file::
+-output file::
+Print the output into the designated file.
+
+--append::
+Append to the output file designated with the -o option. Ignored if -o is not specified.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 555aefd7fe01..c5be28851f01 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -267,6 +267,12 @@ static const struct option options[] = {
 	OPT_BOOLEAN('P', "full-paths", &full_paths,
 		    "Don't shorten the displayed pathnames"),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		   "Look for files with symbols relative to this directory"),
+	OPT_BOOLEAN('0', "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN('0', "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5deb17d9e795..bec64a9e741c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -194,6 +194,8 @@ static const char		*cpu_list;
 static const char		*csv_sep			= NULL;
 static bool			csv_output			= false;
 static bool			group				= false;
+static const char		*output_name			= NULL;
+static FILE			*output				= NULL;
 
 static volatile int done = 0;
 
@@ -352,7 +354,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 		update_stats(&ps->res_stats[i], count[i]);
 
 	if (verbose) {
-		fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+		fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
 			event_name(counter), count[0], count[1], count[2]);
 	}
 
@@ -519,9 +521,9 @@ static void print_noise_pct(double total, double avg)
 		pct = 100.0*total/avg;
 
 	if (csv_output)
-		fprintf(stderr, "%s%.2f%%", csv_sep, pct);
+		fprintf(output, "%s%.2f%%", csv_sep, pct);
 	else
-		fprintf(stderr, "  ( +-%6.2f%% )", pct);
+		fprintf(output, "  ( +-%6.2f%% )", pct);
 }
 
 static void print_noise(struct perf_evsel *evsel, double avg)
@@ -546,16 +548,17 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 			csv_output ? 0 : -4,
 			evsel_list->cpus->map[cpu], csv_sep);
 
-	fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
+	fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel));
 
 	if (evsel->cgrp)
-		fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
 	if (csv_output)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(stderr, " # %8.3f CPUs utilized          ", avg / avg_stats(&walltime_nsecs_stats));
+		fprintf(output, " # %8.3f CPUs utilized          ",
+			avg / avg_stats(&walltime_nsecs_stats));
 }
 
 static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -576,9 +579,9 @@ static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __us
 	else if (ratio > 10.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " frontend cycles idle   ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " frontend cycles idle   ");
 }
 
 static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -599,9 +602,9 @@ static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __use
 	else if (ratio > 20.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " backend  cycles idle   ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " backend  cycles idle   ");
 }
 
 static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -622,9 +625,9 @@ static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all branches        ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all branches        ");
 }
 
 static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -645,9 +648,9 @@ static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, dou
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all L1-dcache hits  ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all L1-dcache hits  ");
 }
 
 static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -668,9 +671,9 @@ static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, dou
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all L1-icache hits  ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all L1-icache hits  ");
 }
 
 static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -691,9 +694,9 @@ static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all dTLB cache hits ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all dTLB cache hits ");
 }
 
 static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -714,9 +717,9 @@ static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all iTLB cache hits ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all iTLB cache hits ");
 }
 
 static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
@@ -737,9 +740,9 @@ static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, doub
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	fprintf(stderr, " #  ");
-	color_fprintf(stderr, color, "%6.2f%%", ratio);
-	fprintf(stderr, " of all LL-cache hits   ");
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all LL-cache hits   ");
 }
 
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
@@ -762,10 +765,10 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	else
 		cpu = 0;
 
-	fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
+	fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel));
 
 	if (evsel->cgrp)
-		fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
 	if (csv_output)
 		return;
@@ -776,14 +779,14 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 		if (total)
 			ratio = avg / total;
 
-		fprintf(stderr, " #   %5.2f  insns per cycle        ", ratio);
+		fprintf(output, " #   %5.2f  insns per cycle        ", ratio);
 
 		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
 
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(stderr, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+			fprintf(output, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
 		}
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -831,7 +834,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(stderr, " # %8.3f %% of all cache refs    ", ratio);
+		fprintf(output, " # %8.3f %% of all cache refs    ", ratio);
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
 		print_stalled_cycles_frontend(cpu, evsel, avg);
@@ -843,16 +846,16 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 		if (total)
 			ratio = 1.0 * avg / total;
 
-		fprintf(stderr, " # %8.3f GHz                    ", ratio);
+		fprintf(output, " # %8.3f GHz                    ", ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
 
-		fprintf(stderr, " # %8.3f M/sec                  ", ratio);
+		fprintf(output, " # %8.3f M/sec                  ", ratio);
 	} else {
-		fprintf(stderr, "                                   ");
+		fprintf(output, "                                   ");
 	}
 }
 
@@ -867,7 +870,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 	int scaled = counter->counts->scaled;
 
 	if (scaled == -1) {
-		fprintf(stderr, "%*s%s%*s",
+		fprintf(output, "%*s%s%*s",
 			csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep,
@@ -875,9 +878,9 @@ static void print_counter_aggr(struct perf_evsel *counter)
 			event_name(counter));
 
 		if (counter->cgrp)
-			fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
 
-		fputc('\n', stderr);
+		fputc('\n', output);
 		return;
 	}
 
@@ -889,7 +892,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 	print_noise(counter, avg);
 
 	if (csv_output) {
-		fputc('\n', stderr);
+		fputc('\n', output);
 		return;
 	}
 
@@ -899,9 +902,9 @@ static void print_counter_aggr(struct perf_evsel *counter)
 		avg_enabled = avg_stats(&ps->res_stats[1]);
 		avg_running = avg_stats(&ps->res_stats[2]);
 
-		fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
+		fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled);
 	}
-	fprintf(stderr, "\n");
+	fprintf(output, "\n");
 }
 
 /*
@@ -918,7 +921,7 @@ static void print_counter(struct perf_evsel *counter)
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
 		if (run == 0 || ena == 0) {
-			fprintf(stderr, "CPU%*d%s%*s%s%*s",
+			fprintf(output, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
 				evsel_list->cpus->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
@@ -928,9 +931,10 @@ static void print_counter(struct perf_evsel *counter)
 				event_name(counter));
 
 			if (counter->cgrp)
-				fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+				fprintf(output, "%s%s",
+					csv_sep, counter->cgrp->name);
 
-			fputc('\n', stderr);
+			fputc('\n', output);
 			continue;
 		}
 
@@ -943,9 +947,10 @@ static void print_counter(struct perf_evsel *counter)
 			print_noise(counter, 1.0);
 
 			if (run != ena)
-				fprintf(stderr, "  (%.2f%%)", 100.0 * run / ena);
+				fprintf(output, "  (%.2f%%)",
+					100.0 * run / ena);
 		}
-		fputc('\n', stderr);
+		fputc('\n', output);
 	}
 }
 
@@ -957,21 +962,21 @@ static void print_stat(int argc, const char **argv)
 	fflush(stdout);
 
 	if (!csv_output) {
-		fprintf(stderr, "\n");
-		fprintf(stderr, " Performance counter stats for ");
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
 		if(target_pid == -1 && target_tid == -1) {
-			fprintf(stderr, "\'%s", argv[0]);
+			fprintf(output, "\'%s", argv[0]);
 			for (i = 1; i < argc; i++)
-				fprintf(stderr, " %s", argv[i]);
+				fprintf(output, " %s", argv[i]);
 		} else if (target_pid != -1)
-			fprintf(stderr, "process id \'%d", target_pid);
+			fprintf(output, "process id \'%d", target_pid);
 		else
-			fprintf(stderr, "thread id \'%d", target_tid);
+			fprintf(output, "thread id \'%d", target_tid);
 
-		fprintf(stderr, "\'");
+		fprintf(output, "\'");
 		if (run_count > 1)
-			fprintf(stderr, " (%d runs)", run_count);
-		fprintf(stderr, ":\n\n");
+			fprintf(output, " (%d runs)", run_count);
+		fprintf(output, ":\n\n");
 	}
 
 	if (no_aggr) {
@@ -984,15 +989,15 @@ static void print_stat(int argc, const char **argv)
 
 	if (!csv_output) {
 		if (!null_run)
-			fprintf(stderr, "\n");
-		fprintf(stderr, " %17.9f seconds time elapsed",
+			fprintf(output, "\n");
+		fprintf(output, " %17.9f seconds time elapsed",
 				avg_stats(&walltime_nsecs_stats)/1e9);
 		if (run_count > 1) {
-			fprintf(stderr, "                                        ");
+			fprintf(output, "                                        ");
 			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
 					avg_stats(&walltime_nsecs_stats));
 		}
-		fprintf(stderr, "\n\n");
+		fprintf(output, "\n\n");
 	}
 }
 
@@ -1030,6 +1035,8 @@ static int stat__set_big_num(const struct option *opt __used,
 	return 0;
 }
 
+static bool append_file;
+
 static const struct option options[] = {
 	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
@@ -1070,6 +1077,9 @@ static const struct option options[] = {
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
+	OPT_STRING('o', "output", &output_name, "file",
+		    "output file name"),
+	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
 	OPT_END()
 };
 
@@ -1141,6 +1151,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	struct perf_evsel *pos;
 	int status = -ENOMEM;
+	const char *mode;
 
 	setlocale(LC_ALL, "");
 
@@ -1151,6 +1162,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 
+	output = stderr;
+	if (output_name && strcmp(output_name, "-"))
+		output = NULL;
+
+	if (!output) {
+		struct timespec tm;
+		mode = append_file ? "a" : "w";
+
+		output = fopen(output_name, mode);
+		if (!output) {
+			perror("failed to create output file");
+			exit(-1);
+		}
+		clock_gettime(CLOCK_REALTIME, &tm);
+		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
+	}
+
 	if (csv_sep)
 		csv_output = true;
 	else
@@ -1226,7 +1254,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	status = 0;
 	for (run_idx = 0; run_idx < run_count; run_idx++) {
 		if (run_count != 1 && verbose)
-			fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
+				run_idx + 1);
 
 		if (sync_run)
 			sync();
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e01af2b1a469..01d36ba54053 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -324,9 +324,12 @@ fallback:
 
 	snprintf(command, sizeof(command),
 		 "objdump --start-address=0x%016" PRIx64
-		 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
+		 " --stop-address=0x%016" PRIx64
+		 " -d %s %s -C %s|grep -v %s|expand",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
+		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
+		 symbol_conf.annotate_src ? "-S" : "",
 		 symfs_filename, filename);
 
 	pr_debug("Executing: %s\n", command);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e191eb9a667f..521c38a79190 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -200,7 +200,7 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 	 * Auto-detect:
 	 */
 	if (perf_use_color_default < 0) {
-		if (isatty(1) || pager_in_use())
+		if (isatty(fileno(fp)) || pager_in_use())
 			perf_use_color_default = 1;
 		else
 			perf_use_color_default = 0;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 469c0264ed29..245e60d6b4e7 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -46,6 +46,8 @@ struct symbol_conf symbol_conf = {
 	.exclude_other	  = true,
 	.use_modules	  = true,
 	.try_vmlinux_path = true,
+	.annotate_asm_raw = true,
+	.annotate_src	  = true,
 	.symfs            = "",
 };
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 4f377d92e75a..7733f0b3cd41 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -76,7 +76,9 @@ struct symbol_conf {
 			exclude_other,
 			show_cpu_utilization,
 			initialized,
-			kptr_restrict;
+			kptr_restrict,
+			annotate_asm_raw,
+			annotate_src;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,