Merge tag 'perf-urgent-for-mingo-4.10-20170104' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes and one improvement from Arnaldo Carvalho de Melo:

Fixes:

  - Fix prev/next_prio formatting for deadline tasks in libtraceevent (Daniel Bristot de Oliveira)

  - Robustify reading of build-ids from /sys/kernel/note (Arnaldo Carvalho de Melo)

  - Fix building some sample/bpf in Alpine Linux 3.4 (Arnaldo Carvalho de Melo)

  - Fix 'make install-bin' to install libtraceevent plugins (Arnaldo Carvalho de Melo)

  - Fix 'perf record --switch-output' documentation and comment (Jiri Olsa)

  - Fix 'perf probe' for cross arch probing (Masami Hiramatsu)

Improvement:

  - Show total scheduling time in 'perf sched timehist' (Namhyumg Kim)

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Ingo Molnar

samples/bpf/sock_example.h

@@ -4,7 +4,7 @@
 #include <unistd.h>
 #include <string.h>
 #include <errno.h>
-#include <net/ethernet.h>
+#include <linux/if_ether.h>
 #include <net/if.h>
 #include <linux/if_packet.h>
 #include <arpa/inet.h>

samples/bpf/trace_output_user.c

@@ -9,7 +9,6 @@
 #include <string.h>
 #include <fcntl.h>
 #include <poll.h>
-#include <sys/ioctl.h>
 #include <linux/perf_event.h>
 #include <linux/bpf.h>
 #include <errno.h>

tools/lib/subcmd/parse-options.c

@@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 		else
 			err = get_arg(p, opt, flags, (const char **)opt->value);
 
+		if (opt->set)
+			*(bool *)opt->set = true;
+
 		/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
 		if (opt->flags & PARSE_OPT_NOEMPTY) {
 			const char *val = *(const char **)opt->value;

tools/lib/subcmd/parse-options.h

@@ -137,6 +137,11 @@ struct option {
 	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
 	  .value = check_vtype(v, const char **), (a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+	{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+	  .set = check_vtype(os, bool *)}
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }

tools/lib/traceevent/plugin_sched_switch.c

@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld ", val);
 
 	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, "[%lld] ", val);
+		trace_seq_printf(s, "[%d] ", (int) val);
 
 	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
 		write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld", val);
 
 	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, " [%lld]", val);
+		trace_seq_printf(s, " [%d]", (int) val);
 
 	return 0;
 }

tools/perf/Documentation/perf-record.txt

@@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that
 particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+  --switch-output --no-no-buildid  --no-no-buildid-cache
 
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline

tools/perf/Makefile.perf

@@ -704,9 +704,9 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
 
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
 
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'

tools/perf/builtin-record.c

@@ -1405,7 +1405,7 @@ static bool dry_run;
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-struct option __record_options[] = {
+static struct option __record_options[] = {
 	OPT_CALLBACK('e', "event", &record.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),
@@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		 * overhead. Still generate buildid if they are required
 		 * explicitly using
 		 *
-		 *  perf record --signal-trigger --no-no-buildid \
+		 *  perf record --switch-output --no-no-buildid \
 		 *              --no-no-buildid-cache
 		 *
 		 * Following code equals to:

tools/perf/builtin-sched.c

@@ -209,6 +209,7 @@ struct perf_sched {
 	u64		skipped_samples;
 	const char	*time_str;
 	struct perf_time_interval ptime;
+	struct perf_time_interval hist_time;
 };
 
 /* per thread run time data */
@@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		timehist_print_sample(sched, sample, &al, thread, t);
 
 out:
+	if (sched->hist_time.start == 0 && t >= ptime->start)
+		sched->hist_time.start = t;
+	if (ptime->end == 0 || t <= ptime->end)
+		sched->hist_time.end = t;
+
 	if (tr) {
 		/* time of this sched_switch event becomes last time task seen */
 		tr->last_time = sample->time;
@@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 	struct thread *t;
 	struct thread_runtime *r;
 	int i;
+	u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
 	memset(&totals, 0, sizeof(totals));
 
@@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 			totals.sched_count += r->run_stats.n;
 			printf("    CPU %2d idle for ", i);
 			print_sched_time(r->total_run_time, 6);
-			printf(" msec\n");
+			printf(" msec  (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time);
 		} else
 			printf("    CPU %2d idle entire time window\n", i);
 	}
@@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	printf("\n"
 	       "    Total number of unique tasks: %" PRIu64 "\n"
-	       "Total number of context switches: %" PRIu64 "\n"
-	       "           Total run time (msec): ",
+	       "Total number of context switches: %" PRIu64 "\n",
 	       totals.task_count, totals.sched_count);
 
+	printf("           Total run time (msec): ");
 	print_sched_time(totals.total_run_time, 2);
 	printf("\n");
+
+	printf("    Total scheduling time (msec): ");
+	print_sched_time(hist_time, 2);
+	printf(" (x %d)\n", sched->max_cpu);
 }
 
 typedef int (*sched_handler)(struct perf_tool *tool,

tools/perf/util/probe-event.c

@@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module)
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__findnew_module_map(host_machine, 0, module);
+		return dso__new_map(module);
 
 	if (!module)
 		module = "kernel";
@@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module)
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0 &&
 		    module[pos->dso->short_name_len - 2] == '\0') {
+			map__get(pos);
 			return pos;
 		}
 	}
@@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user)
 		return kernel_get_module_map(target);
 }
 
-static void put_target_map(struct map *map, bool user)
-{
-	if (map && user) {
-		/* Only the user map needs to be released */
-		map__put(map);
-	}
-}
-
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -267,21 +259,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 	return true;
 }
 
-/*
- * NOTE:
- * '.gnu.linkonce.this_module' section of kernel module elf directly
- * maps to 'struct module' from linux/module.h. This section contains
- * actual module name which will be used by kernel after loading it.
- * But, we cannot use 'struct module' here since linux/module.h is not
- * exposed to user-space. Offset of 'name' has remained same from long
- * time, so hardcoding it here.
- */
-#ifdef __LP64__
-#define MOD_NAME_OFFSET 24
-#else
-#define MOD_NAME_OFFSET 12
-#endif
-
 /*
  * @module can be module name of module file path. In case of path,
  * inspect elf and find out what is actual module name.
@@ -296,6 +273,7 @@ static char *find_module_name(const char *module)
 	Elf_Data *data;
 	Elf_Scn *sec;
 	char *mod_name = NULL;
+	int name_offset;
 
 	fd = open(module, O_RDONLY);
 	if (fd < 0)
@@ -317,7 +295,21 @@ static char *find_module_name(const char *module)
 	if (!data || !data->d_buf)
 		goto ret_err;
 
-	mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+	/*
+	 * NOTE:
+	 * '.gnu.linkonce.this_module' section of kernel module elf directly
+	 * maps to 'struct module' from linux/module.h. This section contains
+	 * actual module name which will be used by kernel after loading it.
+	 * But, we cannot use 'struct module' here since linux/module.h is not
+	 * exposed to user-space. Offset of 'name' has remained same from long
+	 * time, so hardcoding it here.
+	 */
+	if (ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+		name_offset = 12;
+	else	/* expect ELFCLASS64 by default */
+		name_offset = 24;
+
+	mod_name = strdup((char *)data->d_buf + name_offset);
 
 ret_err:
 	elf_end(elf);
@@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 	}
 
 out:
-	put_target_map(map, uprobes);
+	map__put(map);
 	return ret;
 
 }
@@ -618,6 +610,51 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	return ret ? : -ENOENT;
 }
 
+/*
+ * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
+ * and generate new symbols with suffixes such as .constprop.N or .isra.N
+ * etc. Since those symbols are not recorded in DWARF, we have to find
+ * correct generated symbols from offline ELF binary.
+ * For online kernel or uprobes we don't need this because those are
+ * rebased on _text, or already a section relative address.
+ */
+static int
+post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
+					int ntevs, const char *pathname)
+{
+	struct symbol *sym;
+	struct map *map;
+	unsigned long stext = 0;
+	u64 addr;
+	int i;
+
+	/* Prepare a map for offline binary */
+	map = dso__new_map(pathname);
+	if (!map || get_text_start_address(pathname, &stext) < 0) {
+		pr_warning("Failed to get ELF symbols for %s\n", pathname);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ntevs; i++) {
+		addr = tevs[i].point.address + tevs[i].point.offset - stext;
+		sym = map__find_symbol(map, addr);
+		if (!sym)
+			continue;
+		if (!strcmp(sym->name, tevs[i].point.symbol))
+			continue;
+		/* If we have no realname, use symbol for it */
+		if (!tevs[i].point.realname)
+			tevs[i].point.realname = tevs[i].point.symbol;
+		else
+			free(tevs[i].point.symbol);
+		tevs[i].point.symbol = strdup(sym->name);
+		tevs[i].point.offset = addr - sym->start;
+	}
+	map__put(map);
+
+	return 0;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  int ntevs, const char *exec)
 {
@@ -679,7 +716,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 
 	/* Skip post process if the target is an offline kernel */
 	if (symbol_conf.ignore_vmlinux_buildid)
-		return 0;
+		return post_process_offline_probe_trace_events(tevs, ntevs,
+						symbol_conf.vmlinux_name);
 
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (!reloc_sym) {
@@ -2869,7 +2907,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 out:
-	put_target_map(map, pev->uprobes);
+	map__put(map);
 	free(syms);
 	return ret;
 
@@ -3362,10 +3400,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 		return ret;
 
 	/* Get a symbol map */
-	if (user)
-		map = dso__new_map(target);
-	else
-		map = kernel_get_module_map(target);
+	map = get_target_map(target, user);
 	if (!map) {
 		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
 		return -EINVAL;
@@ -3397,9 +3432,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
         }
 
 end:
-	if (user) {
-		map__put(map);
-	}
+	map__put(map);
 	exit_probe_symbol_maps();
 
 	return ret;