Merge tag 'perf-core-for-mingo-20160803' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

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

New features:

- Add --sample-cpu to 'perf record', to explicitely ask for sampling
  the CPU (Jiri Olsa)

Fixes:

- Fix processing of multi byte chunks in objdump output, fixing
  disassemble processing for annotation on at least ARM64 (Jan Stancek)

- Use SyS_epoll_wait in a BPF 'perf test' entry instead of sys_epoll_wait, that
  is not present in the DWARF info in vmlinux files (Arnaldo Carvalho de Melo)

- Add -wno-shadow when processing files using perl headers, fixing
  the build on Fedora Rawhide and Arch Linux (Namhyung Kim)

Infrastructure changes:

- Annotate prep work to better catch and report errors related to
  using objdump to disassemble DSOs (Arnaldo Carvalho de Melo)

- Add 'alloc', 'scnprintf' and 'and' methods for bitmap processing (Jiri Olsa)

- Add nested output resorting callback in hists processing (Jiri Olsa)

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

8 files changed, 152 insertions, 65 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e9825fe825fd..4024d309bb00 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1123,7 +1123,46 @@ static void delete_last_nop(struct symbol *sym)
 	}
 }
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *map,
+			      int errnum, char *buf, size_t buflen)
+{
+	struct dso *dso = map->dso;
+
+	BUG_ON(buflen == 0);
+
+	if (errnum >= 0) {
+		str_error_r(errnum, buf, buflen);
+		return 0;
+	}
+
+	switch (errnum) {
+	case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
+		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
+		char *build_id_msg = NULL;
+
+		if (dso->has_build_id) {
+			build_id__sprintf(dso->build_id,
+					  sizeof(dso->build_id), bf + 15);
+			build_id_msg = bf;
+		}
+		scnprintf(buf, buflen,
+			  "No vmlinux file%s\nwas found in the path.\n\n"
+			  "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
+			  "Please use:\n\n"
+			  "  perf buildid-cache -vu vmlinux\n\n"
+			  "or:\n\n"
+			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
+	}
+		break;
+	default:
+		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
+		break;
+	}
+
+	return 0;
+}
+
+int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
 {
 	struct dso *dso = map->dso;
 	char *filename = dso__build_id_filename(dso, NULL, 0);
@@ -1134,22 +1173,20 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	char symfs_filename[PATH_MAX];
 	struct kcore_extract kce;
 	bool delete_extract = false;
+	int stdout_fd[2];
 	int lineno = 0;
 	int nline;
+	pid_t pid;
 
 	if (filename)
 		symbol__join_symfs(symfs_filename, filename);
 
 	if (filename == NULL) {
-		if (dso->has_build_id) {
-			pr_err("Can't annotate %s: not enough memory\n",
-			       sym->name);
-			return -ENOMEM;
-		}
+		if (dso->has_build_id)
+			return ENOMEM;
 		goto fallback;
-	} else if (dso__is_kcore(dso)) {
-		goto fallback;
-	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+	} else if (dso__is_kcore(dso) ||
+		   readlink(symfs_filename, command, sizeof(command)) < 0 ||
 		   strstr(command, DSO__NAME_KALLSYMS) ||
 		   access(symfs_filename, R_OK)) {
 		free(filename);
@@ -1166,27 +1203,7 @@ fallback:
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso)) {
-		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
-		char *build_id_msg = NULL;
-
-		if (dso->annotate_warned)
-			goto out_free_filename;
-
-		if (dso->has_build_id) {
-			build_id__sprintf(dso->build_id,
-					  sizeof(dso->build_id), bf + 15);
-			build_id_msg = bf;
-		}
-		err = -ENOENT;
-		dso->annotate_warned = 1;
-		pr_err("Can't annotate %s:\n\n"
-		       "No vmlinux file%s\nwas found in the path.\n\n"
-		       "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
-		       "Please use:\n\n"
-		       "  perf buildid-cache -vu vmlinux\n\n"
-		       "or:\n\n"
-		       "  --vmlinux vmlinux\n",
-		       sym->name, build_id_msg ?: "");
+		err = SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
 		goto out_free_filename;
 	}
 
@@ -1258,9 +1275,32 @@ fallback:
 
 	pr_debug("Executing: %s\n", command);
 
-	file = popen(command, "r");
+	err = -1;
+	if (pipe(stdout_fd) < 0) {
+		pr_err("Failure creating the pipe to run %s\n", command);
+		goto out_remove_tmp;
+	}
+
+	pid = fork();
+	if (pid < 0) {
+		pr_err("Failure forking to run %s\n", command);
+		goto out_close_stdout;
+	}
+
+	if (pid == 0) {
+		close(stdout_fd[0]);
+		dup2(stdout_fd[1], 1);
+		close(stdout_fd[1]);
+		execl("/bin/sh", "sh", "-c", command, NULL);
+		perror(command);
+		exit(-1);
+	}
+
+	close(stdout_fd[1]);
+
+	file = fdopen(stdout_fd[0], "r");
 	if (!file) {
-		pr_err("Failure running %s\n", command);
+		pr_err("Failure creating FILE stream for %s\n", command);
 		/*
 		 * If we were using debug info should retry with
 		 * original binary.
@@ -1286,9 +1326,11 @@ fallback:
 	if (dso__is_kcore(dso))
 		delete_last_nop(sym);
 
-	pclose(file);
-
+	fclose(file);
+	err = 0;
 out_remove_tmp:
+	close(stdout_fd[0]);
+
 	if (dso__needs_decompress(dso))
 		unlink(symfs_filename);
 out_free_filename:
@@ -1297,6 +1339,10 @@ out_free_filename:
 	if (free_filename)
 		free(filename);
 	return err;
+
+out_close_stdout:
+	close(stdout_fd[1]);
+	goto out_remove_tmp;
 }
 
 static void insert_source_line(struct rb_root *root, struct source_line *src_line)
@@ -1663,7 +1709,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	struct rb_root source_line = RB_ROOT;
 	u64 len;
 
-	if (symbol__annotate(sym, map, 0) < 0)
+	if (symbol__disassemble(sym, map, 0) < 0)
 		return -1;
 
 	len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index a23084f54128..f67ccb027561 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -155,7 +155,27 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize);
+
+enum symbol_disassemble_errno {
+	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
+
+	/*
+	 * Choose an arbitrary negative big number not to clash with standard
+	 * errno since SUS requires the errno has distinct positive values.
+	 * See 'Issue 6' in the link below.
+	 *
+	 * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+	 */
+	__SYMBOL_ANNOTATE_ERRNO__START		= -10000,
+
+	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
+
+	__SYMBOL_ANNOTATE_ERRNO__END,
+};
+
+int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
+				 int errnum, char *buf, size_t buflen);
 
 int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2a40b8e1def7..097b3ed77fdd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -239,31 +239,13 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
 
 int perf_evlist__add_default(struct perf_evlist *evlist)
 {
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_HARDWARE,
-		.config = PERF_COUNT_HW_CPU_CYCLES,
-	};
-	struct perf_evsel *evsel;
-
-	event_attr_init(&attr);
+	struct perf_evsel *evsel = perf_evsel__new_cycles();
 
-	perf_event_attr__set_max_precise_ip(&attr);
-
-	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL)
-		goto error;
-
-	/* use asprintf() because free(evsel) assumes name is allocated */
-	if (asprintf(&evsel->name, "cycles%.*s",
-		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
-		goto error_free;
+		return -ENOMEM;
 
 	perf_evlist__add(evlist, evsel);
 	return 0;
-error_free:
-	perf_evsel__delete(evsel);
-error:
-	return -ENOMEM;
 }
 
 int perf_evlist__add_dummy(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8c54df61fe64..d9b80ef881cd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -253,6 +253,34 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
+struct perf_evsel *perf_evsel__new_cycles(void)
+{
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_HARDWARE,
+		.config	= PERF_COUNT_HW_CPU_CYCLES,
+	};
+	struct perf_evsel *evsel;
+
+	event_attr_init(&attr);
+
+	perf_event_attr__set_max_precise_ip(&attr);
+
+	evsel = perf_evsel__new(&attr);
+	if (evsel == NULL)
+		goto out;
+
+	/* use asprintf() because free(evsel) assumes name is allocated */
+	if (asprintf(&evsel->name, "cycles%.*s",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+		goto error_free;
+out:
+	return evsel;
+error_free:
+	perf_evsel__delete(evsel);
+	evsel = NULL;
+	goto out;
+}
+
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
@@ -854,7 +882,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
-	if (target__has_cpu(&opts->target))
+	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8a4a6c9f1480..4d44129e050b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -175,6 +175,8 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
 	return perf_evsel__newtp_idx(sys, name, 0);
 }
 
+struct perf_evsel *perf_evsel__new_cycles(void);
+
 struct event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a18d142cdca3..de15dbcdcecf 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1672,7 +1672,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 }
 
 static void output_resort(struct hists *hists, struct ui_progress *prog,
-			  bool use_callchain)
+			  bool use_callchain, hists__resort_cb_t cb)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -1711,6 +1711,9 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
+		if (cb && cb(n))
+			continue;
+
 		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain);
 		hists__inc_stats(hists, n);
 
@@ -1731,12 +1734,18 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
 	else
 		use_callchain = symbol_conf.use_callchain;
 
-	output_resort(evsel__hists(evsel), prog, use_callchain);
+	output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
 }
 
 void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
-	output_resort(hists, prog, symbol_conf.use_callchain);
+	output_resort(hists, prog, symbol_conf.use_callchain, NULL);
+}
+
+void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
+			     hists__resort_cb_t cb)
+{
+	output_resort(hists, prog, symbol_conf.use_callchain, cb);
 }
 
 static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 49aa4fac148f..0a1edf1ab450 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -153,8 +153,12 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+typedef int (*hists__resort_cb_t)(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__output_resort_cb(struct hists *hists, struct ui_progress *prog,
+			     hists__resort_cb_t cb);
 int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 8cdcf4641c51..21c4d9b23c24 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -122,11 +122,7 @@ int target__strerror(struct target *target, int errnum,
 	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
-		const char *err = str_error_r(errnum, buf, buflen);
-
-		if (err != buf)
-			scnprintf(buf, buflen, "%s", err);
-
+		str_error_r(errnum, buf, buflen);
 		return 0;
 	}