From 7c48dcfd32b45b69aa8d5e81108fff8c7a2272ed Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 28 Jul 2016 18:33:20 -0300
Subject: [PATCH 01/17] perf evsel: Introduce constructor for cycles event

That is the default used when no events is specified in tools, separate
it so that simpler tools that need no evlist can use it directly.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-67mwuthscwroz88x9pswcqyv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 22 ++--------------------
 tools/perf/util/evsel.c  | 28 ++++++++++++++++++++++++++++
 tools/perf/util/evsel.h  |  2 ++
 3 files changed, 32 insertions(+), 20 deletions(-)

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;
+	struct perf_evsel *evsel = perf_evsel__new_cycles();
 
-	event_attr_init(&attr);
-
-	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..4c2b31dc4e4d 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.
  */
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,

From 9955d0be161a9baa241ae7b98426a4c705cb21cb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 15 Jun 2016 15:48:08 -0300
Subject: [PATCH 02/17] perf annotate: Use pipe + fork instead of popen

We will need to redirect the stderr as well, so open code popen as
a starting point.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-k0zt9svg4bswiglem7ornts4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 39 ++++++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e9825fe825fd..2dd396a1f64b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1134,8 +1134,10 @@ 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);
@@ -1258,9 +1260,32 @@ 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 +1311,11 @@ 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 +1324,10 @@ 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)

From ce92834407a465c25c0be1a4a0339c625e44c4db Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 29 Jul 2016 11:54:35 -0300
Subject: [PATCH 03/17] perf target: str_error_r() always returns the buffer it
 receives

So no need for checking if it uses the strerror_r() GNU variant error
reporting mechanism, i.e. if it returns a pointer to a immutable string
internal to glibc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: c8b5f2c96d1b ("tools: Introduce str_error_r()")
Link: http://lkml.kernel.org/n/tip-xr83cd4y4r3cn6tq6w4f59jb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/target.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

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;
 	}
 

From 5cb725a9723aebb248106ff7f8c6c7253b24bbb1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 29 Jul 2016 16:44:56 -0300
Subject: [PATCH 04/17] perf annotate: Rename symbol__annotate() to
 symbol__disassemble()

This function will not annotate anything, it will just disassembly the
given map->dso and symbol.

It currently does this by parsing the output of 'objdump --disassemble',
but this could conceivably be done using a library or an offshot of
the kernel's instruction decoder (arch/x86/lib/inat.c), etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2xpfl4bfnrd6x584b390qok7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c          | 2 +-
 tools/perf/ui/browsers/annotate.c | 2 +-
 tools/perf/ui/gtk/annotate.c      | 2 +-
 tools/perf/util/annotate.c        | 4 ++--
 tools/perf/util/annotate.h        | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index bd108683fcb8..823dbbbf82a9 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -128,7 +128,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(sym, map, 0);
+	err = symbol__disassemble(sym, map, 0);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 29dc6d20364e..f4d6a8a962af 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1050,7 +1050,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
+	if (symbol__disassemble(sym, map, sizeof_bdl) < 0) {
 		ui__error("%s", ui_helpline__last_msg);
 		goto out_free_offsets;
 	}
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 9c7ff8d31b27..35e4b9e28c8d 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -166,7 +166,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	if (symbol__annotate(sym, map, 0) < 0) {
+	if (symbol__disassemble(sym, map, 0) < 0) {
 		ui__error("%s", ui_helpline__current);
 		return -1;
 	}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2dd396a1f64b..4f47b6069197 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1123,7 +1123,7 @@ static void delete_last_nop(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)
 {
 	struct dso *dso = map->dso;
 	char *filename = dso__build_id_filename(dso, NULL, 0);
@@ -1694,7 +1694,7 @@ 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..b0750d8bee1f 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -155,7 +155,7 @@ 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);
 
 int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,

From ee51d851392e1fe3e8be30b3c5847f34da343424 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 29 Jul 2016 16:27:18 -0300
Subject: [PATCH 05/17] perf annotate: Introduce strerror for handling
 symbol__disassemble() errors

We were just using pr_error() which makes it difficult for non stdio UIs
to provide errors using its widgets, as they need to somehow catch what
was passed to pr_error().

Fix it by introducing a __strerror() interface like the ones used
elsewhere, for instance target__strerror().

This is just the initial step, more work will be done, but first some
error handling bugs noticed while working on this need to be dealt with.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-dgd22zl2xg7x4vcnoa83jxfb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c          |  4 ++
 tools/perf/ui/browsers/annotate.c |  9 ++--
 tools/perf/ui/gtk/annotate.c      |  8 +++-
 tools/perf/util/annotate.c        | 68 +++++++++++++++++++------------
 tools/perf/util/annotate.h        | 20 +++++++++
 5 files changed, 78 insertions(+), 31 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 823dbbbf82a9..418ed94756d3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -132,6 +132,10 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;
+	} else {
+		char msg[BUFSIZ];
+		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+		pr_err("Couldn't annotate %s: %s\n", sym->name, msg);
 	}
 
 	pthread_mutex_unlock(&notes->lock);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index f4d6a8a962af..2e2d10022355 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1026,7 +1026,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			.use_navkeypressed = true,
 		},
 	};
-	int ret = -1;
+	int ret = -1, err;
 	int nr_pcnt = 1;
 	size_t sizeof_bdl = sizeof(struct browser_disasm_line);
 
@@ -1050,8 +1050,11 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	if (symbol__disassemble(sym, map, sizeof_bdl) < 0) {
-		ui__error("%s", ui_helpline__last_msg);
+	err = symbol__disassemble(sym, map, sizeof_bdl);
+	if (err) {
+		char msg[BUFSIZ];
+		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+		ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
 		goto out_free_offsets;
 	}
 
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 35e4b9e28c8d..42d319927762 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -162,12 +162,16 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	GtkWidget *notebook;
 	GtkWidget *scrolled_window;
 	GtkWidget *tab_label;
+	int err;
 
 	if (map->dso->annotate_warned)
 		return -1;
 
-	if (symbol__disassemble(sym, map, 0) < 0) {
-		ui__error("%s", ui_helpline__current);
+	err = symbol__disassemble(sym, map, 0);
+	if (err) {
+		char msg[BUFSIZ];
+		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+		ui__error("Couldn't annotate %s: %s\n", sym->name, msg);
 		return -1;
 	}
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4f47b6069197..4982ed487e96 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1123,6 +1123,45 @@ static void delete_last_nop(struct symbol *sym)
 	}
 }
 
+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;
@@ -1143,11 +1182,8 @@ int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
 		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;
@@ -1168,27 +1204,7 @@ 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;
 	}
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b0750d8bee1f..f67ccb027561 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -157,6 +157,26 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 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,
 			    struct perf_evsel *evsel, bool full_paths,

From c17c17e8c26a5d44b3a8a6ef8c55233d72eed6c0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 1 Aug 2016 18:49:13 -0300
Subject: [PATCH 06/17] perf annotate: Plug filename string leak

If dso__build_id_filename(..., NULL, ...) returns !NULL its because it
allocated it, so, when reaching the  'if (dso__is_kcore()) test, we
already checked that and were just "fallbacking" to using
dso->long_name, but without freeing filename, thus leaking it.

Fix it by adding the dso__is_kcore() test to the 'or' group just after
it, the one containing the full fallback code, including freeing the
filename.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: ee205503f233 ("perf tools: Fix annotation with kcore")
Link: http://lkml.kernel.org/n/tip-qi4rpjq8yo6myvg99kkgt0xz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4982ed487e96..4024d309bb00 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1185,9 +1185,8 @@ int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
 		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);

From b581c01fff646b5075d65359c8667de9c667da9e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 2 Aug 2016 11:43:17 +0900
Subject: [PATCH 07/17] perf tools: Fix build failure on perl script context

On my Archlinux machine, perf faild to build like below:

    CC       scripts/perl/Perf-Trace-Util/Context.o
  In file included from /usr/lib/perl5/core/perl/CORE/perl.h:3905:0,
                   from Context.xs:23:
  /usr/lib/perl5/core/perl/CORE/inline.h: In function :
  /usr/lib/perl5/core/perl/CORE/cop.h:612:13: warning: declaration of 'av'
                                  shadows a previous local [-Werror-shadow]
             AV *av =3D GvAV(PL_defgv);
                 ^
  /usr/lib/perl5/core/perl/CORE/inline.h:526:5: note: in expansion of
                                  macro 'CX_POP_SAVEARRAY'
         CX_POP_SAVEARRAY(cx);
         ^~~~~~~~~~~~~~~~
  In file included from /usr/lib/perl5/core/perl/CORE/perl.h:5853:0,
                   from Context.xs:23:
  /usr/lib/perl5/core/perl/CORE/inline.h:518:9: note:
                                  shadowed declaration is here
         AV *av;
             ^~

What I did to fix is adding '-Wno-shadow' as the error message said it's
the cause of the failure.  Since it's from the perl (not perf) code
base, we don't have the control so I just wanted to ignore the warning
when compiling perl scripting code.

Committer note:

This also fixes the build on Fedora Rawhide.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20160802024317.31725-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/perl/Perf-Trace-Util/Build | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Build b/tools/perf/scripts/perl/Perf-Trace-Util/Build
index 928e110179cb..34faecf774ae 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Build
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Build
@@ -1,3 +1,5 @@
 libperf-y += Context.o
 
-CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default
+CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes
+CFLAGS_Context.o += -Wno-unused-parameter -Wno-nested-externs -Wno-undef
+CFLAGS_Context.o += -Wno-switch-default -Wno-shadow

From 979a70a237efb68e15b1cee36f9f92037e71d1fd Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 2 Aug 2016 14:01:47 +0900
Subject: [PATCH 08/17] tools lib traceevent: Ignore generated library files

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20160802050148.3413-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore
index 3c60335fe7be..9e9f25fb1922 100644
--- a/tools/lib/traceevent/.gitignore
+++ b/tools/lib/traceevent/.gitignore
@@ -1,2 +1,3 @@
 TRACEEVENT-CFLAGS
 libtraceevent-dynamic-list
+libtraceevent.so.*

From 98c032967a299ee4bf14ef19eded02b65df32e6f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 2 Aug 2016 13:33:02 +0200
Subject: [PATCH 09/17] tools lib: Add bitmap_alloc function

Adding bitmap_alloc function to dynamically allocate bitmap.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20160802113302.GA7479@krava
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bitmap.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 28f5493da491..60c44b615902 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -3,6 +3,7 @@
 
 #include <string.h>
 #include <linux/bitops.h>
+#include <stdlib.h>
 
 #define DECLARE_BITMAP(name,bits) \
 	unsigned long name[BITS_TO_LONGS(bits)]
@@ -65,4 +66,13 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 	return (old & mask) != 0;
 }
 
+/**
+ * bitmap_alloc - Allocate bitmap
+ * @nr: Bit to set
+ */
+static inline unsigned long *bitmap_alloc(int nbits)
+{
+	return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
+}
+
 #endif /* _PERF_BITOPS_H */

From 820d12b70f91a19eb4a3152b9dd4ea9aee194a36 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:30 +0200
Subject: [PATCH 10/17] tools lib: Add bitmap_scnprintf function

Add support to print bitmap list. Code mostly taken from kernel's
bitmap_list_string.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-3-git-send-email-jolsa@kernel.org
[ s/bitmap_snprintf/bitmap_scnprintf/g as it is a scnprintf wrapper, having the same semantics wrt return value ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bitmap.h | 10 ++++++++++
 tools/lib/bitmap.c           | 29 +++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 60c44b615902..1cdded0041a8 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -75,4 +75,14 @@ static inline unsigned long *bitmap_alloc(int nbits)
 	return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
 }
 
+/*
+ * bitmap_scnprintf - print bitmap list into buffer
+ * @bitmap: bitmap
+ * @nbits: size of bitmap
+ * @buf: buffer to store output
+ * @size: size of @buf
+ */
+size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
+			char *buf, size_t size);
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 0a1adc1111fd..5c7e3185507c 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -29,3 +29,32 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 	for (k = 0; k < nr; k++)
 		dst[k] = bitmap1[k] | bitmap2[k];
 }
+
+size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
+			char *buf, size_t size)
+{
+	/* current bit is 'cur', most recently seen range is [rbot, rtop] */
+	int cur, rbot, rtop;
+	bool first = true;
+	size_t ret = 0;
+
+	rbot = cur = find_first_bit(bitmap, nbits);
+	while (cur < nbits) {
+		rtop = cur;
+		cur = find_next_bit(bitmap, nbits, cur + 1);
+		if (cur < nbits && cur <= rtop + 1)
+			continue;
+
+		if (!first)
+			ret += scnprintf(buf + ret, size - ret, ",");
+
+		first = false;
+
+		ret += scnprintf(buf + ret, size - ret, "%d", rbot);
+		if (rbot < rtop)
+			ret += scnprintf(buf + ret, size - ret, "-%d", rtop);
+
+		rbot = cur;
+	}
+	return ret;
+}

From 741c74f55e8a66f3bc5bbc29dc162c952759e47b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:31 +0200
Subject: [PATCH 11/17] tools lib: Add bitmap_and function

Add support to perform logical and on bitmaps.  Code taken from kernel's
include/linux/bitmap.h.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-4-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bitmap.h | 17 +++++++++++++++++
 tools/lib/bitmap.c           | 15 +++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 1cdded0041a8..43c1c5021e4b 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -11,6 +11,8 @@
 int __bitmap_weight(const unsigned long *bitmap, int bits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
+int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, unsigned int bits);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
@@ -85,4 +87,19 @@ static inline unsigned long *bitmap_alloc(int nbits)
 size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
 			char *buf, size_t size);
 
+/**
+ * bitmap_and - Do logical and on bitmaps
+ * @dst: resulting bitmap
+ * @src1: operand 1
+ * @src2: operand 2
+ * @nbits: size of bitmap
+ */
+static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+			     const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	return __bitmap_and(dst, src1, src2, nbits);
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 5c7e3185507c..38748b0e342f 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -58,3 +58,18 @@ size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
 	}
 	return ret;
 }
+
+int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k;
+	unsigned int lim = bits/BITS_PER_LONG;
+	unsigned long result = 0;
+
+	for (k = 0; k < lim; k++)
+		result |= (dst[k] = bitmap1[k] & bitmap2[k]);
+	if (bits % BITS_PER_LONG)
+		result |= (dst[k] = bitmap1[k] & bitmap2[k] &
+			   BITMAP_LAST_WORD_MASK(bits));
+	return result != 0;
+}

From ff3e33b075fe45c669e2cb27489d570e29d3abeb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:32 +0200
Subject: [PATCH 12/17] perf tests: Add test for bitmap_scnprintf function

Automatically test the bitmap_scnprintf function.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-5-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/Build          |  1 +
 tools/perf/tests/bitmap.c       | 53 +++++++++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c |  4 +++
 tools/perf/tests/tests.h        |  1 +
 4 files changed, 59 insertions(+)
 create mode 100644 tools/perf/tests/bitmap.c

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index cb20ae1c0d35..dc51bc570e51 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -41,6 +41,7 @@ perf-y += event-times.o
 perf-y += backward-ring-buffer.o
 perf-y += sdt.o
 perf-y += is_printable_array.o
+perf-y += bitmap.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
new file mode 100644
index 000000000000..9abe6c13090f
--- /dev/null
+++ b/tools/perf/tests/bitmap.c
@@ -0,0 +1,53 @@
+#include <linux/compiler.h>
+#include <linux/bitmap.h>
+#include "tests.h"
+#include "cpumap.h"
+#include "debug.h"
+
+#define NBITS 100
+
+static unsigned long *get_bitmap(const char *str, int nbits)
+{
+	struct cpu_map *map = cpu_map__new(str);
+	unsigned long *bm = NULL;
+	int i;
+
+	bm = bitmap_alloc(nbits);
+
+	if (map && bm) {
+		bitmap_zero(bm, nbits);
+
+		for (i = 0; i < map->nr; i++)
+			set_bit(map->map[i], bm);
+	}
+
+	if (map)
+		cpu_map__put(map);
+	return bm;
+}
+
+static int test_bitmap(const char *str)
+{
+	unsigned long *bm = get_bitmap(str, NBITS);
+	char buf[100];
+	int ret;
+
+	bitmap_scnprintf(bm, NBITS, buf, sizeof(buf));
+	pr_debug("bitmap: %s\n", buf);
+
+	ret = !strcmp(buf, str);
+	free(bm);
+	return ret;
+}
+
+int test__bitmap_print(int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3,5,7,9,11,13,15,17,19,21-40"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("2-5"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37"));
+	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40"));
+	return 0;
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 10eb30686c9c..778668a2a966 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -225,6 +225,10 @@ static struct test generic_tests[] = {
 		.desc = "Test is_printable_array function",
 		.func = test__is_printable_array,
 	},
+	{
+		.desc = "Test bitmap print",
+		.func = test__bitmap_print,
+	},
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 9bfc0e06c61a..7c196c585472 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -90,6 +90,7 @@ int test__backward_ring_buffer(int subtest);
 int test__cpu_map_print(int subtest);
 int test__sdt_event(int subtest);
 int test__is_printable_array(int subtest);
+int test__bitmap_print(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT

From 4842576cd857887ddfed58f452af38b9457639d7 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:33 +0200
Subject: [PATCH 13/17] perf tools: Move config/Makefile into Makefile.config

There's no reason to keep it in separate directory now when we moved out
the rest of the files.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-6-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/{config/Makefile => Makefile.config} | 0
 tools/perf/Makefile.perf                        | 6 +++---
 2 files changed, 3 insertions(+), 3 deletions(-)
 rename tools/perf/{config/Makefile => Makefile.config} (100%)

diff --git a/tools/perf/config/Makefile b/tools/perf/Makefile.config
similarity index 100%
rename from tools/perf/config/Makefile
rename to tools/perf/Makefile.config
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 6641abb97f0a..2d9087501633 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -161,7 +161,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR		= $(srctree)/tools/lib/bpf/
 SUBCMD_DIR	= $(srctree)/tools/lib/subcmd/
 
-# include config/Makefile by default and rule out
+# include Makefile.config by default and rule out
 # non-config cases
 config := 1
 
@@ -183,7 +183,7 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
 FEATURE_TESTS := all
 endif
 endif
-include config/Makefile
+include Makefile.config
 endif
 
 ifeq ($(config),0)
@@ -706,7 +706,7 @@ $(INSTALL_DOC_TARGETS):
 ### Cleaning rules
 
 #
-# This is here, not in config/Makefile, because config/Makefile does
+# This is here, not in Makefile.config, because Makefile.config does
 # not get included for the clean target:
 #
 config-clean:

From 52c5cc363f2c5f50e88d2d340c039cc72797d69a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:34 +0200
Subject: [PATCH 14/17] perf hists: Introduce output_resort_cb method

When dealing with nested hist entries it's helpful to have a way to
resort those nested objects.

Adding optional callback call into output_resort function and following
new interface function:

  typedef int (*hists__resort_cb_t)(struct hist_entry *he);

  void hists__output_resort_cb(struct hists *hists,
                               struct ui_progress *prog,
                               hists__resort_cb_t cb);

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-7-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 15 ++++++++++++---
 tools/perf/util/hist.h |  4 ++++
 2 files changed, 16 insertions(+), 3 deletions(-)

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);

From b6f35ed774aeaf441e66cfa243fd1dff1321d69e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Aug 2016 20:02:35 +0200
Subject: [PATCH 15/17] perf record: Add --sample-cpu option

Adding --sample-cpu option to be able to explicitly enable CPU sample
type. Currently it's only enable implicitly in case the target is cpu
related.

It will be useful for following c2c record tool.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1470074555-24889-8-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-record.txt | 3 +++
 tools/perf/builtin-record.c              | 1 +
 tools/perf/perf.h                        | 1 +
 tools/perf/util/evsel.c                  | 2 +-
 4 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 69966abf65d1..379a2bed07c0 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -192,6 +192,9 @@ OPTIONS
 --period::
 	Record the sample period.
 
+--sample-cpu::
+	Record the sample cpu.
+
 -n::
 --no-samples::
 	Don't sample.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8f2c16d9275f..6355902fbfc8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1434,6 +1434,7 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
 	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+	OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
 	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
 			&record.opts.sample_time_set,
 			"Record the sample timestamps"),
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a7e0f1497244..cb0f1356ff81 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -52,6 +52,7 @@ struct record_opts {
 	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     sample_time_set;
+	bool	     sample_cpu;
 	bool	     period;
 	bool	     running_time;
 	bool	     full_auxtrace;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4c2b31dc4e4d..d9b80ef881cd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -882,7 +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)

From b2d0dbf09772d091368261ce95db3afce45d994d Mon Sep 17 00:00:00 2001
From: Jan Stancek <jstancek@redhat.com>
Date: Tue, 12 Jan 2016 11:07:44 +0100
Subject: [PATCH 16/17] perf tests: objdump output can contain multi byte
 chunks

objdump's raw insn output can vary across architectures on the number of
bytes per chunk (bpc) displayed and their endianness.

The code-reading test relied on reading objdump output as 1 bpc. Kaixu
Xia reported test failure on ARM64, where objdump displays 4 bpc:

  70c48:        f90027bf         str        xzr, [x29,#72]
  70c4c:        91224000         add        x0, x0, #0x890
  70c50:        f90023a0         str        x0, [x29,#64]

This patch adds support to read raw insn output for any bpc length.
In case of 2+ bpc it also guesses objdump's display endian.

Reported-and-Tested-by: Kaixu Xia <xiakaixu@huawei.com>
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/07f0f7bcbda78deb423298708ef9b6a54d6b92bd.1452592712.git.jstancek@redhat.com
[ Fix up pr_fmt() call to use %zd for size_t variables, fixing the build on Ubuntu cross-compiling to armhf and ppc64 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/code-reading.c | 100 +++++++++++++++++++++++---------
 1 file changed, 71 insertions(+), 29 deletions(-)

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 68a69a195545..2af156a8d4e5 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -33,44 +33,86 @@ static unsigned int hex(char c)
 	return c - 'A' + 10;
 }
 
-static size_t read_objdump_line(const char *line, size_t line_len, void *buf,
-			      size_t len)
+static size_t read_objdump_chunk(const char **line, unsigned char **buf,
+				 size_t *buf_len)
+{
+	size_t bytes_read = 0;
+	unsigned char *chunk_start = *buf;
+
+	/* Read bytes */
+	while (*buf_len > 0) {
+		char c1, c2;
+
+		/* Get 2 hex digits */
+		c1 = *(*line)++;
+		if (!isxdigit(c1))
+			break;
+		c2 = *(*line)++;
+		if (!isxdigit(c2))
+			break;
+
+		/* Store byte and advance buf */
+		**buf = (hex(c1) << 4) | hex(c2);
+		(*buf)++;
+		(*buf_len)--;
+		bytes_read++;
+
+		/* End of chunk? */
+		if (isspace(**line))
+			break;
+	}
+
+	/*
+	 * objdump will display raw insn as LE if code endian
+	 * is LE and bytes_per_chunk > 1. In that case reverse
+	 * the chunk we just read.
+	 *
+	 * see disassemble_bytes() at binutils/objdump.c for details
+	 * how objdump chooses display endian)
+	 */
+	if (bytes_read > 1 && !bigendian()) {
+		unsigned char *chunk_end = chunk_start + bytes_read - 1;
+		unsigned char tmp;
+
+		while (chunk_start < chunk_end) {
+			tmp = *chunk_start;
+			*chunk_start = *chunk_end;
+			*chunk_end = tmp;
+			chunk_start++;
+			chunk_end--;
+		}
+	}
+
+	return bytes_read;
+}
+
+static size_t read_objdump_line(const char *line, unsigned char *buf,
+				size_t buf_len)
 {
 	const char *p;
-	size_t i, j = 0;
+	size_t ret, bytes_read = 0;
 
 	/* Skip to a colon */
 	p = strchr(line, ':');
 	if (!p)
 		return 0;
-	i = p + 1 - line;
+	p++;
 
-	/* Read bytes */
-	while (j < len) {
-		char c1, c2;
-
-		/* Skip spaces */
-		for (; i < line_len; i++) {
-			if (!isspace(line[i]))
-				break;
-		}
-		/* Get 2 hex digits */
-		if (i >= line_len || !isxdigit(line[i]))
+	/* Skip initial spaces */
+	while (*p) {
+		if (!isspace(*p))
 			break;
-		c1 = line[i++];
-		if (i >= line_len || !isxdigit(line[i]))
-			break;
-		c2 = line[i++];
-		/* Followed by a space */
-		if (i < line_len && line[i] && !isspace(line[i]))
-			break;
-		/* Store byte */
-		*(unsigned char *)buf = (hex(c1) << 4) | hex(c2);
-		buf += 1;
-		j++;
+		p++;
 	}
+
+	do {
+		ret = read_objdump_chunk(&p, &buf, &buf_len);
+		bytes_read += ret;
+		p++;
+	} while (ret > 0);
+
 	/* return number of successfully read bytes */
-	return j;
+	return bytes_read;
 }
 
 static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
@@ -95,7 +137,7 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
 		}
 
 		/* read objdump data into temporary buffer */
-		read_bytes = read_objdump_line(line, ret, tmp, sizeof(tmp));
+		read_bytes = read_objdump_line(line, tmp, sizeof(tmp));
 		if (!read_bytes)
 			continue;
 
@@ -152,7 +194,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 
 	ret = read_objdump_output(f, buf, &len, addr);
 	if (len) {
-		pr_debug("objdump read too few bytes\n");
+		pr_debug("objdump read too few bytes: %zd\n", len);
 		if (!ret)
 			ret = len;
 	}

From c369e0a1a8fa6ca80e6c37c8735d9427b623ae62 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 2 Aug 2016 16:48:19 -0300
Subject: [PATCH 17/17] perf tests bpf: Use SyS_epoll_wait alias

Something made the sys_epoll_wait() function alias not to be found in
the vmlinux DWARF info, being found only in /proc/kallsyms, which made
the BPF perf tests to fail:

  [root@jouet ~]# perf test BPF
  37: Test BPF filter                                          :
  37.1: Test basic BPF filtering                               : FAILED!
  37.2: Test BPF prologue generation                           : Skip
  37.3: Test BPF relocation checker                            : Skip
  [root@jouet ~]#

Using -v we can see it is failing to find DWARF info for the probed function,
sys_epoll_wait, which we can find in /proc/kallsyms but not in vmlinux with
CONFIG_DEBUG_INFO:

  [root@jouet ~]# grep -w sys_epoll_wait /proc/kallsyms
  ffffffffbd295b50 T sys_epoll_wait
  [root@jouet ~]#

  [root@jouet ~]# readelf -wi /lib/modules/4.7.0+/build/vmlinux | grep -w sys_epoll_wait
  [root@jouet ~]#

If we try to use perf probe:

[root@jouet ~]# perf probe sys_epoll_wait
Failed to find debug information for address ffffffffbd295b50
Probe point 'sys_epoll_wait' not found.
  Error: Failed to add events.
[root@jouet ~]#

It all works if we use SyS_epoll_wait, that is just an alias to the probed
function:

  [root@jouet ~]# grep -i sys_epoll_wait /proc/kallsyms
  ffffffffbd295b50 T SyS_epoll_wait
  ffffffffbd295b50 T sys_epoll_wait
  [root@jouet ~]#

So use it:

  [root@jouet ~]# perf test BPF
  37: Test BPF filter                                          :
  37.1: Test basic BPF filtering                               : Ok
  37.2: Test BPF prologue generation                           : Ok
  37.3: Test BPF relocation checker                            : Ok
  [root@jouet ~]#

Further info:

  [root@jouet ~]# gcc --version
  gcc (GCC) 6.1.1 20160621 (Red Hat 6.1.1-3)
  [acme@jouet linux]$ cat /etc/fedora-release
  Fedora release 24 (Twenty Four)

Investigation as to why it fails is still underway, but it was always
going from sys_epoll_wait to SyS_epoll_wait when looking up the DWARF
info in vmlinux, and this is what is breaking now.

Switching to use SyS_epoll_wait allows this test to proceed and test the
BPF code it was designed for, so lets have this in to allow passing this
test while we fix the root cause.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-7hekjp0bodwjbb419sl2b55h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf-script-example.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index e53bc91fa260..268e5f8e4aa2 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = {
 	.max_entries = 1,
 };
 
-SEC("func=sys_epoll_wait")
-int bpf_func__sys_epoll_wait(void *ctx)
+SEC("func=SyS_epoll_wait")
+int bpf_func__SyS_epoll_wait(void *ctx)
 {
 	int ind =0;
 	int *flag = bpf_map_lookup_elem(&flip_table, &ind);