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

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

User visible changes:

  - Fix SIGBUS failures due to misaligned accesses in Sparc64 (David Ahern)

  - Fix branch stack mode in 'perf report' (He Kuang)

  - Fix a 'perf probe' operator precedence bug (He Kuang)

  - Fix Support for different binaries with same name in 'perf diff' (Kan Liang)

  - Check kprobes blacklist when adding new events via 'perf probe' (Masami Hiramatsu)

  - Add --purge FILE to remove all caches of FILE in 'perf buildid-cache' (Masami Hiramatsu)

  - Show usage with some incorrect params (Masami Hiramatsu)

  - Add new buildid cache if update target is not cached in 'buildid-cache' (Masami Hiramatsu)

  - Allow listing events with 'tracepoint' prefix in 'perf list' (Yunlong Song)

  - Sort the output of 'perf list' (Yunlong Song)

  - Fix bash completion of 'perf --' (Yunlong Song)

Developer Zone:

  - Handle strdup() failure path in 'perf probe' (Arnaldo Carvalho de Melo)

  - Fix get_real_path to free allocated memory in error path in 'perf probe' (Masami Hiramatsu)

  - Use pr_debug instead of verbose && pr_info perf buildid-cache (Masami Hiramatsu)

  - Fix building of 'perf data' with some gcc versions due to incorrect array struct
    entry (Yunlong Song)

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

17 files changed, 542 insertions, 127 deletions

diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 0294c57b1f5e..dd07b55f58d8 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command manages the build-id cache. It can add and remove files to/from
-the cache. In the future it should as well purge older entries, set upper
-limits for the space used by the cache, etc.
+This command manages the build-id cache. It can add, remove, update and purge
+files to/from the cache. In the future it should as well set upper limits for
+the space used by the cache, etc.
 
 OPTIONS
 -------
@@ -36,14 +36,24 @@ OPTIONS
         actually made.
 -r::
 --remove=::
-        Remove specified file from the cache.
+        Remove a cached binary which has same build-id of specified file
+        from the cache.
+-p::
+--purge=::
+        Purge all cached binaries including older caches which have specified
+	path from the cache.
 -M::
 --missing=::
 	List missing build ids in the cache for the specified file.
 -u::
---update::
-	Update specified file of the cache. It can be used to update kallsyms
-	kernel dso to vmlinux in order to support annotation.
+--update=::
+	Update specified file of the cache. Note that this doesn't remove
+	older entires since those may be still needed for annotating old
+	(or remote) perf.data. Only if there is already a cache which has
+	exactly same build-id, that is replaced by new one. It can be used
+	to update kallsyms and kernel dso to vmlinux in order to support
+	annotation.
+
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index e463caa3eb49..518266192d67 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -20,6 +20,11 @@ If no parameters are passed it will assume perf.data.old and perf.data.
 The differential profile is displayed only for events matching both
 specified perf.data files.
 
+If no parameters are passed the samples will be sorted by dso and symbol.
+As the perf.data files could come from different binaries, the symbols addresses
+could vary. So perf diff is based on the comparison of the files and
+symbols name.
+
 OPTIONS
 -------
 -D::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 3e2aec94f806..4692d277980b 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -127,6 +127,12 @@ To limit the list use:
 One or more types can be used at the same time, listing the events for the
 types specified.
 
+Support raw format:
+
+. '--raw-dump', shows the raw-dump of all the events.
+. '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of
+  a certain kind of events.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-top[1],
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d929d9544664..d47a0cdc71c9 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -196,9 +196,8 @@ static int build_id_cache__add_file(const char *filename)
 	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
 	err = build_id_cache__add_s(sbuild_id, filename,
 				    false, false);
-	if (verbose)
-		pr_info("Adding %s %s: %s\n", sbuild_id, filename,
-			err ? "FAIL" : "Ok");
+	pr_debug("Adding %s %s: %s\n", sbuild_id, filename,
+		 err ? "FAIL" : "Ok");
 	return err;
 }
 
@@ -216,9 +215,33 @@ static int build_id_cache__remove_file(const char *filename)
 
 	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
 	err = build_id_cache__remove_s(sbuild_id);
-	if (verbose)
-		pr_info("Removing %s %s: %s\n", sbuild_id, filename,
-			err ? "FAIL" : "Ok");
+	pr_debug("Removing %s %s: %s\n", sbuild_id, filename,
+		 err ? "FAIL" : "Ok");
+
+	return err;
+}
+
+static int build_id_cache__purge_path(const char *pathname)
+{
+	struct strlist *list;
+	struct str_node *pos;
+	int err;
+
+	err = build_id_cache__list_build_ids(pathname, &list);
+	if (err)
+		goto out;
+
+	strlist__for_each(pos, list) {
+		err = build_id_cache__remove_s(pos->s);
+		pr_debug("Removing %s %s: %s\n", pos->s, pathname,
+			 err ? "FAIL" : "Ok");
+		if (err)
+			break;
+	}
+	strlist__delete(list);
+
+out:
+	pr_debug("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok");
 
 	return err;
 }
@@ -255,7 +278,7 @@ static int build_id_cache__update_file(const char *filename)
 	u8 build_id[BUILD_ID_SIZE];
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-	int err;
+	int err = 0;
 
 	if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
@@ -263,13 +286,14 @@ static int build_id_cache__update_file(const char *filename)
 	}
 
 	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-	err = build_id_cache__remove_s(sbuild_id);
+	if (build_id_cache__cached(sbuild_id))
+		err = build_id_cache__remove_s(sbuild_id);
+
 	if (!err)
 		err = build_id_cache__add_s(sbuild_id, filename, false, false);
 
-	if (verbose)
-		pr_info("Updating %s %s: %s\n", sbuild_id, filename,
-			err ? "FAIL" : "Ok");
+	pr_debug("Updating %s %s: %s\n", sbuild_id, filename,
+		 err ? "FAIL" : "Ok");
 
 	return err;
 }
@@ -283,6 +307,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	bool force = false;
 	char const *add_name_list_str = NULL,
 		   *remove_name_list_str = NULL,
+		   *purge_name_list_str = NULL,
 		   *missing_filename = NULL,
 		   *update_name_list_str = NULL,
 		   *kcore_filename = NULL;
@@ -300,6 +325,8 @@ int cmd_buildid_cache(int argc, const char **argv,
 		   "file", "kcore file to add"),
 	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
 		    "file(s) to remove"),
+	OPT_STRING('p', "purge", &purge_name_list_str, "path list",
+		    "path(s) to remove (remove old caches too)"),
 	OPT_STRING('M', "missing", &missing_filename, "file",
 		   "to find missing build ids in the cache"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -316,6 +343,11 @@ int cmd_buildid_cache(int argc, const char **argv,
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
 
+	if (argc || (!add_name_list_str && !kcore_filename &&
+		     !remove_name_list_str && !purge_name_list_str &&
+		     !missing_filename && !update_name_list_str))
+		usage_with_options(buildid_cache_usage, buildid_cache_options);
+
 	if (missing_filename) {
 		file.path = missing_filename;
 		file.force = force;
@@ -366,6 +398,24 @@ int cmd_buildid_cache(int argc, const char **argv,
 		}
 	}
 
+	if (purge_name_list_str) {
+		list = strlist__new(true, purge_name_list_str);
+		if (list) {
+			strlist__for_each(pos, list)
+				if (build_id_cache__purge_path(pos->s)) {
+					if (errno == ENOENT) {
+						pr_debug("%s wasn't in the cache\n",
+							 pos->s);
+						continue;
+					}
+					pr_warning("Couldn't remove %s: %s\n",
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+				}
+
+			strlist__delete(list);
+		}
+	}
+
 	if (missing_filename)
 		ret = build_id_cache__fprintf_missing(session, stdout);
 
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 9705ba7e4c16..155cf75b8199 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -86,7 +86,7 @@ static int cmd_data_convert(int argc, const char **argv,
 
 static struct data_cmd data_cmds[] = {
 	{ "convert", "converts data file between formats", cmd_data_convert },
-	{ NULL },
+	{ .name = NULL, },
 };
 
 int cmd_data(int argc, const char **argv, const char *prefix)
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index ad8018e26aa0..af5bd0514108 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -36,41 +36,36 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_pager();
 
-	if (raw_dump) {
-		print_events(NULL, true);
-		return 0;
-	}
-
 	if (!raw_dump)
 		printf("\nList of pre-defined events (to be used in -e):\n\n");
 
 	if (argc == 0) {
-		print_events(NULL, false);
+		print_events(NULL, raw_dump);
 		return 0;
 	}
 
 	for (i = 0; i < argc; ++i) {
-		if (i)
-			putchar('\n');
-		if (strncmp(argv[i], "tracepoint", 10) == 0)
-			print_tracepoint_events(NULL, NULL, false);
+		if (strcmp(argv[i], "tracepoint") == 0)
+			print_tracepoint_events(NULL, NULL, raw_dump);
 		else if (strcmp(argv[i], "hw") == 0 ||
 			 strcmp(argv[i], "hardware") == 0)
-			print_events_type(PERF_TYPE_HARDWARE);
+			print_symbol_events(NULL, PERF_TYPE_HARDWARE,
+					event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 		else if (strcmp(argv[i], "sw") == 0 ||
 			 strcmp(argv[i], "software") == 0)
-			print_events_type(PERF_TYPE_SOFTWARE);
+			print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
+					event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
 		else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
-			print_hwcache_events(NULL, false);
+			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
-			print_pmu_events(NULL, false);
+			print_pmu_events(NULL, raw_dump);
 		else {
 			char *sep = strchr(argv[i], ':'), *s;
 			int sep_idx;
 
 			if (sep == NULL) {
-				print_events(argv[i], false);
+				print_events(argv[i], raw_dump);
 				continue;
 			}
 			sep_idx = sep - argv[i];
@@ -79,7 +74,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 				return -1;
 
 			s[sep_idx] = '\0';
-			print_tracepoint_events(s, s + sep_idx + 1, false);
+			print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
 			free(s);
 		}
 	}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0ba5f07906fb..fb350343b1d7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -768,7 +768,7 @@ repeat:
 	 * 0/1 means the user chose a mode.
 	 */
 	if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) &&
-	    branch_call_mode == -1) {
+	    !branch_call_mode) {
 		sort__mode = SORT_MODE__BRANCH;
 		symbol_conf.cumulate_callchain = false;
 	}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5cd8497445fe..d95a8f4d988c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -52,7 +52,9 @@ struct tp_field {
 #define TP_UINT_FIELD(bits) \
 static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
 { \
-	return *(u##bits *)(sample->raw_data + field->offset); \
+	u##bits value; \
+	memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
+	return value;  \
 }
 
 TP_UINT_FIELD(8);
@@ -63,7 +65,8 @@ TP_UINT_FIELD(64);
 #define TP_UINT_FIELD__SWAPPED(bits) \
 static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
 { \
-	u##bits value = *(u##bits *)(sample->raw_data + field->offset); \
+	u##bits value; \
+	memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
 	return bswap_##bits(value);\
 }
 
@@ -1517,11 +1520,22 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	return syscall__set_arg_fmts(sc);
 }
 
+/*
+ * args is to be interpreted as a series of longs but we need to handle
+ * 8-byte unaligned accesses. args points to raw_data within the event
+ * and raw_data is guaranteed to be 8-byte unaligned because it is
+ * preceded by raw_size which is a u32. So we need to copy args to a temp
+ * variable to read it. Most notably this avoids extended load instructions
+ * on unaligned addresses
+ */
+
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
-				      unsigned long *args, struct trace *trace,
+				      unsigned char *args, struct trace *trace,
 				      struct thread *thread)
 {
 	size_t printed = 0;
+	unsigned char *p;
+	unsigned long val;
 
 	if (sc->tp_format != NULL) {
 		struct format_field *field;
@@ -1537,12 +1551,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 		     field = field->next, ++arg.idx, bit <<= 1) {
 			if (arg.mask & bit)
 				continue;
+
+			/* special care for unaligned accesses */
+			p = args + sizeof(unsigned long) * arg.idx;
+			memcpy(&val, p, sizeof(val));
+
 			/*
  			 * Suppress this argument if its value is zero and
  			 * and we don't have a string associated in an
  			 * strarray for it.
  			 */
-			if (args[arg.idx] == 0 &&
+			if (val == 0 &&
 			    !(sc->arg_scnprintf &&
 			      sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
 			      sc->arg_parm[arg.idx]))
@@ -1551,23 +1570,26 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 			printed += scnprintf(bf + printed, size - printed,
 					     "%s%s: ", printed ? ", " : "", field->name);
 			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
-				arg.val = args[arg.idx];
+				arg.val = val;
 				if (sc->arg_parm)
 					arg.parm = sc->arg_parm[arg.idx];
 				printed += sc->arg_scnprintf[arg.idx](bf + printed,
 								      size - printed, &arg);
 			} else {
 				printed += scnprintf(bf + printed, size - printed,
-						     "%ld", args[arg.idx]);
+						     "%ld", val);
 			}
 		}
 	} else {
 		int i = 0;
 
 		while (i < 6) {
+			/* special care for unaligned accesses */
+			p = args + sizeof(unsigned long) * i;
+			memcpy(&val, p, sizeof(val));
 			printed += scnprintf(bf + printed, size - printed,
 					     "%sarg%d: %ld",
-					     printed ? ", " : "", i, args[i]);
+					     printed ? ", " : "", i, val);
 			++i;
 		}
 	}
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index 33569847fdcc..c2595e9bd69b 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -110,13 +110,11 @@ __perf_main ()
 	# List perf subcommands or long options
 	if [ $cword -eq 1 ]; then
 		if [[ $cur == --* ]]; then
-			__perfcomp '--help --version \
-			--exec-path --html-path --paginate --no-pager \
-			--perf-dir --work-tree --debugfs-dir' -- "$cur"
+			cmds=$($cmd --list-opts)
 		else
 			cmds=$($cmd --list-cmds)
-			__perfcomp "$cmds" "$cur"
 		fi
+		__perfcomp "$cmds" "$cur"
 	# List possible events for -e option
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index f3c66b81c6be..b857fcbd00cf 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,6 +13,7 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
+#include "util/parse-options.h"
 #include "util/debug.h"
 #include <api/fs/debugfs.h>
 #include <pthread.h>
@@ -125,6 +126,23 @@ static void commit_pager_choice(void)
 	}
 }
 
+struct option options[] = {
+	OPT_ARGUMENT("help", "help"),
+	OPT_ARGUMENT("version", "version"),
+	OPT_ARGUMENT("exec-path", "exec-path"),
+	OPT_ARGUMENT("html-path", "html-path"),
+	OPT_ARGUMENT("paginate", "paginate"),
+	OPT_ARGUMENT("no-pager", "no-pager"),
+	OPT_ARGUMENT("perf-dir", "perf-dir"),
+	OPT_ARGUMENT("work-tree", "work-tree"),
+	OPT_ARGUMENT("debugfs-dir", "debugfs-dir"),
+	OPT_ARGUMENT("buildid-dir", "buildid-dir"),
+	OPT_ARGUMENT("list-cmds", "list-cmds"),
+	OPT_ARGUMENT("list-opts", "list-opts"),
+	OPT_ARGUMENT("debug", "debug"),
+	OPT_END()
+};
+
 static int handle_options(const char ***argv, int *argc, int *envchanged)
 {
 	int handled = 0;
@@ -223,6 +241,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 				struct cmd_struct *p = commands+i;
 				printf("%s ", p->cmd);
 			}
+			putchar('\n');
+			exit(0);
+		} else if (!strcmp(cmd, "--list-opts")) {
+			unsigned int i;
+
+			for (i = 0; i < ARRAY_SIZE(options)-1; i++) {
+				struct option *p = options+i;
+				printf("--%s ", p->long_name);
+			}
+			putchar('\n');
 			exit(0);
 		} else if (!strcmp(cmd, "--debug")) {
 			if (*argc < 2) {
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index adbc36028636..ffdc338df925 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -281,35 +281,93 @@ void disable_buildid_cache(void)
 	no_buildid_cache = true;
 }
 
+static char *build_id_cache__dirname_from_path(const char *name,
+					       bool is_kallsyms, bool is_vdso)
+{
+	char *realname = (char *)name, *filename;
+	bool slash = is_kallsyms || is_vdso;
+
+	if (!slash) {
+		realname = realpath(name, NULL);
+		if (!realname)
+			return NULL;
+	}
+
+	if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "",
+		     is_vdso ? DSO__NAME_VDSO : realname) < 0)
+		filename = NULL;
+
+	if (!slash)
+		free(realname);
+
+	return filename;
+}
+
+int build_id_cache__list_build_ids(const char *pathname,
+				   struct strlist **result)
+{
+	struct strlist *list;
+	char *dir_name;
+	DIR *dir;
+	struct dirent *d;
+	int ret = 0;
+
+	list = strlist__new(true, NULL);
+	dir_name = build_id_cache__dirname_from_path(pathname, false, false);
+	if (!list || !dir_name) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* List up all dirents */
+	dir = opendir(dir_name);
+	if (!dir) {
+		ret = -errno;
+		goto out;
+	}
+
+	while ((d = readdir(dir)) != NULL) {
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+		strlist__add(list, d->d_name);
+	}
+	closedir(dir);
+
+out:
+	free(dir_name);
+	if (ret)
+		strlist__delete(list);
+	else
+		*result = list;
+
+	return ret;
+}
+
 int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			  bool is_kallsyms, bool is_vdso)
 {
 	const size_t size = PATH_MAX;
-	char *realname, *filename = zalloc(size),
+	char *realname = NULL, *filename = NULL, *dir_name = NULL,
 	     *linkname = zalloc(size), *targetname, *tmp;
-	int len, err = -1;
-	bool slash = is_kallsyms || is_vdso;
+	int err = -1;
 
-	if (is_kallsyms) {
-		if (symbol_conf.kptr_restrict) {
-			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			err = 0;
-			goto out_free;
-		}
-		realname = (char *) name;
-	} else
+	if (!is_kallsyms) {
 		realname = realpath(name, NULL);
+		if (!realname)
+			goto out_free;
+	}
 
-	if (realname == NULL || filename == NULL || linkname == NULL)
+	dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso);
+	if (!dir_name)
 		goto out_free;
 
-	len = scnprintf(filename, size, "%s%s%s",
-		       buildid_dir, slash ? "/" : "",
-		       is_vdso ? DSO__NAME_VDSO : realname);
-	if (mkdir_p(filename, 0755))
+	if (mkdir_p(dir_name, 0755))
 		goto out_free;
 
-	snprintf(filename + len, size - len, "/%s", sbuild_id);
+	if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
+		filename = NULL;
+		goto out_free;
+	}
 
 	if (access(filename, F_OK)) {
 		if (is_kallsyms) {
@@ -337,6 +395,7 @@ out_free:
 	if (!is_kallsyms)
 		free(realname);
 	free(filename);
+	free(dir_name);
 	free(linkname);
 	return err;
 }
@@ -352,6 +411,18 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 	return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso);
 }
 
+bool build_id_cache__cached(const char *sbuild_id)
+{
+	bool ret = false;
+	char *filename = build_id__filename(sbuild_id, NULL, 0);
+
+	if (filename && !access(filename, F_OK))
+		ret = true;
+	free(filename);
+
+	return ret;
+}
+
 int build_id_cache__remove_s(const char *sbuild_id)
 {
 	const size_t size = PATH_MAX;
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 31b3c6332a1a..85011222cc14 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -4,6 +4,7 @@
 #define BUILD_ID_SIZE 20
 
 #include "tool.h"
+#include "strlist.h"
 #include <linux/types.h>
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
@@ -22,6 +23,9 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
 int perf_session__write_buildid_table(struct perf_session *session, int fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
+int build_id_cache__list_build_ids(const char *pathname,
+				   struct strlist **result);
+bool build_id_cache__cached(const char *sbuild_id);
 int build_id_cache__add_s(const char *sbuild_id,
 			  const char *name, bool is_kallsyms, bool is_vdso);
 int build_id_cache__remove_s(const char *sbuild_id);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 109ba5c8c2e5..fe07573d5ed4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -20,11 +20,6 @@
 
 #define MAX_NAME_LEN 100
 
-struct event_symbol {
-	const char	*symbol;
-	const char	*alias;
-};
-
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
@@ -39,7 +34,7 @@ static struct perf_pmu_event_symbol *perf_pmu_events_list;
  */
 static int perf_pmu_events_list_num;
 
-static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
 		.alias  = "cycles",
@@ -82,7 +77,7 @@ static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	},
 };
 
-static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 	[PERF_COUNT_SW_CPU_CLOCK] = {
 		.symbol = "cpu-clock",
 		.alias  = "",
@@ -1089,6 +1084,14 @@ static const char * const event_type_descriptors[] = {
 	"Hardware breakpoint",
 };
 
+static int cmp_string(const void *a, const void *b)
+{
+	const char * const *as = a;
+	const char * const *bs = b;
+
+	return strcmp(*as, *bs);
+}
+
 /*
  * Print the events from <debugfs_mount_point>/tracing/events
  */
@@ -1100,11 +1103,21 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
+	char **evt_list = NULL;
+	unsigned int evt_i = 0, evt_num = 0;
+	bool evt_num_known = false;
 
+restart:
 	sys_dir = opendir(tracing_events_path);
 	if (!sys_dir)
 		return;
 
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_close_sys_dir;
+	}
+
 	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
 		if (subsys_glob != NULL &&
 		    !strglobmatch(sys_dirent.d_name, subsys_glob))
@@ -1121,19 +1134,56 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			    !strglobmatch(evt_dirent.d_name, event_glob))
 				continue;
 
-			if (name_only) {
-				printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name);
+			if (!evt_num_known) {
+				evt_num++;
 				continue;
 			}
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
-			printf("  %-50s [%s]\n", evt_path,
-				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
+
+			evt_list[evt_i] = strdup(evt_path);
+			if (evt_list[evt_i] == NULL)
+				goto out_close_evt_dir;
+			evt_i++;
 		}
 		closedir(evt_dir);
 	}
 	closedir(sys_dir);
+
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++],
+				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
+	}
+	if (evt_num)
+		printf("\n");
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+	return;
+
+out_close_evt_dir:
+	closedir(evt_dir);
+out_close_sys_dir:
+	closedir(sys_dir);
+
+	printf("FATAL: not enough memory to print %s\n",
+			event_type_descriptors[PERF_TYPE_TRACEPOINT]);
+	if (evt_list)
+		goto out_free;
 }
 
 /*
@@ -1214,38 +1264,19 @@ static bool is_event_supported(u8 type, unsigned config)
 	return ret;
 }
 
-static void __print_events_type(u8 type, struct event_symbol *syms,
-				unsigned max)
-{
-	char name[64];
-	unsigned i;
-
-	for (i = 0; i < max ; i++, syms++) {
-		if (!is_event_supported(type, i))
-			continue;
-
-		if (strlen(syms->alias))
-			snprintf(name, sizeof(name),  "%s OR %s",
-				 syms->symbol, syms->alias);
-		else
-			snprintf(name, sizeof(name), "%s", syms->symbol);
-
-		printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
-	}
-}
-
-void print_events_type(u8 type)
-{
-	if (type == PERF_TYPE_SOFTWARE)
-		__print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX);
-	else
-		__print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
-}
-
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
-	unsigned int type, op, i, printed = 0;
+	unsigned int type, op, i, evt_i = 0, evt_num = 0;
 	char name[64];
+	char **evt_list = NULL;
+	bool evt_num_known = false;
+
+restart:
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_enomem;
+	}
 
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
@@ -1263,27 +1294,66 @@ int print_hwcache_events(const char *event_glob, bool name_only)
 							type | (op << 8) | (i << 16)))
 					continue;
 
-				if (name_only)
-					printf("%s ", name);
-				else
-					printf("  %-50s [%s]\n", name,
-					       event_type_descriptors[PERF_TYPE_HW_CACHE]);
-				++printed;
+				if (!evt_num_known) {
+					evt_num++;
+					continue;
+				}
+
+				evt_list[evt_i] = strdup(name);
+				if (evt_list[evt_i] == NULL)
+					goto out_enomem;
+				evt_i++;
 			}
 		}
 	}
 
-	if (printed)
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++],
+				event_type_descriptors[PERF_TYPE_HW_CACHE]);
+	}
+	if (evt_num)
 		printf("\n");
-	return printed;
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+	return evt_num;
+
+out_enomem:
+	printf("FATAL: not enough memory to print %s\n", event_type_descriptors[PERF_TYPE_HW_CACHE]);
+	if (evt_list)
+		goto out_free;
+	return evt_num;
 }
 
-static void print_symbol_events(const char *event_glob, unsigned type,
+void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only)
 {
-	unsigned i, printed = 0;
+	unsigned int i, evt_i = 0, evt_num = 0;
 	char name[MAX_NAME_LEN];
+	char **evt_list = NULL;
+	bool evt_num_known = false;
+
+restart:
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_enomem;
+		syms -= max;
+	}
 
 	for (i = 0; i < max; i++, syms++) {
 
@@ -1295,23 +1365,49 @@ static void print_symbol_events(const char *event_glob, unsigned type,
 		if (!is_event_supported(type, i))
 			continue;
 
-		if (name_only) {
-			printf("%s ", syms->symbol);
+		if (!evt_num_known) {
+			evt_num++;
 			continue;
 		}
 
-		if (strlen(syms->alias))
+		if (!name_only && strlen(syms->alias))
 			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
 		else
 			strncpy(name, syms->symbol, MAX_NAME_LEN);
 
-		printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
-
-		printed++;
+		evt_list[evt_i] = strdup(name);
+		if (evt_list[evt_i] == NULL)
+			goto out_enomem;
+		evt_i++;
 	}
 
-	if (printed)
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]);
+	}
+	if (evt_num)
 		printf("\n");
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]);
+	if (evt_list)
+		goto out_free;
 }
 
 /*
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 39c3b57965d1..52a2dda4f954 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -116,7 +116,16 @@ void parse_events_update_lists(struct list_head *list_event,
 void parse_events_error(void *data, void *scanner, char const *msg);
 
 void print_events(const char *event_glob, bool name_only);
-void print_events_type(u8 type);
+
+struct event_symbol {
+	const char	*symbol;
+	const char	*alias;
+};
+extern struct event_symbol event_symbols_hw[];
+extern struct event_symbol event_symbols_sw[];
+void print_symbol_events(const char *event_glob, unsigned type,
+				struct event_symbol *syms, unsigned max,
+				bool name_only);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 4ee9a86705ed..1457d6639b60 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -505,15 +505,18 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 		break;
 	case PARSE_OPT_LIST_OPTS:
 		while (options->type != OPTION_END) {
-			printf("--%s ", options->long_name);
+			if (options->long_name)
+				printf("--%s ", options->long_name);
 			options++;
 		}
+		putchar('\n');
 		exit(130);
 	case PARSE_OPT_LIST_SUBCMDS:
 		if (subcommands) {
 			for (int i = 0; subcommands[i]; i++)
 				printf("%s ", subcommands[i]);
 		}
+		putchar('\n');
 		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
 		if (ctx.argv[0][1] == '-') {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9dfbed96bf39..7c0e765fa2e3 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -151,7 +151,7 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 		sym = __find_kernel_function_by_name(name, &map);
 		if (sym)
 			return map->unmap_ip(map, sym->start) -
-				(reloc) ? 0 : map->reloc;
+				((reloc) ? 0 : map->reloc);
 	}
 	return 0;
 }
@@ -533,7 +533,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 		else {
 			if (access(raw_path, R_OK) == 0) {
 				*new_path = strdup(raw_path);
-				return 0;
+				return *new_path ? 0 : -ENOMEM;
 			} else
 				return -errno;
 		}
@@ -549,9 +549,11 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 		if (access(*new_path, R_OK) == 0)
 			return 0;
 
-		if (!symbol_conf.source_prefix)
+		if (!symbol_conf.source_prefix) {
 			/* In case of searching comp_dir, don't retry */
+			zfree(new_path);
 			return -errno;
+		}
 
 		switch (errno) {
 		case ENAMETOOLONG:
@@ -1903,6 +1905,95 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
 	return sl;
 }
 
+struct kprobe_blacklist_node {
+	struct list_head list;
+	unsigned long start;
+	unsigned long end;
+	char *symbol;
+};
+
+static void kprobe_blacklist__delete(struct list_head *blacklist)
+{
+	struct kprobe_blacklist_node *node;
+
+	while (!list_empty(blacklist)) {
+		node = list_first_entry(blacklist,
+					struct kprobe_blacklist_node, list);
+		list_del(&node->list);
+		free(node->symbol);
+		free(node);
+	}
+}
+
+static int kprobe_blacklist__load(struct list_head *blacklist)
+{
+	struct kprobe_blacklist_node *node;
+	const char *__debugfs = debugfs_find_mountpoint();
+	char buf[PATH_MAX], *p;
+	FILE *fp;
+	int ret;
+
+	if (__debugfs == NULL)
+		return -ENOTSUP;
+
+	ret = e_snprintf(buf, PATH_MAX, "%s/kprobes/blacklist", __debugfs);
+	if (ret < 0)
+		return ret;
+
+	fp = fopen(buf, "r");
+	if (!fp)
+		return -errno;
+
+	ret = 0;
+	while (fgets(buf, PATH_MAX, fp)) {
+		node = zalloc(sizeof(*node));
+		if (!node) {
+			ret = -ENOMEM;
+			break;
+		}
+		INIT_LIST_HEAD(&node->list);
+		list_add_tail(&node->list, blacklist);
+		if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) {
+			ret = -EINVAL;
+			break;
+		}
+		p = strchr(buf, '\t');
+		if (p) {
+			p++;
+			if (p[strlen(p) - 1] == '\n')
+				p[strlen(p) - 1] = '\0';
+		} else
+			p = (char *)"unknown";
+		node->symbol = strdup(p);
+		if (!node->symbol) {
+			ret = -ENOMEM;
+			break;
+		}
+		pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n",
+			  node->start, node->end, node->symbol);
+		ret++;
+	}
+	if (ret < 0)
+		kprobe_blacklist__delete(blacklist);
+	fclose(fp);
+
+	return ret;
+}
+
+static struct kprobe_blacklist_node *
+kprobe_blacklist__find_by_address(struct list_head *blacklist,
+				  unsigned long address)
+{
+	struct kprobe_blacklist_node *node;
+
+	list_for_each_entry(node, blacklist, list) {
+		if (node->start <= address && address <= node->end)
+			return node;
+	}
+
+	return NULL;
+}
+
 /* Show an event */
 static int show_perf_probe_event(struct perf_probe_event *pev,
 				 const char *module)
@@ -2117,6 +2208,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	char buf[64];
 	const char *event, *group;
 	struct strlist *namelist;
+	LIST_HEAD(blacklist);
+	struct kprobe_blacklist_node *node;
 
 	if (pev->uprobes)
 		fd = open_uprobe_events(true);
@@ -2134,11 +2227,25 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		pr_debug("Failed to get current event list.\n");
 		return -EIO;
 	}
+	/* Get kprobe blacklist if exists */
+	if (!pev->uprobes) {
+		ret = kprobe_blacklist__load(&blacklist);
+		if (ret < 0)
+			pr_debug("No kprobe blacklist support, ignored\n");
+	}
 
 	ret = 0;
 	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
+		/* Ensure that the address is NOT blacklisted */
+		node = kprobe_blacklist__find_by_address(&blacklist,
+							 tev->point.address);
+		if (node) {
+			pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol);
+			continue;
+		}
+
 		if (pev->event)
 			event = pev->event;
 		else
@@ -2189,13 +2296,15 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		allow_suffix = true;
 	}
 
-	if (ret >= 0) {
+	/* Note that it is possible to skip all events because of blacklist */
+	if (ret >= 0 && tev->event) {
 		/* Show how to use the event. */
 		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
 		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
 			 tev->event);
 	}
 
+	kprobe_blacklist__delete(&blacklist);
 	strlist__delete(namelist);
 	close(fd);
 	return ret;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7a39c1ed8d37..4593f36ecc4c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1463,6 +1463,15 @@ int sort_dimension__add(const char *tok)
 			sort__has_parent = 1;
 		} else if (sd->entry == &sort_sym) {
 			sort__has_sym = 1;
+			/*
+			 * perf diff displays the performance difference amongst
+			 * two or more perf.data files. Those files could come
+			 * from different binaries. So we should not compare
+			 * their ips, but the name of symbol.
+			 */
+			if (sort__mode == SORT_MODE__DIFF)
+				sd->entry->se_collapse = sort__sym_sort;
+
 		} else if (sd->entry == &sort_dso) {
 			sort__has_dso = 1;
 		}