Merge tag 'perf-core-for-mingo-5.1-20190225' 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:

perf annotate:

  Wei Li:

  - Fix getting source line failure

perf script:

  Andi Kleen:

  - Handle missing fields with -F +...

perf data:

  Jiri Olsa:

  - Prep work to support per-cpu files in a directory.

Intel PT:

  Adrian Hunter:

  - Improve thread_stack__no_call_return()

  - Hide x86 retpolines in thread stacks.

  - exported SQL viewer refactorings, new 'top calls' report..

  Alexander Shishkin:

  - Copy parent's address filter offsets on clone

  - Fix address filters for vmas with non-zero offset. Applies to
    ARM's CoreSight as well.

python scripts:

  Tony Jones:

  - Python3 support for several 'perf script' python scripts.

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

8 files changed, 398 insertions, 42 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2468b8aa0b6b..11a8a447a3af 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1891,6 +1891,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct annotation_options *options,
 		     struct arch **parch)
 {
+	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
 		.privsize	= privsize,
 		.evsel		= evsel,
@@ -1921,6 +1922,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 
 	args.ms.map = map;
 	args.ms.sym = sym;
+	notes->start = map__rip_2objdump(map, sym->start);
 
 	return symbol__disassemble(sym, &args);
 }
@@ -2796,8 +2798,6 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev
 
 	symbol__calc_percent(sym, evsel);
 
-	notes->start = map__rip_2objdump(map, sym->start);
-
 	annotation__set_offsets(notes, size);
 	annotation__mark_jump_targets(notes, sym);
 	annotation__compute_ipc(notes, size);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2a36fab76994..26af43ad9ddd 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = { .path = input, .fd = -1 },
+		.path	   = input,
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
-		data.file.path, path);
+		data.path, path);
 
 	fprintf(stderr,
 		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index d8cfc19ddb10..7bd5ddeb7a41 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,11 +7,117 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
+#include <asm/bug.h>
+#include <sys/types.h>
+#include <dirent.h>
 
 #include "data.h"
 #include "util.h"
 #include "debug.h"
 
+static void close_dir(struct perf_data_file *files, int nr)
+{
+	while (--nr >= 1) {
+		close(files[nr].fd);
+		free(files[nr].path);
+	}
+	free(files);
+}
+
+void perf_data__close_dir(struct perf_data *data)
+{
+	close_dir(data->dir.files, data->dir.nr);
+}
+
+int perf_data__create_dir(struct perf_data *data, int nr)
+{
+	struct perf_data_file *files = NULL;
+	int i, ret = -1;
+
+	files = zalloc(nr * sizeof(*files));
+	if (!files)
+		return -ENOMEM;
+
+	data->dir.files = files;
+	data->dir.nr    = nr;
+
+	for (i = 0; i < nr; i++) {
+		struct perf_data_file *file = &files[i];
+
+		if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0)
+			goto out_err;
+
+		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
+		if (ret < 0)
+			goto out_err;
+
+		file->fd = ret;
+	}
+
+	return 0;
+
+out_err:
+	close_dir(files, i);
+	return ret;
+}
+
+int perf_data__open_dir(struct perf_data *data)
+{
+	struct perf_data_file *files = NULL;
+	struct dirent *dent;
+	int ret = -1;
+	DIR *dir;
+	int nr = 0;
+
+	dir = opendir(data->path);
+	if (!dir)
+		return -EINVAL;
+
+	while ((dent = readdir(dir)) != NULL) {
+		struct perf_data_file *file;
+		char path[PATH_MAX];
+		struct stat st;
+
+		snprintf(path, sizeof(path), "%s/%s", data->path, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4))
+			continue;
+
+		ret = -ENOMEM;
+
+		file = realloc(files, (nr + 1) * sizeof(*files));
+		if (!file)
+			goto out_err;
+
+		files = file;
+		file = &files[nr++];
+
+		file->path = strdup(path);
+		if (!file->path)
+			goto out_err;
+
+		ret = open(file->path, O_RDONLY);
+		if (ret < 0)
+			goto out_err;
+
+		file->fd = ret;
+		file->size = st.st_size;
+	}
+
+	if (!files)
+		return -EINVAL;
+
+	data->dir.files = files;
+	data->dir.nr    = nr;
+	return 0;
+
+out_err:
+	close_dir(files, nr);
+	return ret;
+}
+
 static bool check_pipe(struct perf_data *data)
 {
 	struct stat st;
@@ -19,11 +125,11 @@ static bool check_pipe(struct perf_data *data)
 	int fd = perf_data__is_read(data) ?
 		 STDIN_FILENO : STDOUT_FILENO;
 
-	if (!data->file.path) {
+	if (!data->path) {
 		if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
 			is_pipe = true;
 	} else {
-		if (!strcmp(data->file.path, "-"))
+		if (!strcmp(data->path, "-"))
 			is_pipe = true;
 	}
 
@@ -37,13 +143,31 @@ static int check_backup(struct perf_data *data)
 {
 	struct stat st;
 
-	if (!stat(data->file.path, &st) && st.st_size) {
-		/* TODO check errors properly */
+	if (perf_data__is_read(data))
+		return 0;
+
+	if (!stat(data->path, &st) && st.st_size) {
 		char oldname[PATH_MAX];
+		int ret;
+
 		snprintf(oldname, sizeof(oldname), "%s.old",
-			 data->file.path);
-		unlink(oldname);
-		rename(data->file.path, oldname);
+			 data->path);
+
+		ret = rm_rf_perf_data(oldname);
+		if (ret) {
+			pr_err("Can't remove old data: %s (%s)\n",
+			       ret == -2 ?
+			       "Unknown file found" : strerror(errno),
+			       oldname);
+			return -1;
+		}
+
+		if (rename(data->path, oldname)) {
+			pr_err("Can't move data: %s (%s to %s)\n",
+			       strerror(errno),
+			       data->path, oldname);
+			return -1;
+		}
 	}
 
 	return 0;
@@ -82,7 +206,7 @@ static int open_file_read(struct perf_data *data)
 		goto out_close;
 	}
 
-	data->size = st.st_size;
+	data->file.size = st.st_size;
 	return fd;
 
  out_close:
@@ -95,9 +219,6 @@ static int open_file_write(struct perf_data *data)
 	int fd;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (check_backup(data))
-		return -1;
-
 	fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
 		  S_IRUSR|S_IWUSR);
 
@@ -115,8 +236,22 @@ static int open_file(struct perf_data *data)
 	fd = perf_data__is_read(data) ?
 	     open_file_read(data) : open_file_write(data);
 
+	if (fd < 0) {
+		free(data->file.path);
+		return -1;
+	}
+
 	data->file.fd = fd;
-	return fd < 0 ? -1 : 0;
+	return 0;
+}
+
+static int open_file_dup(struct perf_data *data)
+{
+	data->file.path = strdup(data->path);
+	if (!data->file.path)
+		return -ENOMEM;
+
+	return open_file(data);
 }
 
 int perf_data__open(struct perf_data *data)
@@ -124,14 +259,18 @@ int perf_data__open(struct perf_data *data)
 	if (check_pipe(data))
 		return 0;
 
-	if (!data->file.path)
-		data->file.path = "perf.data";
+	if (!data->path)
+		data->path = "perf.data";
 
-	return open_file(data);
+	if (check_backup(data))
+		return -1;
+
+	return open_file_dup(data);
 }
 
 void perf_data__close(struct perf_data *data)
 {
+	free(data->file.path);
 	close(data->file.fd);
 }
 
@@ -159,15 +298,15 @@ int perf_data__switch(struct perf_data *data,
 	if (perf_data__is_read(data))
 		return -EINVAL;
 
-	if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
+	if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0)
 		return -ENOMEM;
 
 	/*
 	 * Only fire a warning, don't return error, continue fill
 	 * original file.
 	 */
-	if (rename(data->file.path, new_filepath))
-		pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
+	if (rename(data->path, new_filepath))
+		pr_warning("Failed to rename %s to %s\n", data->path, new_filepath);
 
 	if (!at_exit) {
 		close(data->file.fd);
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 4828f7feea89..14b47be2bd69 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,16 +10,22 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-	const char	*path;
+	char		*path;
 	int		 fd;
+	unsigned long	 size;
 };
 
 struct perf_data {
+	const char		*path;
 	struct perf_data_file	 file;
 	bool			 is_pipe;
 	bool			 force;
-	unsigned long		 size;
 	enum perf_data_mode	 mode;
+
+	struct {
+		struct perf_data_file	*files;
+		int			 nr;
+	} dir;
 };
 
 static inline bool perf_data__is_read(struct perf_data *data)
@@ -44,7 +50,7 @@ static inline int perf_data__fd(struct perf_data *data)
 
 static inline unsigned long perf_data__size(struct perf_data *data)
 {
-	return data->size;
+	return data->file.size;
 }
 
 int perf_data__open(struct perf_data *data);
@@ -63,4 +69,8 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
 			   size_t pos, bool at_exit);
+
+int perf_data__create_dir(struct perf_data *data, int nr);
+int perf_data__open_dir(struct perf_data *data);
+void perf_data__close_dir(struct perf_data *data);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a2323d777dae..01b324c275b9 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -527,17 +527,11 @@ static int write_event_desc(struct feat_fd *ff,
 static int write_cmdline(struct feat_fd *ff,
 			 struct perf_evlist *evlist __maybe_unused)
 {
-	char buf[MAXPATHLEN];
-	u32 n;
-	int i, ret;
+	char pbuf[MAXPATHLEN], *buf;
+	int i, ret, n;
 
 	/* actual path to perf binary */
-	ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
-	if (ret <= 0)
-		return -1;
-
-	/* readlink() does not add null termination */
-	buf[ret] = '\0';
+	buf = perf_exe(pbuf, MAXPATHLEN);
 
 	/* account for binary path */
 	n = perf_env.nr_cmdline + 1;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index f52c0f90915d..a8b45168513c 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -20,6 +20,7 @@
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
+#include "env.h"
 #include "util.h"
 #include "debug.h"
 #include "symbol.h"
@@ -29,6 +30,19 @@
 
 #define STACK_GROWTH 2048
 
+/*
+ * State of retpoline detection.
+ *
+ * RETPOLINE_NONE: no retpoline detection
+ * X86_RETPOLINE_POSSIBLE: x86 retpoline possible
+ * X86_RETPOLINE_DETECTED: x86 retpoline detected
+ */
+enum retpoline_state_t {
+	RETPOLINE_NONE,
+	X86_RETPOLINE_POSSIBLE,
+	X86_RETPOLINE_DETECTED,
+};
+
 /**
  * struct thread_stack_entry - thread stack entry.
  * @ret_addr: return address
@@ -64,6 +78,7 @@ struct thread_stack_entry {
  * @crp: call/return processor
  * @comm: current comm
  * @arr_sz: size of array if this is the first element of an array
+ * @rstate: used to detect retpolines
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -76,6 +91,7 @@ struct thread_stack {
 	struct call_return_processor *crp;
 	struct comm *comm;
 	unsigned int arr_sz;
+	enum retpoline_state_t rstate;
 };
 
 /*
@@ -115,10 +131,16 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 	if (err)
 		return err;
 
-	if (thread->mg && thread->mg->machine)
-		ts->kernel_start = machine__kernel_start(thread->mg->machine);
-	else
+	if (thread->mg && thread->mg->machine) {
+		struct machine *machine = thread->mg->machine;
+		const char *arch = perf_env__arch(machine->env);
+
+		ts->kernel_start = machine__kernel_start(machine);
+		if (!strcmp(arch, "x86"))
+			ts->rstate = X86_RETPOLINE_POSSIBLE;
+	} else {
 		ts->kernel_start = 1ULL << 63;
+	}
 	ts->crp = crp;
 
 	return 0;
@@ -638,14 +660,57 @@ static int thread_stack__no_call_return(struct thread *thread,
 	else
 		parent = root;
 
-	/* This 'return' had no 'call', so push and pop top of stack */
-	cp = call_path__findnew(cpr, parent, fsym, ip, ks);
+	if (parent->sym == from_al->sym) {
+		/*
+		 * At the bottom of the stack, assume the missing 'call' was
+		 * before the trace started. So, pop the current symbol and push
+		 * the 'to' symbol.
+		 */
+		if (ts->cnt == 1) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							tm, ref, false);
+			if (err)
+				return err;
+		}
+
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+
+			return thread_stack__push_cp(ts, addr, tm, ref, cp,
+						     true, false);
+		}
+
+		/*
+		 * Otherwise assume the 'return' is being used as a jump (e.g.
+		 * retpoline) and just push the 'to' symbol.
+		 */
+		cp = call_path__findnew(cpr, parent, tsym, addr, ks);
+
+		err = thread_stack__push_cp(ts, 0, tm, ref, cp, true, false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
+
+		return err;
+	}
+
+	/*
+	 * Assume 'parent' has not yet returned, so push 'to', and then push and
+	 * pop 'from'.
+	 */
+
+	cp = call_path__findnew(cpr, parent, tsym, addr, ks);
 
 	err = thread_stack__push_cp(ts, addr, tm, ref, cp, true, false);
 	if (err)
 		return err;
 
-	return thread_stack__pop_cp(thread, ts, addr, tm, ref, tsym);
+	cp = call_path__findnew(cpr, cp, fsym, ip, ks);
+
+	err = thread_stack__push_cp(ts, ip, tm, ref, cp, true, false);
+	if (err)
+		return err;
+
+	return thread_stack__call_return(thread, ts, --ts->cnt, tm, ref, false);
 }
 
 static int thread_stack__trace_begin(struct thread *thread,
@@ -690,6 +755,70 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 				     false, true);
 }
 
+static bool is_x86_retpoline(const char *name)
+{
+	const char *p = strstr(name, "__x86_indirect_thunk_");
+
+	return p == name || !strcmp(name, "__indirect_thunk_start");
+}
+
+/*
+ * x86 retpoline functions pollute the call graph. This function removes them.
+ * This does not handle function return thunks, nor is there any improvement
+ * for the handling of inline thunks or extern thunks.
+ */
+static int thread_stack__x86_retpoline(struct thread_stack *ts,
+				       struct perf_sample *sample,
+				       struct addr_location *to_al)
+{
+	struct thread_stack_entry *tse = &ts->stack[ts->cnt - 1];
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct symbol *sym = tse->cp->sym;
+	struct symbol *tsym = to_al->sym;
+	struct call_path *cp;
+
+	if (sym && is_x86_retpoline(sym->name)) {
+		/*
+		 * This is a x86 retpoline fn. It pollutes the call graph by
+		 * showing up everywhere there is an indirect branch, but does
+		 * not itself mean anything. Here the top-of-stack is removed,
+		 * by decrementing the stack count, and then further down, the
+		 * resulting top-of-stack is replaced with the actual target.
+		 * The result is that the retpoline functions will no longer
+		 * appear in the call graph. Note this only affects the call
+		 * graph, since all the original branches are left unchanged.
+		 */
+		ts->cnt -= 1;
+		sym = ts->stack[ts->cnt - 2].cp->sym;
+		if (sym && sym == tsym && to_al->addr != tsym->start) {
+			/*
+			 * Target is back to the middle of the symbol we came
+			 * from so assume it is an indirect jmp and forget it
+			 * altogether.
+			 */
+			ts->cnt -= 1;
+			return 0;
+		}
+	} else if (sym && sym == tsym) {
+		/*
+		 * Target is back to the symbol we came from so assume it is an
+		 * indirect jmp and forget it altogether.
+		 */
+		ts->cnt -= 1;
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 2].cp, tsym,
+				sample->addr, ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	/* Replace the top-of-stack with the actual target */
+	ts->stack[ts->cnt - 1].cp = cp;
+
+	return 0;
+}
+
 int thread_stack__process(struct thread *thread, struct comm *comm,
 			  struct perf_sample *sample,
 			  struct addr_location *from_al,
@@ -697,6 +826,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 			  struct call_return_processor *crp)
 {
 	struct thread_stack *ts = thread__stack(thread, sample->cpu);
+	enum retpoline_state_t rstate;
 	int err = 0;
 
 	if (ts && !ts->crp) {
@@ -712,6 +842,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		ts->comm = comm;
 	}
 
+	rstate = ts->rstate;
+	if (rstate == X86_RETPOLINE_DETECTED)
+		ts->rstate = X86_RETPOLINE_POSSIBLE;
+
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
 		err = __thread_stack__flush(thread, ts);
@@ -748,10 +882,25 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 					ts->kernel_start);
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
 					    cp, false, trace_end);
+
+		/*
+		 * A call to the same symbol but not the start of the symbol,
+		 * may be the start of a x86 retpoline.
+		 */
+		if (!err && rstate == X86_RETPOLINE_POSSIBLE && to_al->sym &&
+		    from_al->sym == to_al->sym &&
+		    to_al->addr != to_al->sym->start)
+			ts->rstate = X86_RETPOLINE_DETECTED;
+
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
 
+		/* x86 retpoline 'return' doesn't match the stack */
+		if (rstate == X86_RETPOLINE_DETECTED && ts->cnt > 2 &&
+		    ts->stack[ts->cnt - 1].ret_addr != sample->addr)
+			return thread_stack__x86_retpoline(ts, sample, to_al);
+
 		err = thread_stack__pop_cp(thread, ts, sample->addr,
 					   sample->time, ref, from_al->sym);
 		if (err) {
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 3ee410fc047a..d388f80d8703 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -21,6 +21,7 @@
 #include <linux/time64.h>
 #include <unistd.h>
 #include "strlist.h"
+#include "string2.h"
 
 /*
  * XXX We need to find a better place for these things...
@@ -117,7 +118,38 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-int rm_rf(const char *path)
+static bool match_pat(char *file, const char **pat)
+{
+	int i = 0;
+
+	if (!pat)
+		return true;
+
+	while (pat[i]) {
+		if (strglobmatch(file, pat[i]))
+			return true;
+
+		i++;
+	}
+
+	return false;
+}
+
+/*
+ * The depth specify how deep the removal will go.
+ * 0       - will remove only files under the 'path' directory
+ * 1 .. x  - will dive in x-level deep under the 'path' directory
+ *
+ * If specified the pat is array of string patterns ended with NULL,
+ * which are checked upon every file/directory found. Only matching
+ * ones are removed.
+ *
+ * The function returns:
+ *    0 on success
+ *   -1 on removal failure with errno set
+ *   -2 on pattern failure
+ */
+static int rm_rf_depth_pat(const char *path, int depth, const char **pat)
 {
 	DIR *dir;
 	int ret;
@@ -144,6 +176,9 @@ int rm_rf(const char *path)
 		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
 			continue;
 
+		if (!match_pat(d->d_name, pat))
+			return -2;
+
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
 
@@ -155,7 +190,7 @@ int rm_rf(const char *path)
 		}
 
 		if (S_ISDIR(statbuf.st_mode))
-			ret = rm_rf(namebuf);
+			ret = depth ? rm_rf_depth_pat(namebuf, depth - 1, pat) : 0;
 		else
 			ret = unlink(namebuf);
 	}
@@ -167,6 +202,22 @@ int rm_rf(const char *path)
 	return rmdir(path);
 }
 
+int rm_rf_perf_data(const char *path)
+{
+	const char *pat[] = {
+		"header",
+		"data.*",
+		NULL,
+	};
+
+	return rm_rf_depth_pat(path, 0, pat);
+}
+
+int rm_rf(const char *path)
+{
+	return rm_rf_depth_pat(path, INT_MAX, NULL);
+}
+
 /* A filter which removes dot files */
 bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d)
 {
@@ -517,3 +568,13 @@ out:
 
 	return tip;
 }
+
+char *perf_exe(char *buf, int len)
+{
+	int n = readlink("/proc/self/exe", buf, len);
+	if (n > 0) {
+		buf[n] = 0;
+		return buf;
+	}
+	return strcpy(buf, "perf");
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ece040b799f6..09c1b0f91f65 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -31,6 +31,7 @@ struct strlist;
 
 int mkdir_p(char *path, mode_t mode);
 int rm_rf(const char *path);
+int rm_rf_perf_data(const char *path);
 struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
@@ -76,6 +77,8 @@ extern bool perf_singlethreaded;
 void perf_set_singlethreaded(void);
 void perf_set_multithreaded(void);
 
+char *perf_exe(char *buf, int len);
+
 #ifndef O_CLOEXEC
 #ifdef __sparc__
 #define O_CLOEXEC      0x400000