Merge tag 'perf-core-for-mingo-5.5-20191021' 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 trace:

- Add syscall failure stats to -s/--summary and -S/--with-summary, works in
  combination with specifying just a set of syscalls, see below first with
  -s/--summary, then with -S/--with-summary just for the syscalls we saw failing
  with -s:

    # perf trace -s sleep 1

     Summary of events:

     sleep (16218), 80 events, 93.0%

       syscall     calls  errors  total      min      avg      max   stddev
                                  (msec)   (msec)   (msec)   (msec)    (%)
       ----------- -----  ------ -------- -------- -------- -------- ------
       nanosleep       1      0  1000.091 1000.091 1000.091 1000.091  0.00%
       mmap            8      0     0.045    0.005    0.006    0.008  7.09%
       mprotect        4      0     0.028    0.005    0.007    0.009 11.38%
       openat          3      0     0.021    0.005    0.007    0.009 14.07%
       munmap          1      0     0.017    0.017    0.017    0.017  0.00%
       brk             4      0     0.010    0.001    0.002    0.004 23.15%
       read            4      0     0.009    0.002    0.002    0.003  8.13%
       close           5      0     0.008    0.001    0.002    0.002 10.83%
       fstat           3      0     0.006    0.002    0.002    0.002  6.97%
       access          1      1     0.006    0.006    0.006    0.006  0.00%
       lseek           3      0     0.005    0.001    0.002    0.002  7.37%
       arch_prctl      2      1     0.004    0.001    0.002    0.002 17.64%
       execve          1      0     0.000    0.000    0.000    0.000  0.00%

    # perf trace -e access,arch_prctl -S sleep 1
         0.000 ( 0.006 ms): sleep/19503 arch_prctl(option: 0x3001, arg2: 0x7fff165996b0) = -1 EINVAL (Invalid argument)
         0.024 ( 0.006 ms): sleep/19503 access(filename: 0x2177e510, mode: R)            = -1 ENOENT (No such file or directory)
         0.136 ( 0.002 ms): sleep/19503 arch_prctl(option: SET_FS, arg2: 0x7f9421737580) = 0

     Summary of events:

     sleep (19503), 6 events, 50.0%

       syscall    calls  errors total    min    avg    max  stddev
                                (msec) (msec) (msec) (msec)    (%)
       ---------- -----  ------ ------ ------ ------ ------ ------
       arch_prctl   2       1    0.008  0.002  0.004  0.006 57.22%
       access       1       1    0.006  0.006  0.006  0.006  0.00%

    #

  - Introduce --errno-summary, to drill down a bit more in the errno stats:

    # perf trace --errno-summary -e access,arch_prctl -S sleep 1
         0.000 ( 0.006 ms): sleep/5587 arch_prctl(option: 0x3001, arg2: 0x7ffd6ba6aa00) = -1 EINVAL (Invalid argument)
         0.028 ( 0.007 ms): sleep/5587 access(filename: 0xb83d9510, mode: R)            = -1 ENOENT (No such file or directory)
         0.172 ( 0.003 ms): sleep/5587 arch_prctl(option: SET_FS, arg2: 0x7f45b8392580) = 0

     Summary of events:

     sleep (5587), 6 events, 50.0%

       syscall    calls  errors total    min    avg    max  stddev
                                (msec) (msec) (msec) (msec)   (%)
       ---------- -----  ------ ------ ------ ------ ------ ------
       arch_prctl     2     1    0.009  0.003  0.005  0.006 38.90%
			   EINVAL: 1
       access         1     1    0.007  0.007  0.007  0.007  0.00%
                           ENOENT: 1
    #

  - Filter own pid to avoid a feedback look in 'perf trace record -a'

  - Add the glue for the auto generated x86 IRQ vector array.

  - Show error message when not finding a field used in a filter expression

    # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="cnt>32767"
    Failed to set filter "(cnt>32767) && (common_pid != 19938 && common_pid != 8922)" on event syscalls:sys_enter_write with 22 (Invalid argument)
    #
    # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="count>32767"
         0.000 python3.5/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dc53600, count: 172086)
        12.641 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db63660, count: 75994)
        27.738 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db4b1e0, count: 41635)
       136.070 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dbab510, count: 62232)
    #

  - Add a generator for x86's IRQ vectors -> strings

  - Introduce stroul() (string -> number) methods for the strarray and
    strarrays classes, also strtoul_flags, allowing to go from both strings
    and or-ed strings to numbers, allowing things like:

    # perf trace -e syscalls:sys_enter_mmap --filter="flags==DENYWRITE|PRIVATE|FIXED" sleep 1
         0.000 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2aa5000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000)
         0.011 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2bf2000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000)
         0.015 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2c3f000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000)
    #

  Allowing to narrow down from the complete set of mmap calls for that workload:

    # perf trace -e syscalls:sys_enter_mmap sleep 1
         0.000 sleep/22695 syscalls:sys_enter_mmap(len: 134773, prot: READ, flags: PRIVATE, fd: 3)
         0.041 sleep/22695 syscalls:sys_enter_mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS)
         0.053 sleep/22695 syscalls:sys_enter_mmap(len: 1857472, prot: READ, flags: PRIVATE|DENYWRITE, fd: 3)
         0.069 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd23ffb6000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000)
         0.077 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240103000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000)
         0.083 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240150000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000)
         0.095 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240156000, len: 14272, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS)
         0.339 sleep/22695 syscalls:sys_enter_mmap(len: 217750512, prot: READ, flags: PRIVATE, fd: 3)
    #

  Works with all targets, so, for system wide, looking at who calls mmap with flags set to just "PRIVATE":

    # perf trace --max-events=5 -e syscalls:sys_enter_mmap --filter="flags==PRIVATE"
         0.000 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.050 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.062 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.145 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18)
         0.183 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18)
    #

  # perf trace --max-events=2 -e syscalls:sys_enter_lseek --filter="whence==SET && offset != 0"
         0.000 Cache2 I/O/12047 syscalls:sys_enter_lseek(fd: 277, offset: 43, whence: SET)
      1142.070 mozStorage #5/12302 syscalls:sys_enter_lseek(fd: 44</home/acme/.mozilla/firefox/ina67tev.default/cookies.sqlite-wal>, offset: 393536, whence: SET)
  #

perf annotate:

  - Fix objdump --no-show-raw-insn flag to work with goth gcc and clang.

  - Streamline objdump execution, preserving the right error codes for better
    reporting to user.

perf report:

  - Add warning when libunwind not compiled in.

perf stat:

  Jin Yao:

  - Support --all-kernel/--all-user, to match options available in 'perf record',
    asking that all the events specified work just with kernel or user events.

perf list:

  Jin Yao:

  - Hide deprecated events by default, allow showing them with --deprecated.

libbperf:

  Jiri Olsa:

  - Allow to build with -ltcmalloc.

  - Finish mmap interface, getting more stuff from tools/perf while adding
    abstractions to avoid pulling too much stuff, to get libperf to grow as
    tools needs things like auxtrace, etc.

perf scripting engines:

  Steven Rostedt (VMware):

  - Iterate on tep event arrays directly, fixing script generation with
    '-g python' when having multiple tracepoints in a perf.data file.

core:

  - Allow to build with -ltcmalloc.

perf test:

  Leo Yan:

  - Report failure for mmap events.

  - Avoid infinite loop for task exit case.

  - Remove needless headers for bp_account test.

  - Add dedicated checking helper is_supported().

  - Disable bp_signal testing for arm64.

Vendor events:

arm64:

  John Garry:

  - Fix Hisi hip08 DDRC PMU eventname.

  - Add some missing events for Hisi hip08 DDRC, L3C and HHA PMUs.

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

15 files changed, 222 insertions, 130 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bc69ca63b88e..ef1866a902c4 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -43,6 +43,7 @@
 #include <linux/string.h>
 #include <bpf/libbpf.h>
 #include <subcmd/parse-options.h>
+#include <subcmd/run-command.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -1489,44 +1490,26 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
  * means that it's not a disassembly line so should be treated differently.
  * The ops.raw part will be parsed further according to type of the instruction.
  */
-static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
+static int symbol__parse_objdump_line(struct symbol *sym,
 				      struct annotate_args *args,
-				      int *line_nr)
+				      char *parsed_line, int *line_nr)
 {
 	struct map *map = args->ms.map;
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
-	char *line = NULL, *parsed_line, *tmp, *tmp2;
-	size_t line_len;
+	char *tmp;
 	s64 line_ip, offset = -1;
 	regmatch_t match[2];
 
-	if (getline(&line, &line_len, file) < 0)
-		return -1;
-
-	if (!line)
-		return -1;
-
-	line_ip = -1;
-	parsed_line = strim(line);
-
 	/* /filename:linenr ? Save line number and ignore. */
 	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
 		*line_nr = atoi(parsed_line + match[1].rm_so);
 		return 0;
 	}
 
-	tmp = skip_spaces(parsed_line);
-	if (*tmp) {
-		/*
-		 * Parse hexa addresses followed by ':'
-		 */
-		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
-			line_ip = -1;
-	}
-
-	if (line_ip != -1) {
+	/* Process hex address followed by ':'. */
+	line_ip = strtoull(parsed_line, &tmp, 16);
+	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
 		u64 start = map__rip_2objdump(map, sym->start),
 		    end = map__rip_2objdump(map, sym->end);
 
@@ -1534,7 +1517,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 		if ((u64)line_ip < start || (u64)line_ip >= end)
 			offset = -1;
 		else
-			parsed_line = tmp2 + 1;
+			parsed_line = tmp + 1;
 	}
 
 	args->offset  = offset;
@@ -1543,7 +1526,6 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 	args->ms.sym  = sym;
 
 	dl = disasm_line__new(args);
-	free(line);
 	(*line_nr)++;
 
 	if (dl == NULL)
@@ -1861,6 +1843,67 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
 }
 #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
 
+/*
+ * Possibly create a new version of line with tabs expanded. Returns the
+ * existing or new line, storage is updated if a new line is allocated. If
+ * allocation fails then NULL is returned.
+ */
+static char *expand_tabs(char *line, char **storage, size_t *storage_len)
+{
+	size_t i, src, dst, len, new_storage_len, num_tabs;
+	char *new_line;
+	size_t line_len = strlen(line);
+
+	for (num_tabs = 0, i = 0; i < line_len; i++)
+		if (line[i] == '\t')
+			num_tabs++;
+
+	if (num_tabs == 0)
+		return line;
+
+	/*
+	 * Space for the line and '\0', less the leading and trailing
+	 * spaces. Each tab may introduce 7 additional spaces.
+	 */
+	new_storage_len = line_len + 1 + (num_tabs * 7);
+
+	new_line = malloc(new_storage_len);
+	if (new_line == NULL) {
+		pr_err("Failure allocating memory for tab expansion\n");
+		return NULL;
+	}
+
+	/*
+	 * Copy regions starting at src and expand tabs. If there are two
+	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
+	 * are inserted.
+	 */
+	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
+		if (line[i] == '\t') {
+			len = i - src;
+			memcpy(&new_line[dst], &line[src], len);
+			dst += len;
+			new_line[dst++] = ' ';
+			while (dst % 8 != 0)
+				new_line[dst++] = ' ';
+			src = i + 1;
+			num_tabs--;
+		}
+	}
+
+	/* Expand the last region. */
+	len = line_len + 1 - src;
+	memcpy(&new_line[dst], &line[src], len);
+	dst += len;
+	new_line[dst] = '\0';
+
+	free(*storage);
+	*storage = new_line;
+	*storage_len = new_storage_len;
+	return new_line;
+
+}
+
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct annotation_options *opts = args->options;
@@ -1872,10 +1915,19 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 	bool decomp = false;
-	int stdout_fd[2];
 	int lineno = 0;
 	int nline;
-	pid_t pid;
+	char *line;
+	size_t line_len;
+	const char *objdump_argv[] = {
+		"/bin/sh",
+		"-c",
+		NULL, /* Will be the objdump command to run. */
+		"--",
+		NULL, /* Will be the symfs path. */
+		NULL,
+	};
+	struct child_process objdump_process;
 	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
 
 	if (err)
@@ -1905,7 +1957,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 		if (dso__decompress_kmodule_path(dso, symfs_filename,
 						 tmp, sizeof(tmp)) < 0)
-			goto out;
+			return -1;
 
 		decomp = true;
 		strcpy(symfs_filename, tmp);
@@ -1914,13 +1966,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
+		 " -l -d %s %s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
-		 opts->show_asm_raw ? "" : "--no-show-raw",
+		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
 		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
@@ -1930,55 +1982,73 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	pr_debug("Executing: %s\n", command);
 
-	err = -1;
-	if (pipe(stdout_fd) < 0) {
-		pr_err("Failure creating the pipe to run %s\n", command);
-		goto out_free_command;
-	}
+	objdump_argv[2] = command;
+	objdump_argv[4] = symfs_filename;
 
-	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, "--", symfs_filename,
-		      NULL);
-		perror(command);
-		exit(-1);
+	/* Create a pipe to read from for stdout */
+	memset(&objdump_process, 0, sizeof(objdump_process));
+	objdump_process.argv = objdump_argv;
+	objdump_process.out = -1;
+	if (start_command(&objdump_process)) {
+		pr_err("Failure starting to run %s\n", command);
+		err = -1;
+		goto out_free_command;
 	}
 
-	close(stdout_fd[1]);
-
-	file = fdopen(stdout_fd[0], "r");
+	file = fdopen(objdump_process.out, "r");
 	if (!file) {
 		pr_err("Failure creating FILE stream for %s\n", command);
 		/*
 		 * If we were using debug info should retry with
 		 * original binary.
 		 */
-		goto out_free_command;
+		err = -1;
+		goto out_close_stdout;
 	}
 
+	/* Storage for getline. */
+	line = NULL;
+	line_len = 0;
+
 	nline = 0;
 	while (!feof(file)) {
+		const char *match;
+		char *expanded_line;
+
+		if (getline(&line, &line_len, file) < 0 || !line)
+			break;
+
+		/* Skip lines containing "filename:" */
+		match = strstr(line, symfs_filename);
+		if (match && match[strlen(symfs_filename)] == ':')
+			continue;
+
+		expanded_line = strim(line);
+		expanded_line = expand_tabs(expanded_line, &line, &line_len);
+		if (!expanded_line)
+			break;
+
 		/*
 		 * The source code line number (lineno) needs to be kept in
 		 * across calls to symbol__parse_objdump_line(), so that it
 		 * can associate it with the instructions till the next one.
 		 * See disasm_line__new() and struct disasm_line::line_nr.
 		 */
-		if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0)
+		if (symbol__parse_objdump_line(sym, args, expanded_line,
+					       &lineno) < 0)
 			break;
 		nline++;
 	}
+	free(line);
+
+	err = finish_command(&objdump_process);
+	if (err)
+		pr_err("Error running %s\n", command);
 
-	if (nline == 0)
+	if (nline == 0) {
+		err = -1;
 		pr_err("No output from %s\n", command);
+	}
 
 	/*
 	 * kallsyms does not have symbol sizes so there may a nop at the end.
@@ -1988,23 +2058,21 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		delete_last_nop(sym);
 
 	fclose(file);
-	err = 0;
+
+out_close_stdout:
+	close(objdump_process.out);
+
 out_free_command:
 	free(command);
-out_remove_tmp:
-	close(stdout_fd[0]);
 
+out_remove_tmp:
 	if (decomp)
 		unlink(symfs_filename);
 
 	if (delete_extract)
 		kcore_extract__delete(&kce);
-out:
-	return err;
 
-out_close_stdout:
-	close(stdout_fd[1]);
-	goto out_free_command;
+	return err;
 }
 
 static void calc_percent(struct sym_hist *sym_hist,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8793b4e322b0..fdce590d2278 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -21,6 +21,7 @@
 #include "../perf.h"
 #include "asm/bug.h"
 #include "bpf-event.h"
+#include "util/string2.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -598,14 +599,13 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 	int i;
 	struct mmap *map;
 
-	evlist->core.nr_mmaps = perf_cpu_map__nr(evlist->core.cpus);
-	if (perf_cpu_map__empty(evlist->core.cpus))
-		evlist->core.nr_mmaps = perf_thread_map__nr(evlist->core.threads);
 	map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap));
 	if (!map)
 		return NULL;
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
+		struct perf_mmap *prev = i ? &map[i - 1].core : NULL;
+
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -615,7 +615,7 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
 		 * thus does perf_mmap__get() on it.
 		 */
-		perf_mmap__init(&map[i].core, overwrite, perf_mmap__unmap_cb);
+		perf_mmap__init(&map[i].core, prev, overwrite, perf_mmap__unmap_cb);
 	}
 
 	return map;
@@ -636,19 +636,21 @@ static struct perf_mmap*
 perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
 {
 	struct evlist *evlist = container_of(_evlist, struct evlist, core);
-	struct mmap *maps = evlist->mmap;
+	struct mmap *maps;
 
-	if (overwrite) {
-		maps = evlist->overwrite_mmap;
+	maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
 
-		if (!maps) {
-			maps = evlist__alloc_mmap(evlist, true);
-			if (!maps)
-				return NULL;
+	if (!maps) {
+		maps = evlist__alloc_mmap(evlist, overwrite);
+		if (!maps)
+			return NULL;
 
+		if (overwrite) {
 			evlist->overwrite_mmap = maps;
 			if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
 				perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+		} else {
+			evlist->mmap = maps;
 		}
 	}
 
@@ -809,14 +811,8 @@ int evlist__mmap_ex(struct evlist *evlist, unsigned int pages,
 		.mmap = perf_evlist__mmap_cb_mmap,
 	};
 
-	if (!evlist->mmap)
-		evlist->mmap = evlist__alloc_mmap(evlist, false);
-	if (!evlist->mmap)
-		return -ENOMEM;
-
 	evlist->core.mmap_len = evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->core.mmap_len);
-	mp.core.mask = evlist->core.mmap_len - page_size - 1;
 
 	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
@@ -959,7 +955,7 @@ int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
 	return err;
 }
 
-static char *asprintf__tp_filter_pids(size_t npids, pid_t *pids)
+char *asprintf__tp_filter_pids(size_t npids, pid_t *pids)
 {
 	char *filter;
 	size_t i;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b5e2adef49de..db882f630f7e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2600,7 +2600,7 @@ out_enomem:
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc, bool details_flag)
+			bool long_desc, bool details_flag, bool deprecated)
 {
 	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
 			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
@@ -2612,7 +2612,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 	print_hwcache_events(event_glob, name_only);
 
 	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
-			details_flag);
+			details_flag, deprecated);
 
 	if (event_glob != NULL)
 		return;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 616ca1eda0eb..769e07cddaa2 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -195,7 +195,7 @@ void parse_events_evlist_error(struct parse_events_state *parse_state,
 			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
-		  bool long_desc, bool details_flag);
+		  bool long_desc, bool details_flag, bool deprecated);
 
 struct event_symbol {
 	const char	*symbol;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 5608da82ad23..adbe97e941dd 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -308,7 +308,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *long_desc, char *topic,
 				 char *unit, char *perpkg,
 				 char *metric_expr,
-				 char *metric_name)
+				 char *metric_name,
+				 char *deprecated)
 {
 	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
@@ -325,6 +326,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 	alias->snapshot = false;
+	alias->deprecated = false;
 
 	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
@@ -379,6 +381,9 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
 	alias->str = strdup(newval);
 
+	if (deprecated)
+		alias->deprecated = true;
+
 	if (!perf_pmu_merge_alias(alias, list))
 		list_add_tail(&alias->list, list);
 
@@ -400,7 +405,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	strim(buf);
 
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
-				     NULL, NULL, NULL);
+				     NULL, NULL, NULL, NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -787,7 +792,8 @@ new_alias:
 				(char *)pe->long_desc, (char *)pe->topic,
 				(char *)pe->unit, (char *)pe->perpkg,
 				(char *)pe->metric_expr,
-				(char *)pe->metric_name);
+				(char *)pe->metric_name,
+				(char *)pe->deprecated);
 	}
 }
 
@@ -1383,7 +1389,7 @@ static void wordwrap(char *s, int start, int max, int corr)
 }
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc, bool details_flag)
+			bool long_desc, bool details_flag, bool deprecated)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
@@ -1414,6 +1420,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 				format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
 
+			if (alias->deprecated && !deprecated)
+				continue;
+
 			if (event_glob != NULL &&
 			    !(strglobmatch_nocase(name, event_glob) ||
 			      (!is_cpu && strglobmatch_nocase(alias->name,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index f36ade6df76d..3e8cd31a89cc 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -57,6 +57,7 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	bool deprecated;
 	char *metric_expr;
 	char *metric_name;
 };
@@ -85,7 +86,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
-		      bool long_desc, bool details_flag);
+		      bool long_desc, bool details_flag,
+		      bool deprecated);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 15961854ba67..741f040648b5 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -539,10 +539,11 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.pl", outfile);
@@ -603,8 +604,11 @@ sub print_backtrace\n\
 }\n\n\
 ");
 
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5d341efc3237..93c03b39cd9c 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1687,10 +1687,11 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.py", outfile);
@@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
+
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ebdd130557fb..6822e4ffe224 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel,
 	if (config->identifier)
 		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
+	if (config->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (config->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Disabling all counters initially, they will be enabled
 	 * either manually by us or by kernel via enable_on_exec
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index edbeb2f63e8d..081c4a5113c6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -106,6 +106,8 @@ struct perf_stat_config {
 	bool			 big_num;
 	bool			 no_merge;
 	bool			 walltime_run_table;
+	bool			 all_kernel;
+	bool			 all_user;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 708805f5573e..73df616ced43 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -4,6 +4,7 @@
 
 #include <linux/string.h>
 #include <linux/types.h>
+#include <sys/types.h> // pid_t
 #include <stddef.h>
 #include <string.h>
 
@@ -32,6 +33,8 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 	return asprintf_expr_inout_ints(var, false, nints, ints);
 }
 
+char *asprintf__tp_filter_pids(size_t npids, pid_t *pids);
+
 char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
 
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 9796a2e43f67..302443921681 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -458,10 +458,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 	return true;
 }
 
-int perf_time__parse_for_ranges(const char *time_str,
+int perf_time__parse_for_ranges_reltime(const char *time_str,
 				struct perf_session *session,
 				struct perf_time_interval **ranges,
-				int *range_size, int *range_num)
+				int *range_size, int *range_num,
+				bool reltime)
 {
 	bool has_percent = strchr(time_str, '%');
 	struct perf_time_interval *ptime_range;
@@ -471,7 +472,7 @@ int perf_time__parse_for_ranges(const char *time_str,
 	if (!ptime_range)
 		return -ENOMEM;
 
-	if (has_percent) {
+	if (has_percent || reltime) {
 		if (session->evlist->first_sample_time == 0 &&
 		    session->evlist->last_sample_time == 0) {
 			pr_err("HINT: no first/last sample time found in perf data.\n"
@@ -479,7 +480,9 @@ int perf_time__parse_for_ranges(const char *time_str,
 			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
 			goto error;
 		}
+	}
 
+	if (has_percent) {
 		num = perf_time__percent_parse_str(
 				ptime_range, size,
 				time_str,
@@ -492,6 +495,15 @@ int perf_time__parse_for_ranges(const char *time_str,
 	if (num < 0)
 		goto error_invalid;
 
+	if (reltime) {
+		int i;
+
+		for (i = 0; i < num; i++) {
+			ptime_range[i].start += session->evlist->first_sample_time;
+			ptime_range[i].end += session->evlist->first_sample_time;
+		}
+	}
+
 	*range_size = size;
 	*range_num = num;
 	*ranges = ptime_range;
@@ -504,6 +516,15 @@ error:
 	return ret;
 }
 
+int perf_time__parse_for_ranges(const char *time_str,
+				struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num)
+{
+	return perf_time__parse_for_ranges_reltime(time_str, session, ranges,
+					range_size, range_num, false);
+}
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 {
 	u64  sec = timestamp / NSEC_PER_SEC;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 4f42988eb2f7..1142b0bddd5e 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -26,6 +26,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 
 struct perf_session;
 
+int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num,
+				bool reltime);
+
 int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
 				struct perf_time_interval **ranges,
 				int *range_size, int *range_num);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 5d6bfc70b210..9634f0ae57be 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event)
-{
-	static int idx;
-	int events_count;
-	struct tep_event *all_events;
-
-	all_events = tep_get_first_event(pevent);
-	events_count = tep_get_events_count(pevent);
-	if (!pevent || !all_events || events_count < 1)
-		return NULL;
-
-	if (!event) {
-		idx = 0;
-		return all_events;
-	}
-
-	if (idx < events_count && event == (all_events + idx)) {
-		idx++;
-		if (idx == events_count)
-			return NULL;
-		return (all_events + idx);
-	}
-
-	for (idx = 1; idx < events_count; idx++) {
-		if (event == (all_events + (idx - 1)))
-			return (all_events + idx);
-	}
-	return NULL;
-}
-
 struct flag {
 	const char *name;
 	unsigned long long value;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 2e158387b3d7..72fdf2a3577c 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event);
 unsigned long long read_size(struct tep_event *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);