Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Intel Knights Landing support.  (Harish Chegondi)

   - Intel Broadwell-EP uncore PMU support.  (Kan Liang)

   - Core code improvements.  (Peter Zijlstra.)

   - Event filter, LBR and PEBS fixes.  (Stephane Eranian)

   - Enable cycles:pp on Intel Atom.  (Stephane Eranian)

   - Add cycles:ppp support for Skylake.  (Andi Kleen)

   - Various x86 NMI overhead optimizations.  (Andi Kleen)

   - Intel PT enhancements.  (Takao Indoh)

   - AMD cache events fix.  (Vince Weaver)

  Tons of tooling changes:

   - Show random perf tool tips in the 'perf report' bottom line
     (Namhyung Kim)

   - perf report now defaults to --group if the perf.data file has
     grouped events, try it with:

      # perf record -e '{cycles,instructions}' -a sleep 1
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
      # perf report
      # Samples: 1K of event 'anon group { cycles, instructions }'
      # Event count (approx.): 1955219195
      #
      #       Overhead  Command     Shared Object      Symbol

         2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
         1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
         1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
         0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
         0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
         0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
         0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
         0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
         0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

   - Introduce the 'perf stat record/report' workflow:

     Generate perf.data files from 'perf stat', to tap into the
     scripting capabilities perf has instead of defining a 'perf stat'
     specific scripting support to calculate event ratios, etc.

     Simple example:

        $ perf stat record -e cycles usleep 1

         Performance counter stats for 'usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $ perf stat report

         Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $

     It generates PERF_RECORD_ userspace records to store the details:

        $ perf report -D | grep PERF_RECORD
        0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
        0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
        0x12a [0x40]: PERF_RECORD_STAT_CONFIG
        0x16a [0x30]: PERF_RECORD_STAT
        -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
        0x1da [0x18]: PERF_RECORD_STAT_ROUND
        [acme@ssdandy linux]$

     An effort was made to make perf.data files generated like this to
     not generate cryptic messages when processed by older tools.

     The 'perf script' bits need rebasing, will go up later.

   - Make command line options always available, even when they depend
     on some feature being enabled, warning the user about use of such
     options (Wang Nan)

   - Support hw breakpoint events (mem:0xAddress) in the default output
     mode in 'perf script' (Wang Nan)

   - Fixes and improvements for supporting annotating ARM binaries,
     support ARM call and jump instructions, more work needed to have
     arch specific stuff separated into tools/perf/arch/*/annotate/
     (Russell King)

   - Add initial 'perf config' command, for now just with a --list
     command to the contents of the configuration file in use and a
     basic man page describing its format, commands for doing edits and
     detailed documentation are being reviewed and proof-read.  (Taeung
     Song)

   - Allows BPF scriptlets specify arguments to be fetched using DWARF
     info, using a prologue generated at compile/build time (He Kuang,
     Wang Nan)

   - Allow attaching BPF scriptlets to module symbols (Wang Nan)

   - Allow attaching BPF scriptlets to userspace code using uprobe (Wang
     Nan)

   - BPF programs now can specify 'perf probe' tunables via its section
     name, separating key=val values using semicolons (Wang Nan)

     Testing some of these new BPF features:

        Use case: get callchains when receiving SSL packets, filter then in the
                  kernel, at arbitrary place.

        # cat ssl.bpf.c
        #define SEC(NAME) __attribute__((section(NAME), used))

        struct pt_regs;

        SEC("func=__inet_lookup_established hnum")
        int func(struct pt_regs *ctx, int err, unsigned short port)
        {
                return err == 0 && port == 443;
        }

        char _license[] SEC("license") = "GPL";
        int  _version   SEC("version") = LINUX_VERSION_CODE;
        #
        # perf record -a -g -e ssl.bpf.c
        ^C[ perf record: Woken up 1 times to write data ]
        [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
        # perf script | head -30
        swapper     0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
           856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
           2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
           2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
           96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
           969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
           2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
           95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
          1163ffa start_kernel ([kernel.vmlinux].init.text)
          11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
          1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)

        qemu-system-x86  9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
           8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
             430a br_handle_frame_finish ([bridge])
             48bc br_handle_frame ([bridge])
           855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
        #

   - Use 'perf probe' various options to list functions, see what
     variables can be collected at any given point, experiment first
     collecting without a filter, then filter, use it together with
     'perf trace', 'perf top', with or without callchains, if it
     explodes, please tell us!

   - Introduce a new callchain mode: "folded", that will list per line
     representations of all callchains for a give histogram entry,
     facilitating 'perf report' output processing by other tools, such
     as Brendan Gregg's flamegraph tools (Namhyung Kim)

     E.g:

        # perf report | grep -v ^# | head
           18.37%     0.00%  swapper  [kernel.kallsyms]   [k] cpu_startup_entry
                           |
                           ---cpu_startup_entry
                              |
                              |--12.07%--start_secondary
                              |
                               --6.30%--rest_init
                                         start_kernel
                                         x86_64_start_reservations
                                         x86_64_start_kernel
         #

     Becomes, in "folded" mode:

        # perf report -g folded | grep -v ^# | head -5
            18.37%     0.00%  swapper [kernel.kallsyms]   [k] cpu_startup_entry
          12.07% cpu_startup_entry;start_secondary
           6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] call_cpuidle
          11.23% call_cpuidle;cpu_startup_entry;start_secondary
           5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter
          11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
           5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            15.12%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter_state
         #

     The user can also select one of "count", "period" or "percent" as
     the first column.

  ... and lots of infrastructure enhancements, plus fixes and other
  changes, features I failed to list - see the shortlog and the git log
  for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
  perf evlist: Add --trace-fields option to show trace fields
  perf record: Store data mmaps for dwarf unwind
  perf libdw: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Use find_map function in access_dso_mem
  perf evlist: Remove perf_evlist__(enable|disable)_event functions
  perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
  perf report: Show random usage tip on the help line
  perf hists: Export a couple of hist functions
  perf diff: Use perf_hpp__register_sort_field interface
  perf tools: Add overhead/overhead_children keys defaults via string
  perf tools: Remove list entry from struct sort_entry
  perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
  perf script: Align event name properly
  perf tools: Add missing headers in perf's MANIFEST
  perf tools: Do not show trace command if it's not compiled in
  perf report: Change default to use event group view
  perf top: Decay periods in callchains
  tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
  tools lib: Sync tools/lib/find_bit.c with the kernel
  ...

1 files changed, 0 insertions, 339 deletions

diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
deleted file mode 100644
index 86c37c472263..000000000000
--- a/tools/perf/util/help.c
+++ /dev/null
@@ -1,339 +0,0 @@
-#include "cache.h"
-#include "../builtin.h"
-#include "exec_cmd.h"
-#include "levenshtein.h"
-#include "help.h"
-#include <termios.h>
-
-void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
-{
-	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
-
-	ent->len = len;
-	memcpy(ent->name, name, len);
-	ent->name[len] = 0;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
-	cmds->names[cmds->cnt++] = ent;
-}
-
-static void clean_cmdnames(struct cmdnames *cmds)
-{
-	unsigned int i;
-
-	for (i = 0; i < cmds->cnt; ++i)
-		zfree(&cmds->names[i]);
-	zfree(&cmds->names);
-	cmds->cnt = 0;
-	cmds->alloc = 0;
-}
-
-static int cmdname_compare(const void *a_, const void *b_)
-{
-	struct cmdname *a = *(struct cmdname **)a_;
-	struct cmdname *b = *(struct cmdname **)b_;
-	return strcmp(a->name, b->name);
-}
-
-static void uniq(struct cmdnames *cmds)
-{
-	unsigned int i, j;
-
-	if (!cmds->cnt)
-		return;
-
-	for (i = j = 1; i < cmds->cnt; i++)
-		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
-			cmds->names[j++] = cmds->names[i];
-
-	cmds->cnt = j;
-}
-
-void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
-{
-	size_t ci, cj, ei;
-	int cmp;
-
-	ci = cj = ei = 0;
-	while (ci < cmds->cnt && ei < excludes->cnt) {
-		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
-		if (cmp < 0)
-			cmds->names[cj++] = cmds->names[ci++];
-		else if (cmp == 0)
-			ci++, ei++;
-		else if (cmp > 0)
-			ei++;
-	}
-
-	while (ci < cmds->cnt)
-		cmds->names[cj++] = cmds->names[ci++];
-
-	cmds->cnt = cj;
-}
-
-static void pretty_print_string_list(struct cmdnames *cmds, int longest)
-{
-	int cols = 1, rows;
-	int space = longest + 1; /* min 1 SP between words */
-	struct winsize win;
-	int max_cols;
-	int i, j;
-
-	get_term_dimensions(&win);
-	max_cols = win.ws_col - 1; /* don't print *on* the edge */
-
-	if (space < max_cols)
-		cols = max_cols / space;
-	rows = (cmds->cnt + cols - 1) / cols;
-
-	for (i = 0; i < rows; i++) {
-		printf("  ");
-
-		for (j = 0; j < cols; j++) {
-			unsigned int n = j * rows + i;
-			unsigned int size = space;
-
-			if (n >= cmds->cnt)
-				break;
-			if (j == cols-1 || n + rows >= cmds->cnt)
-				size = 1;
-			printf("%-*s", size, cmds->names[n]->name);
-		}
-		putchar('\n');
-	}
-}
-
-static int is_executable(const char *name)
-{
-	struct stat st;
-
-	if (stat(name, &st) || /* stat, not lstat */
-	    !S_ISREG(st.st_mode))
-		return 0;
-
-	return st.st_mode & S_IXUSR;
-}
-
-static void list_commands_in_dir(struct cmdnames *cmds,
-					 const char *path,
-					 const char *prefix)
-{
-	int prefix_len;
-	DIR *dir = opendir(path);
-	struct dirent *de;
-	struct strbuf buf = STRBUF_INIT;
-	int len;
-
-	if (!dir)
-		return;
-	if (!prefix)
-		prefix = "perf-";
-	prefix_len = strlen(prefix);
-
-	strbuf_addf(&buf, "%s/", path);
-	len = buf.len;
-
-	while ((de = readdir(dir)) != NULL) {
-		int entlen;
-
-		if (prefixcmp(de->d_name, prefix))
-			continue;
-
-		strbuf_setlen(&buf, len);
-		strbuf_addstr(&buf, de->d_name);
-		if (!is_executable(buf.buf))
-			continue;
-
-		entlen = strlen(de->d_name) - prefix_len;
-		if (has_extension(de->d_name, ".exe"))
-			entlen -= 4;
-
-		add_cmdname(cmds, de->d_name + prefix_len, entlen);
-	}
-	closedir(dir);
-	strbuf_release(&buf);
-}
-
-void load_command_list(const char *prefix,
-		struct cmdnames *main_cmds,
-		struct cmdnames *other_cmds)
-{
-	const char *env_path = getenv("PATH");
-	const char *exec_path = perf_exec_path();
-
-	if (exec_path) {
-		list_commands_in_dir(main_cmds, exec_path, prefix);
-		qsort(main_cmds->names, main_cmds->cnt,
-		      sizeof(*main_cmds->names), cmdname_compare);
-		uniq(main_cmds);
-	}
-
-	if (env_path) {
-		char *paths, *path, *colon;
-		path = paths = strdup(env_path);
-		while (1) {
-			if ((colon = strchr(path, PATH_SEP)))
-				*colon = 0;
-			if (!exec_path || strcmp(path, exec_path))
-				list_commands_in_dir(other_cmds, path, prefix);
-
-			if (!colon)
-				break;
-			path = colon + 1;
-		}
-		free(paths);
-
-		qsort(other_cmds->names, other_cmds->cnt,
-		      sizeof(*other_cmds->names), cmdname_compare);
-		uniq(other_cmds);
-	}
-	exclude_cmds(other_cmds, main_cmds);
-}
-
-void list_commands(const char *title, struct cmdnames *main_cmds,
-		   struct cmdnames *other_cmds)
-{
-	unsigned int i, longest = 0;
-
-	for (i = 0; i < main_cmds->cnt; i++)
-		if (longest < main_cmds->names[i]->len)
-			longest = main_cmds->names[i]->len;
-	for (i = 0; i < other_cmds->cnt; i++)
-		if (longest < other_cmds->names[i]->len)
-			longest = other_cmds->names[i]->len;
-
-	if (main_cmds->cnt) {
-		const char *exec_path = perf_exec_path();
-		printf("available %s in '%s'\n", title, exec_path);
-		printf("----------------");
-		mput_char('-', strlen(title) + strlen(exec_path));
-		putchar('\n');
-		pretty_print_string_list(main_cmds, longest);
-		putchar('\n');
-	}
-
-	if (other_cmds->cnt) {
-		printf("%s available from elsewhere on your $PATH\n", title);
-		printf("---------------------------------------");
-		mput_char('-', strlen(title));
-		putchar('\n');
-		pretty_print_string_list(other_cmds, longest);
-		putchar('\n');
-	}
-}
-
-int is_in_cmdlist(struct cmdnames *c, const char *s)
-{
-	unsigned int i;
-
-	for (i = 0; i < c->cnt; i++)
-		if (!strcmp(s, c->names[i]->name))
-			return 1;
-	return 0;
-}
-
-static int autocorrect;
-static struct cmdnames aliases;
-
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
-{
-	if (!strcmp(var, "help.autocorrect"))
-		autocorrect = perf_config_int(var,value);
-	/* Also use aliases for command lookup */
-	if (!prefixcmp(var, "alias."))
-		add_cmdname(&aliases, var + 6, strlen(var + 6));
-
-	return perf_default_config(var, value, cb);
-}
-
-static int levenshtein_compare(const void *p1, const void *p2)
-{
-	const struct cmdname *const *c1 = p1, *const *c2 = p2;
-	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
-	int l1 = (*c1)->len;
-	int l2 = (*c2)->len;
-	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
-}
-
-static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
-{
-	unsigned int i;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
-
-	for (i = 0; i < old->cnt; i++)
-		cmds->names[cmds->cnt++] = old->names[i];
-	zfree(&old->names);
-	old->cnt = 0;
-}
-
-const char *help_unknown_cmd(const char *cmd)
-{
-	unsigned int i, n = 0, best_similarity = 0;
-	struct cmdnames main_cmds, other_cmds;
-
-	memset(&main_cmds, 0, sizeof(main_cmds));
-	memset(&other_cmds, 0, sizeof(main_cmds));
-	memset(&aliases, 0, sizeof(aliases));
-
-	perf_config(perf_unknown_cmd_config, NULL);
-
-	load_command_list("perf-", &main_cmds, &other_cmds);
-
-	add_cmd_list(&main_cmds, &aliases);
-	add_cmd_list(&main_cmds, &other_cmds);
-	qsort(main_cmds.names, main_cmds.cnt,
-	      sizeof(main_cmds.names), cmdname_compare);
-	uniq(&main_cmds);
-
-	if (main_cmds.cnt) {
-		/* This reuses cmdname->len for similarity index */
-		for (i = 0; i < main_cmds.cnt; ++i)
-			main_cmds.names[i]->len =
-				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-		qsort(main_cmds.names, main_cmds.cnt,
-		      sizeof(*main_cmds.names), levenshtein_compare);
-
-		best_similarity = main_cmds.names[0]->len;
-		n = 1;
-		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
-			++n;
-	}
-
-	if (autocorrect && n == 1) {
-		const char *assumed = main_cmds.names[0]->name;
-
-		main_cmds.names[0] = NULL;
-		clean_cmdnames(&main_cmds);
-		fprintf(stderr, "WARNING: You called a perf program named '%s', "
-			"which does not exist.\n"
-			"Continuing under the assumption that you meant '%s'\n",
-			cmd, assumed);
-		if (autocorrect > 0) {
-			fprintf(stderr, "in %0.1f seconds automatically...\n",
-				(float)autocorrect/10.0);
-			poll(NULL, 0, autocorrect * 100);
-		}
-		return assumed;
-	}
-
-	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
-
-	if (main_cmds.cnt && best_similarity < 6) {
-		fprintf(stderr, "\nDid you mean %s?\n",
-			n < 2 ? "this": "one of these");
-
-		for (i = 0; i < n; i++)
-			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
-	}
-
-	exit(1);
-}
-
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-		const char *prefix __maybe_unused)
-{
-	printf("perf version %s\n", perf_version_string);
-	return 0;
-}