diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 10:29:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 10:29:15 -0700 |
commit | 9c2b957db1772ebf942ae7a9346b14eba6c8ca66 (patch) | |
tree | 0dbb83e57260ea7fc0dc421f214d5f1b26262005 /tools/perf/util/ui/browsers | |
parent | 0bbfcaff9b2a69c71a95e6902253487ab30cb498 (diff) | |
parent | bea95c152dee1791dd02cbc708afbb115bb00f9a (diff) | |
download | blackbird-op-linux-9c2b957db1772ebf942ae7a9346b14eba6c8ca66.tar.gz blackbird-op-linux-9c2b957db1772ebf942ae7a9346b14eba6c8ca66.zip |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events changes for v3.4 from Ingo Molnar:
- New "hardware based branch profiling" feature both on the kernel and
the tooling side, on CPUs that support it. (modern x86 Intel CPUs
with the 'LBR' hardware feature currently.)
This new feature is basically a sophisticated 'magnifying glass' for
branch execution - something that is pretty difficult to extract from
regular, function histogram centric profiles.
The simplest mode is activated via 'perf record -b', and the result
looks like this in perf report:
$ perf record -b any_call,u -e cycles:u branchy
$ perf report -b --sort=symbol
52.34% [.] main [.] f1
24.04% [.] f1 [.] f3
23.60% [.] f1 [.] f2
0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow
0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn
0.01% [k] _IO_vfprintf_internal [k] strchrnul
0.01% [k] __printf [k] _IO_vfprintf_internal
0.01% [k] main [k] __printf
This output shows from/to branch columns and shows the highest
percentage (from,to) jump combinations - i.e. the most likely taken
branches in the system. "branches" can also include function calls
and any other synchronous and asynchronous transitions of the
instruction pointer that are not 'next instruction' - such as system
calls, traps, interrupts, etc.
This feature comes with (hopefully intuitive) flat ascii and TUI
support in perf report.
- Various 'perf annotate' visual improvements for us assembly junkies.
It will now recognize function calls in the TUI and by hitting enter
you can follow the call (recursively) and back, amongst other
improvements.
- Multiple threads/processes recording support in perf record, perf
stat, perf top - which is activated via a comma-list of PIDs:
perf top -p 21483,21485
perf stat -p 21483,21485 -ddd
perf record -p 21483,21485
- Support for per UID views, via the --uid paramter to perf top, perf
report, etc. For example 'perf top --uid mingo' will only show the
tasks that I am running, excluding other users, root, etc.
- Jump label restructurings and improvements - this includes the
factoring out of the (hopefully much clearer) include/linux/static_key.h
generic facility:
struct static_key key = STATIC_KEY_INIT_FALSE;
...
if (static_key_false(&key))
do unlikely code
else
do likely code
...
static_key_slow_inc();
...
static_key_slow_inc();
...
The static_key_false() branch will be generated into the code with as
little impact to the likely code path as possible. the
static_key_slow_*() APIs flip the branch via live kernel code patching.
This facility can now be used more widely within the kernel to
micro-optimize hot branches whose likelihood matches the static-key
usage and fast/slow cost patterns.
- SW function tracer improvements: perf support and filtering support.
- Various hardenings of the perf.data ABI, to make older perf.data's
smoother on newer tool versions, to make new features integrate more
smoothly, to support cross-endian recording/analyzing workflows
better, etc.
- Restructuring of the kprobes code, the splitting out of 'optprobes',
and a corner case bugfix.
- Allow the tracing of kernel console output (printk).
- Improvements/fixes to user-space RDPMC support, allowing user-space
self-profiling code to extract PMU counts without performing any
system calls, while playing nice with the kernel side.
- 'perf bench' improvements
- ... and lots of internal restructurings, cleanups and fixes that made
these features possible. And, as usual this list is incomplete as
there were also lots of other improvements
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
perf report: Fix annotate double quit issue in branch view mode
perf report: Remove duplicate annotate choice in branch view mode
perf/x86: Prettify pmu config literals
perf report: Enable TUI in branch view mode
perf report: Auto-detect branch stack sampling mode
perf record: Add HEADER_BRANCH_STACK tag
perf record: Provide default branch stack sampling mode option
perf tools: Make perf able to read files from older ABIs
perf tools: Fix ABI compatibility bug in print_event_desc()
perf tools: Enable reading of perf.data files from different ABI rev
perf: Add ABI reference sizes
perf report: Add support for taken branch sampling
perf record: Add support for sampling taken branch
perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
x86/kprobes: Split out optprobe related code to kprobes-opt.c
x86/kprobes: Fix a bug which can modify kernel code permanently
x86/kprobes: Fix instruction recovery on optimized path
perf: Add callback to flush branch_stack on context switch
perf: Disable PERF_SAMPLE_BRANCH_* when not supported
perf/x86: Add LBR software filter support for Intel CPUs
...
Diffstat (limited to 'tools/perf/util/ui/browsers')
-rw-r--r-- | tools/perf/util/ui/browsers/annotate.c | 18 | ||||
-rw-r--r-- | tools/perf/util/ui/browsers/hists.c | 105 | ||||
-rw-r--r-- | tools/perf/util/ui/browsers/map.c | 2 |
3 files changed, 99 insertions, 26 deletions
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 295a9c93f945..57a4c6ef3fd2 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -69,14 +69,17 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro if (!self->navkeypressed) width += 1; + if (!ab->hide_src_code && ol->offset != -1) + if (!current_entry || (self->use_navkeypressed && + !self->navkeypressed)) + ui_browser__set_color(self, HE_COLORSET_CODE); + if (!*ol->line) slsmg_write_nstring(" ", width - 18); else slsmg_write_nstring(ol->line, width - 18); - if (!current_entry) - ui_browser__set_color(self, HE_COLORSET_CODE); - else + if (current_entry) ab->selection = ol; } @@ -230,9 +233,9 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, struct rb_node *nd = NULL; struct map_symbol *ms = self->b.priv; struct symbol *sym = ms->sym; - const char *help = "<-, ESC: exit, TAB/shift+TAB: cycle hottest lines, " - "H: Hottest, -> Line action, S -> Toggle source " - "code view"; + const char *help = "<-/ESC: Exit, TAB/shift+TAB: Cycle hot lines, " + "H: Go to hottest line, ->/ENTER: Line action, " + "S: Toggle source code view"; int key; if (ui_browser__show(&self->b, sym->name, help) < 0) @@ -284,9 +287,11 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, nd = self->curr_hot; break; case 'H': + case 'h': nd = self->curr_hot; break; case 'S': + case 's': if (annotate_browser__toggle_source(self)) ui_helpline__puts(help); continue; @@ -338,6 +343,7 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, pthread_mutex_unlock(¬es->lock); symbol__tui_annotate(target, ms->map, evidx, timer, arg, delay_secs); + ui_browser__show_title(&self->b, sym->name); } continue; case K_LEFT: diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index bb9197c9c4a4..fa530fcc764a 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -805,8 +805,11 @@ static struct hist_browser *hist_browser__new(struct hists *hists) self->hists = hists; self->b.refresh = hist_browser__refresh; self->b.seek = ui_browser__hists_seek; - self->b.use_navkeypressed = true, - self->has_symbols = sort_sym.list.next != NULL; + self->b.use_navkeypressed = true; + if (sort__branch_mode == 1) + self->has_symbols = sort_sym_from.list.next != NULL; + else + self->has_symbols = sort_sym.list.next != NULL; } return self; @@ -839,6 +842,9 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, nr_events = convert_unit(nr_events, &unit); printed = scnprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name); + if (self->uid_filter_str) + printed += snprintf(bf + printed, size - printed, + ", UID: %s", self->uid_filter_str); if (thread) printed += scnprintf(bf + printed, size - printed, ", Thread: %s(%d)", @@ -850,6 +856,16 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, return printed; } +static inline void free_popup_options(char **options, int n) +{ + int i; + + for (i = 0; i < n; ++i) { + free(options[i]); + options[i] = NULL; + } +} + static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, bool left_exits, @@ -858,7 +874,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, { struct hists *self = &evsel->hists; struct hist_browser *browser = hist_browser__new(self); + struct branch_info *bi; struct pstack *fstack; + char *options[16]; + int nr_options = 0; int key = -1; if (browser == NULL) @@ -870,13 +889,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, ui_helpline__push(helpline); + memset(options, 0, sizeof(options)); + while (1) { const struct thread *thread = NULL; const struct dso *dso = NULL; - char *options[16]; - int nr_options = 0, choice = 0, i, + int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, - browse_map = -2; + annotate_f = -2, annotate_t = -2, browse_map = -2; + + nr_options = 0; key = hist_browser__run(browser, ev_name, timer, arg, delay_secs); @@ -884,7 +906,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, thread = hist_browser__selected_thread(browser); dso = browser->selection->map ? browser->selection->map->dso : NULL; } - switch (key) { case K_TAB: case K_UNTAB: @@ -899,7 +920,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (!browser->has_symbols) { ui_browser__warning(&browser->b, delay_secs * 2, "Annotation is only available for symbolic views, " - "include \"sym\" in --sort to use it."); + "include \"sym*\" in --sort to use it."); continue; } @@ -969,12 +990,34 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (!browser->has_symbols) goto add_exit_option; - if (browser->selection != NULL && - browser->selection->sym != NULL && - !browser->selection->map->dso->annotate_warned && - asprintf(&options[nr_options], "Annotate %s", - browser->selection->sym->name) > 0) - annotate = nr_options++; + if (sort__branch_mode == 1) { + bi = browser->he_selection->branch_info; + if (browser->selection != NULL && + bi && + bi->from.sym != NULL && + !bi->from.map->dso->annotate_warned && + asprintf(&options[nr_options], "Annotate %s", + bi->from.sym->name) > 0) + annotate_f = nr_options++; + + if (browser->selection != NULL && + bi && + bi->to.sym != NULL && + !bi->to.map->dso->annotate_warned && + (bi->to.sym != bi->from.sym || + bi->to.map->dso != bi->from.map->dso) && + asprintf(&options[nr_options], "Annotate %s", + bi->to.sym->name) > 0) + annotate_t = nr_options++; + } else { + + if (browser->selection != NULL && + browser->selection->sym != NULL && + !browser->selection->map->dso->annotate_warned && + asprintf(&options[nr_options], "Annotate %s", + browser->selection->sym->name) > 0) + annotate = nr_options++; + } if (thread != NULL && asprintf(&options[nr_options], "Zoom %s %s(%d) thread", @@ -995,25 +1038,39 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, browse_map = nr_options++; add_exit_option: options[nr_options++] = (char *)"Exit"; - +retry_popup_menu: choice = ui__popup_menu(nr_options, options); - for (i = 0; i < nr_options - 1; ++i) - free(options[i]); - if (choice == nr_options - 1) break; - if (choice == -1) + if (choice == -1) { + free_popup_options(options, nr_options - 1); continue; + } - if (choice == annotate) { + if (choice == annotate || choice == annotate_t || choice == annotate_f) { struct hist_entry *he; int err; do_annotate: he = hist_browser__selected_entry(browser); if (he == NULL) continue; + + /* + * we stash the branch_info symbol + map into the + * the ms so we don't have to rewrite all the annotation + * code to use branch_info. + * in branch mode, the ms struct is not used + */ + if (choice == annotate_f) { + he->ms.sym = he->branch_info->from.sym; + he->ms.map = he->branch_info->from.map; + } else if (choice == annotate_t) { + he->ms.sym = he->branch_info->to.sym; + he->ms.map = he->branch_info->to.map; + } + /* * Don't let this be freed, say, by hists__decay_entry. */ @@ -1021,9 +1078,18 @@ do_annotate: err = hist_entry__tui_annotate(he, evsel->idx, timer, arg, delay_secs); he->used = false; + /* + * offer option to annotate the other branch source or target + * (if they exists) when returning from annotate + */ + if ((err == 'q' || err == CTRL('c')) + && annotate_t != -2 && annotate_f != -2) + goto retry_popup_menu; + ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries); if (err) ui_browser__handle_resize(&browser->b); + } else if (choice == browse_map) map__browse(browser->selection->map); else if (choice == zoom_dso) { @@ -1069,6 +1135,7 @@ out_free_stack: pstack__delete(fstack); out: hist_browser__delete(browser); + free_popup_options(options, nr_options - 1); return key; } diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c index 6905bcc8be2d..eca6575abfd0 100644 --- a/tools/perf/util/ui/browsers/map.c +++ b/tools/perf/util/ui/browsers/map.c @@ -3,9 +3,9 @@ #include <newt.h> #include <inttypes.h> #include <sys/ttydefaults.h> -#include <ctype.h> #include <string.h> #include <linux/bitops.h> +#include "../../util.h" #include "../../debug.h" #include "../../symbol.h" #include "../browser.h" |