From d85ce830eef6c10d1e9617172dea4681f02b8424 Mon Sep 17 00:00:00 2001 From: Markus Trippelsdorf Date: Mon, 14 Dec 2015 16:44:40 +0100 Subject: [PATCH 01/26] perf pmu: Fix misleadingly indented assignment (whitespace) One line in perf_pmu__parse_unit() is indented wrongly, leading to a warning (=> error) from gcc 6: util/pmu.c:156:3: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation] sret = read(fd, alias->unit, UNIT_MAX_LEN); ^~~~ util/pmu.c:153:2: note: ...this 'if' clause, but it is not if (fd == -1) ^~ Signed-off-by: Markus Trippelsdorf Acked-by: Ingo Molnar Cc: Ben Hutchings Cc: Matt Fleming Cc: Peter Zijlstra Fixes: 410136f5dd96 ("tools/perf/stat: Add event unit and scale support") Link: http://lkml.kernel.org/r/20151214154440.GC1409@x4 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b597bcc8fc78..41a9c875e492 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -153,7 +153,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n if (fd == -1) return -1; - sret = read(fd, alias->unit, UNIT_MAX_LEN); + sret = read(fd, alias->unit, UNIT_MAX_LEN); if (sret < 0) goto error; From 403567217d3fa5d4801f820317ada52e5c5f0e53 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Jan 2016 12:56:32 +0100 Subject: [PATCH 02/26] perf symbols: Do not read symbols/data from device files With mem sampling we could get data source within mapped device file. Processing such sample would block during report phase on trying to read the device file. Chacking for device files and skip the processing if it's detected. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1453290995-18485-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 5 +++++ tools/perf/util/symbol.c | 6 +++++- tools/perf/util/util.c | 10 ++++++++++ tools/perf/util/util.h | 1 + 4 files changed, 21 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e8e9a9dbf5e3..8e6395439ca0 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso, debuglink--; if (*debuglink == '/') debuglink++; + + ret = -1; + if (!is_regular_file(filename)) + break; + ret = filename__read_debuglink(filename, debuglink, size - (debuglink - filename)); } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index ab02209a7cf3..90cedfa30e43 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + if (is_regular_file(name) && + filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); /* @@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) root_dir, name, PATH_MAX)) continue; + if (!is_regular_file(name)) + continue; + /* Name is now the name of the next image to try */ if (symsrc__init(ss, dso, name, symtab_type) < 0) continue; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index ead9509835d2..7a2da7ef556e 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -691,3 +691,13 @@ out: return tip; } + +bool is_regular_file(const char *file) +{ + struct stat st; + + if (stat(file, &st)) + return false; + + return S_ISREG(st.st_mode); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index fe915e616f9b..61650f05e5c1 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -343,5 +343,6 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) const char *perf_tip(const char *dirpath); +bool is_regular_file(const char *file); #endif /* GIT_COMPAT_UTIL_H */ From 86a2cf3123bfec118bfb98728d88be0668779b2b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Jan 2016 12:56:35 +0100 Subject: [PATCH 03/26] perf stat: Making several helper functions static There's no need for the following functions to be global: perf_evsel__reset_stat_priv perf_evsel__alloc_stat_priv perf_evsel__free_stat_priv perf_evsel__alloc_prev_raw_counts perf_evsel__free_prev_raw_counts perf_evsel__alloc_stats They all ended up in util/stat.c, and they no longer need to be called from outside this object. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1453290995-18485-5-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat.c | 14 +++++++------- tools/perf/util/stat.h | 10 ---------- 2 files changed, 7 insertions(+), 17 deletions(-) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2b58edccd56f..beeed0bd3bee 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; struct perf_stat_evsel *ps = evsel->priv; @@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) perf_stat_evsel_id_init(evsel); } -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat_evsel)); if (evsel->priv == NULL) @@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) return 0; } -void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { zfree(&evsel->priv); } -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) { struct perf_counts *counts; @@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, return counts ? 0 : -ENOMEM; } -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) { perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); int nthreads = thread_map__nr(evsel->threads); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 086f4e128d63..2af63c9cb59f 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -74,16 +74,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); -void perf_evsel__free_stat_priv(struct perf_evsel *evsel); - -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads); -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); - -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw); - int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct perf_evlist *evlist); void perf_evlist__reset_stats(struct perf_evlist *evlist); From c84a5d16711619621f368e84a179790df3377c87 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 20 Jan 2016 10:15:20 +0900 Subject: [PATCH 04/26] perf hists: Remove parent filter check in DSO filter function The --exclude-other option sets HIST_FILTER__PARENT bit and it's only set when a hist entry was created. DSO filters don't change this so no need to have the check in hists__filter_by_dso() IMHO. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Acked-by: Pekka Enberg Cc: Andi Kleen Cc: David Ahern Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1453252521-24398-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 68a7612019dc..1d8c8eab9daa 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1266,9 +1266,6 @@ void hists__filter_by_dso(struct hists *hists) for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (symbol_conf.exclude_other && !h->parent) - continue; - if (hists__filter_entry_by_dso(hists, h)) continue; From 1f7c254132f098d19ff3fd452ba9f826cd85c4c0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 20 Jan 2016 10:15:21 +0900 Subject: [PATCH 05/26] perf hists: Cleanup filtering functions The hists__filter_by_xxx functions share same logic with different filters. Factor out the common code into the hists__filter_by_type. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Acked-by: Pekka Enberg Cc: Andi Kleen Cc: David Ahern Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1453252521-24398-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 89 ++++++++++++++---------------------------- 1 file changed, 29 insertions(+), 60 deletions(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 1d8c8eab9daa..81ce0aff69d1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1254,25 +1254,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists, return false; } -void hists__filter_by_dso(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_dso(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__DSO); - } -} - static bool hists__filter_entry_by_thread(struct hists *hists, struct hist_entry *he) { @@ -1285,25 +1266,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, return false; } -void hists__filter_by_thread(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_thread(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD); - } -} - static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he) { @@ -1317,25 +1279,6 @@ static bool hists__filter_entry_by_symbol(struct hists *hists, return false; } -void hists__filter_by_symbol(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_symbol(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL); - } -} - static bool hists__filter_entry_by_socket(struct hists *hists, struct hist_entry *he) { @@ -1348,7 +1291,9 @@ static bool hists__filter_entry_by_socket(struct hists *hists, return false; } -void hists__filter_by_socket(struct hists *hists) +typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he); + +static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter) { struct rb_node *nd; @@ -1360,13 +1305,37 @@ void hists__filter_by_socket(struct hists *hists) for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (hists__filter_entry_by_socket(hists, h)) + if (filter(hists, h)) continue; - hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET); + hists__remove_entry_filter(hists, h, type); } } +void hists__filter_by_thread(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__THREAD, + hists__filter_entry_by_thread); +} + +void hists__filter_by_dso(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__DSO, + hists__filter_entry_by_dso); +} + +void hists__filter_by_symbol(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__SYMBOL, + hists__filter_entry_by_symbol); +} + +void hists__filter_by_socket(struct hists *hists) +{ + hists__filter_by_type(hists, HIST_FILTER__SOCKET, + hists__filter_entry_by_socket); +} + void events_stats__inc(struct events_stats *stats, u32 type) { ++stats->nr_events[0]; From 3379e0c3effa87d7734fc06277a7023292aadb0c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 19 Jan 2016 21:35:15 +0000 Subject: [PATCH 06/26] perf tools: Document the perf sysctls perf_event_paranoid was only documented in source code and a perf error message. Copy the documentation from the error message to Documentation/sysctl/kernel.txt. perf_cpu_time_max_percent was already documented but missing from the list at the top, so add it there. Signed-off-by: Ben Hutchings Cc: Peter Zijlstra Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/20160119213515.GG2637@decadent.org.uk [ Remove reference to external Documentation file, provide info inline, as before ] Signed-off-by: Arnaldo Carvalho de Melo --- Documentation/sysctl/kernel.txt | 13 +++++++++++++ tools/perf/util/evsel.c | 15 +++++++++------ 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 73c6b1ef0e84..c803e7300f0b 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -58,6 +58,8 @@ show up in /proc/sys/kernel: - panic_on_stackoverflow - panic_on_unrecovered_nmi - panic_on_warn +- perf_cpu_time_max_percent +- perf_event_paranoid - pid_max - powersave-nap [ PPC only ] - printk @@ -639,6 +641,17 @@ allowed to execute. ============================================================== +perf_event_paranoid: + +Controls use of the performance events system by unprivileged +users (without CAP_SYS_ADMIN). The default value is 1. + + -1: Allow use of (almost) all events by all users +>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK +>=1: Disallow CPU event access by users without CAP_SYS_ADMIN +>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN + +============================================================== pid_max: diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index cdbaf9b51e42..467808680ee4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2362,12 +2362,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, case EPERM: case EACCES: return scnprintf(msg, size, - "You may not have permission to collect %sstats.\n" - "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" - " -1 - Not paranoid at all\n" - " 0 - Disallow raw tracepoint access for unpriv\n" - " 1 - Disallow cpu events for unpriv\n" - " 2 - Disallow kernel profiling for unpriv", + "You may not have permission to collect %sstats.\n\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" + "which controls use of the performance events system by\n" + "unprivileged users (without CAP_SYS_ADMIN).\n\n" + "The default value is 1:\n\n" + " -1: Allow use of (almost) all events by all users\n" + ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" + ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", target->system_wide ? "system-wide " : ""); case ENOENT: return scnprintf(msg, size, "The %s event is not supported.", From 78ce08dfbd180fb85312ee76e607a6c5fe34a06c Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 17:16:11 +0900 Subject: [PATCH 07/26] perf annotate: Rename 'colors.code' to 'colors.jump_arrows' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit USe 'jump_arrows' config name instead of 'code' on 'colors' section. 'colors.code' config is only for jump arrows on assembly code listings i.e. │ ┌──jmp 1333 │ │ xchg %ax,%ax │ │ mov %r15,%r10 │ └─→cmp %r15,%r14 But this config name seems unfit. 'jump_arrows' is more descriptive than 'code'. Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452240971-25418-1-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 2 +- tools/perf/Documentation/perfconfig.example | 2 +- tools/perf/ui/browser.c | 4 ++-- tools/perf/ui/browser.h | 2 +- tools/perf/ui/browsers/annotate.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index b9ca1e304158..1ee488b9aaf7 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -62,7 +62,7 @@ Given a $HOME/.perfconfig like this: medium = green, default normal = lightgray, default selected = white, lightgray - code = blue, default + jump_arrows = blue, default addr = magenta, default root = white, blue diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example index 767ea2436e1c..1d8d5bc4cd2d 100644 --- a/tools/perf/Documentation/perfconfig.example +++ b/tools/perf/Documentation/perfconfig.example @@ -5,7 +5,7 @@ medium = green, lightgray normal = black, lightgray selected = lightgray, magenta - code = blue, lightgray + jump_arrows = blue, lightgray addr = magenta, lightgray [tui] diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index d37202121689..af68a9d488bf 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -531,8 +531,8 @@ static struct ui_browser_colorset { .bg = "yellow", }, { - .colorset = HE_COLORSET_CODE, - .name = "code", + .colorset = HE_COLORSET_JUMP_ARROWS, + .name = "jump_arrows", .fg = "blue", .bg = "default", }, diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 01781de59532..be3b70eb5fca 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -7,7 +7,7 @@ #define HE_COLORSET_MEDIUM 51 #define HE_COLORSET_NORMAL 52 #define HE_COLORSET_SELECTED 53 -#define HE_COLORSET_CODE 54 +#define HE_COLORSET_JUMP_ARROWS 54 #define HE_COLORSET_ADDR 55 #define HE_COLORSET_ROOT 56 diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 718bd46d47fa..4fc208e82c6f 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) to = (u64)btarget->idx; } - ui_browser__set_color(browser, HE_COLORSET_CODE); + ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS); __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, from, to); } From 89debf178708458ac62f5b53dfc97437009d02d3 Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 20:39:31 +0900 Subject: [PATCH 08/26] perf config: Document variables for 'colors' section in man page Explain 'colors' section and its variables, used for The variables for customizing the colors used in the output for the 'report', 'top' and 'annotate' in the TUI, those are: 'top', 'medium', 'normal', 'selected', 'jump_arrows', 'addr' and 'root'. Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452253193-30502-2-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 46 ++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 1ee488b9aaf7..80517823b7e5 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -98,6 +98,52 @@ Given a $HOME/.perfconfig like this: order = caller sort-key = function +Variables +~~~~~~~~~ + +colors.*:: + The variables for customizing the colors used in the output for the + 'report', 'top' and 'annotate' in the TUI. They should specify the + foreground and background colors, separated by a comma, for example: + + medium = green, lightgray + + If you want to use the color configured for you terminal, just leave it + as 'default', for example: + + medium = default, lightgray + + Available colors: + red, yellow, green, cyan, gray, black, blue, + white, default, magenta, lightgray + + colors.top:: + 'top' means a overhead percentage which is more than 5%. + And values of this variable specify percentage colors. + Basic key values are foreground-color 'red' and + background-color 'default'. + colors.medium:: + 'medium' means a overhead percentage which has more than 0.5%. + Default values are 'green' and 'default'. + colors.normal:: + 'normal' means the rest of overhead percentages + except 'top', 'medium', 'selected'. + Default values are 'lightgray' and 'default'. + colors.selected:: + This selects the colors for the current entry in a list of entries + from sub-commands (top, report, annotate). + Default values are 'black' and 'lightgray'. + colors.jump_arrows:: + Colors for jump arrows on assembly code listings + such as 'jns', 'jmp', 'jane', etc. + Default values are 'blue', 'default'. + colors.addr:: + This selects colors for addresses from 'annotate'. + Default values are 'magenta', 'default'. + colors.root:: + Colors for headers in the output of a sub-commands (top, report). + Default values are 'white', 'blue'. + SEE ALSO -------- linkperf:perf[1] From 3fa9f40718a33d27eb2f4bd36c13318a2d58839d Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 20:39:32 +0900 Subject: [PATCH 09/26] perf config: Document variables for 'tui' and 'gtk' sections in man page Explain 'tui' and 'gtk' sections and these variables. 'top', 'report' and 'annotate' Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452253193-30502-3-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 80517823b7e5..ccbdb64696a7 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -144,6 +144,16 @@ colors.*:: Colors for headers in the output of a sub-commands (top, report). Default values are 'white', 'blue'. +tui.*, gtk.*:: + Subcommands that can be configured here are 'top', 'report' and 'annotate'. + These values are booleans, for example: + + [tui] + top = true + + will make the TUI be the default for the 'top' subcommand. Those will be + available if the required libs were detected at tool build time. + SEE ALSO -------- linkperf:perf[1] From 2733525b8c1a5f9b6e55338d836b835c9c698913 Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 20:39:33 +0900 Subject: [PATCH 10/26] perf config: Document 'buildid.dir' variable in man page Explain 'buildid.dir' variable. Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452253193-30502-4-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index ccbdb64696a7..a095f0cabf5e 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -154,6 +154,21 @@ tui.*, gtk.*:: will make the TUI be the default for the 'top' subcommand. Those will be available if the required libs were detected at tool build time. +buildid.*:: + buildid.dir:: + Each executable and shared library in modern distributions comes with a + content based identifier that, if available, will be inserted in a + 'perf.data' file header to, at analysis time find what is needed to do + symbol resolution, code annotation, etc. + + The recording tools also stores a hard link or copy in a per-user + directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms + and /proc/kcore files to be used at analysis time. + + The buildid.dir variable can be used to either change this directory + cache location, or to disable it altogether. If you want to disable it, + set buildid.dir to /dev/null. The default is $HOME/.debug + SEE ALSO -------- linkperf:perf[1] From 3b97629d139b19cbcd15b0b3c128a4d6587d2091 Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 20:39:34 +0900 Subject: [PATCH 11/26] perf config: Document variables for 'annotate' section in man page Explain 'annotate' section and its variables. 'hide_src_code', 'use_offset', 'jump_arrows', 'show_linenr', 'show_nr_jump' and 'show_total_period'. Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452253193-30502-5-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 110 +++++++++++++++++++++++ 1 file changed, 110 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index a095f0cabf5e..cb7ca507ec5e 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -169,6 +169,116 @@ buildid.*:: cache location, or to disable it altogether. If you want to disable it, set buildid.dir to /dev/null. The default is $HOME/.debug +annotate.*:: + These options work only for TUI. + These are in control of addresses, jump function, source code + in lines of assembly code from a specific program. + + annotate.hide_src_code:: + If a program which is analyzed has source code, + this option lets 'annotate' print a list of assembly code with the source code. + For example, let's see a part of a program. There're four lines. + If this option is 'true', they can be printed + without source code from a program as below. + + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ mov (%rdi),%rdx + + But if this option is 'false', source code of the part + can be also printed as below. Default is 'false'. + + │ struct rb_node *rb_next(const struct rb_node *node) + │ { + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ struct rb_node *parent; + │ + │ if (RB_EMPTY_NODE(node)) + │ mov (%rdi),%rdx + │ return n; + + annotate.use_offset:: + Basing on a first address of a loaded function, offset can be used. + Instead of using original addresses of assembly code, + addresses subtracted from a base address can be printed. + Let's illustrate an example. + If a base address is 0XFFFFFFFF81624d50 as below, + + ffffffff81624d50 + + an address on assembly code has a specific absolute address as below + + ffffffff816250b8:│ mov 0x8(%r14),%rdi + + but if use_offset is 'true', an address subtracted from a base address is printed. + Default is true. This option is only applied to TUI. + + 368:│ mov 0x8(%r14),%rdi + + annotate.jump_arrows:: + There can be jump instruction among assembly code. + Depending on a boolean value of jump_arrows, + arrows can be printed or not which represent + where do the instruction jump into as below. + + │ ┌──jmp 1333 + │ │ xchg %ax,%ax + │1330:│ mov %r15,%r10 + │1333:└─→cmp %r15,%r14 + + If jump_arrow is 'false', the arrows isn't printed as below. + Default is 'false'. + + │ ↓ jmp 1333 + │ xchg %ax,%ax + │1330: mov %r15,%r10 + │1333: cmp %r15,%r14 + + annotate.show_linenr:: + When showing source code if this option is 'true', + line numbers are printed as below. + + │1628 if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │1628 data->id = *array; + │1629 array++; + │1630 } + + However if this option is 'false', they aren't printed as below. + Default is 'false'. + + │ if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │ data->id = *array; + │ array++; + │ } + + annotate.show_nr_jumps:: + Let's see a part of assembly code. + + │1382: movb $0x1,-0x270(%rbp) + + If use this, the number of branches jumping to that address can be printed as below. + Default is 'false'. + + │1 1382: movb $0x1,-0x270(%rbp) + + annotate.show_total_period:: + To compare two records on an instruction base, with this option + provided, display total number of samples that belong to a line + in assembly code. If this option is 'true', total periods are printed + instead of percent values as below. + + 302 │ mov %eax,%eax + + But if this option is 'false', percent values for overhead are printed i.e. + Default is 'false'. + + 99.93 │ mov %eax,%eax + SEE ALSO -------- linkperf:perf[1] From 485311d97863f2810646e17c8075be2992225f98 Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Fri, 8 Jan 2016 20:39:36 +0900 Subject: [PATCH 12/26] perf config: Document 'hist.percentage' variable in man page Explain 'hist.percentage' variable. Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1452253193-30502-7-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index cb7ca507ec5e..74589c68558a 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -279,6 +279,23 @@ annotate.*:: 99.93 │ mov %eax,%eax +hist.*:: + hist.percentage:: + This option control the way to calculate overhead of filtered entries - + that means the value of this option is effective only if there's a + filter (by comm, dso or symbol name). Suppose a following example: + + Overhead Symbols + ........ ....... + 33.33% foo + 33.33% bar + 33.33% baz + + This is an original overhead and we'll filter out the first 'foo' + entry. The value of 'relative' would increase the overhead of 'bar' + and 'baz' to 50.00% for each, while 'absolute' would show their + current overhead (33.33%). + SEE ALSO -------- linkperf:perf[1] From cfd92dadc5e830268036efb25ff41618f29c3306 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 21 Jan 2016 19:13:24 -0300 Subject: [PATCH 13/26] perf sort: Provide a way to find out if per-thread bucketing is in place Now the UI browsers will be able to offer thread related operations only if the thread is part of the sort order in use, i.e. if hist_entry stats are all for a single thread. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 3 +++ tools/perf/util/sort.h | 1 + 2 files changed, 4 insertions(+) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index ec722346e6ff..898e4b0724bf 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -25,6 +25,7 @@ int sort__has_parent = 0; int sort__has_sym = 0; int sort__has_dso = 0; int sort__has_socket = 0; +int sort__has_thread = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; @@ -2136,6 +2137,8 @@ static int sort_dimension__add(const char *tok, sort__has_dso = 1; } else if (sd->entry == &sort_socket) { sort__has_socket = 1; + } else if (sd->entry == &sort_thread) { + sort__has_thread = 1; } return __sort_dimension__add(sd); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 687bbb124428..09616f03d412 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -35,6 +35,7 @@ extern int sort__need_collapse; extern int sort__has_parent; extern int sort__has_sym; extern int sort__has_socket; +extern int sort__has_thread; extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; From 2eafd410e669c744208f8110940e42caa7d79447 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 21 Jan 2016 19:13:24 -0300 Subject: [PATCH 14/26] perf hists browser: Only 'Zoom into thread' only when sort order has 'pid' We can't offer a zoom into thread when a bucket (struct hist_entry) may have samples for more than one thread, i.e. when 'pid' is not part of the sort order, fix it. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 08c09ad755d2..e66b3a30dd9f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1782,7 +1782,7 @@ static int add_thread_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct thread *thread) { - if (thread == NULL) + if (!sort__has_thread || thread == NULL) return 0; if (asprintf(optstr, "Zoom %s %s(%d) thread", @@ -2307,10 +2307,12 @@ skip_annotation: socked_id); /* perf script support */ if (browser->he_selection) { - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - thread, NULL); + if (sort__has_thread && thread) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + thread, NULL); + } /* * Note that browser->selection != NULL * when browser->he_selection is not NULL, From c221acb0f970d3b80d72c812cda19c121acf5d52 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 21 Jan 2016 19:50:09 -0300 Subject: [PATCH 15/26] perf hists browser: Only offer symbol scripting when a symbol is under the cursor When this feature was introduced a check was made if there was a resolved symbol under the cursor, it got lost in commit ea7cd5923309 ("perf hists browser: Split popup menu actions - part 2"), reinstate it. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Fixes: ea7cd5923309 ("perf hists browser: Split popup menu actions - part 2") Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index e66b3a30dd9f..2801d80c6903 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2322,10 +2322,12 @@ skip_annotation: * * See hist_browser__show_entry. */ - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - NULL, browser->selection->sym); + if (sort__has_sym && browser->selection->sym) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + NULL, browser->selection->sym); + } } nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], NULL, NULL); From b1447a54f5b41eaf1cc469d9bd3834caa2ff9afb Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 22 Jan 2016 11:22:41 -0300 Subject: [PATCH 16/26] perf hists browser: Offer 'Zoom into DSO'/'Map details' only when sort order has 'dso' We can't offer a zoom into DSO when a bucket (struct hist_entry) may have samples for more than one DSO, i.e. when 'dso' is not part of the sort order, ditto for 'Map details', fix it. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch, moved check to add_{dso,map}_opt() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 4 ++-- tools/perf/util/sort.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 2801d80c6903..e892106410a7 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1825,7 +1825,7 @@ static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Zoom %s %s DSO", @@ -1850,7 +1850,7 @@ static int add_map_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Browse map details") < 0) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 09616f03d412..89a1273fd2da 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -32,6 +32,7 @@ extern const char default_sort_order[]; extern regex_t ignore_callees_regex; extern int have_ignore_callees; extern int sort__need_collapse; +extern int sort__has_dso; extern int sort__has_parent; extern int sort__has_sym; extern int sort__has_socket; From d9695d9f93649ecc00877ec2c847739c54a4cbb3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 22 Jan 2016 12:20:18 -0300 Subject: [PATCH 17/26] perf hists browser: Be a bit more strict about presenting CPU socket zoom For consistency with the other sort order checks. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch, moved check to add_socket_opt() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index e892106410a7..b919582add0f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1971,7 +1971,7 @@ static int add_socket_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, int socket_id) { - if (socket_id < 0) + if (!sort__has_socket || socket_id < 0) return 0; if (asprintf(optstr, "Zoom %s Processor Socket %d", From 4056132e1072f02bbad77f2071770271cc5b58fc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 22 Jan 2016 12:26:06 -0300 Subject: [PATCH 18/26] perf hists browser: Offer non-symbol specific menu options for --sort without 'sym' Now that we check more strictly what each of the menu entries need, we can stop bailing out when 'sym' is not in the --sort order, instead we let each option be added if what it needs is present. This way, for instance, we can run scripts on all samples, see DSO map details when 'dso' is in the --sort provided, etc. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452960197-5323-9-git-send-email-namhyung@kernel.org [ Carved out from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b919582add0f..d07e6be42ab1 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2263,10 +2263,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } - if (!sort__has_sym) - goto add_exit_option; - - if (browser->selection == NULL) + if (!sort__has_sym || browser->selection == NULL) goto skip_annotation; if (sort__mode == SORT_MODE__BRANCH) { @@ -2333,7 +2330,6 @@ skip_annotation: &options[nr_options], NULL, NULL); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); -add_exit_option: nr_options += add_exit_opt(browser, &actions[nr_options], &options[nr_options]); From 8acd3da03c3f6e4e31472c5c73402b95a5d0f6cb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 25 Jan 2016 18:01:57 -0300 Subject: [PATCH 19/26] perf machine: Introduce machine__find_kernel_symbol_by_name() To be used in the 'vmlinux matches kallsyms' 'perf test' entry. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-m56g1853lz2c6nhnqxibq4jd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2c2b443df5ba..1a3e45baf97f 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -179,6 +179,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine, mapp, filter); } +static inline +struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, + enum map_type type, const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol_by_name(&machine->kmaps, type, name, + mapp, filter); +} + static inline struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, struct map **mapp, From ab414dcda8fa307388c40a540b35e3c98a9da5ae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 25 Jan 2016 18:04:47 -0300 Subject: [PATCH 20/26] perf test: Fixup aliases checking in the 'vmlinux matches kallsyms' test There are cases where looking at just the next and prev entries is not enough, like with: $ readelf -sW /usr/lib/debug/lib/modules/4.3.3-301.fc23.x86_64/vmlinux | grep ffffffff81065ec0 4979: ffffffff81065ec0 53 FUNC LOCAL DEFAULT 1 try_to_free_pud_page 4980: ffffffff81065ec0 53 FUNC LOCAL DEFAULT 1 try_to_free_pte_page 4981: ffffffff81065ec0 53 FUNC LOCAL DEFAULT 1 try_to_free_pmd_page So just search by name to see if the symbol is in kallsyms. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-jj1vlljg7ol4i713l60rt5ai@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/vmlinux-kallsyms.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index f0bfc9e8fd9f..630b0b409b97 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) */ for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { struct symbol *pair, *first_pair; - bool backwards = true; sym = rb_entry(nd, struct symbol, rb_node); @@ -151,27 +150,14 @@ next_pair: continue; } else { - struct rb_node *nnd; -detour: - nnd = backwards ? rb_prev(&pair->rb_node) : - rb_next(&pair->rb_node); - if (nnd) { - struct symbol *next = rb_entry(nnd, struct symbol, rb_node); - - if (UM(next->start) == mem_start) { - pair = next; + pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL); + if (pair) { + if (UM(pair->start) == mem_start) goto next_pair; - } - } - if (backwards) { - backwards = false; - pair = first_pair; - goto detour; + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", + mem_start, sym->name, pair->name); } - - pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", - mem_start, sym->name, pair->name); } } else pr_debug("%#" PRIx64 ": %s not on kallsyms\n", From 7b6982ce4b38ecc3f63be46beb7bd079aa290fd7 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 25 Jan 2016 09:55:48 +0000 Subject: [PATCH 21/26] perf test: Add libbpf relocation checker There's a bug in LLVM that it can generate unneeded relocation information. See [1] and [2]. Libbpf should check the target section of a relocation symbol. This patch adds a testcase which references a global variable (BPF doesn't support global variables). Before fixing libbpf, the new test case can be loaded into kernel, the global variable acts like the first map. It is incorrect. Result: # ~/perf test BPF 37: Test BPF filter : 37.1: Test basic BPF filtering : Ok 37.2: Test BPF prologue generation : Ok 37.3: Test BPF relocation checker : FAILED! # ~/perf test -v BPF ... libbpf: loading object '[bpf_relocation_test]' from buffer libbpf: section .strtab, size 126, link 0, flags 0, type=3 libbpf: section .text, size 0, link 0, flags 6, type=1 libbpf: section .data, size 0, link 0, flags 3, type=1 libbpf: section .bss, size 0, link 0, flags 3, type=8 libbpf: section func=sys_write, size 104, link 0, flags 6, type=1 libbpf: found program func=sys_write libbpf: section .relfunc=sys_write, size 16, link 10, flags 0, type=9 libbpf: section maps, size 16, link 0, flags 3, type=1 libbpf: maps in [bpf_relocation_test]: 16 bytes libbpf: section license, size 4, link 0, flags 3, type=1 libbpf: license of [bpf_relocation_test] is GPL libbpf: section version, size 4, link 0, flags 3, type=1 libbpf: kernel version of [bpf_relocation_test] is 40400 libbpf: section .symtab, size 144, link 1, flags 0, type=2 libbpf: map 0 is "my_table" libbpf: collecting relocating info for: 'func=sys_write' libbpf: relocation: insn_idx=7 Success unexpectedly: libbpf error when dealing with relocation test child finished with -1 ---- end ---- Test BPF filter subtest 2: FAILED! [1] https://llvm.org/bugs/show_bug.cgi?id=26243 [2] https://patchwork.ozlabs.org/patch/571385/ Signed-off-by: Wang Nan Tested-by: Arnaldo Carvalho de Melo Cc: "David S. Miller" Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: He Kuang Cc: Jiri Olsa Cc: Li Zefan Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1453715801-7732-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 +- tools/perf/tests/.gitignore | 1 + tools/perf/tests/Build | 9 +++- tools/perf/tests/bpf-script-test-relocation.c | 50 +++++++++++++++++++ tools/perf/tests/bpf.c | 26 ++++++++-- tools/perf/tests/llvm.c | 17 +++++-- tools/perf/tests/llvm.h | 5 +- 7 files changed, 98 insertions(+), 12 deletions(-) create mode 100644 tools/perf/tests/bpf-script-test-relocation.c diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5d34815c7ccb..97ce8695199e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -618,7 +618,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ - $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c + $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore index bf016c439fbd..8cc30e731c73 100644 --- a/tools/perf/tests/.gitignore +++ b/tools/perf/tests/.gitignore @@ -1,3 +1,4 @@ llvm-src-base.c llvm-src-kbuild.c llvm-src-prologue.c +llvm-src-relocation.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 614899b88b37..1ba628ed049a 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -31,7 +31,7 @@ perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o perf-y += thread-map.o -perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o +perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o perf-y += bpf.o perf-y += topology.o perf-y += cpumap.o @@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ +$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build + $(call rule_mkdir) + $(Q)echo '#include ' > $@ + $(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@ + $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ + $(Q)echo ';' >> $@ + ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c new file mode 100644 index 000000000000..93af77421816 --- /dev/null +++ b/tools/perf/tests/bpf-script-test-relocation.c @@ -0,0 +1,50 @@ +/* + * bpf-script-test-relocation.c + * Test BPF loader checking relocation + */ +#ifndef LINUX_VERSION_CODE +# error Need LINUX_VERSION_CODE +# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' +#endif +#define BPF_ANY 0 +#define BPF_MAP_TYPE_ARRAY 2 +#define BPF_FUNC_map_lookup_elem 1 +#define BPF_FUNC_map_update_elem 2 + +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_lookup_elem; +static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = + (void *) BPF_FUNC_map_update_elem; + +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; +}; + +#define SEC(NAME) __attribute__((section(NAME), used)) +struct bpf_map_def SEC("maps") my_table = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, +}; + +int this_is_a_global_val; + +SEC("func=sys_write") +int bpf_func__sys_write(void *ctx) +{ + int key = 0; + int value = 0; + + /* + * Incorrect relocation. Should not allow this program be + * loaded into kernel. + */ + bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0); + return 0; +} +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 33689a0cf821..952ca99aba6b 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -71,6 +71,15 @@ static struct { (NR_ITERS + 1) / 4, }, #endif + { + LLVM_TESTCASE_BPF_RELOCATION, + "Test BPF relocation checker", + "[bpf_relocation_test]", + "fix 'perf test LLVM' first", + "libbpf error when dealing with relocation", + NULL, + 0, + }, }; static int do_test(struct bpf_object *obj, int (*func)(void), @@ -190,7 +199,7 @@ static int __test__bpf(int idx) ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, bpf_testcase_table[idx].prog_id, - true); + true, NULL); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", bpf_testcase_table[idx].msg_compile_fail); @@ -202,14 +211,21 @@ static int __test__bpf(int idx) obj = prepare_bpf(obj_buf, obj_buf_sz, bpf_testcase_table[idx].name); - if (!obj) { + if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) { + if (!obj) + pr_debug("Fail to load BPF object: %s\n", + bpf_testcase_table[idx].msg_load_fail); + else + pr_debug("Success unexpectedly: %s\n", + bpf_testcase_table[idx].msg_load_fail); ret = TEST_FAIL; goto out; } - ret = do_test(obj, - bpf_testcase_table[idx].target_func, - bpf_testcase_table[idx].expect_result); + if (obj) + ret = do_test(obj, + bpf_testcase_table[idx].target_func, + bpf_testcase_table[idx].expect_result); out: bpf__clear(); return ret; diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 06f45c1d4256..70edcdfa5672 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -35,6 +35,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused, static struct { const char *source; const char *desc; + bool should_load_fail; } bpf_source_table[__LLVM_TESTCASE_MAX] = { [LLVM_TESTCASE_BASE] = { .source = test_llvm__bpf_base_prog, @@ -48,14 +49,19 @@ static struct { .source = test_llvm__bpf_test_prologue_prog, .desc = "Compile source for BPF prologue generation test", }, + [LLVM_TESTCASE_BPF_RELOCATION] = { + .source = test_llvm__bpf_test_relocation, + .desc = "Compile source for BPF relocation test", + .should_load_fail = true, + }, }; - int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, enum test_llvm__testcase idx, - bool force) + bool force, + bool *should_load_fail) { const char *source; const char *desc; @@ -68,6 +74,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, source = bpf_source_table[idx].source; desc = bpf_source_table[idx].desc; + if (should_load_fail) + *should_load_fail = bpf_source_table[idx].should_load_fail; perf_config(perf_config_cb, NULL); @@ -136,14 +144,15 @@ int test__llvm(int subtest) int ret; void *obj_buf = NULL; size_t obj_buf_sz = 0; + bool should_load_fail = false; if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) return TEST_FAIL; ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - subtest, false); + subtest, false, &should_load_fail); - if (ret == TEST_OK) { + if (ret == TEST_OK && !should_load_fail) { ret = test__bpf_parsing(obj_buf, obj_buf_sz); if (ret != TEST_OK) { pr_debug("Failed to parse test case '%s'\n", diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h index 5150b4d6ef50..0eaa604be99d 100644 --- a/tools/perf/tests/llvm.h +++ b/tools/perf/tests/llvm.h @@ -7,14 +7,17 @@ extern const char test_llvm__bpf_base_prog[]; extern const char test_llvm__bpf_test_kbuild_prog[]; extern const char test_llvm__bpf_test_prologue_prog[]; +extern const char test_llvm__bpf_test_relocation[]; enum test_llvm__testcase { LLVM_TESTCASE_BASE, LLVM_TESTCASE_KBUILD, LLVM_TESTCASE_BPF_PROLOGUE, + LLVM_TESTCASE_BPF_RELOCATION, __LLVM_TESTCASE_MAX, }; int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, - enum test_llvm__testcase index, bool force); + enum test_llvm__testcase index, bool force, + bool *should_load_fail); #endif From 666810e86a3b7531cce892fbeda3b2f2322e1d72 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 25 Jan 2016 09:55:49 +0000 Subject: [PATCH 22/26] perf bpf: Check relocation target section Libbpf should check the target section before doing relocation to ensure the relocation is correct. If not, a bug in LLVM causes an error. See [1]. Also, if an incorrect BPF script uses both global variable and map, global variable whould be treated as map and be relocated without error. This patch saves the id of the map section into obj->efile and compare target section of a relocation symbol against it during relocation. Previous patch introduces a test case about this problem. After this patch: # ~/perf test BPF 37: Test BPF filter : 37.1: Test basic BPF filtering : Ok 37.2: Test BPF prologue generation : Ok 37.3: Test BPF relocation checker : Ok # perf test -v BPF ... 37.3: Test BPF relocation checker : ... libbpf: loading object '[bpf_relocation_test]' from buffer libbpf: section .strtab, size 126, link 0, flags 0, type=3 libbpf: section .text, size 0, link 0, flags 6, type=1 libbpf: section .data, size 0, link 0, flags 3, type=1 libbpf: section .bss, size 0, link 0, flags 3, type=8 libbpf: section func=sys_write, size 104, link 0, flags 6, type=1 libbpf: found program func=sys_write libbpf: section .relfunc=sys_write, size 16, link 10, flags 0, type=9 libbpf: section maps, size 16, link 0, flags 3, type=1 libbpf: maps in [bpf_relocation_test]: 16 bytes libbpf: section license, size 4, link 0, flags 3, type=1 libbpf: license of [bpf_relocation_test] is GPL libbpf: section version, size 4, link 0, flags 3, type=1 libbpf: kernel version of [bpf_relocation_test] is 40400 libbpf: section .symtab, size 144, link 1, flags 0, type=2 libbpf: map 0 is "my_table" libbpf: collecting relocating info for: 'func=sys_write' libbpf: Program 'func=sys_write' contains non-map related relo data pointing to section 65522 bpf: failed to load buffer Compile BPF program failed. test child finished with 0 ---- end ---- Test BPF filter subtest 2: Ok [1] https://llvm.org/bugs/show_bug.cgi?id=26243 Signed-off-by: Wang Nan Acked-by: Alexei Starovoitov Tested-by: Arnaldo Carvalho de Melo Cc: "David S. Miller" Cc: Brendan Gregg Cc: Daniel Borkmann Cc: He Kuang Cc: Jiri Olsa Cc: Li Zefan Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1453715801-7732-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8334a5a9d5d7..7e543c3102d4 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -201,6 +201,7 @@ struct bpf_object { Elf_Data *data; } *reloc; int nr_reloc; + int maps_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path, */ obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; + obj->efile.maps_shndx = -1; obj->loaded = false; @@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data, } static int -bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) +bpf_object__init_maps_name(struct bpf_object *obj) { int i; Elf_Data *symbols = obj->efile.symbols; - if (!symbols || maps_shndx < 0) + if (!symbols || obj->efile.maps_shndx < 0) return -EINVAL; for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { @@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) if (!gelf_getsym(symbols, i, &sym)) continue; - if (sym.st_shndx != maps_shndx) + if (sym.st_shndx != obj->efile.maps_shndx) continue; map_name = elf_strptr(obj->efile.elf, @@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Scn *scn = NULL; - int idx = 0, err = 0, maps_shndx = -1; + int idx = 0, err = 0; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { @@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) else if (strcmp(name, "maps") == 0) { err = bpf_object__init_maps(obj, data->d_buf, data->d_size); - maps_shndx = idx; + obj->efile.maps_shndx = idx; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", @@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } - if (maps_shndx >= 0) - err = bpf_object__init_maps_name(obj, maps_shndx); + if (obj->efile.maps_shndx >= 0) + err = bpf_object__init_maps_name(obj); out: return err; } @@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) static int bpf_program__collect_reloc(struct bpf_program *prog, size_t nr_maps, GElf_Shdr *shdr, - Elf_Data *data, Elf_Data *symbols) + Elf_Data *data, Elf_Data *symbols, + int maps_shndx) { int i, nrels; @@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { @@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } + if (sym.st_shndx != maps_shndx) { + pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", + prog->section_name, sym.st_shndx); + return -LIBBPF_ERRNO__RELOC; + } + + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u\n", insn_idx); + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", insn_idx, insns[insn_idx].code); @@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) err = bpf_program__collect_reloc(prog, nr_maps, shdr, data, - obj->efile.symbols); + obj->efile.symbols, + obj->efile.maps_shndx); if (err) return err; } From 9fd4186ac19a4c8182dffc9b15dd288b50f09f76 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 25 Jan 2016 09:55:50 +0000 Subject: [PATCH 23/26] tools build: Allow subprojects select all feature checkers Put feature checkers not in original FEATURE_TESTS to a new list and allow subproject select all feature checkers by setting FEATURE_TESTS to 'all'. Signed-off-by: Wang Nan Cc: "David S. Miller" Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: He Kuang Cc: Jiri Olsa Cc: Li Zefan Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Link: http://lkml.kernel.org/r/1453715801-7732-4-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 02db3cdff20f..674c47d5f9d1 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -27,7 +27,7 @@ endef # the rule that uses them - an example for that is the 'bionic' # feature check. ] # -FEATURE_TESTS ?= \ +FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ fortify-source \ @@ -56,6 +56,25 @@ FEATURE_TESTS ?= \ get_cpuid \ bpf +# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list +# of all feature tests +FEATURE_TESTS_EXTRA := \ + bionic \ + compile-32 \ + compile-x32 \ + cplus-demangle \ + hello \ + libbabeltrace \ + liberty \ + liberty-z \ + libunwind-debug-frame + +FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) + +ifeq ($(FEATURE_TESTS),all) + FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA) +endif + FEATURE_DISPLAY ?= \ dwarf \ glibc \ From c053a1506faee399cbc2105f2131bb5a5d99eedd Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 25 Jan 2016 09:55:51 +0000 Subject: [PATCH 24/26] perf build: Select all feature checkers for feature-dump Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. Without this setting the output feature dump file miss some feature, for example, liberity. Select all checker so we won't get an incomplete feature dump file. Signed-off-by: Wang Nan Cc: "David S. Miller" Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: He Kuang Cc: Jiri Olsa Cc: Li Zefan Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Link: http://lkml.kernel.org/r/1453715801-7732-5-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 97ce8695199e..0ef3d97d7954 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -165,7 +165,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) endif endif +# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. +# Without this setting the output feature dump file misses some features, for +# example, liberty. Select all checkers so we won't get an incomplete feature +# dump file. ifeq ($(config),1) +ifdef MAKECMDGOALS +ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) +FEATURE_TESTS := all +endif +endif include config/Makefile endif From b1baae89197e21cd115e9493d5a17f18fca81e6a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Jan 2016 15:37:30 -0300 Subject: [PATCH 25/26] perf hists browser: Skip scripting when perf.data file not available The script and data-switch context menu are only meaningful when it deals with a data file. So add a check so that it cannot be shown when perf-top is run. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa , Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1453555902-18401-4-git-send-email-namhyung@kernel.org [ Use goto skip_scripting instead of two is_report_browser() tests ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index d07e6be42ab1..1da30f8aa7a5 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2303,6 +2303,9 @@ skip_annotation: &options[nr_options], socked_id); /* perf script support */ + if (!is_report_browser(hbt)) + goto skip_scripting; + if (browser->he_selection) { if (sort__has_thread && thread) { nr_options += add_script_opt(browser, @@ -2330,6 +2333,7 @@ skip_annotation: &options[nr_options], NULL, NULL); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); +skip_scripting: nr_options += add_exit_opt(browser, &actions[nr_options], &options[nr_options]); From 5ac76283b32b116c58e362e99542182ddcfc8262 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 26 Jan 2016 15:51:46 -0300 Subject: [PATCH 26/26] perf cpumap: Auto initialize cpu__max_{node,cpu} Since it was always checking if the initialization was done, use that branch to do the initialization if not done already. With this we reduce the number of exported globals from these files. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Kan Liang Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/20160125212955.GG22501@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 30 ++++++++++++++++++++++++++++++ tools/perf/util/cpumap.h | 32 +++----------------------------- 2 files changed, 33 insertions(+), 29 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index fa935093a599..9bcf2bed3a6d 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -8,6 +8,10 @@ #include #include "asm/bug.h" +static int max_cpu_num; +static int max_node_num; +static int *cpunode_map; + static struct cpu_map *cpu_map__default_new(void) { struct cpu_map *cpus; @@ -486,6 +490,32 @@ out: pr_err("Failed to read max nodes, using default of %d\n", max_node_num); } +int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + set_max_node_num(); + + return max_node_num; +} + +int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + set_max_cpu_num(); + + return max_cpu_num; +} + +int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} + static int init_cpunode_map(void) { int i; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 71c41b9efabb..81a2562aaa2b 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } -int max_cpu_num; -int max_node_num; -int *cpunode_map; - int cpu__setup_cpunode_map(void); -static inline int cpu__max_node(void) -{ - if (unlikely(!max_node_num)) - pr_debug("cpu_map not initialized\n"); - - return max_node_num; -} - -static inline int cpu__max_cpu(void) -{ - if (unlikely(!max_cpu_num)) - pr_debug("cpu_map not initialized\n"); - - return max_cpu_num; -} - -static inline int cpu__get_node(int cpu) -{ - if (unlikely(cpunode_map == NULL)) { - pr_debug("cpu_map not initialized\n"); - return -1; - } - - return cpunode_map[cpu]; -} +int cpu__max_node(void); +int cpu__max_cpu(void); +int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data),