From 5ad4da4302712fba10624d28cb6c269fee592b69 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 2 Sep 2015 09:56:31 +0200 Subject: perf tools: Fix parse_events_add_pmu caller Following commit changed parse_events_add_pmu interface: 36adec85a86f perf tools: Change parse_events_add_pmu interface but forgot to change one caller. Because of lessen compilation rules for the bison parser, the compiler did not warn on that. Signed-off-by: Jiri Olsa Cc: Raphael Beamonte Cc: David Ahern Cc: Matt Fleming Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt Fixes: 36adec85a86f ("perf tools: Change parse_events_add_pmu interface") Link: http://lkml.kernel.org/r/1441180605-24737-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 591905a..9cd7081 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -255,7 +255,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc list_add_tail(&term->list, head); ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); parse_events__free_terms(head); $$ = list; } -- cgit v0.10.2 From 53ff6bc37be449f546158a39c528d7814dfb15a1 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 18 Aug 2015 12:07:05 +0300 Subject: perf tools: Fix use of wrong event when processing exit events In a couple of cases the 'comm' member of 'union event' has been used instead of the correct member ('fork') when processing exit events. In the cases where it has been used incorrectly, only the 'pid' and 'tid' are affected. The 'pid' value would be correct anyway because it is in the same position in 'comm' and 'fork' events, but the 'tid' would have been incorrectly assigned from 'ppid'. However, for exit events, the kernel puts the current task in the 'ppid' and 'ttid' which is the same as the exiting task. That is 'ppid' == 'pid' and if the task is not multi-threaded, 'pid' == 'tid' i.e. the data goes wrong only when tracing multi-threaded programs. It is hard to find an example of how this would produce an error in practice. There are 3 occurences of the fix: 1. perf script is only affected if !sample_id_all which only happens on old kernels. 2. intel_pt is only affected when decoding without timestamps and would probably still decode correctly - the exit event is only used to flush out data which anyway gets flushed at the end of the session 3. intel_bts also uses the exit event to flush data which would probably not cause errors as it would get flushed at the end of the session instead Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1439888825-27708-1-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index eb51325..284a76e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -768,8 +768,8 @@ static int process_exit_event(struct perf_tool *tool, if (!evsel->attr.sample_id_all) { sample->cpu = 0; sample->time = 0; - sample->tid = event->comm.tid; - sample->pid = event->comm.pid; + sample->tid = event->fork.tid; + sample->pid = event->fork.pid; } print_sample_start(sample, thread, evsel); perf_event__fprintf(event, stdout); diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index ea76862..eb0e7f8 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -623,7 +623,7 @@ static int intel_bts_process_event(struct perf_session *session, if (err) return err; if (event->header.type == PERF_RECORD_EXIT) { - err = intel_bts_process_tid_exit(bts, event->comm.tid); + err = intel_bts_process_tid_exit(bts, event->fork.tid); if (err) return err; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index bb41c20..535d86f 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1494,7 +1494,7 @@ static int intel_pt_process_event(struct perf_session *session, if (pt->timeless_decoding) { if (event->header.type == PERF_RECORD_EXIT) { err = intel_pt_process_timeless_queues(pt, - event->comm.tid, + event->fork.tid, sample->time); } } else if (timestamp) { -- cgit v0.10.2 From d249872939bfa86c9cce44a56a8cbdbc7086519b Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 17 Jul 2015 16:34:10 +0300 Subject: perf/x86/intel/bts: Set event->hw.itrace_started in pmu::start to match the new logic Since event->hw.itrace_started is now set in pmu::start() to signal the beginning of the trace, do so also in the intel_bts driver. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: hpa@zytor.com Link: http://lkml.kernel.org/r/1437140050-23363-4-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 54690e8..d1c0f25 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -222,6 +222,7 @@ static void __bts_event_start(struct perf_event *event) if (!buf || bts_buffer_is_full(buf, bts)) return; + event->hw.itrace_started = 1; event->hw.state = 0; if (!buf->snapshot) -- cgit v0.10.2 From ebfb4988f0378e2ac3b4a0aa1ea20d724293f392 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2015 11:58:27 +0200 Subject: perf/x86/intel: Fix constraint access Sasha reported that we can get here with .idx==-1, and cpuc->event_constraints unallocated. Suggested-by: Stephane Eranian Reported-by: Sasha Levin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Fixes: b371b5943178 ("perf/x86: Fix event/group validation") Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 3f124d5..f41e4dc 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2316,9 +2316,12 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = cpuc->event_constraint[idx]; + struct event_constraint *c1 = NULL; struct event_constraint *c2; + if (idx >= 0) /* fake does < 0 */ + c1 = cpuc->event_constraint[idx]; + /* * first time only * - static constraint: no change across incremental scheduling calls -- cgit v0.10.2 From caa470475d9b59eeff093ae650800d34612c4379 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 11 Sep 2015 12:36:12 -0300 Subject: perf header: Fixup reading of HEADER_NRCPUS feature The original patch introducing this header wrote the number of CPUs available and online in one order and then swapped those values when reading, fix it. Before: # perf record usleep 1 # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 4 # nrcpus avail : 4 # echo 0 > /sys/devices/system/cpu/cpu2/online # perf record usleep 1 # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 4 # nrcpus avail : 3 # echo 0 > /sys/devices/system/cpu/cpu1/online # perf record usleep 1 # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 4 # nrcpus avail : 2 After the fix, bringing back the CPUs online: # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 2 # nrcpus avail : 4 # echo 1 > /sys/devices/system/cpu/cpu2/online # perf record usleep 1 # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 3 # nrcpus avail : 4 # echo 1 > /sys/devices/system/cpu/cpu1/online # perf record usleep 1 # perf report --header-only | grep 'nrcpus \(online\|avail\)' # nrcpus online : 4 # nrcpus avail : 4 Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Kan Liang Cc: Stephane Eranian Cc: Wang Nan Fixes: fbe96f29ce4b ("perf tools: Make perf.data more self-descriptive (v8)") Link: http://lkml.kernel.org/r/20150911153323.GP23511@kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 4181454..fce6634 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1438,7 +1438,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, if (ph->needs_swap) nr = bswap_32(nr); - ph->env.nr_cpus_online = nr; + ph->env.nr_cpus_avail = nr; ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) @@ -1447,7 +1447,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, if (ph->needs_swap) nr = bswap_32(nr); - ph->env.nr_cpus_avail = nr; + ph->env.nr_cpus_online = nr; return 0; } -- cgit v0.10.2 From bd315aab8a3ab1bc7074774b89a5d8ec7c1ff7ab Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 14 Sep 2015 10:23:55 +0000 Subject: perf top: Fix segfault pressing -> with no hist entries 'perf top' segfaults with following operation: # perf top -e page-faults -p 11400 # 11400 never generates page-fault Then on the resulting empty interface, press right key: # ./perf top -e page-faults -p 11400 perf: Segmentation fault -------- backtrace -------- ./perf[0x535428] /lib64/libc.so.6(+0x3545f)[0x7f0dd360745f] ./perf[0x531d46] ./perf(perf_evlist__tui_browse_hists+0x96)[0x5340d6] ./perf[0x44ba2f] /lib64/libpthread.so.0(+0x81d0)[0x7f0dd49dc1d0] /lib64/libc.so.6(clone+0x6c)[0x7f0dd36b90dc] The bug resides in perf_evsel__hists_browse() that, in the above circumstance browser->selection can be NULL, but code after skip_annotation doesn't consider it. This patch fix it by checking browser->selection before fetching browser->selection->map. Signed-off-by: Wang Nan Tested-by: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1442226235-117265-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index cf86f2d..c04c60d 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1968,7 +1968,8 @@ skip_annotation: &options[nr_options], dso); nr_options += add_map_opt(browser, &actions[nr_options], &options[nr_options], - browser->selection->map); + browser->selection ? + browser->selection->map : NULL); /* perf script support */ if (browser->he_selection) { @@ -1976,6 +1977,15 @@ skip_annotation: &actions[nr_options], &options[nr_options], thread, NULL); + /* + * Note that browser->selection != NULL + * when browser->he_selection is not NULL, + * so we don't need to check browser->selection + * before fetching browser->selection->sym like what + * we do before fetching browser->selection->map. + * + * See hist_browser__show_entry. + */ nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], -- cgit v0.10.2 From a69b09e2342a9c144b0291b9aeb849ab7d5843bf Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:49 +0300 Subject: perf evlist: Simplify propagate_maps() logic If evsel->cpus is to be reassigned then the current value must be "put", which works even if it is NULL. Simplify the current logic by moving the "put" next to the assignment. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d51a520..95e07ea 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1113,11 +1113,10 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (evsel->cpus && has_user_cpus) + if (!evsel->cpus || has_user_cpus) { cpu_map__put(evsel->cpus); - - if (!evsel->cpus || has_user_cpus) evsel->cpus = cpu_map__get(evlist->cpus); + } evsel->threads = thread_map__get(evlist->threads); -- cgit v0.10.2 From 725e06b2e2754fbff61521fa76fee51cee5bcb5f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:50 +0300 Subject: perf evlist: Simplify set_maps() logic Don't need to check for NULL when "putting" evlist->maps and evlist->threads because the "put" functions already do that. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 95e07ea..9cb9296 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1156,14 +1156,10 @@ int perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads) { - if (evlist->cpus) - cpu_map__put(evlist->cpus); - + cpu_map__put(evlist->cpus); evlist->cpus = cpus; - if (evlist->threads) - thread_map__put(evlist->threads); - + thread_map__put(evlist->threads); evlist->threads = threads; return perf_evlist__propagate_maps(evlist, false); -- cgit v0.10.2 From d5bc056e73841d4bc941474a342ef9b6a207ac84 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:51 +0300 Subject: perf evlist: Remove redundant validation from propagate_maps() The validation checks that the values that were just assigned, got assigned i.e. the error can't ever happen. Subsequent patches will call this code in places where errors are not being returned. Changing those code paths to return this non-existent error is counter-productive, so just remove it. That in turn results in perf_evlist__set_maps not needing to return an error, but callers aren't checking it either, so remove that too. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-4-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9cb9296..785bfd3 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1103,8 +1103,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false); } -static int perf_evlist__propagate_maps(struct perf_evlist *evlist, - bool has_user_cpus) +static void perf_evlist__propagate_maps(struct perf_evlist *evlist, + bool has_user_cpus) { struct perf_evsel *evsel; @@ -1119,13 +1119,7 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist, } evsel->threads = thread_map__get(evlist->threads); - - if ((evlist->cpus && !evsel->cpus) || - (evlist->threads && !evsel->threads)) - return -ENOMEM; } - - return 0; } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) @@ -1144,7 +1138,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) if (evlist->cpus == NULL) goto out_delete_threads; - return perf_evlist__propagate_maps(evlist, !!target->cpu_list); + perf_evlist__propagate_maps(evlist, !!target->cpu_list); + + return 0; out_delete_threads: thread_map__put(evlist->threads); @@ -1152,9 +1148,8 @@ out_delete_threads: return -1; } -int perf_evlist__set_maps(struct perf_evlist *evlist, - struct cpu_map *cpus, - struct thread_map *threads) +void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads) { cpu_map__put(evlist->cpus); evlist->cpus = cpus; @@ -1162,7 +1157,7 @@ int perf_evlist__set_maps(struct perf_evlist *evlist, thread_map__put(evlist->threads); evlist->threads = threads; - return perf_evlist__propagate_maps(evlist, false); + perf_evlist__propagate_maps(evlist, false); } int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b39a619..da2fa91 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -155,9 +155,8 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist, void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); -int perf_evlist__set_maps(struct perf_evlist *evlist, - struct cpu_map *cpus, - struct thread_map *threads); +void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads); int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); -- cgit v0.10.2 From ec9a77a7e3346a05b1287597982d0dd09dd1c3bd Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:52 +0300 Subject: perf evlist: Add has_user_cpus member Subsequent patches will need to call perf_evlist__propagate_maps without reference to a "target". Add evlist->has_user_cpus to record whether the user has specified which cpus to target (and therefore whether that list of cpus should override the default settings for a selected event i.e. the cpu maps should be propagated) Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-5-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 785bfd3..3a4445f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1103,8 +1103,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false); } -static void perf_evlist__propagate_maps(struct perf_evlist *evlist, - bool has_user_cpus) +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -1113,7 +1112,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (!evsel->cpus || has_user_cpus) { + if (!evsel->cpus || evlist->has_user_cpus) { cpu_map__put(evsel->cpus); evsel->cpus = cpu_map__get(evlist->cpus); } @@ -1138,7 +1137,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) if (evlist->cpus == NULL) goto out_delete_threads; - perf_evlist__propagate_maps(evlist, !!target->cpu_list); + evlist->has_user_cpus = !!target->cpu_list; + + perf_evlist__propagate_maps(evlist); return 0; @@ -1157,7 +1158,7 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, thread_map__put(evlist->threads); evlist->threads = threads; - perf_evlist__propagate_maps(evlist, false); + perf_evlist__propagate_maps(evlist); } int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index da2fa91..cfc4df6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -42,6 +42,7 @@ struct perf_evlist { int nr_mmaps; bool overwrite; bool enabled; + bool has_user_cpus; size_t mmap_len; int id_pos; int is_pos; -- cgit v0.10.2 From f114d6eff76d20b521d8716e969e71b1f56f82b5 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:53 +0300 Subject: perf evlist: Fix splice_list_tail() not setting evlist Commit d49e46950772 ("perf evsel: Add a backpointer to the evlist a evsel is in") updated perf_evlist__add() but not perf_evlist__splice_list_tail(). This illustrates that it is better if perf_evlist__splice_list_tail() calls perf_evlist__add() instead of duplicating the logic, so do that. This will also simplify a subsequent fix for propagating maps. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-6-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 3a4445f..961560b 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -136,15 +136,14 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, - struct list_head *list, - int nr_entries) + struct list_head *list) { - bool set_id_pos = !evlist->nr_entries; + struct perf_evsel *evsel, *temp; - list_splice_tail(list, &evlist->entries); - evlist->nr_entries += nr_entries; - if (set_id_pos) - perf_evlist__set_id_pos(evlist); + __evlist__for_each_safe(list, temp, evsel) { + list_del_init(&evsel->node); + perf_evlist__add(evlist, evsel); + } } void __perf_evlist__set_leader(struct list_head *list) @@ -210,7 +209,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist, list_add_tail(&evsel->node, &head); } - perf_evlist__splice_list_tail(evlist, &head, nr_attrs); + perf_evlist__splice_list_tail(evlist, &head); return 0; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index cfc4df6..115d8b5 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -179,8 +179,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, - struct list_head *list, - int nr_entries); + struct list_head *list); static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) { diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d826e6f..7e8ae21 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1140,10 +1140,9 @@ int parse_events(struct perf_evlist *evlist, const char *str, ret = parse_events__scanner(str, &data, PE_START_EVENTS); perf_pmu__parse_cleanup(); if (!ret) { - int entries = data.idx - evlist->nr_entries; struct perf_evsel *last; - perf_evlist__splice_list_tail(evlist, &data.list, entries); + perf_evlist__splice_list_tail(evlist, &data.list); evlist->nr_groups += data.nr_groups; last = perf_evlist__last(evlist); last->cmdline_group_boundary = true; -- cgit v0.10.2 From b278c364b35ae940b05f6a9edf8061fc886cd09e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:54 +0300 Subject: perf evlist: Fix missing thread_map__put in propagate_maps() perf_evlist__propagate_maps() incorrectly assumes evsel->threads is NULL before reassigning it, but it won't be NULL when perf_evlist__set_maps() is used to set different (or NULL) maps. Thus thread_map__put must be used, which works even if evsel->threads is NULL. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-7-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 961560b..79056c6 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1116,6 +1116,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) evsel->cpus = cpu_map__get(evlist->cpus); } + thread_map__put(evsel->threads); evsel->threads = thread_map__get(evlist->threads); } } -- cgit v0.10.2 From fce4d296b405b03fba033a55017348bf55b10db6 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:55 +0300 Subject: perf evsel: Add own_cpus member perf_evlist__propagate_maps() cannot easily tell if an evsel has its own cpu map. To make that simpler, keep a copy of the PMU cpu map and adjust the propagation logic accordingly. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-8-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 79056c6..5bd3b49 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1111,9 +1111,12 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (!evsel->cpus || evlist->has_user_cpus) { + if (!evsel->own_cpus || evlist->has_user_cpus) { cpu_map__put(evsel->cpus); evsel->cpus = cpu_map__get(evlist->cpus); + } else if (evsel->cpus != evsel->own_cpus) { + cpu_map__put(evsel->cpus); + evsel->cpus = cpu_map__get(evsel->own_cpus); } thread_map__put(evsel->threads); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c53f791..5410483 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1033,6 +1033,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_config_terms(evsel); close_cgroup(evsel->cgrp); cpu_map__put(evsel->cpus); + cpu_map__put(evsel->own_cpus); thread_map__put(evsel->threads); zfree(&evsel->group_name); zfree(&evsel->name); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 298e6bb..ef8925f 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -98,6 +98,7 @@ struct perf_evsel { struct cgroup_sel *cgrp; void *handler; struct cpu_map *cpus; + struct cpu_map *own_cpus; struct thread_map *threads; unsigned int sample_size; int id_pos; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 7e8ae21..21ed6ee 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -287,8 +287,8 @@ __add_event(struct list_head *list, int *idx, if (!evsel) return NULL; - if (cpus) - evsel->cpus = cpu_map__get(cpus); + evsel->cpus = cpu_map__get(cpus); + evsel->own_cpus = cpu_map__get(cpus); if (name) evsel->name = strdup(name); -- cgit v0.10.2 From 934e0f2053ce299893ca48a411bf7fdc8ac6254f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:56 +0300 Subject: perf evlist: Make set_maps() more resilient Make perf_evlist__set_maps() more resilient by allowing for the possibility that one or another of the maps isn't being changed and therefore should not be "put". Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-9-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 5bd3b49..78ff52e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1155,11 +1155,22 @@ out_delete_threads: void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads) { - cpu_map__put(evlist->cpus); - evlist->cpus = cpus; + /* + * Allow for the possibility that one or another of the maps isn't being + * changed i.e. don't put it. Note we are assuming the maps that are + * being applied are brand new and evlist is taking ownership of the + * original reference count of 1. If that is not the case it is up to + * the caller to increase the reference count. + */ + if (cpus != evlist->cpus) { + cpu_map__put(evlist->cpus); + evlist->cpus = cpus; + } - thread_map__put(evlist->threads); - evlist->threads = threads; + if (threads != evlist->threads) { + thread_map__put(evlist->threads); + evlist->threads = threads; + } perf_evlist__propagate_maps(evlist); } -- cgit v0.10.2 From 74bfd2b25de354feb4484c553dce4fe8d9c3b60b Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:57 +0300 Subject: perf evlist: Make create_maps() use set_maps() Since there is a function to set maps, perf_evlist__create_maps() should use it. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-10-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 78ff52e..c17f355 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1126,29 +1126,30 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) { - evlist->threads = thread_map__new_str(target->pid, target->tid, - target->uid); + struct cpu_map *cpus; + struct thread_map *threads; - if (evlist->threads == NULL) + threads = thread_map__new_str(target->pid, target->tid, target->uid); + + if (!threads) return -1; if (target__uses_dummy_map(target)) - evlist->cpus = cpu_map__dummy_new(); + cpus = cpu_map__dummy_new(); else - evlist->cpus = cpu_map__new(target->cpu_list); + cpus = cpu_map__new(target->cpu_list); - if (evlist->cpus == NULL) + if (!cpus) goto out_delete_threads; evlist->has_user_cpus = !!target->cpu_list; - perf_evlist__propagate_maps(evlist); + perf_evlist__set_maps(evlist, cpus, threads); return 0; out_delete_threads: - thread_map__put(evlist->threads); - evlist->threads = NULL; + thread_map__put(threads); return -1; } -- cgit v0.10.2 From adc0c3e87b0e1baeccabe09b6dba738f17d0e91d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:58 +0300 Subject: perf evlist: Factor out a function to propagate maps for a single evsel Subsequent fixes will need a function that just propagates maps for a single evsel so factor it out. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-11-git-send-email-adrian.hunter@intel.com [ Moved them to before perf_evlist__add() to avoid having to move it in the next patch ] Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c17f355..4e840bf 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -124,6 +124,33 @@ void perf_evlist__delete(struct perf_evlist *evlist) free(evlist); } +static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + /* + * We already have cpus for evsel (via PMU sysfs) so + * keep it, if there's no target cpu list defined. + */ + if (!evsel->own_cpus || evlist->has_user_cpus) { + cpu_map__put(evsel->cpus); + evsel->cpus = cpu_map__get(evlist->cpus); + } else if (evsel->cpus != evsel->own_cpus) { + cpu_map__put(evsel->cpus); + evsel->cpus = cpu_map__get(evsel->own_cpus); + } + + thread_map__put(evsel->threads); + evsel->threads = thread_map__get(evlist->threads); +} + +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evlist__propagate_maps(evlist, evsel); +} + void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { entry->evlist = evlist; @@ -1102,28 +1129,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false); } -static void perf_evlist__propagate_maps(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. - */ - if (!evsel->own_cpus || evlist->has_user_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evlist->cpus); - } else if (evsel->cpus != evsel->own_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evsel->own_cpus); - } - - thread_map__put(evsel->threads); - evsel->threads = thread_map__get(evlist->threads); - } -} - int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) { struct cpu_map *cpus; -- cgit v0.10.2 From 44c42d71c659527c81bf169808959c9339116d85 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:58:59 +0300 Subject: perf evlist: Fix add() not propagating maps If evsels are added after maps are created, then they won't have any maps propagated to them. Fix that. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-12-git-send-email-adrian.hunter@intel.com [ Moved the moving of propagate_maps() to the patch before, so that this one does _just_ the one lile fix calling in add()] Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 4e840bf..99267ab 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -160,6 +160,8 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) if (!evlist->nr_entries++) perf_evlist__set_id_pos(evlist); + + __perf_evlist__propagate_maps(evlist, entry); } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, -- cgit v0.10.2 From 8c0498b6891d7ca5c379c6283de7fc7fe8eebe5c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:59:00 +0300 Subject: perf evlist: Fix create_syswide_maps() not propagating maps Fix it by making it call perf_evlist__set_maps() instead of setting the maps itself. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-13-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 99267ab..c8fc8a2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1400,6 +1400,8 @@ void perf_evlist__close(struct perf_evlist *evlist) static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) { + struct cpu_map *cpus; + struct thread_map *threads; int err = -ENOMEM; /* @@ -1411,20 +1413,19 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) * error, and we may not want to do that fallback to a * default cpu identity map :-\ */ - evlist->cpus = cpu_map__new(NULL); - if (evlist->cpus == NULL) + cpus = cpu_map__new(NULL); + if (!cpus) goto out; - evlist->threads = thread_map__new_dummy(); - if (evlist->threads == NULL) - goto out_free_cpus; + threads = thread_map__new_dummy(); + if (!threads) + goto out_put; - err = 0; + perf_evlist__set_maps(evlist, cpus, threads); out: return err; -out_free_cpus: - cpu_map__put(evlist->cpus); - evlist->cpus = NULL; +out_put: + cpu_map__put(cpus); goto out; } -- cgit v0.10.2 From 2998272275fc31fc3d478ef9c95e7eaef67dafa3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:59:01 +0300 Subject: perf tests: Fix task exit test setting maps The test titled "Test number of exit event of a simple workload" was setting cpu/thread maps directly. Make it use the proper function perf_evlist__set_maps() especially now that it also propagates the maps. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-14-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 3a8fedef..add1638 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -43,6 +43,8 @@ int test__task_exit(void) }; const char *argv[] = { "true", NULL }; char sbuf[STRERR_BUFSIZE]; + struct cpu_map *cpus; + struct thread_map *threads; signal(SIGCHLD, sig_handler); @@ -58,14 +60,19 @@ int test__task_exit(void) * perf_evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - evlist->cpus = cpu_map__dummy_new(); - evlist->threads = thread_map__new_by_tid(-1); - if (!evlist->cpus || !evlist->threads) { + cpus = cpu_map__dummy_new(); + threads = thread_map__new_by_tid(-1); + if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; + goto out_free_maps; } + perf_evlist__set_maps(evlist, cpus, threads); + + cpus = NULL; + threads = NULL; + err = perf_evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal); if (err < 0) { @@ -114,6 +121,9 @@ retry: err = -1; } +out_free_maps: + cpu_map__put(cpus); + thread_map__put(threads); out_delete_evlist: perf_evlist__delete(evlist); return err; -- cgit v0.10.2 From c5e6bd2ed3e81df443e4ae11e95ed71ff77bf9e5 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Sep 2015 10:59:02 +0300 Subject: perf tests: Fix software clock events test setting maps The test titled "Test software clock events have valid period values" was setting cpu/thread maps directly. Make it use the proper function perf_evlist__set_maps() especially now that it also propagates the maps. Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Kan Liang Link: http://lkml.kernel.org/r/1441699142-18905-15-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 1aa21c9..5b83f56 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -34,6 +34,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) .disabled = 1, .freq = 1, }; + struct cpu_map *cpus; + struct thread_map *threads; attr.sample_freq = 500; @@ -50,14 +52,19 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) } perf_evlist__add(evlist, evsel); - evlist->cpus = cpu_map__dummy_new(); - evlist->threads = thread_map__new_by_tid(getpid()); - if (!evlist->cpus || !evlist->threads) { + cpus = cpu_map__dummy_new(); + threads = thread_map__new_by_tid(getpid()); + if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; + goto out_free_maps; } + perf_evlist__set_maps(evlist, cpus, threads); + + cpus = NULL; + threads = NULL; + if (perf_evlist__open(evlist)) { const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate"; @@ -107,6 +114,9 @@ next_event: err = -1; } +out_free_maps: + cpu_map__put(cpus); + thread_map__put(threads); out_delete_evlist: perf_evlist__delete(evlist); return err; -- cgit v0.10.2