From 5d2cd90922c778908bd0cd669e572a5b5eafd737 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Apr 2011 11:20:14 -0300 Subject: perf evsel: Fix use of inherit perf stat doesn't mmap and its perfectly fine for it to use task-bound counters with inheritance. So set the attr.inherit on the caller and leave the syscall itself to validate it. When the mmap fails perf_evlist__mmap will just emit a warning if this is the failure reason. Reported-by: Peter Zijlstra Acked-by: Peter Zijlstra Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi Link: http://lkml.kernel.org/r/20110414170121.GC3229@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index a9f2d7e1204..f5e38451fdc 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, struct cpu_map *cpus = NULL; struct thread_map *threads = NULL; PyObject *pcpus = NULL, *pthreads = NULL; - int group = 0, overwrite = 0; - static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL}; + int group = 0, inherit = 0; + static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL}; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, - &pcpus, &pthreads, &group, &overwrite)) + &pcpus, &pthreads, &group, &inherit)) return NULL; if (pthreads != NULL) @@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, if (pcpus != NULL) cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; - if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) { + evsel->attr.inherit = inherit; + if (perf_evsel__open(evsel, cpus, threads, group) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } -- cgit v1.2.3-70-g09d2 From 94403f8863d0d1d2005291b2ef0719c2534aa303 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 24 Apr 2011 08:18:31 +0200 Subject: perf events: Add stalled cycles generic event - PERF_COUNT_HW_STALLED_CYCLES The new PERF_COUNT_HW_STALLED_CYCLES event tries to approximate cycles the CPU does nothing useful, because it is stalled on a cache-miss or some other condition. Acked-by: Peter Zijlstra Acked-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Link: http://lkml.kernel.org/n/tip-fue11vymwqsoo5to72jxxjyl@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 3 +++ include/linux/perf_event.h | 1 + tools/perf/util/parse-events.c | 1 + tools/perf/util/python.c | 1 + 4 files changed, 6 insertions(+) (limited to 'tools/perf/util/python.c') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9ae4a2aa739..efa2704c9df 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1413,6 +1413,9 @@ static __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + /* Install the stalled-cycles event: 0xff: All reasons, 0xa2: Resource stalls */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES] = 0xffa2; + if (ebx & 0x40) { /* * Erratum AAJ80 detected, we work it around by using diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ee9f1e78280..ac636dd20a0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -52,6 +52,7 @@ enum perf_hw_id { PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES = 7, PERF_COUNT_HW_MAX, /* non-ABI */ }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 952b4ae3d95..1869e4c646d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -38,6 +38,7 @@ static struct event_symbol event_symbols[] = { { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, { CHW(BRANCH_MISSES), "branch-misses", "" }, { CHW(BUS_CYCLES), "bus-cycles", "" }, + { CHW(STALLED_CYCLES), "stalled-cycles", "" }, { CSW(CPU_CLOCK), "cpu-clock", "" }, { CSW(TASK_CLOCK), "task-clock", "" }, diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index f5e38451fdc..406f613ee61 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -798,6 +798,7 @@ static struct { { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, + { "COUNT_HW_STALLED_CYCLES", PERF_COUNT_HW_STALLED_CYCLES }, { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, -- cgit v1.2.3-70-g09d2 From 129c04cb8ce2e4bf3f17223f58ef16aa8a2cb3b8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 29 Apr 2011 14:41:28 +0200 Subject: perf tools: Add front-end and back-end stalled cycles support Update perf tooling to deal with front-end and back-end stalled cycles events. Add both the default 'perf stat' output. Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Link: http://lkml.kernel.org/n/tip-7y40wib8n002io7hjpn1dsrm@git.kernel.org Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 10 ++++++---- tools/perf/util/parse-events.c | 37 +++++++++++++++++++------------------ tools/perf/util/python.c | 4 +++- 3 files changed, 28 insertions(+), 23 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index da77077450c..6a4a8a399d9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -66,7 +66,8 @@ static struct perf_event_attr default_attrs[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, @@ -84,7 +85,8 @@ static struct perf_event_attr detailed_attrs[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, @@ -249,7 +251,7 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count) update_stats(&runtime_nsecs_stats[0], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_stats(&runtime_cycles_stats[0], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES)) + else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_stats(&runtime_stalled_cycles_stats[0], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) update_stats(&runtime_branches_stats[0], count[0]); @@ -607,7 +609,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) fprintf(stderr, " # %8.3f %% of all cache refs ", ratio); - } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES)) { + } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { print_stalled_cycles(cpu, evsel, avg); } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { total = avg_stats(&runtime_nsecs_stats[cpu]); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index bbbb735268e..04d2f0a9667 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -31,24 +31,25 @@ char debugfs_path[MAXPATHLEN]; #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x static struct event_symbol event_symbols[] = { - { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, - { CHW(STALLED_CYCLES), "stalled-cycles", "idle-cycles" }, - { CHW(INSTRUCTIONS), "instructions", "" }, - { CHW(CACHE_REFERENCES), "cache-references", "" }, - { CHW(CACHE_MISSES), "cache-misses", "" }, - { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, - { CHW(BRANCH_MISSES), "branch-misses", "" }, - { CHW(BUS_CYCLES), "bus-cycles", "" }, - - { CSW(CPU_CLOCK), "cpu-clock", "" }, - { CSW(TASK_CLOCK), "task-clock", "" }, - { CSW(PAGE_FAULTS), "page-faults", "faults" }, - { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, - { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, - { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, - { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, - { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, - { CSW(EMULATION_FAULTS), "emulation-faults", "" }, + { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, + { CHW(STALLED_CYCLES_FRONTEND), "stalled-cycles-frontend", "idle-cycles-frontend" }, + { CHW(STALLED_CYCLES_BACKEND), "stalled-cycles-backend", "idle-cycles-backend" }, + { CHW(INSTRUCTIONS), "instructions", "" }, + { CHW(CACHE_REFERENCES), "cache-references", "" }, + { CHW(CACHE_MISSES), "cache-misses", "" }, + { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, + { CHW(BRANCH_MISSES), "branch-misses", "" }, + { CHW(BUS_CYCLES), "bus-cycles", "" }, + + { CSW(CPU_CLOCK), "cpu-clock", "" }, + { CSW(TASK_CLOCK), "task-clock", "" }, + { CSW(PAGE_FAULTS), "page-faults", "faults" }, + { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, + { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, + { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, + { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, + { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, + { CSW(EMULATION_FAULTS), "emulation-faults", "" }, }; #define __PERF_EVENT_FIELD(config, name) \ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 406f613ee61..8b0eff8b828 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -798,7 +798,6 @@ static struct { { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, - { "COUNT_HW_STALLED_CYCLES", PERF_COUNT_HW_STALLED_CYCLES }, { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, @@ -811,6 +810,9 @@ static struct { { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS }, { "COUNT_HW_CACHE_RESULT_MISS", PERF_COUNT_HW_CACHE_RESULT_MISS }, + { "COUNT_HW_STALLED_CYCLES_FRONTEND", PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + { "COUNT_HW_STALLED_CYCLES_BACKEND", PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, + { "COUNT_SW_CPU_CLOCK", PERF_COUNT_SW_CPU_CLOCK }, { "COUNT_SW_TASK_CLOCK", PERF_COUNT_SW_TASK_CLOCK }, { "COUNT_SW_PAGE_FAULTS", PERF_COUNT_SW_PAGE_FAULTS }, -- cgit v1.2.3-70-g09d2 From aece948f5ddd70d70df2f35855c706ef9a4f62e2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 15 May 2011 09:39:00 -0300 Subject: perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern Tested-by: Lin Ming Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-test.c | 2 +- tools/perf/builtin-top.c | 8 +-- tools/perf/util/evlist.c | 151 +++++++++++++++++++++++++++++++------------- tools/perf/util/evlist.h | 3 +- tools/perf/util/python.c | 2 +- 6 files changed, 115 insertions(+), 53 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 416538248a4..0974f957b8f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -427,7 +427,7 @@ static void mmap_read_all(void) { int i; - for (i = 0; i < evsel_list->cpus->nr; i++) { + for (i = 0; i < evsel_list->nr_mmaps; i++) { if (evsel_list->mmap[i].base) mmap_read(&evsel_list->mmap[i]); } diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 11e3c845836..2f9a337b182 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -549,7 +549,7 @@ static int test__basic_mmap(void) ++foo; } - while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) { + while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e3d6e310bf..ebfc7cf5f63 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event, } } -static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu) +static void perf_session__mmap_read_idx(struct perf_session *self, int idx) { struct perf_sample sample; union perf_event *event; - while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) { + while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) { perf_session__parse_sample(self, event, &sample); if (event->header.type == PERF_RECORD_SAMPLE) @@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self) { int i; - for (i = 0; i < top.evlist->cpus->nr; i++) - perf_session__mmap_read_cpu(self, i); + for (i = 0; i < top.evlist->nr_mmaps; i++) + perf_session__mmap_read_idx(self, i); } static void start_counters(struct perf_evlist *evlist) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 1884a7c7eb8..23eb22b05d2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -166,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } -union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu) +union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { /* XXX Move this to perf.c, making it generally available */ unsigned int page_size = sysconf(_SC_PAGE_SIZE); - struct perf_mmap *md = &evlist->mmap[cpu]; + struct perf_mmap *md = &evlist->mmap[idx]; unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; unsigned char *data = md->base + page_size; @@ -235,31 +235,37 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu) void perf_evlist__munmap(struct perf_evlist *evlist) { - int cpu; + int i; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; + for (i = 0; i < evlist->nr_mmaps; i++) { + if (evlist->mmap[i].base != NULL) { + munmap(evlist->mmap[i].base, evlist->mmap_len); + evlist->mmap[i].base = NULL; } } + + free(evlist->mmap); + evlist->mmap = NULL; } int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { - evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap)); + evlist->nr_mmaps = evlist->cpus->nr; + if (evlist->cpus->map[0] == -1) + evlist->nr_mmaps = evlist->threads->nr; + evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; } static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int prot, int mask, int fd) + int idx, int prot, int mask, int fd) { - evlist->mmap[cpu].prev = 0; - evlist->mmap[cpu].mask = mask; - evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot, + evlist->mmap[idx].prev = 0; + evlist->mmap[idx].mask = mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, MAP_SHARED, fd, 0); - if (evlist->mmap[cpu].base == MAP_FAILED) { - if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit) + if (evlist->mmap[idx].base == MAP_FAILED) { + if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit) ui__warning("Inherit is not allowed on per-task " "events using mmap.\n"); return -1; @@ -269,6 +275,86 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev return 0; } +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask) +{ + struct perf_evsel *evsel; + int cpu, thread; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + int output = -1; + + for (thread = 0; thread < evlist->threads->nr; thread++) { + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, cpu, thread); + + if (output == -1) { + output = fd; + if (__perf_evlist__mmap(evlist, evsel, cpu, + prot, mask, output) < 0) + goto out_unmap; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) + goto out_unmap; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) + goto out_unmap; + } + } + } + + return 0; + +out_unmap: + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + if (evlist->mmap[cpu].base != NULL) { + munmap(evlist->mmap[cpu].base, evlist->mmap_len); + evlist->mmap[cpu].base = NULL; + } + } + return -1; +} + +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask) +{ + struct perf_evsel *evsel; + int thread; + + for (thread = 0; thread < evlist->threads->nr; thread++) { + int output = -1; + + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, 0, thread); + + if (output == -1) { + output = fd; + if (__perf_evlist__mmap(evlist, evsel, thread, + prot, mask, output) < 0) + goto out_unmap; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) + goto out_unmap; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0) + goto out_unmap; + } + } + + return 0; + +out_unmap: + for (thread = 0; thread < evlist->threads->nr; thread++) { + if (evlist->mmap[thread].base != NULL) { + munmap(evlist->mmap[thread].base, evlist->mmap_len); + evlist->mmap[thread].base = NULL; + } + } + return -1; +} + /** perf_evlist__mmap - Create per cpu maps to receive events * * @evlist - list of events @@ -287,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) { unsigned int page_size = sysconf(_SC_PAGE_SIZE); - int mask = pages * page_size - 1, cpu; - struct perf_evsel *first_evsel, *evsel; + int mask = pages * page_size - 1; + struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; - int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE); + int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE); if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -301,43 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) evlist->overwrite = overwrite; evlist->mmap_len = (pages + 1) * page_size; - first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node); list_for_each_entry(evsel, &evlist->entries, node) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0) return -ENOMEM; - - for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { - int fd = FD(evsel, cpu, thread); - - if (evsel->idx || thread) { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, - FD(first_evsel, cpu, 0)) != 0) - goto out_unmap; - } else if (__perf_evlist__mmap(evlist, evsel, cpu, - prot, mask, fd) < 0) - goto out_unmap; - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) - goto out_unmap; - } - } } - return 0; + if (evlist->cpus->map[0] == -1) + return perf_evlist__mmap_per_thread(evlist, prot, mask); -out_unmap: - for (cpu = 0; cpu < cpus->nr; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; - } - } - return -1; + return perf_evlist__mmap_per_cpu(evlist, prot, mask); } int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 8b1cb7a4c5f..7109d7add14 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -17,6 +17,7 @@ struct perf_evlist { struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; int nr_fds; + int nr_mmaps; int mmap_len; bool overwrite; union perf_event event_copy; @@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); -union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu); +union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__alloc_mmap(struct perf_evlist *evlist); int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index f5e38451fdc..99c722672f8 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -680,7 +680,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, &cpu, &sample_id_all)) return NULL; - event = perf_evlist__read_on_cpu(evlist, cpu); + event = perf_evlist__mmap_read(evlist, cpu); if (event != NULL) { struct perf_evsel *first; PyObject *pyevent = pyrf_event__new(event); -- cgit v1.2.3-70-g09d2 From a285412479b6d5af3e48273a92ec2f1987df8cd1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 21 May 2011 19:33:04 +0200 Subject: perf tools: Pre-check sample size before parsing Check that the total size of the sample fields having a fixed size do not exceed the one of the whole event. This robustifies the sample parsing. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian --- tools/perf/builtin-test.c | 4 +++- tools/perf/util/event.c | 16 ++++++++++++++++ tools/perf/util/event.h | 12 +++++++++++- tools/perf/util/evsel.c | 6 +++++- tools/perf/util/python.c | 5 +++-- tools/perf/util/session.c | 1 + tools/perf/util/session.h | 2 ++ 7 files changed, 41 insertions(+), 5 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 11e3c845836..44d7df28043 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -474,6 +474,7 @@ static int test__basic_mmap(void) unsigned int nr_events[nsyscalls], expected_nr_events[nsyscalls], i, j; struct perf_evsel *evsels[nsyscalls], *evsel; + int sample_size = perf_sample_size(attr.sample_type); for (i = 0; i < nsyscalls; ++i) { char name[64]; @@ -558,7 +559,8 @@ static int test__basic_mmap(void) goto out_munmap; } - perf_event__parse_sample(event, attr.sample_type, false, &sample); + perf_event__parse_sample(event, attr.sample_type, sample_size, + false, &sample); evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { pr_debug("event with id %" PRIu64 diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1023f67633a..17c1c3c875c 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -35,6 +35,22 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } +int perf_sample_size(u64 sample_type) +{ + u64 mask = sample_type & PERF_SAMPLE_MASK; + int size = 0; + int i; + + for (i = 0; i < 64; i++) { + if ((mask << i) & 1) + size++; + } + + size *= sizeof(u64); + + return size; +} + static struct perf_sample synth_sample = { .pid = -1, .tid = -1, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 9c35170fb37..c0833287140 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -56,6 +56,13 @@ struct read_event { u64 id; }; + +#define PERF_SAMPLE_MASK \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ + PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) + struct sample_event { struct perf_event_header header; u64 array[]; @@ -75,6 +82,8 @@ struct perf_sample { struct ip_callchain *callchain; }; +int perf_sample_size(u64 sample_type); + #define BUILD_ID_SIZE 20 struct build_id_event { @@ -178,6 +187,7 @@ int perf_event__preprocess_sample(const union perf_event *self, const char *perf_event__name(unsigned int id); int perf_event__parse_sample(const union perf_event *event, u64 type, - bool sample_id_all, struct perf_sample *sample); + int sample_size, bool sample_id_all, + struct perf_sample *sample); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d6fd59beb86..bfce8bf642f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -304,7 +304,8 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type, } int perf_event__parse_sample(const union perf_event *event, u64 type, - bool sample_id_all, struct perf_sample *data) + int sample_size, bool sample_id_all, + struct perf_sample *data) { const u64 *array; @@ -319,6 +320,9 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, array = event->sample.array; + if (sample_size + sizeof(event->header) > event->header.size) + return -EFAULT; + if (type & PERF_SAMPLE_IP) { data->ip = event->ip.ip; array++; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 8b0eff8b828..4174c099032 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -690,8 +690,9 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return PyErr_NoMemory(); first = list_entry(evlist->entries.next, struct perf_evsel, node); - perf_event__parse_sample(event, first->attr.sample_type, sample_id_all, - &pevent->sample); + perf_event__parse_sample(event, first->attr.sample_type, + perf_sample_size(first->attr.sample_type), + sample_id_all, &pevent->sample); return pyevent; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index db652068c39..8940fd871ea 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -97,6 +97,7 @@ out: void perf_session__update_sample_type(struct perf_session *self) { self->sample_type = perf_evlist__sample_type(self->evlist); + self->sample_size = perf_sample_size(self->sample_type); self->sample_id_all = perf_evlist__sample_id_all(self->evlist); perf_session__id_header_size(self); } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 8daaa2d1539..66d4e149087 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -43,6 +43,7 @@ struct perf_session { */ struct hists hists; u64 sample_type; + int sample_size; int fd; bool fd_pipe; bool repipe; @@ -159,6 +160,7 @@ static inline int perf_session__parse_sample(struct perf_session *session, struct perf_sample *sample) { return perf_event__parse_sample(event, session->sample_type, + session->sample_size, session->sample_id_all, sample); } -- cgit v1.2.3-70-g09d2 From 5538becaec9ca2ff21e7826372941dc46f498487 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 22 May 2011 02:17:22 +0200 Subject: perf tools: Propagate event parse error handling Better handle event parsing error by propagating the details in upper layers or by dumping some failure message. So that the user knows he has some crazy events in the batch. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian --- tools/perf/builtin-test.c | 9 +++++++-- tools/perf/builtin-top.c | 7 ++++++- tools/perf/util/python.c | 14 ++++++++++---- tools/perf/util/session.c | 14 ++++++++++---- 4 files changed, 33 insertions(+), 11 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 44d7df28043..1fa9f58c2af 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -559,8 +559,13 @@ static int test__basic_mmap(void) goto out_munmap; } - perf_event__parse_sample(event, attr.sample_type, sample_size, - false, &sample); + err = perf_event__parse_sample(event, attr.sample_type, sample_size, + false, &sample); + if (err) { + pr_err("Can't parse sample, err = %d\n", err); + goto out_munmap; + } + evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { pr_debug("event with id %" PRIu64 diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e3d6e310bf..74f533cbf6c 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -805,9 +805,14 @@ static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu) { struct perf_sample sample; union perf_event *event; + int ret; while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) { - perf_session__parse_sample(self, event, &sample); + ret = perf_session__parse_sample(self, event, &sample); + if (ret) { + pr_err("Can't parse sample, err = %d\n", ret); + continue; + } if (event->header.type == PERF_RECORD_SAMPLE) perf_event__process_sample(event, &sample, self); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 4174c099032..3344d6e6f04 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -675,6 +675,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, union perf_event *event; int sample_id_all = 1, cpu; static char *kwlist[] = {"sample_id_all", NULL, NULL}; + int err; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, &cpu, &sample_id_all)) @@ -690,12 +691,17 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return PyErr_NoMemory(); first = list_entry(evlist->entries.next, struct perf_evsel, node); - perf_event__parse_sample(event, first->attr.sample_type, - perf_sample_size(first->attr.sample_type), - sample_id_all, &pevent->sample); + err = perf_event__parse_sample(event, first->attr.sample_type, + perf_sample_size(first->attr.sample_type), + sample_id_all, &pevent->sample); + if (err) { + pr_err("Can't parse sample, err = %d\n", err); + goto end; + } + return pyevent; } - +end: Py_INCREF(Py_None); return Py_None; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8940fd871ea..948327d9e92 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -480,6 +480,7 @@ static void flush_sample_queue(struct perf_session *s, struct perf_sample sample; u64 limit = os->next_flush; u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; + int ret; if (!ops->ordered_samples || !limit) return; @@ -488,9 +489,12 @@ static void flush_sample_queue(struct perf_session *s, if (iter->timestamp > limit) break; - perf_session__parse_sample(s, iter->event, &sample); - perf_session_deliver_event(s, iter->event, &sample, ops, - iter->file_offset); + ret = perf_session__parse_sample(s, iter->event, &sample); + if (ret) + pr_err("Can't parse sample, err = %d\n", ret); + else + perf_session_deliver_event(s, iter->event, &sample, ops, + iter->file_offset); os->last_flush = iter->timestamp; list_del(&iter->list); @@ -806,7 +810,9 @@ static int perf_session__process_event(struct perf_session *session, /* * For all kernel events we get the sample data */ - perf_session__parse_sample(session, event, &sample); + ret = perf_session__parse_sample(session, event, &sample); + if (ret) + return ret; /* Preprocess sample records - precheck callchains */ if (perf_session__preprocess_sample(session, event, &sample)) -- cgit v1.2.3-70-g09d2