From 99d86c8b88393e29cf07c020585f2c8afbcdd97d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 17 Jan 2019 12:30:17 +0100 Subject: perf ordered_events: Fix crash in ordered_events__free Song Liu reported crash in 'perf record': > #0 0x0000000000500055 in ordered_events(float, long double,...)(...) () > #1 0x0000000000500196 in ordered_events.reinit () > #2 0x00000000004fe413 in perf_session.process_events () > #3 0x0000000000440431 in cmd_record () > #4 0x00000000004a439f in run_builtin () > #5 0x000000000042b3e5 in main ()" This can happen when we get out of buffers during event processing. The subsequent ordered_events__free() call assumes oe->buffer != NULL and crashes. Add a check to prevent that. Reported-by: Song Liu Signed-off-by: Jiri Olsa Reviewed-by: Song Liu Tested-by: Song Liu Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190117113017.12977-1-jolsa@kernel.org Fixes: d5ceb62b3654 ("perf ordered_events: Add 'struct ordered_events_buffer' layer") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 897589507d97..ea523d3b248f 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe) * Current buffer might not have all the events allocated * yet, we need to free only allocated ones ... */ - list_del(&oe->buffer->list); - ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + if (oe->buffer) { + list_del(&oe->buffer->list); + ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + } /* ... and continue with the rest */ list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) { -- cgit v1.2.3 From 96167167b6e17b25c0e05ecc31119b73baeab094 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 17 Jan 2019 11:48:34 -0800 Subject: perf script: Fix crash with printing mixed trace point and other events 'perf script' crashes currently when printing mixed trace points and other events because the trace format does not handle events without trace meta data. Add a simple check to avoid that. % cat > test.c main() { printf("Hello world\n"); } ^D % gcc -g -o test test.c % sudo perf probe -x test 'test.c:3' % perf record -e '{cpu/cpu-cycles,period=10000/,probe_test:main}:S' ./test % perf script Committer testing: Before: # perf probe -x /lib64/libc-2.28.so malloc Added new event: probe_libc:malloc (on malloc in /usr/lib64/libc-2.28.so) You can now use it in all perf tools, such as: perf record -e probe_libc:malloc -aR sleep 1 # perf probe -l probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.28.so) # perf record -e '{cpu/cpu-cycles,period=10000/,probe_libc:*}:S' sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (40 samples) ] # perf script Segmentation fault (core dumped) ^C # After: # perf script | head -6 sleep 2888 94796.944981: 16198 cpu/cpu-cycles,period=10000/: ffffffff925dc04f get_random_u32+0x1f (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944981: probe_libc:malloc: sleep 2888 94796.944983: 4713 cpu/cpu-cycles,period=10000/: ffffffff922763af change_protection+0xcf (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944983: probe_libc:malloc: sleep 2888 94796.944986: 9934 cpu/cpu-cycles,period=10000/: ffffffff922777e0 move_page_tables+0x0 (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944986: probe_libc:malloc: # Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190117194834.21940-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d079f36d342d..357906ed1898 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1794,7 +1794,7 @@ static void process_event(struct perf_script *script, return; } - if (PRINT_FIELD(TRACE)) { + if (PRINT_FIELD(TRACE) && sample->raw_data) { event_format__fprintf(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size, fp); } -- cgit v1.2.3 From 94ec1eb711db69be1414b56b3160b816e86a5c5b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 18 Jan 2019 11:34:15 -0300 Subject: perf python: Remove -fstack-clash-protection when building with some clang versions These options are not present in some (all?) clang versions, so when we build for a distro that has a gcc new enough to have these options and that the distro python build config settings use them but clang doesn't support, b00m. This is the case with fedora rawhide (now gearing towards f30), so check if clang has the and remove the missing ones from CFLAGS. Cc: Eduardo Habkost Cc: Thiago Macieira Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-5q50q9w458yawgxf9ez54jbp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/setup.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 63f758c655d5..64d1f36dee99 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -17,6 +17,8 @@ if cc == "clang": vars[var] = sub("-mcet", "", vars[var]) if not clang_has_option("-fcf-protection"): vars[var] = sub("-fcf-protection", "", vars[var]) + if not clang_has_option("-fstack-clash-protection"): + vars[var] = sub("-fstack-clash-protection", "", vars[var]) from distutils.core import setup, Extension -- cgit v1.2.3 From 1497e804d1a6e2bd9107ddf64b0310449f4673eb Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Sat, 19 Jan 2019 00:12:39 -0800 Subject: perf tools: Handle TOPOLOGY headers with no CPU This patch fixes an issue in cpumap.c when used with the TOPOLOGY header. In some configurations, some NUMA nodes may have no CPU (empty cpulist). Yet a cpumap map must be created otherwise perf abort with an error. This patch handles this case by creating a dummy map. Before: $ perf record -o - -e cycles noploop 2 | perf script -i - 0x6e8 [0x6c]: failed to process type: 80 After: $ perf record -o - -e cycles noploop 2 | perf script -i - noploop for 2 seconds Signed-off-by: Stephane Eranian Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1547885559-1657-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..383674f448fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (!cpu_list) return cpu_map__read_all_cpu_map(); - if (!isdigit(*cpu_list)) + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') goto out; while (isdigit(*cpu_list)) { @@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else + else if (*cpu_list != '\0') cpus = cpu_map__default_new(); + else + cpus = cpu_map__dummy_new(); invalid: free(tmp_cpus); out: -- cgit v1.2.3 From da06d568386877809532e8ec678f4a5e300f0951 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Mon, 21 Jan 2019 00:05:22 +0800 Subject: perf top: Fix wrong hottest instruction highlighted The annotation line percentage is compared and inserted into the rbtree, but the percent field of 'struct annotation_data' is an array, the comparison result between them is the address difference. This patch compares the right slot of percent array according to opts->percent_type and makes things right. The problem can be reproduced by pressing 'H' in perf top annotation view. It should highlight the instruction line which has the highest sampling percentage. Signed-off-by: He Kuang Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190120160523.4391-1-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/annotate.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 1d00e5ec7906..82e16bf84466 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -224,20 +224,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) return ret; } -static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) +static double disasm__cmp(struct annotation_line *a, struct annotation_line *b, + int percent_type) { int i; for (i = 0; i < a->data_nr; i++) { - if (a->data[i].percent == b->data[i].percent) + if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type]) continue; - return a->data[i].percent < b->data[i].percent; + return a->data[i].percent[percent_type] - + b->data[i].percent[percent_type]; } return 0; } -static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al) +static void disasm_rb_tree__insert(struct annotate_browser *browser, + struct annotation_line *al) { + struct rb_root *root = &browser->entries; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct annotation_line *l; @@ -246,7 +250,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line parent = *p; l = rb_entry(parent, struct annotation_line, rb_node); - if (disasm__cmp(al, l)) + if (disasm__cmp(al, l, browser->opts->percent_type) < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -329,7 +333,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, RB_CLEAR_NODE(&pos->al.rb_node); continue; } - disasm_rb_tree__insert(&browser->entries, &pos->al); + disasm_rb_tree__insert(browser, &pos->al); } pthread_mutex_unlock(¬es->lock); -- cgit v1.2.3 From 8bf8c6da53c2265aea365a1de6038f118f522113 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Sun, 20 Jan 2019 11:14:14 -0800 Subject: perf script: Fix crash when processing recorded stat data While updating perf to work with Python3 and Python2 I noticed that the stat-cpi script was dumping core. $ perf stat -e cycles,instructions record -o /tmp/perf.data /bin/false Performance counter stats for '/bin/false': 802,148 cycles 604,622 instructions 802,148 cycles 604,622 instructions 0.001445842 seconds time elapsed $ perf script -i /tmp/perf.data -s scripts/python/stat-cpi.py Segmentation fault (core dumped) ... ... rblist=rblist@entry=0xb2a200 , new_entry=new_entry@entry=0x7ffcb755c310) at util/rblist.c:33 ctx=, type=, create=, cpu=, evsel=) at util/stat-shadow.c:118 ctx=, type=, st=) at util/stat-shadow.c:196 count=count@entry=727442, cpu=cpu@entry=0, st=0xb2a200 ) at util/stat-shadow.c:239 config=config@entry=0xafeb40 , counter=counter@entry=0x133c6e0) at util/stat.c:372 ... ... The issue is that since 1fcd03946b52 perf_stat__update_shadow_stats now calls update_runtime_stat passing rt_stat rather than calling update_stats but perf_stat__init_shadow_stats has never been called to initialize rt_stat in the script path processing recorded stat data. Since I can't see any reason why perf_stat__init_shadow_stats() is presently initialized like it is in builtin-script.c::perf_sample__fprint_metric() [4bd1bef8bba2f] I'm proposing it instead be initialized once in __cmd_script Committer testing: After applying the patch: # perf script -i /tmp/perf.data -s tools/perf/scripts/python/stat-cpi.py 0.001970: cpu -1, thread -1 -> cpi 1.709079 (1075684/629394) # No segfault. Signed-off-by: Tony Jones Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Ravi Bangoria Cc: Andi Kleen Cc: Jin Yao Fixes: 1fcd03946b52 ("perf stat: Update per-thread shadow stats") Link: http://lkml.kernel.org/r/20190120191414.12925-1-tonyj@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 357906ed1898..ac221f137ed2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1681,13 +1681,8 @@ static void perf_sample__fprint_metric(struct perf_script *script, .force_header = false, }; struct perf_evsel *ev2; - static bool init; u64 val; - if (!init) { - perf_stat__init_shadow_stats(); - init = true; - } if (!evsel->stats) perf_evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) @@ -2359,6 +2354,8 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); + perf_stat__init_shadow_stats(); + /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; -- cgit v1.2.3