From 0823f768b800cca2592fad3b5649766ae6bc4eba Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 3 Sep 2020 15:34:20 -0300 Subject: [PATCH 1/7] perf parse-events: Use uintptr_t when casting numbers to pointers To address these errors found when cross building from x86_64 to MIPS little endian 32-bit: CC /tmp/build/perf/util/parse-events-bison.o util/parse-events.y: In function 'parse_events_parse': util/parse-events.y:514:6: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 514 | (void *) $2, $6, $4); | ^ util/parse-events.y:531:7: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 531 | (void *) $2, NULL, $4)) { | ^ util/parse-events.y:547:6: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 547 | (void *) $2, $4, 0); | ^ util/parse-events.y:564:7: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 564 | (void *) $2, NULL, 0)) { | ^ Fixes: cabbf26821aa210f ("perf parse: Before yyabort-ing free components") Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Daniel Borkmann Cc: Ian Rogers Cc: Jin Yao Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Yonghong Song Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.y | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index b9fb91fdc5de91..645bf4f1859fd7 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4); + (void *)(uintptr_t) $2, $6, $4); free($6); if (err) { free(list); @@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)) { + (void *)(uintptr_t) $2, NULL, $4)) { free(list); YYABORT; } @@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0); + (void *)(uintptr_t) $2, $4, 0); free($4); if (err) { free(list); @@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)) { + (void *)(uintptr_t) $2, NULL, 0)) { free(list); YYABORT; } From e62458e3940eb3dfb009481850e140fbee183b04 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 4 Sep 2020 00:25:10 +0900 Subject: [PATCH 2/7] perf jevents: Fix suspicious code in fixregex() The new string should have enough space for the original string and the back slashes IMHO. Fixes: fbc2844e84038ce3 ("perf vendor events: Use more flexible pattern matching for CPU identification for mapfile.csv") Signed-off-by: Namhyung Kim Reviewed-by: Ian Rogers Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Cc: William Cohen Link: http://lore.kernel.org/lkml/20200903152510.489233-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fa86c5f997cc54..fc9c158bfa134e 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -137,7 +137,7 @@ static char *fixregex(char *s) return s; /* allocate space for a new string */ - fixed = (char *) malloc(len + 1); + fixed = (char *) malloc(len + esc_count + 1); if (!fixed) return NULL; From 10a6f5c3b3ec03c7427b055b1f6081e752762d2e Mon Sep 17 00:00:00 2001 From: "Tzvetomir Stoyanov (VMware)" Date: Wed, 2 Sep 2020 13:31:21 +0300 Subject: [PATCH 3/7] libtraceevent: Fix build warning on 32-bit arches Fixed a compilation warning for casting to pointer from integer of different size on 32-bit platforms. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Tzvetomir Stoyanov (VMware) Cc: Steven Rostedt (VMware) Cc: linux-trace-devel@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 3ba566de821c6b..5acc18b326061f 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -5259,7 +5259,7 @@ static int print_arg_pointer(struct trace_seq *s, const char *format, int plen, default: ret = 0; val = eval_num_arg(data, size, event, arg); - trace_seq_printf(s, "%p", (void *)val); + trace_seq_printf(s, "%p", (void *)(intptr_t)val); break; } From ee6a961432e75393bd69bf70ba70bad90396fa82 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 3 Sep 2020 09:01:13 +0800 Subject: [PATCH 4/7] perf stat: Turn off summary for interval mode by default There's a risk that outputting interval mode summaries by default breaks CSV consumers. It already broke pmu-tools/toplev. So now we turn off the summary by default but we create a new option '--summary' to enable the summary. This is active even when not using CSV mode. Before: root@kbl-ppc:~# perf stat -I1000 --interval-count 2 # time counts unit events 1.000265904 8,005.73 msec cpu-clock # 8.006 CPUs utilized 1.000265904 601 context-switches # 0.075 K/sec 1.000265904 10 cpu-migrations # 0.001 K/sec 1.000265904 0 page-faults # 0.000 K/sec 1.000265904 66,746,521 cycles # 0.008 GHz 1.000265904 71,874,398 instructions # 1.08 insn per cycle 1.000265904 13,356,781 branches # 1.668 M/sec 1.000265904 298,756 branch-misses # 2.24% of all branches 2.001857667 8,012.52 msec cpu-clock # 8.013 CPUs utilized 2.001857667 164 context-switches # 0.020 K/sec 2.001857667 10 cpu-migrations # 0.001 K/sec 2.001857667 2 page-faults # 0.000 K/sec 2.001857667 5,822,188 cycles # 0.001 GHz 2.001857667 2,186,170 instructions # 0.38 insn per cycle 2.001857667 442,378 branches # 0.055 M/sec 2.001857667 44,750 branch-misses # 10.12% of all branches Performance counter stats for 'system wide': 16,018.25 msec cpu-clock # 7.993 CPUs utilized 765 context-switches # 0.048 K/sec 20 cpu-migrations # 0.001 K/sec 2 page-faults # 0.000 K/sec 72,568,709 cycles # 0.005 GHz 74,060,568 instructions # 1.02 insn per cycle 13,799,159 branches # 0.861 M/sec 343,506 branch-misses # 2.49% of all branches 2.004118489 seconds time elapsed After: root@kbl-ppc:~# perf stat -I1000 --interval-count 2 # time counts unit events 1.001336393 8,013.28 msec cpu-clock # 8.013 CPUs utilized 1.001336393 82 context-switches # 0.010 K/sec 1.001336393 8 cpu-migrations # 0.001 K/sec 1.001336393 0 page-faults # 0.000 K/sec 1.001336393 4,199,121 cycles # 0.001 GHz 1.001336393 1,373,991 instructions # 0.33 insn per cycle 1.001336393 270,681 branches # 0.034 M/sec 1.001336393 31,659 branch-misses # 11.70% of all branches 2.003905006 8,020.52 msec cpu-clock # 8.021 CPUs utilized 2.003905006 184 context-switches # 0.023 K/sec 2.003905006 8 cpu-migrations # 0.001 K/sec 2.003905006 2 page-faults # 0.000 K/sec 2.003905006 5,446,190 cycles # 0.001 GHz 2.003905006 2,312,547 instructions # 0.42 insn per cycle 2.003905006 451,691 branches # 0.056 M/sec 2.003905006 37,925 branch-misses # 8.40% of all branches root@kbl-ppc:~# perf stat -I1000 --interval-count 2 --summary # time counts unit events 1.001313128 8,013.20 msec cpu-clock # 8.013 CPUs utilized 1.001313128 83 context-switches # 0.010 K/sec 1.001313128 8 cpu-migrations # 0.001 K/sec 1.001313128 0 page-faults # 0.000 K/sec 1.001313128 4,470,950 cycles # 0.001 GHz 1.001313128 1,440,045 instructions # 0.32 insn per cycle 1.001313128 283,222 branches # 0.035 M/sec 1.001313128 33,576 branch-misses # 11.86% of all branches 2.003857385 8,020.34 msec cpu-clock # 8.020 CPUs utilized 2.003857385 154 context-switches # 0.019 K/sec 2.003857385 8 cpu-migrations # 0.001 K/sec 2.003857385 2 page-faults # 0.000 K/sec 2.003857385 4,515,676 cycles # 0.001 GHz 2.003857385 2,180,449 instructions # 0.48 insn per cycle 2.003857385 435,254 branches # 0.054 M/sec 2.003857385 31,179 branch-misses # 7.16% of all branches Performance counter stats for 'system wide': 16,033.53 msec cpu-clock # 7.992 CPUs utilized 237 context-switches # 0.015 K/sec 16 cpu-migrations # 0.001 K/sec 2 page-faults # 0.000 K/sec 8,986,626 cycles # 0.001 GHz 3,620,494 instructions # 0.40 insn per cycle 718,476 branches # 0.045 M/sec 64,755 branch-misses # 9.01% of all branches 2.006124542 seconds time elapsed Fixes: c7e5b328a8d4 ("perf stat: Report summary for interval mode") Signed-off-by: Jin Yao Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200903010113.32232-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 3 +++ tools/perf/builtin-stat.c | 8 +++++--- tools/perf/util/stat.h | 1 + 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index c9bfefc051fbef..947672fd9c7025 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -416,6 +416,9 @@ counts for all hardware threads in a core but show the sum counts per hardware thread. This is essentially a replacement for the any bit and convenient for post processing. +--summary:: +Print summary for interval mode (-I). + EXAMPLES -------- diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 483a28ef4ec4fe..fddc97cac98415 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs) { struct evsel *counter; - if (!stat_config.summary && (read_affinity_counters(rs) < 0)) + if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0)) return; evlist__for_each_entry(evsel_list, counter) { @@ -897,9 +897,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (stat_config.walltime_run_table) stat_config.walltime_run[run_idx] = t1 - t0; - if (interval) { + if (interval && stat_config.summary) { stat_config.interval = 0; - stat_config.summary = true; + stat_config.stop_read_counter = true; init_stats(&walltime_nsecs_stats); update_stats(&walltime_nsecs_stats, t1 - t0); @@ -1164,6 +1164,8 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), + OPT_BOOLEAN(0, "summary", &stat_config.summary, + "print summary for interval mode"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index f8778cffd9419b..aa3bed48511b32 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -113,6 +113,7 @@ struct perf_stat_config { bool summary; bool metric_no_group; bool metric_no_merge; + bool stop_read_counter; FILE *output; unsigned int interval; unsigned int timeout; From e4d71f79cf5c10fa8bc6f5d3bebea570c9c438f1 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 2 Sep 2020 22:05:26 +0800 Subject: [PATCH 5/7] perf bench: The do_run_multi_threaded() function must use IS_ERR(perf_session__new()) In case of error, the function perf_session__new() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR() Committer notes: This wasn't compiling due to an extraneous '{' not matched by a '}', fix it. Fixes: 13edc237200c ("perf bench: Add a multi-threaded synthesize benchmark") Signed-off-by: YueHaibing Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200902140526.26916-1-yuehaibing@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/synthesize.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 8d624aea1c5e54..b2924e3181dc38 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target, init_stats(&event_stats); for (i = 0; i < multi_iterations; i++) { session = perf_session__new(NULL, false, NULL); - if (!session) - return -ENOMEM; + if (IS_ERR(session)) + return PTR_ERR(session); atomic_set(&event_count, 0); gettimeofday(&start, NULL); From e48a73a312ebf19cc3d72aa74985db25c30757c1 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Tue, 1 Sep 2020 16:58:53 -0500 Subject: [PATCH 6/7] perf record/stat: Explicitly call out event modifiers in the documentation Event modifiers are not mentioned in the perf record or perf stat manpages. Add them to orient new users more effectively by pointing them to the perf list manpage for details. Fixes: 2055fdaf8703 ("perf list: Document precise event sampling for AMD IBS") Signed-off-by: Kim Phillips Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Ian Rogers Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tony Jones Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200901215853.276234-1-kim.phillips@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++++ tools/perf/Documentation/perf-stat.txt | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3f72d8e261f3de..bd50cdff08a88b 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,6 +33,10 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where 'param1', 'param2', etc are defined as formats for the PMU in /sys/bus/event_source/devices//format/*. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 947672fd9c7025..db420dd75e4357 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -39,6 +39,10 @@ report:: - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed event like 'pmu/param1=0x3,param2/' where param1 and param2 are defined as formats for the PMU in /sys/bus/event_source/devices//format/* From 830fadfd954c6782b7a8a2461c76a568c7153b9a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 26 Aug 2020 23:30:17 +0200 Subject: [PATCH 7/7] perf tools: Add bpf image check to __map__is_kmodule When validating kcore modules the do_validate_kcore_modules function checks on every kernel module dso against modules record. The __map__is_kmodule check is used to get only kernel module dso objects through. Currently the bpf images are slipping through the check and making the validation to fail, so report falls back from kcore usage to kallsyms. Adding __map__is_bpf_image check for bpf image and adding it to __map__is_kmodule check. Fixes: 3c29d4483e85 ("perf annotate: Add basic support for bpf_image") Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20200826213017.818788-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 6 ------ tools/perf/util/map.c | 16 ++++++++++++++++ tools/perf/util/map.h | 9 ++++++++- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 208b813e00ea49..85587de027a518 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } -static int is_bpf_image(const char *name) -{ - return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || - strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; -} - static int machine__process_ksymbol_register(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 1d7210804639fd..cc0faf8f132194 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map) return name && (strstr(name, "bpf_prog_") == name); } +bool __map__is_bpf_image(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) + return true; + + /* + * If PERF_RECORD_KSYMBOL is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && is_bpf_image(name); +} + bool __map__is_ool(const struct map *map) { return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9e312ae2d65633..c2f5d28fe73ac4 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); bool __map__is_bpf_prog(const struct map *map); +bool __map__is_bpf_image(const struct map *map); bool __map__is_ool(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && - !__map__is_bpf_prog(map) && !__map__is_ool(map); + !__map__is_bpf_prog(map) && !__map__is_ool(map) && + !__map__is_bpf_image(map); } bool map__has_symbols(const struct map *map); @@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name) return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } +static inline bool is_bpf_image(const char *name) +{ + return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || + strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; +} #endif /* __PERF_MAP_H */