From f006d25a15216a483cec71e886786874f66f9452 Mon Sep 17 00:00:00 2001 From: Han Pingtian Date: Thu, 6 Jan 2011 17:39:22 +0800 Subject: perf tools: Fix buffer overflow error when specifying all tracepoints I found when specifying all tracepoints with -e to one of subcommand, such as 'stat', the program will trigger a buffer overflow error, like this: *** buffer overflow detected ***: ./perf terminated ======= Backtrace: ========= /lib64/libc.so.6(__fortify_fail+0x37)[0x382cefb2c7] .... The tracepoints are separated by comma, something like this: $ perf stat -a -e `perf list |grep Tracepoint|awk -F'[' '{gsub(/[[:space:]]+/,"",$1);array[FNR]=$1}END{outputs=array[1];for (i=2;i<=FNR;i++){ outputs=outputs "," array[i];};print outputs}'` The root reason of this problem is that store_event_type() is called for all events, and will overflow the 'filename' at: strncat(filename, orgname, strlen(orgname)); This patch fixes it by calling store_event_type() only when the event name has been found. LKML-Reference: <20110106093922.GB6713@hpt.nay.redhat.com> Signed-off-by: Han Pingtian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 61 +++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 31 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 649083f27e08..917a0ca521c1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -490,6 +490,31 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp, return EVT_HANDLED_ALL; } +static int store_event_type(const char *orgname) +{ + char filename[PATH_MAX], *c; + FILE *file; + int id, n; + + sprintf(filename, "%s/", debugfs_path); + strncat(filename, orgname, strlen(orgname)); + strcat(filename, "/id"); + + c = strchr(filename, ':'); + if (c) + *c = '/'; + + file = fopen(filename, "r"); + if (!file) + return 0; + n = fscanf(file, "%i", &id); + fclose(file); + if (n < 1) { + pr_err("cannot store event ID\n"); + return -EINVAL; + } + return perf_header__push_event(id, orgname); +} static enum event_result parse_tracepoint_event(const char **strp, struct perf_event_attr *attr) @@ -533,9 +558,13 @@ static enum event_result parse_tracepoint_event(const char **strp, *strp += strlen(sys_name) + evt_length; return parse_multiple_tracepoint_event(sys_name, evt_name, flags); - } else + } else { + if (store_event_type(evt_name) < 0) + return EVT_FAILED; + return parse_single_tracepoint_event(sys_name, evt_name, evt_length, attr, strp); + } } static enum event_result @@ -778,41 +807,11 @@ modifier: return ret; } -static int store_event_type(const char *orgname) -{ - char filename[PATH_MAX], *c; - FILE *file; - int id, n; - - sprintf(filename, "%s/", debugfs_path); - strncat(filename, orgname, strlen(orgname)); - strcat(filename, "/id"); - - c = strchr(filename, ':'); - if (c) - *c = '/'; - - file = fopen(filename, "r"); - if (!file) - return 0; - n = fscanf(file, "%i", &id); - fclose(file); - if (n < 1) { - pr_err("cannot store event ID\n"); - return -EINVAL; - } - return perf_header__push_event(id, orgname); -} - int parse_events(const struct option *opt __used, const char *str, int unset __used) { struct perf_event_attr attr; enum event_result ret; - if (strchr(str, ':')) - if (store_event_type(str) < 0) - return -1; - for (;;) { memset(&attr, 0, sizeof(attr)); ret = parse_event_symbols(&str, &attr); -- cgit v1.2.2 From 6b01f2c4f6188da50d8fe094e369a9c0390424ab Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 6 Jan 2011 15:51:53 +0100 Subject: perf tools: Build with frame pointer It seems that some gcc versions build by default with frame pointers and some others omit them. Just build the tools with frame pointers as the callchains can be an important part of the perf workflow. Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Stephane Eranian LKML-Reference: <1294325513-14276-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 1b9b13ee2a72..2b5387d53ba5 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -227,7 +227,7 @@ ifndef PERF_DEBUG CFLAGS_OPTIMIZE = -O6 endif -CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) +CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) EXTLIBS = -lpthread -lrt -lelf -lm ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 ALL_LDFLAGS = $(LDFLAGS) -- cgit v1.2.2 From 23a2f3ab46596d9fd0b0e592d2101bea90970594 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Fri, 7 Jan 2011 11:11:09 +0800 Subject: perf tools: Pass whole attr to event selectors Since commit 69aad6f1(perf tools: Introduce event selectors), only perf_event_attr::type and ::config are passed to event selector, which makes perf tool not work correctly. For example, PEBS does not work because perf_event_attr::precise_ip is not passed to the syscall. Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra LKML-Reference: <1294369869.20563.19.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 3 +-- tools/perf/builtin-test.c | 6 +++++- tools/perf/util/evsel.c | 5 ++--- tools/perf/util/evsel.h | 2 +- tools/perf/util/parse-events.c | 13 ++++++++++--- 5 files changed, 19 insertions(+), 10 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 02b2d8013a61..2dfcb613e66b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -683,8 +683,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) nr_counters = ARRAY_SIZE(default_attrs); for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) { - pos = perf_evsel__new(default_attrs[c].type, - default_attrs[c].config, + pos = perf_evsel__new(&default_attrs[c], nr_counters); if (pos == NULL) goto out; diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 1c984342a579..e12753f976a1 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -264,6 +264,7 @@ static int test__open_syscall_event(void) int err = -1, fd; struct thread_map *threads; struct perf_evsel *evsel; + struct perf_event_attr attr; unsigned int nr_open_calls = 111, i; int id = trace_event__id("sys_enter_open"); @@ -278,7 +279,10 @@ static int test__open_syscall_event(void) return -1; } - evsel = perf_evsel__new(PERF_TYPE_TRACEPOINT, id, 0); + memset(&attr, 0, sizeof(attr)); + attr.type = PERF_TYPE_TRACEPOINT; + attr.config = id; + evsel = perf_evsel__new(&attr, 0); if (evsel == NULL) { pr_debug("perf_evsel__new\n"); goto out_thread_map_delete; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c95267e63c5b..1a5591d7a245 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -6,14 +6,13 @@ #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx) +struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(sizeof(*evsel)); if (evsel != NULL) { evsel->idx = idx; - evsel->attr.type = type; - evsel->attr.config = config; + evsel->attr = *attr; INIT_LIST_HEAD(&evsel->node); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index a0ccd69c3fc2..b2d755fe88a5 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -37,7 +37,7 @@ struct perf_evsel { struct cpu_map; struct thread_map; -struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx); +struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx); void perf_evsel__delete(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 917a0ca521c1..5cb6f4bde905 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -823,7 +823,7 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u if (ret != EVT_HANDLED_ALL) { struct perf_evsel *evsel; - evsel = perf_evsel__new(attr.type, attr.config, + evsel = perf_evsel__new(&attr, nr_counters); if (evsel == NULL) return -1; @@ -1013,8 +1013,15 @@ void print_events(void) int perf_evsel_list__create_default(void) { - struct perf_evsel *evsel = perf_evsel__new(PERF_TYPE_HARDWARE, - PERF_COUNT_HW_CPU_CYCLES, 0); + struct perf_evsel *evsel; + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.type = PERF_TYPE_HARDWARE; + attr.config = PERF_COUNT_HW_CPU_CYCLES; + + evsel = perf_evsel__new(&attr, 0); + if (evsel == NULL) return -ENOMEM; -- cgit v1.2.2 From e462dc553ea5e09d4713e7c35a11ed331dc6f369 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 Jan 2011 10:48:47 -0200 Subject: perf sched: Fix allocation result check Bug introduced in ce47dc56. Reported-by: Mike Galbraith Cc: Chris Samuel Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 7a4ebeb8b016..54024d2a017e 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1861,7 +1861,7 @@ static int __cmd_record(int argc, const char **argv) rec_argc = ARRAY_SIZE(record_args) + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); - if (rec_argv) + if (rec_argv == NULL) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(record_args); i++) -- cgit v1.2.2 From 5a3446bc648d86a99a895e93d28d7df00bbbfb3c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 9 Jan 2011 11:21:12 -0700 Subject: perf stat: better error message for unsupported events For unsupported events (e.g., H/W events when running in a VM) perf stat currently fails with the error message: Error: open_counter returned with 2 (No such file or directory). /bin/dmesg may provide additional information. Fatal: Not all events could be opened. dmesg is of no help and it is not clear as to why it fails to open the counter. This patch changes the error message to Error: cache-misses event is not supported. Fatal: Not all events could be opened. Cc: Ingo Molnar Cc: Paul Mackerras Cc: a.p.zijlstra@chello.nl LPU-Reference: <1294597272-17335-1-git-send-email-daahern@cisco.com> Signed-off-by: David Ahern Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 2dfcb613e66b..c385a63ebfd1 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -316,6 +316,8 @@ static int run_perf_stat(int argc __used, const char **argv) "\t Consider tweaking" " /proc/sys/kernel/perf_event_paranoid or running as root.", system_wide ? "system-wide " : ""); + } else if (errno == ENOENT) { + error("%s event is not supported. ", event_name(counter)); } else { error("open_counter returned with %d (%s). " "/bin/dmesg may provide additional information.\n", -- cgit v1.2.2 From aa7bc7ef73efc46d7c3a0e185eefaf85744aec98 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 Jan 2011 13:36:24 -0200 Subject: perf tools: Emit clearer message for sys_perf_event_open ENOENT return Improve sys_perf_event_open ENOENT return handling in top and record, just like 5a3446b does for stat. Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 3 +++ tools/perf/builtin-top.c | 2 ++ 2 files changed, 5 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 7bc049035484..7069bd3e90b3 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -331,6 +331,9 @@ try_again: else if (err == ENODEV && cpu_list) { die("No such device - did you specify" " an out-of-range profile CPU?\n"); + } else if (err == ENOENT) { + die("%s event is not supported. ", + event_name(evsel)); } else if (err == EINVAL && sample_id_all_avail) { /* * Old kernel, no attr->sample_id_type_all field diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1e67ab9c7ebc..6ce4042421bd 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1247,6 +1247,8 @@ try_again: die("Permission error - are you root?\n" "\t Consider tweaking" " /proc/sys/kernel/perf_event_paranoid.\n"); + if (err == ENOENT) + die("%s event is not supported. ", event_name(evsel)); /* * If it's cycles then fall back to hrtimer * based cpu-clock-tick sw counter, which -- cgit v1.2.2 From 12f7e0364375ba1ba55abcc5ac082b68fb526c80 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 10 Jan 2011 14:14:23 -0200 Subject: perf sched: Use PTHREAD_STACK_MIN to avoid pthread_attr_setstacksize() fail on ppc64: /usr/include/bits/local_lim.h:#define PTHREAD_STACK_MIN 131072 therefore following set of commands: gives: perf.2.6.37test: builtin-sched.c:493: create_tasks: Assertion `!(err)' failed. So make sure we do not set stack size lower than PTHREAD_STACK_MIN. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <20110110160417.GB2685@psychotron.brq.redhat.com> Signed-off-by: Jiri Pirko Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 54024d2a017e..abd4b8497bc4 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -489,7 +489,8 @@ static void create_tasks(void) err = pthread_attr_init(&attr); BUG_ON(err); - err = pthread_attr_setstacksize(&attr, (size_t)(16*1024)); + err = pthread_attr_setstacksize(&attr, + (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); BUG_ON(err); err = pthread_mutex_lock(&start_work_mutex); BUG_ON(err); -- cgit v1.2.2 From 0252208eb52f6fe8731a47804eddc7ba93f60a87 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 4 Jan 2011 11:55:27 -0200 Subject: perf evsel: Support perf_evsel__open(cpus > 1 && threads > 1) And a test for it: [acme@felicio linux]$ perf test 1: vmlinux symtab matches kallsyms: Ok 2: detect open syscall event: Ok 3: detect open syscall event on all cpus: Ok [acme@felicio linux]$ Translating C the test does: 1. generates different number of open syscalls on each CPU by using sched_setaffinity 2. Verifies that the expected number of events is generated on each CPU It works as expected. LKML-Reference: Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-test.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evsel.c | 82 ++++++++++++++++++++-------------- 2 files changed, 159 insertions(+), 33 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index e12753f976a1..ed5696198d3d 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -234,6 +234,7 @@ out: return err; } +#include "util/cpumap.h" #include "util/evsel.h" #include @@ -321,6 +322,111 @@ out_thread_map_delete: return err; } +#include + +static int test__open_syscall_event_on_all_cpus(void) +{ + int err = -1, fd, cpu; + struct thread_map *threads; + struct cpu_map *cpus; + struct perf_evsel *evsel; + struct perf_event_attr attr; + unsigned int nr_open_calls = 111, i; + cpu_set_t *cpu_set; + size_t cpu_set_size; + int id = trace_event__id("sys_enter_open"); + + if (id < 0) { + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + return -1; + } + + threads = thread_map__new(-1, getpid()); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + cpus = cpu_map__new(NULL); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + cpu_set = CPU_ALLOC(cpus->nr); + + if (cpu_set == NULL) + goto out_thread_map_delete; + + cpu_set_size = CPU_ALLOC_SIZE(cpus->nr); + CPU_ZERO_S(cpu_set_size, cpu_set); + + memset(&attr, 0, sizeof(attr)); + attr.type = PERF_TYPE_TRACEPOINT; + attr.config = id; + evsel = perf_evsel__new(&attr, 0); + if (evsel == NULL) { + pr_debug("perf_evsel__new\n"); + goto out_cpu_free; + } + + if (perf_evsel__open(evsel, cpus, threads) < 0) { + pr_debug("failed to open counter: %s, " + "tweak /proc/sys/kernel/perf_event_paranoid?\n", + strerror(errno)); + goto out_evsel_delete; + } + + for (cpu = 0; cpu < cpus->nr; ++cpu) { + unsigned int ncalls = nr_open_calls + cpu; + + CPU_SET(cpu, cpu_set); + sched_setaffinity(0, cpu_set_size, cpu_set); + for (i = 0; i < ncalls; ++i) { + fd = open("/etc/passwd", O_RDONLY); + close(fd); + } + CPU_CLR(cpu, cpu_set); + } + + /* + * Here we need to explicitely preallocate the counts, as if + * we use the auto allocation it will allocate just for 1 cpu, + * as we start by cpu 0. + */ + if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) { + pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr); + goto out_close_fd; + } + + for (cpu = 0; cpu < cpus->nr; ++cpu) { + unsigned int expected; + + if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) { + pr_debug("perf_evsel__open_read_on_cpu\n"); + goto out_close_fd; + } + + expected = nr_open_calls + cpu; + if (evsel->counts->cpu[cpu].val != expected) { + pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %Ld\n", + expected, cpu, evsel->counts->cpu[cpu].val); + goto out_close_fd; + } + } + + err = 0; +out_close_fd: + perf_evsel__close_fd(evsel, 1, threads->nr); +out_evsel_delete: + perf_evsel__delete(evsel); +out_cpu_free: + CPU_FREE(cpu_set); +out_thread_map_delete: + thread_map__delete(threads); + return err; +} + static struct test { const char *desc; int (*func)(void); @@ -333,6 +439,10 @@ static struct test { .desc = "detect open syscall event", .func = test__open_syscall_event, }, + { + .desc = "detect open syscall event on all cpus", + .func = test__open_syscall_event_on_all_cpus, + }, { .func = NULL, }, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1a5591d7a245..f5cfed60af98 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -127,59 +127,75 @@ int __perf_evsel__read(struct perf_evsel *evsel, return 0; } -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) +static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads) { - int cpu; + int cpu, thread; - if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, 1) < 0) + if (evsel->fd == NULL && + perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) return -1; for (cpu = 0; cpu < cpus->nr; cpu++) { - FD(evsel, cpu, 0) = sys_perf_event_open(&evsel->attr, -1, - cpus->map[cpu], -1, 0); - if (FD(evsel, cpu, 0) < 0) - goto out_close; + for (thread = 0; thread < threads->nr; thread++) { + FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, + threads->map[thread], + cpus->map[cpu], -1, 0); + if (FD(evsel, cpu, thread) < 0) + goto out_close; + } } return 0; out_close: - while (--cpu >= 0) { - close(FD(evsel, cpu, 0)); - FD(evsel, cpu, 0) = -1; - } + do { + while (--thread >= 0) { + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } + thread = threads->nr; + } while (--cpu >= 0); return -1; } -int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) +static struct { + struct cpu_map map; + int cpus[1]; +} empty_cpu_map = { + .map.nr = 1, + .cpus = { -1, }, +}; + +static struct { + struct thread_map map; + int threads[1]; +} empty_thread_map = { + .map.nr = 1, + .threads = { -1, }, +}; + +int perf_evsel__open(struct perf_evsel *evsel, + struct cpu_map *cpus, struct thread_map *threads) { - int thread; - - if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, 1, threads->nr)) - return -1; - for (thread = 0; thread < threads->nr; thread++) { - FD(evsel, 0, thread) = sys_perf_event_open(&evsel->attr, - threads->map[thread], -1, -1, 0); - if (FD(evsel, 0, thread) < 0) - goto out_close; + if (cpus == NULL) { + /* Work around old compiler warnings about strict aliasing */ + cpus = &empty_cpu_map.map; } - return 0; + if (threads == NULL) + threads = &empty_thread_map.map; -out_close: - while (--thread >= 0) { - close(FD(evsel, 0, thread)); - FD(evsel, 0, thread) = -1; - } - return -1; + return __perf_evsel__open(evsel, cpus, threads); } -int perf_evsel__open(struct perf_evsel *evsel, - struct cpu_map *cpus, struct thread_map *threads) +int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) { - if (threads == NULL) - return perf_evsel__open_per_cpu(evsel, cpus); + return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); +} - return perf_evsel__open_per_thread(evsel, threads); +int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) +{ + return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); } -- cgit v1.2.2 From 3d03e2ea74103a50c23d6ab1906cf73399c0dafb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 Jan 2011 21:37:57 -0200 Subject: perf session: Fix infinite loop in __perf_session__process_events In this if statement: if (head + event->header.size >= mmap_size) { if (mmaps[map_idx]) { munmap(mmaps[map_idx], mmap_size); mmaps[map_idx] = NULL; } page_offset = page_size * (head / page_size); file_offset += page_offset; head -= page_offset; goto remap; } With, for instance, these values: head=2992 event->header.size=48 mmap_size=3040 We end up endlessly looping back to remap. Off by one. Problem introduced in 55b4462. Reported-by: Linus Torvalds Reported-by: Ingo Molnar Reported-by: David Ahern Bisected-by: David Ahern Tested-by: David Ahern Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 6fb4694d05fa..313dac2d94ce 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1007,7 +1007,7 @@ more: if (size == 0) size = 8; - if (head + event->header.size >= mmap_size) { + if (head + event->header.size > mmap_size) { if (mmaps[map_idx]) { munmap(mmaps[map_idx], mmap_size); mmaps[map_idx] = NULL; -- cgit v1.2.2 From bd3bfe9eda94d3c050830217c1e1c338808de5b2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 11 Jan 2011 12:42:00 -0200 Subject: perf evsel: Fix order of event list deletion We need to defer calling perf_evsel_list__delete() till after atexit registered routines, because we need to traverse the events being recorded at that time at least on 'perf record'. This fixes the problem reported by Thomas Renninger where cmd_record called by cmd_timechart would not write the tracing data to the perf.data file header because the evsel_list at atexit (control+C on 'perf timechart record') time would be empty, being already deleted by run_builtin(), and thus 'perf timechart' when trying to process such perf.data file would die with: "no trace data in the file" Problem introduced in 70d544d. Reported-by: Thomas Renninger Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Renninger Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 1 + tools/perf/builtin-stat.c | 1 + tools/perf/builtin-top.c | 1 + tools/perf/perf.c | 2 -- 4 files changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 7069bd3e90b3..aa7ece397656 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -480,6 +480,7 @@ static void atexit_header(void) process_buildids(); perf_header__write(&session->header, output, true); perf_session__delete(session); + perf_evsel_list__delete(); symbol__exit(); } } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c385a63ebfd1..0ff11d9b13be 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -743,6 +743,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) out_free_fd: list_for_each_entry(pos, &evsel_list, node) perf_evsel__free_stat_priv(pos); + perf_evsel_list__delete(); out: thread_map__delete(threads); threads = NULL; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 6ce4042421bd..4b995ee099cf 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1490,6 +1490,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) out_free_fd: list_for_each_entry(pos, &evsel_list, node) perf_evsel__free_mmap(pos); + perf_evsel_list__delete(); return status; } diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 5b1ecd66bb36..595d0f4a7103 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -286,8 +286,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) status = p->fn(argc, argv, prefix); exit_browser(status); - perf_evsel_list__delete(); - if (status) return status & 0xff; -- cgit v1.2.2 From cc841580aa58ad7498b23e282859d07f8b721e24 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 11 Jan 2011 15:16:52 -0200 Subject: perf top: Fix annotate segv Before we had sym_counter, it was initialized to zero and we used that as an index in the global attrs variable, now we have a list of evsel entries, and sym_counter became sym_evsel, that remained initialized to zero (NULL): b00m. Fix it by initializing it to the first entry in the evsel list. Bug-introduced: 69aad6f Reported-by: Kirill Smelkov Tested-by: Kirill Smelkov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Kirill Smelkov Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 4b995ee099cf..568b1950e632 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1473,6 +1473,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) pos->attr.sample_period = default_interval; } + sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node); + symbol_conf.priv_size = (sizeof(struct sym_entry) + (nr_counters + 1) * sizeof(unsigned long)); -- cgit v1.2.2 From 4ad9f594d7199c99f6b1b3ef88c64bd5920a4592 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 11 Jan 2011 16:58:54 -0200 Subject: Revert "perf tools: Emit clearer message for sys_perf_event_open ENOENT return" This reverts commit aa7bc7ef73efc46d7c3a0e185eefaf85744aec98. It removed the fallback from hardware profiling to software profiling. .e.g., in a VM with no PMU. Reported-by: David Ahern Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 3 --- tools/perf/builtin-top.c | 2 -- 2 files changed, 5 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index aa7ece397656..1210e6484ad5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -331,9 +331,6 @@ try_again: else if (err == ENODEV && cpu_list) { die("No such device - did you specify" " an out-of-range profile CPU?\n"); - } else if (err == ENOENT) { - die("%s event is not supported. ", - event_name(evsel)); } else if (err == EINVAL && sample_id_all_avail) { /* * Old kernel, no attr->sample_id_type_all field diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 568b1950e632..05344c6210ac 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1247,8 +1247,6 @@ try_again: die("Permission error - are you root?\n" "\t Consider tweaking" " /proc/sys/kernel/perf_event_paranoid.\n"); - if (err == ENOENT) - die("%s event is not supported. ", event_name(evsel)); /* * If it's cycles then fall back to hrtimer * based cpu-clock-tick sw counter, which -- cgit v1.2.2 From 9710118bd4e7f3406865171cb9b9c94547c1c2f9 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 12 Jan 2011 10:29:05 +0100 Subject: perf sched: Fix list of events, dropping unsupported ':r' modifier Looks to me like the :r modifier is not supported anymore, so remove it from the list of events. Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Robert Richter LKML-Reference: Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index abd4b8497bc4..29e7ffd85690 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1843,15 +1843,15 @@ static const char *record_args[] = { "-f", "-m", "1024", "-c", "1", - "-e", "sched:sched_switch:r", - "-e", "sched:sched_stat_wait:r", - "-e", "sched:sched_stat_sleep:r", - "-e", "sched:sched_stat_iowait:r", - "-e", "sched:sched_stat_runtime:r", - "-e", "sched:sched_process_exit:r", - "-e", "sched:sched_process_fork:r", - "-e", "sched:sched_wakeup:r", - "-e", "sched:sched_migrate_task:r", + "-e", "sched:sched_switch", + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + "-e", "sched:sched_stat_runtime", + "-e", "sched:sched_process_exit", + "-e", "sched:sched_process_fork", + "-e", "sched:sched_wakeup", + "-e", "sched:sched_migrate_task", }; static int __cmd_record(int argc, const char **argv) -- cgit v1.2.2 From acac03fa15a8684bb60489ed87b5aae5258c0838 Mon Sep 17 00:00:00 2001 From: Kirill Smelkov Date: Wed, 12 Jan 2011 17:59:36 +0300 Subject: perf record: Add "nodelay" mode, disabled by default Sometimes there is a need to use perf in "live-log" mode. The problem is, for seldom events, actual info output is largely delayed because perf-record reads sample data in whole pages. So for such scenarious, add flag for perf-record to go in "nodelay" mode. To track e.g. what's going on in icmp_rcv while ping is running Use it with something like this: (1) $ perf probe -L icmp_rcv | grep -U8 '^ *43\>' goto error; } 38 if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); 43 ICMPMSGIN_INC_STATS_BH(net, icmph->type); /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ 50 if (icmph->type > NR_ICMP_TYPES) goto error; $ perf probe icmp_rcv:43 'type=icmph->type' (2) $ cat trace-icmp.py [...] def trace_begin(): print "in trace_begin" def trace_end(): print "in trace_end" def probe__icmp_rcv(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, __probe_ip, type): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) print "__probe_ip=%u, type=%u\n" % \ (__probe_ip, type), [...] (3) $ perf record -a -D -e probe:icmp_rcv -o - | \ perf script -i - -s trace-icmp.py Thanks to Peter Zijlstra for pointing how to do it. Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Ingo Molnar , Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: <20110112140613.GA11698@tugrik.mns.mnsspb.ru> Signed-off-by: Kirill Smelkov Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 3 +++ tools/perf/builtin-record.c | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 52462ae26455..e032716c839b 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -61,6 +61,9 @@ OPTIONS -r:: --realtime=:: Collect data with this RT SCHED_FIFO priority. +-D:: +--no-delay:: + Collect data without buffering. -A:: --append:: Append to the output file to do incremental profiling. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 1210e6484ad5..df6064ad9bf2 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -49,6 +49,7 @@ static int pipe_output = 0; static const char *output_name = "perf.data"; static int group = 0; static int realtime_prio = 0; +static bool nodelay = false; static bool raw_samples = false; static bool sample_id_all_avail = true; static bool system_wide = false; @@ -307,6 +308,11 @@ static void create_counter(struct perf_evsel *evsel, int cpu) attr->sample_type |= PERF_SAMPLE_CPU; } + if (nodelay) { + attr->watermark = 0; + attr->wakeup_events = 1; + } + attr->mmap = track; attr->comm = track; attr->inherit = !no_inherit; @@ -843,6 +849,8 @@ const struct option record_options[] = { "record events on existing thread id"), OPT_INTEGER('r', "realtime", &realtime_prio, "collect data with this RT SCHED_FIFO priority"), + OPT_BOOLEAN('D', "no-delay", &nodelay, + "collect data without buffering"), OPT_BOOLEAN('R', "raw-samples", &raw_samples, "collect raw sample records from all opened counters"), OPT_BOOLEAN('a', "all-cpus", &system_wide, -- cgit v1.2.2 From dd9a9ad5e1e94894433110ccbf492ed60d75ffcb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Jan 2011 14:25:06 -0200 Subject: perf tools: Fix handling of wildcards in tracepoint event selectors It wasn't accounting the ':' when consuming bytes in the the event selector string, so parse_events() would fail in this test: if (!(*str == 0 || *str == ',' || isspace(*str))) return -1; as *str would be pointing to '*', the last character in the '-e' arg in: $ perf record -q -a -D -e sched:sched_* | perf script -i - -s perf-script.py Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5cb6f4bde905..1f4cfe5d32fc 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -555,7 +555,7 @@ static enum event_result parse_tracepoint_event(const char **strp, if (evt_length >= MAX_EVENT_LENGTH) return EVT_FAILED; if (strpbrk(evt_name, "*?")) { - *strp += strlen(sys_name) + evt_length; + *strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */ return parse_multiple_tracepoint_event(sys_name, evt_name, flags); } else { -- cgit v1.2.2 From ad7f4e3f7b966ac09c8f98dbc5024813a1685775 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Jan 2011 18:28:13 -0200 Subject: perf tools: Fix tracepoint id to string perf.data header table It was broken by f006d25 that passed just the event name, not the complete sys:event that it expected to open the /sys/.../sys/sys:event/id file to get the id. Fix it by moving it to after parse_events in cmd_record, as at that point we can just traverse the evsel_list and use evsel->attr.config + event_name(evsel) instead of re-opening the /id file. Reported-by: Franck Bui-Huu Cc: Franck Bui-Huu Cc: Frederic Weisbecker Cc: Han Pingtian Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Zanussi LKML-Reference: <20110117202801.GG2085@ghostprotocols.net> Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 ++ tools/perf/util/parse-events.c | 29 ----------------------------- 2 files changed, 2 insertions(+), 29 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index df6064ad9bf2..fcd29e8af29f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -936,6 +936,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) list_for_each_entry(pos, &evsel_list, node) { if (perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0) goto out_free_fd; + if (perf_header__push_event(pos->attr.config, event_name(pos))) + goto out_free_fd; } event_array = malloc((sizeof(struct pollfd) * MAX_NR_CPUS * MAX_COUNTERS * threads->nr)); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1f4cfe5d32fc..bc2732ee23eb 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -490,32 +490,6 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp, return EVT_HANDLED_ALL; } -static int store_event_type(const char *orgname) -{ - char filename[PATH_MAX], *c; - FILE *file; - int id, n; - - sprintf(filename, "%s/", debugfs_path); - strncat(filename, orgname, strlen(orgname)); - strcat(filename, "/id"); - - c = strchr(filename, ':'); - if (c) - *c = '/'; - - file = fopen(filename, "r"); - if (!file) - return 0; - n = fscanf(file, "%i", &id); - fclose(file); - if (n < 1) { - pr_err("cannot store event ID\n"); - return -EINVAL; - } - return perf_header__push_event(id, orgname); -} - static enum event_result parse_tracepoint_event(const char **strp, struct perf_event_attr *attr) { @@ -559,9 +533,6 @@ static enum event_result parse_tracepoint_event(const char **strp, return parse_multiple_tracepoint_event(sys_name, evt_name, flags); } else { - if (store_event_type(evt_name) < 0) - return EVT_FAILED; - return parse_single_tracepoint_event(sys_name, evt_name, evt_length, attr, strp); } -- cgit v1.2.2 From b2f8fb237e9cc407a02aca401369c15babae35dd Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 21 Jan 2011 16:40:19 +0000 Subject: perf symbols: Fix annotation of thumb code In ARM's Thumb mode the bottom bit of the symbol address is set to mark the function as Thumb; the instructions are in reality 2 or 4 byte on 2 byte alignments, and when the +1 address is used in annotate it causes objdump to disassemble invalid instructions. The patch removes that bottom bit during symbol loading. Many thinks to Dave Martin for comments on an initial version of the patch. (For reference this corresponds to this bug https://bugs.launchpad.net/linux-linaro/+bug/677547 ) Cc: Ingo Molnar Cc: Dave Martin LKML-Reference: <20110121163922.GA31398@davesworkthinkpad> Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 15ccfba8cdf8..e32478effed8 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1161,6 +1161,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, section_name = elf_sec__name(&shdr, secstrs); + /* On ARM, symbols for thumb functions have 1 added to + * the symbol address as a flag - remove it */ + if ((ehdr.e_machine == EM_ARM) && + (map->type == MAP__FUNCTION) && + (sym.st_value & 1)) + --sym.st_value; + if (self->kernel != DSO_TYPE_USER || kmodule) { char dso_name[PATH_MAX]; -- cgit v1.2.2 From ffb5e0fb44d0829021a51f972df90166bc9b700e Mon Sep 17 00:00:00 2001 From: Han Pingtian Date: Thu, 20 Jan 2011 19:47:07 +0800 Subject: perf test: Use cpu_map->[cpu] when setting affinity When some of CPUs are offline: # cat /sys/devices/system/cpu/online 0,6-31 perf test will fail on #3 testcase: 3: detect open syscall event on all cpus: --- start --- perf_evsel__read_on_cpu: expected to intercept 111 calls on cpu 0, got 681 perf_evsel__read_on_cpu: expected to intercept 112 calls on cpu 1, got 117 perf_evsel__read_on_cpu: expected to intercept 113 calls on cpu 2, got 118 perf_evsel__read_on_cpu: expected to intercept 114 calls on cpu 3, got 119 perf_evsel__read_on_cpu: expected to intercept 115 calls on cpu 4, got 120 perf_evsel__read_on_cpu: expected to intercept 116 calls on cpu 5, got 121 perf_evsel__read_on_cpu: expected to intercept 117 calls on cpu 6, got 122 perf_evsel__read_on_cpu: expected to intercept 118 calls on cpu 7, got 123 perf_evsel__read_on_cpu: expected to intercept 119 calls on cpu 8, got 124 perf_evsel__read_on_cpu: expected to intercept 120 calls on cpu 9, got 125 perf_evsel__read_on_cpu: expected to intercept 121 calls on cpu 10, got 126 .... This patch try to use 'cpus->map[cpu]' when setting cpu affinity, and will check the return code of sched_setaffinity() LKML-Reference: <20110120114707.GA11781@hpt.nay.redhat.com> Signed-off-by: Han Pingtian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-test.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index ed5696198d3d..02958d6a807f 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -380,13 +380,18 @@ static int test__open_syscall_event_on_all_cpus(void) for (cpu = 0; cpu < cpus->nr; ++cpu) { unsigned int ncalls = nr_open_calls + cpu; - CPU_SET(cpu, cpu_set); - sched_setaffinity(0, cpu_set_size, cpu_set); + CPU_SET_S(cpus->map[cpu], cpu_set_size, cpu_set); + if (sched_setaffinity(0, cpu_set_size, cpu_set) < 0) { + pr_debug("sched_setaffinity() failed on CPU %d: %s ", + cpus->map[cpu], + strerror(errno)); + goto out_close_fd; + } for (i = 0; i < ncalls; ++i) { fd = open("/etc/passwd", O_RDONLY); close(fd); } - CPU_CLR(cpu, cpu_set); + CPU_CLR_S(cpus->map[cpu], cpu_set_size, cpu_set); } /* @@ -410,7 +415,7 @@ static int test__open_syscall_event_on_all_cpus(void) expected = nr_open_calls + cpu; if (evsel->counts->cpu[cpu].val != expected) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %Ld\n", - expected, cpu, evsel->counts->cpu[cpu].val); + expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); goto out_close_fd; } } -- cgit v1.2.2 From 57b84e53171ce672683faf1cab2e660965a6bdaf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 22 Jan 2011 23:14:20 -0200 Subject: perf test: Fix build on older glibcs Where we don't have CPU_ALLOC & friends. As the tools are being used in older distros where the only allowed change are to replace the kernel, like RHEL4 and 5. Reported-by: Eric Dumazet Cc: Eric Dumazet Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-test.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 02958d6a807f..0e01834a48d0 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -332,8 +332,7 @@ static int test__open_syscall_event_on_all_cpus(void) struct perf_evsel *evsel; struct perf_event_attr attr; unsigned int nr_open_calls = 111, i; - cpu_set_t *cpu_set; - size_t cpu_set_size; + cpu_set_t cpu_set; int id = trace_event__id("sys_enter_open"); if (id < 0) { @@ -353,13 +352,8 @@ static int test__open_syscall_event_on_all_cpus(void) return -1; } - cpu_set = CPU_ALLOC(cpus->nr); - if (cpu_set == NULL) - goto out_thread_map_delete; - - cpu_set_size = CPU_ALLOC_SIZE(cpus->nr); - CPU_ZERO_S(cpu_set_size, cpu_set); + CPU_ZERO(&cpu_set); memset(&attr, 0, sizeof(attr)); attr.type = PERF_TYPE_TRACEPOINT; @@ -367,7 +361,7 @@ static int test__open_syscall_event_on_all_cpus(void) evsel = perf_evsel__new(&attr, 0); if (evsel == NULL) { pr_debug("perf_evsel__new\n"); - goto out_cpu_free; + goto out_thread_map_delete; } if (perf_evsel__open(evsel, cpus, threads) < 0) { @@ -379,9 +373,19 @@ static int test__open_syscall_event_on_all_cpus(void) for (cpu = 0; cpu < cpus->nr; ++cpu) { unsigned int ncalls = nr_open_calls + cpu; + /* + * XXX eventually lift this restriction in a way that + * keeps perf building on older glibc installations + * without CPU_ALLOC. 1024 cpus in 2010 still seems + * a reasonable upper limit tho :-) + */ + if (cpus->map[cpu] >= CPU_SETSIZE) { + pr_debug("Ignoring CPU %d\n", cpus->map[cpu]); + continue; + } - CPU_SET_S(cpus->map[cpu], cpu_set_size, cpu_set); - if (sched_setaffinity(0, cpu_set_size, cpu_set) < 0) { + CPU_SET(cpus->map[cpu], &cpu_set); + if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", cpus->map[cpu], strerror(errno)); @@ -391,7 +395,7 @@ static int test__open_syscall_event_on_all_cpus(void) fd = open("/etc/passwd", O_RDONLY); close(fd); } - CPU_CLR_S(cpus->map[cpu], cpu_set_size, cpu_set); + CPU_CLR(cpus->map[cpu], &cpu_set); } /* @@ -407,6 +411,9 @@ static int test__open_syscall_event_on_all_cpus(void) for (cpu = 0; cpu < cpus->nr; ++cpu) { unsigned int expected; + if (cpus->map[cpu] >= CPU_SETSIZE) + continue; + if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) { pr_debug("perf_evsel__open_read_on_cpu\n"); goto out_close_fd; @@ -425,8 +432,6 @@ out_close_fd: perf_evsel__close_fd(evsel, 1, threads->nr); out_evsel_delete: perf_evsel__delete(evsel); -out_cpu_free: - CPU_FREE(cpu_set); out_thread_map_delete: thread_map__delete(threads); return err; -- cgit v1.2.2 From 9486aa38771661e96fbb51c549b9901b5df609d8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 22 Jan 2011 20:37:02 -0200 Subject: perf tools: Fix 64 bit integer format strings Using %L[uxd] has issues in some architectures, like on ppc64. Fix it by making our 64 bit integers typedefs of stdint.h types and using PRI[ux]64 like, for instance, git does. Reported by Denis Kirjanov that provided a patch for one case, I went and changed all cases. Reported-by: Denis Kirjanov Tested-by: Denis Kirjanov LKML-Reference: <20110120093246.GA8031@hera.kernel.org> Cc: Denis Kirjanov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Pingtian Han Cc: Stephane Eranian Cc: Tom Zanussi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 6 +++--- tools/perf/builtin-kmem.c | 4 ++-- tools/perf/builtin-lock.c | 6 +++--- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-sched.c | 20 ++++++++++---------- tools/perf/builtin-script.c | 6 +++--- tools/perf/builtin-stat.c | 4 ++-- tools/perf/builtin-test.c | 14 +++++++------- tools/perf/builtin-top.c | 9 +++++---- tools/perf/util/event.c | 5 +++-- tools/perf/util/header.c | 4 ++-- tools/perf/util/hist.c | 17 +++++++++-------- tools/perf/util/map.c | 3 ++- tools/perf/util/parse-events.c | 2 +- tools/perf/util/probe-event.c | 2 +- tools/perf/util/session.c | 28 +++++++++++++++------------- tools/perf/util/svghelper.c | 5 +++-- tools/perf/util/symbol.c | 9 +++++---- tools/perf/util/types.h | 10 ++++++---- tools/perf/util/ui/browsers/hists.c | 2 +- tools/perf/util/ui/browsers/map.c | 5 +++-- tools/perf/util/values.c | 10 +++++----- 23 files changed, 93 insertions(+), 82 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index c056cdc06912..8879463807e4 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -212,7 +212,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename) continue; offset = start + i; - sprintf(cmd, "addr2line -e %s %016llx", filename, offset); + sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); fp = popen(cmd, "r"); if (!fp) continue; @@ -270,9 +270,9 @@ static void hist_entry__print_hits(struct hist_entry *self) for (offset = 0; offset < len; ++offset) if (h->ip[offset] != 0) - printf("%*Lx: %Lu\n", BITS_PER_LONG / 2, + printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, sym->start + offset, h->ip[offset]); - printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum); + printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); } static int hist_entry__tty_annotate(struct hist_entry *he) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index def7ddc2fd4f..d97256d65980 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -371,10 +371,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session, addr = data->ptr; if (sym != NULL) - snprintf(buf, sizeof(buf), "%s+%Lx", sym->name, + snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name, addr - map->unmap_ip(map, sym->start)); else - snprintf(buf, sizeof(buf), "%#Lx", addr); + snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr); printf(" %-34s |", buf); printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n", diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index b9c6e5432971..2b36defc5d73 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -782,9 +782,9 @@ static void print_result(void) pr_info("%10u ", st->nr_acquired); pr_info("%10u ", st->nr_contended); - pr_info("%15llu ", st->wait_time_total); - pr_info("%15llu ", st->wait_time_max); - pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ? + pr_info("%15" PRIu64 " ", st->wait_time_total); + pr_info("%15" PRIu64 " ", st->wait_time_max); + pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ? 0 : st->wait_time_min); pr_info("\n"); } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fcd29e8af29f..b2f729fdb317 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -817,7 +817,7 @@ static int __cmd_record(int argc, const char **argv) * Approximate RIP event size: 24 bytes. */ fprintf(stderr, - "[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n", + "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", (double)bytes_written / 1024.0 / 1024.0, output_name, bytes_written / 24); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 75183a4518e6..c27e31f289e6 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -197,7 +197,7 @@ static int process_read_event(event_t *event, struct sample_data *sample __used, event->read.value); } - dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid, + dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, attr ? __event_name(attr->type, attr->config) : "FAIL", event->read.value); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 29e7ffd85690..29acb894e035 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -193,7 +193,7 @@ static void calibrate_run_measurement_overhead(void) } run_measurement_overhead = min_delta; - printf("run measurement overhead: %Ld nsecs\n", min_delta); + printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta); } static void calibrate_sleep_measurement_overhead(void) @@ -211,7 +211,7 @@ static void calibrate_sleep_measurement_overhead(void) min_delta -= 10000; sleep_measurement_overhead = min_delta; - printf("sleep measurement overhead: %Ld nsecs\n", min_delta); + printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta); } static struct sched_atom * @@ -617,13 +617,13 @@ static void test_calibrations(void) burn_nsecs(1e6); T1 = get_nsecs(); - printf("the run test took %Ld nsecs\n", T1-T0); + printf("the run test took %" PRIu64 " nsecs\n", T1 - T0); T0 = get_nsecs(); sleep_nsecs(1e6); T1 = get_nsecs(); - printf("the sleep test took %Ld nsecs\n", T1-T0); + printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0); } #define FILL_FIELD(ptr, field, event, data) \ @@ -816,10 +816,10 @@ replay_switch_event(struct trace_switch_event *switch_event, delta = 0; if (delta < 0) - die("hm, delta: %Ld < 0 ?\n", delta); + die("hm, delta: %" PRIu64 " < 0 ?\n", delta); if (verbose) { - printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n", + printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n", switch_event->prev_comm, switch_event->prev_pid, switch_event->next_comm, switch_event->next_pid, delta); @@ -1048,7 +1048,7 @@ latency_switch_event(struct trace_switch_event *switch_event, delta = 0; if (delta < 0) - die("hm, delta: %Ld < 0 ?\n", delta); + die("hm, delta: %" PRIu64 " < 0 ?\n", delta); sched_out = perf_session__findnew(session, switch_event->prev_pid); @@ -1221,7 +1221,7 @@ static void output_lat_thread(struct work_atoms *work_list) avg = work_list->total_lat / work_list->nb_atoms; - printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", + printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", (double)work_list->total_runtime / 1e6, work_list->nb_atoms, (double)avg / 1e6, (double)work_list->max_lat / 1e6, @@ -1423,7 +1423,7 @@ map_switch_event(struct trace_switch_event *switch_event, delta = 0; if (delta < 0) - die("hm, delta: %Ld < 0 ?\n", delta); + die("hm, delta: %" PRIu64 " < 0 ?\n", delta); sched_out = perf_session__findnew(session, switch_event->prev_pid); @@ -1713,7 +1713,7 @@ static void __cmd_lat(void) } printf(" -----------------------------------------------------------------------------------------\n"); - printf(" TOTAL: |%11.3f ms |%9Ld |\n", + printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", (double)all_runtime/1e6, all_count); printf(" ---------------------------------------------------\n"); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 150a606002eb..b766c2a9ac97 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -77,8 +77,8 @@ static int process_sample_event(event_t *event, struct sample_data *sample, if (session->sample_type & PERF_SAMPLE_RAW) { if (debug_mode) { if (sample->time < last_timestamp) { - pr_err("Samples misordered, previous: %llu " - "this: %llu\n", last_timestamp, + pr_err("Samples misordered, previous: %" PRIu64 + " this: %" PRIu64 "\n", last_timestamp, sample->time); nr_unordered++; } @@ -126,7 +126,7 @@ static int __cmd_script(struct perf_session *session) ret = perf_session__process_events(session, &event_ops); if (debug_mode) - pr_err("Misordered timestamps: %llu\n", nr_unordered); + pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); return ret; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0ff11d9b13be..a482a191a0ca 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -206,8 +206,8 @@ static int read_counter_aggr(struct perf_evsel *counter) update_stats(&ps->res_stats[i], count[i]); if (verbose) { - fprintf(stderr, "%s: %Ld %Ld %Ld\n", event_name(counter), - count[0], count[1], count[2]); + fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + event_name(counter), count[0], count[1], count[2]); } /* diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 0e01834a48d0..5dcdba653d70 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -146,7 +146,7 @@ next_pair: if (llabs(skew) < page_size) continue; - pr_debug("%#Lx: diff end addr for %s v: %#Lx k: %#Lx\n", + pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n", sym->start, sym->name, sym->end, pair->end); } else { struct rb_node *nnd; @@ -168,11 +168,11 @@ detour: goto detour; } - pr_debug("%#Lx: diff name v: %s k: %s\n", + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", sym->start, sym->name, pair->name); } } else - pr_debug("%#Lx: %s not on kallsyms\n", sym->start, sym->name); + pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name); err = -1; } @@ -211,10 +211,10 @@ detour: if (pair->start == pos->start) { pair->priv = 1; - pr_info(" %Lx-%Lx %Lx %s in kallsyms as", + pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", pos->start, pos->end, pos->pgoff, pos->dso->name); if (pos->pgoff != pair->pgoff || pos->end != pair->end) - pr_info(": \n*%Lx-%Lx %Lx", + pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "", pair->start, pair->end, pair->pgoff); pr_info(" %s\n", pair->dso->name); pair->priv = 1; @@ -307,7 +307,7 @@ static int test__open_syscall_event(void) } if (evsel->counts->cpu[0].val != nr_open_calls) { - pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %Ld\n", + pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", nr_open_calls, evsel->counts->cpu[0].val); goto out_close_fd; } @@ -421,7 +421,7 @@ static int test__open_syscall_event_on_all_cpus(void) expected = nr_open_calls + cpu; if (evsel->counts->cpu[cpu].val != expected) { - pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %Ld\n", + pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); goto out_close_fd; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 05344c6210ac..b6998e055767 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -214,7 +215,7 @@ static int parse_source(struct sym_entry *syme) len = sym->end - sym->start; sprintf(command, - "objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s", + "objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s", BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start), BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path); @@ -308,7 +309,7 @@ static void lookup_sym_source(struct sym_entry *syme) struct source_line *line; char pattern[PATTERN_LEN + 1]; - sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4, + sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4, map__rip_2objdump(syme->map, symbol->start)); pthread_mutex_lock(&syme->src->lock); @@ -537,7 +538,7 @@ static void print_sym_table(void) if (nr_counters == 1 || !display_weighted) { struct perf_evsel *first; first = list_entry(evsel_list.next, struct perf_evsel, node); - printf("%Ld", first->attr.sample_period); + printf("%" PRIu64, (uint64_t)first->attr.sample_period); if (freq) printf("Hz "); else @@ -640,7 +641,7 @@ static void print_sym_table(void) percent_color_fprintf(stdout, "%4.1f%%", pcnt); if (verbose) - printf(" %016llx", sym->start); + printf(" %016" PRIx64, sym->start); printf(" %-*.*s", sym_width, sym_width, sym->name); printf(" %-*.*s\n", dso_width, dso_width, dso_width >= syme->map->dso->long_name_len ? diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2302ec051bb4..1478ab4ee222 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -459,7 +459,8 @@ int event__process_comm(event_t *self, struct sample_data *sample __used, int event__process_lost(event_t *self, struct sample_data *sample __used, struct perf_session *session) { - dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost); + dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", + self->lost.id, self->lost.lost); session->hists.stats.total_lost += self->lost.lost; return 0; } @@ -575,7 +576,7 @@ int event__process_mmap(event_t *self, struct sample_data *sample __used, u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; int ret = 0; - dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", + dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n", self->mmap.pid, self->mmap.tid, self->mmap.start, self->mmap.len, self->mmap.pgoff, self->mmap.filename); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 989fa2dee2fd..f6a929e74981 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -798,8 +798,8 @@ static int perf_file_section__process(struct perf_file_section *self, int feat, int fd) { if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) { - pr_debug("Failed to lseek to %Ld offset for feature %d, " - "continuing...\n", self->offset, feat); + pr_debug("Failed to lseek to %" PRIu64 " offset for feature " + "%d, continuing...\n", self->offset, feat); return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c749ba6136a0..32f4f1f2f6e4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -636,13 +636,13 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, } } } else - ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period); + ret = snprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period); if (symbol_conf.show_nr_samples) { if (sep) - ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period); + ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period); else - ret += snprintf(s + ret, size - ret, "%11lld", period); + ret += snprintf(s + ret, size - ret, "%11" PRIu64, period); } if (pair_hists) { @@ -971,7 +971,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip) sym_size = sym->end - sym->start; offset = ip - sym->start; - pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip)); + pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip)); if (offset >= sym_size) return 0; @@ -980,8 +980,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip) h->sum++; h->ip[offset]++; - pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start, - self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]); + pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64 + "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name, + ip, ip - self->ms.sym->start, h->ip[offset]); return 0; } @@ -1132,7 +1133,7 @@ fallback: goto out_free_filename; } - pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__, + pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); @@ -1142,7 +1143,7 @@ fallback: dso, dso->long_name, sym, sym->name); snprintf(command, sizeof(command), - "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand", + "objdump --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), symfs_filename, filename); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 3a7eb6ec0eec..a16ecab5229d 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,5 +1,6 @@ #include "symbol.h" #include +#include #include #include #include @@ -195,7 +196,7 @@ int map__overlap(struct map *l, struct map *r) size_t map__fprintf(struct map *self, FILE *fp) { - return fprintf(fp, " %Lx-%Lx %Lx %s\n", + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", self->start, self->end, self->pgoff, self->dso->name); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index bc2732ee23eb..135f69baf966 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -279,7 +279,7 @@ const char *__event_name(int type, u64 config) static char buf[32]; if (type == PERF_TYPE_RAW) { - sprintf(buf, "raw 0x%llx", config); + sprintf(buf, "raw 0x%" PRIx64, config); return buf; } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 128aaab0aeda..6e29d9c9dccc 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -172,7 +172,7 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, sym = __find_kernel_function_by_name(tp->symbol, &map); if (sym) { addr = map->unmap_ip(map, sym->start + tp->offset); - pr_debug("try to find %s+%ld@%llx\n", tp->symbol, + pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol, tp->offset, addr); ret = find_perf_probe_point((unsigned long)addr, pp); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 313dac2d94ce..105f00bfd555 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -652,10 +652,11 @@ static void callchain__printf(struct sample_data *sample) { unsigned int i; - printf("... chain: nr:%Lu\n", sample->callchain->nr); + printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr); for (i = 0; i < sample->callchain->nr; i++) - printf("..... %2d: %016Lx\n", i, sample->callchain->ips[i]); + printf("..... %2d: %016" PRIx64 "\n", + i, sample->callchain->ips[i]); } static void perf_session__print_tstamp(struct perf_session *session, @@ -672,7 +673,7 @@ static void perf_session__print_tstamp(struct perf_session *session, printf("%u ", sample->cpu); if (session->sample_type & PERF_SAMPLE_TIME) - printf("%Lu ", sample->time); + printf("%" PRIu64 " ", sample->time); } static void dump_event(struct perf_session *session, event_t *event, @@ -681,16 +682,16 @@ static void dump_event(struct perf_session *session, event_t *event, if (!dump_trace) return; - printf("\n%#Lx [%#x]: event: %d\n", file_offset, event->header.size, - event->header.type); + printf("\n%#" PRIx64 " [%#x]: event: %d\n", + file_offset, event->header.size, event->header.type); trace_event(event); if (sample) perf_session__print_tstamp(session, event, sample); - printf("%#Lx [%#x]: PERF_RECORD_%s", file_offset, event->header.size, - event__get_event_name(event->header.type)); + printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, + event->header.size, event__get_event_name(event->header.type)); } static void dump_sample(struct perf_session *session, event_t *event, @@ -699,8 +700,9 @@ static void dump_sample(struct perf_session *session, event_t *event, if (!dump_trace) return; - printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc, - sample->pid, sample->tid, sample->ip, sample->period); + printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 "\n", + event->header.misc, sample->pid, sample->tid, sample->ip, + sample->period); if (session->sample_type & PERF_SAMPLE_CALLCHAIN) callchain__printf(sample); @@ -843,8 +845,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session, { if (ops->lost == event__process_lost && session->hists.stats.total_lost != 0) { - ui__warning("Processed %Lu events and LOST %Lu!\n\n" - "Check IO/CPU overload!\n\n", + ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64 + "!\n\nCheck IO/CPU overload!\n\n", session->hists.stats.total_period, session->hists.stats.total_lost); } @@ -918,7 +920,7 @@ more: if (size == 0 || (skip = perf_session__process_event(self, &event, ops, head)) < 0) { - dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n", + dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", head, event.header.size, event.header.type); /* * assume we lost track of the stream, check alignment, and @@ -1023,7 +1025,7 @@ more: if (size == 0 || perf_session__process_event(session, event, ops, file_pos) < 0) { - dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n", + dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", file_offset + head, event->header.size, event->header.type); /* diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index b3637db025a2..805220afc083 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -12,6 +12,7 @@ * of the License. */ +#include #include #include #include @@ -94,7 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT; fprintf(svgfile, " \n"); - fprintf(svgfile, "\n", svg_page_width, total_height); + fprintf(svgfile, "\n", svg_page_width, total_height); fprintf(svgfile, "\n