From 9ae7d3351aac238eef9646479693105688fd9cc9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 Jan 2012 14:07:23 -0200 Subject: perf tools: Add fprintf methods for thread_map and cpu_map classes For helping with debugging. Cc: David Ahern Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-m06n4rp7pwr6dlzwoq89cl69@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread_map.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/perf/util/thread_map.c') diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index a5df131b77c..894d52f6516 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -62,3 +62,14 @@ void thread_map__delete(struct thread_map *threads) { free(threads); } + +size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) +{ + int i; + size_t printed = fprintf(fp, "%d thread%s: ", + threads->nr, threads->nr > 1 ? "s" : ""); + for (i = 0; i < threads->nr; ++i) + printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]); + + return printed + fprintf(fp, "\n"); +} -- cgit v1.2.3-70-g09d2 From 0d37aa34f8806bb443dd3c8621fd9bdbb50c58bb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 Jan 2012 14:08:15 -0200 Subject: perf tools: Introduce per user view The new --uid command line option will show only the tasks for a given user, using the proc interface to figure out the existing tasks. Kernel work is needed to close races at startup, but this should already be useful in many use cases. Cc: David Ahern Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-bdnspm000gw2l984a2t53o8z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++ tools/perf/Documentation/perf-top.txt | 4 ++ tools/perf/builtin-record.c | 12 +++- tools/perf/builtin-stat.c | 2 +- tools/perf/builtin-test.c | 8 +-- tools/perf/builtin-top.c | 22 ++++++- tools/perf/perf.h | 1 + tools/perf/util/evlist.c | 6 +- tools/perf/util/evlist.h | 2 +- tools/perf/util/hist.h | 1 + tools/perf/util/python.c | 10 ++-- tools/perf/util/thread_map.c | 98 +++++++++++++++++++++++++++++++- tools/perf/util/thread_map.h | 3 +- tools/perf/util/top.c | 3 + tools/perf/util/top.h | 2 + tools/perf/util/ui/browsers/hists.c | 3 + tools/perf/util/usage.c | 39 +++++++++++++ tools/perf/util/util.h | 2 + 18 files changed, 200 insertions(+), 22 deletions(-) (limited to 'tools/perf/util/thread_map.c') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 2937f7e14bb..ff9a66e0d4e 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -58,6 +58,10 @@ OPTIONS --tid=:: Record events on existing thread ID. +-u:: +--uid=:: + Record events in threads owned by uid. Name or number. + -r:: --realtime=:: Collect data with this RT SCHED_FIFO priority. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index b1a5bbbfebe..ab1454ed450 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -78,6 +78,10 @@ Default is to monitor all CPUS. --tid=:: Profile events on existing thread ID. +-u:: +--uid=:: + Record events in threads owned by uid. Name or number. + -r :: --realtime=:: Collect data with this RT SCHED_FIFO priority. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0abfb18b911..32870eef952 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -44,6 +44,7 @@ struct perf_record { struct perf_evlist *evlist; struct perf_session *session; const char *progname; + const char *uid_str; int output; unsigned int page_size; int realtime_prio; @@ -727,6 +728,7 @@ const struct option record_options[] = { OPT_CALLBACK('G', "cgroup", &record.evlist, "name", "monitor event in cgroup name only", parse_cgroups), + OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"), OPT_END() }; @@ -748,7 +750,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 && - !rec->opts.system_wide && !rec->opts.cpu_list) + !rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str) usage_with_options(record_usage, record_options); if (rec->force && rec->append_file) { @@ -788,11 +790,17 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) goto out_symbol_exit; } + rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid, + rec->opts.target_pid); + if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1) + goto out_free_fd; + if (rec->opts.target_pid != -1) rec->opts.target_tid = rec->opts.target_pid; if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid, - rec->opts.target_tid, rec->opts.cpu_list) < 0) + rec->opts.target_tid, rec->opts.uid, + rec->opts.cpu_list) < 0) usage_with_options(record_usage, record_options); list_for_each_entry(pos, &evsel_list->entries, node) { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f5d2a63eba6..459b8620a5d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1201,7 +1201,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) if (target_pid != -1) target_tid = target_pid; - evsel_list->threads = thread_map__new(target_pid, target_tid); + evsel_list->threads = thread_map__new(target_pid, target_tid, UINT_MAX); if (evsel_list->threads == NULL) { pr_err("Problems finding threads of monitor\n"); usage_with_options(stat_usage, options); diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 3854e869dce..3ce709e9746 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -276,7 +276,7 @@ static int test__open_syscall_event(void) return -1; } - threads = thread_map__new(-1, getpid()); + threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); return -1; @@ -342,7 +342,7 @@ static int test__open_syscall_event_on_all_cpus(void) return -1; } - threads = thread_map__new(-1, getpid()); + threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); return -1; @@ -490,7 +490,7 @@ static int test__basic_mmap(void) expected_nr_events[i] = random() % 257; } - threads = thread_map__new(-1, getpid()); + threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); return -1; @@ -1054,7 +1054,7 @@ static int test__PERF_RECORD(void) * we're monitoring, the one forked there. */ err = perf_evlist__create_maps(evlist, opts.target_pid, - opts.target_tid, opts.cpu_list); + opts.target_tid, UINT_MAX, opts.cpu_list); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8f80df89603..e8b033c074f 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -64,7 +64,6 @@ #include #include - void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); @@ -537,10 +536,20 @@ static void perf_top__sort_new_samples(void *arg) static void *display_thread_tui(void *arg) { + struct perf_evsel *pos; struct perf_top *top = arg; const char *help = "For a higher level overview, try: perf top --sort comm,dso"; perf_top__sort_new_samples(top); + + /* + * Initialize the uid_filter_str, in the future the TUI will allow + * Zooming in/out UIDs. For now juse use whatever the user passed + * via --uid. + */ + list_for_each_entry(pos, &top->evlist->entries, node) + pos->hists.uid_filter_str = top->uid_str; + perf_evlist__tui_browse_hists(top->evlist, help, perf_top__sort_new_samples, top, top->delay_secs); @@ -949,7 +958,7 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (top->target_tid != -1) + if (top->target_tid != -1 || top->uid != UINT_MAX) perf_event__synthesize_thread_map(&top->tool, top->evlist->threads, perf_event__process, &top->session->host_machine); @@ -1089,6 +1098,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) .delay_secs = 2, .target_pid = -1, .target_tid = -1, + .uid = UINT_MAX, .freq = 1000, /* 1 KHz */ .sample_id_all_avail = true, .mmap_pages = 128, @@ -1162,6 +1172,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING('u', "uid", &top.uid_str, "user", "user to profile"), OPT_END() }; @@ -1187,6 +1198,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) setup_browser(false); + top.uid = parse_target_uid(top.uid_str, top.target_tid, top.target_pid); + if (top.uid_str != NULL && top.uid == UINT_MAX - 1) + goto out_delete_evlist; + /* CPU and PID are mutually exclusive */ if (top.target_tid > 0 && top.cpu_list) { printf("WARNING: PID switch overriding CPU\n"); @@ -1198,7 +1213,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) top.target_tid = top.target_pid; if (perf_evlist__create_maps(top.evlist, top.target_pid, - top.target_tid, top.cpu_list) < 0) + top.target_tid, top.uid, top.cpu_list) < 0) usage_with_options(top_usage, options); if (!top.evlist->nr_entries && @@ -1262,6 +1277,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) status = __cmd_top(&top); +out_delete_evlist: perf_evlist__delete(top.evlist); return status; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 64f8bee31ce..92af1688bae 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -188,6 +188,7 @@ void pthread__unblock_sigwinch(void); struct perf_record_opts { pid_t target_pid; pid_t target_tid; + uid_t uid; bool call_graph; bool group; bool inherit_stat; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 3f16e08a5c8..a6d50e37625 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -594,14 +594,14 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, } int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, - pid_t target_tid, const char *cpu_list) + pid_t target_tid, uid_t uid, const char *cpu_list) { - evlist->threads = thread_map__new(target_pid, target_tid); + evlist->threads = thread_map__new(target_pid, target_tid, uid); if (evlist->threads == NULL) return -1; - if (cpu_list == NULL && target_tid != -1) + if (uid != UINT_MAX || (cpu_list == NULL && target_tid != -1)) evlist->cpus = cpu_map__dummy_new(); else evlist->cpus = cpu_map__new(cpu_list); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 8922aeed046..9c516607ce2 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -107,7 +107,7 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, } int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, - pid_t target_tid, const char *cpu_list); + pid_t tid, uid_t uid, const char *cpu_list); void perf_evlist__delete_maps(struct perf_evlist *evlist); int perf_evlist__set_filters(struct perf_evlist *evlist); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index f55f0a8d1f8..0d486135d10 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -55,6 +55,7 @@ struct hists { u64 nr_entries; const struct thread *thread_filter; const struct dso *dso_filter; + const char *uid_filter_str; pthread_mutex_t lock; struct events_stats stats; u64 event_stream; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 9dd47a4f259..e03b58a4842 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -425,14 +425,14 @@ struct pyrf_thread_map { static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, PyObject *args, PyObject *kwargs) { - static char *kwlist[] = { "pid", "tid", NULL }; - int pid = -1, tid = -1; + static char *kwlist[] = { "pid", "tid", "uid", NULL }; + int pid = -1, tid = -1, uid = UINT_MAX; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", - kwlist, &pid, &tid)) + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii", + kwlist, &pid, &tid, &uid)) return -1; - pthreads->threads = thread_map__new(pid, tid); + pthreads->threads = thread_map__new(pid, tid, uid); if (pthreads->threads == NULL) return -1; return 0; diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 894d52f6516..3d4b6c5931b 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -1,6 +1,11 @@ #include +#include +#include #include #include +#include +#include +#include #include "thread_map.h" /* Skip "." and ".." directories */ @@ -23,7 +28,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) sprintf(name, "/proc/%d/task", pid); items = scandir(name, &namelist, filter, NULL); if (items <= 0) - return NULL; + return NULL; threads = malloc(sizeof(*threads) + sizeof(pid_t) * items); if (threads != NULL) { @@ -51,10 +56,99 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) return threads; } -struct thread_map *thread_map__new(pid_t pid, pid_t tid) +struct thread_map *thread_map__new_by_uid(uid_t uid) +{ + DIR *proc; + int max_threads = 32, items, i; + char path[256]; + struct dirent dirent, *next, **namelist = NULL; + struct thread_map *threads = malloc(sizeof(*threads) + + max_threads * sizeof(pid_t)); + if (threads == NULL) + goto out; + + proc = opendir("/proc"); + if (proc == NULL) + goto out_free_threads; + + threads->nr = 0; + + while (!readdir_r(proc, &dirent, &next) && next) { + char *end; + bool grow = false; + struct stat st; + pid_t pid = strtol(dirent.d_name, &end, 10); + + if (*end) /* only interested in proper numerical dirents */ + continue; + + snprintf(path, sizeof(path), "/proc/%s", dirent.d_name); + + if (stat(path, &st) != 0) + continue; + + if (st.st_uid != uid) + continue; + + snprintf(path, sizeof(path), "/proc/%d/task", pid); + items = scandir(path, &namelist, filter, NULL); + if (items <= 0) + goto out_free_closedir; + + while (threads->nr + items >= max_threads) { + max_threads *= 2; + grow = true; + } + + if (grow) { + struct thread_map *tmp; + + tmp = realloc(threads, (sizeof(*threads) + + max_threads * sizeof(pid_t))); + if (tmp == NULL) + goto out_free_namelist; + + threads = tmp; + } + + for (i = 0; i < items; i++) + threads->map[threads->nr + i] = atoi(namelist[i]->d_name); + + for (i = 0; i < items; i++) + free(namelist[i]); + free(namelist); + + threads->nr += items; + } + +out_closedir: + closedir(proc); +out: + return threads; + +out_free_threads: + free(threads); + return NULL; + +out_free_namelist: + for (i = 0; i < items; i++) + free(namelist[i]); + free(namelist); + +out_free_closedir: + free(threads); + threads = NULL; + goto out_closedir; +} + +struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) { if (pid != -1) return thread_map__new_by_pid(pid); + + if (tid == -1 && uid != UINT_MAX) + return thread_map__new_by_uid(uid); + return thread_map__new_by_tid(tid); } diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 736ab4a2621..c75ddbaba00 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -11,7 +11,8 @@ struct thread_map { struct thread_map *thread_map__new_by_pid(pid_t pid); struct thread_map *thread_map__new_by_tid(pid_t tid); -struct thread_map *thread_map__new(pid_t pid, pid_t tid); +struct thread_map *thread_map__new_by_uid(uid_t uid); +struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); void thread_map__delete(struct thread_map *threads); size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 500471dffa4..e4370ca2719 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -75,6 +75,9 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) else if (top->target_tid != -1) ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d", top->target_tid); + else if (top->uid_str != NULL) + ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", + top->uid_str); else ret += SNPRINTF(bf + ret, size - ret, " (all"); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index a248f3c2c60..def3e53e0fe 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -24,6 +24,7 @@ struct perf_top { int print_entries, count_filter, delay_secs; int freq; pid_t target_pid, target_tid; + uid_t uid; bool hide_kernel_symbols, hide_user_symbols, zero; bool system_wide; bool use_tui, use_stdio; @@ -45,6 +46,7 @@ struct perf_top { int realtime_prio; int sym_pcnt_filter; const char *sym_filter; + const char *uid_str; }; size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 1212a386a03..7b6669d1f11 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -841,6 +841,9 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, nr_events = convert_unit(nr_events, &unit); printed = snprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name); + if (self->uid_filter_str) + printed += snprintf(bf + printed, size - printed, + ", UID: %s", self->uid_filter_str); if (thread) printed += snprintf(bf + printed, size - printed, ", Thread: %s(%d)", diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index d76d1c0ff98..d0c013934f3 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -7,6 +7,7 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "util.h" +#include "debug.h" static void report(const char *prefix, const char *err, va_list params) { @@ -81,3 +82,41 @@ void warning(const char *warn, ...) warn_routine(warn, params); va_end(params); } + +uid_t parse_target_uid(const char *str, pid_t tid, pid_t pid) +{ + struct passwd pwd, *result; + char buf[1024]; + + if (str == NULL) + return UINT_MAX; + + /* CPU and PID are mutually exclusive */ + if (tid > 0 || pid > 0) { + ui__warning("PID/TID switch overriding UID\n"); + sleep(1); + return UINT_MAX; + } + + getpwnam_r(str, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) { + char *endptr; + int uid = strtol(str, &endptr, 10); + + if (*endptr != '\0') { + ui__error("Invalid user %s\n", str); + return UINT_MAX - 1; + } + + getpwuid_r(uid, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) { + ui__error("Problems obtaining information for user %s\n", + str); + return UINT_MAX - 1; + } + } + + return result->pw_uid; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b9c530cce79..061dbf8c038 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -246,6 +246,8 @@ struct perf_event_attr; void event_attr_init(struct perf_event_attr *attr); +uid_t parse_target_uid(const char *str, pid_t tid, pid_t pid); + #define _STR(x) #x #define STR(x) _STR(x) -- cgit v1.2.3-70-g09d2 From b52956c961be3a04182ae7b776623531601e0fb7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 8 Feb 2012 09:32:52 -0700 Subject: perf tools: Allow multiple threads or processes in record, stat, top Allow a user to collect events for multiple threads or processes using a comma separated list. e.g., collect data on a VM and its vhost thread: perf top -p 21483,21485 perf stat -p 21483,21485 -ddd perf record -p 21483,21485 or monitoring vcpu threads perf top -t 21488,21489 perf stat -t 21488,21489 -ddd perf record -t 21488,21489 Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1328718772-16688-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 +- tools/perf/Documentation/perf-stat.txt | 4 +- tools/perf/Documentation/perf-top.txt | 4 +- tools/perf/builtin-record.c | 10 +-- tools/perf/builtin-stat.c | 31 ++++---- tools/perf/builtin-test.c | 2 - tools/perf/builtin-top.c | 12 ++- tools/perf/perf.h | 4 +- tools/perf/util/evlist.c | 10 +-- tools/perf/util/evlist.h | 4 +- tools/perf/util/evsel.c | 2 +- tools/perf/util/python-ext-sources | 2 + tools/perf/util/thread_map.c | 128 +++++++++++++++++++++++++++++++ tools/perf/util/thread_map.h | 4 + tools/perf/util/top.c | 10 +-- tools/perf/util/top.h | 2 +- tools/perf/util/usage.c | 6 +- tools/perf/util/util.h | 2 +- 18 files changed, 185 insertions(+), 56 deletions(-) (limited to 'tools/perf/util/thread_map.c') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index ff9a66e0d4e..a5766b4b012 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -52,11 +52,11 @@ OPTIONS -p:: --pid=:: - Record events on existing process ID. + Record events on existing process ID (comma separated list). -t:: --tid=:: - Record events on existing thread ID. + Record events on existing thread ID (comma separated list). -u:: --uid=:: diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 8966b9ab201..2fa173b5197 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -35,11 +35,11 @@ OPTIONS child tasks do not inherit counters -p:: --pid=:: - stat events on existing process id + stat events on existing process id (comma separated list) -t:: --tid=:: - stat events on existing thread id + stat events on existing thread id (comma separated list) -a:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index ab1454ed450..4a5680cb242 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -72,11 +72,11 @@ Default is to monitor all CPUS. -p :: --pid=:: - Profile events on existing Process ID. + Profile events on existing Process ID (comma separated list). -t :: --tid=:: - Profile events on existing thread ID. + Profile events on existing thread ID (comma separated list). -u:: --uid=:: diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d6d1c6cdcfe..08ed24b66ff 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -645,8 +645,6 @@ static const char * const record_usage[] = { */ static struct perf_record record = { .opts = { - .target_pid = -1, - .target_tid = -1, .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, @@ -670,9 +668,9 @@ const struct option record_options[] = { parse_events_option), OPT_CALLBACK(0, "filter", &record.evlist, "filter", "event filter", parse_filter), - OPT_INTEGER('p', "pid", &record.opts.target_pid, + OPT_STRING('p', "pid", &record.opts.target_pid, "pid", "record events on existing process id"), - OPT_INTEGER('t', "tid", &record.opts.target_tid, + OPT_STRING('t', "tid", &record.opts.target_tid, "tid", "record events on existing thread id"), OPT_INTEGER('r', "realtime", &record.realtime_prio, "collect data with this RT SCHED_FIFO priority"), @@ -739,7 +737,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 && + if (!argc && !rec->opts.target_pid && !rec->opts.target_tid && !rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str) usage_with_options(record_usage, record_options); @@ -785,7 +783,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1) goto out_free_fd; - if (rec->opts.target_pid != -1) + if (rec->opts.target_pid) rec->opts.target_tid = rec->opts.target_pid; if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d14b37ad763..ea40e4e8b22 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -182,8 +182,8 @@ static int run_count = 1; static bool no_inherit = false; static bool scale = true; static bool no_aggr = false; -static pid_t target_pid = -1; -static pid_t target_tid = -1; +static const char *target_pid; +static const char *target_tid; static pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; @@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel, if (system_wide) return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, group, group_fd); - if (target_pid == -1 && target_tid == -1) { + if (!target_pid && !target_tid) { attr->disabled = 1; attr->enable_on_exec = 1; } @@ -446,7 +446,7 @@ static int run_perf_stat(int argc __used, const char **argv) exit(-1); } - if (target_tid == -1 && target_pid == -1 && !system_wide) + if (!target_tid && !target_pid && !system_wide) evsel_list->threads->map[0] = child_pid; /* @@ -968,14 +968,14 @@ static void print_stat(int argc, const char **argv) if (!csv_output) { fprintf(output, "\n"); fprintf(output, " Performance counter stats for "); - if(target_pid == -1 && target_tid == -1) { + if (!target_pid && !target_tid) { fprintf(output, "\'%s", argv[0]); for (i = 1; i < argc; i++) fprintf(output, " %s", argv[i]); - } else if (target_pid != -1) - fprintf(output, "process id \'%d", target_pid); + } else if (target_pid) + fprintf(output, "process id \'%s", target_pid); else - fprintf(output, "thread id \'%d", target_tid); + fprintf(output, "thread id \'%s", target_tid); fprintf(output, "\'"); if (run_count > 1) @@ -1049,10 +1049,10 @@ static const struct option options[] = { "event filter", parse_filter), OPT_BOOLEAN('i', "no-inherit", &no_inherit, "child tasks do not inherit counters"), - OPT_INTEGER('p', "pid", &target_pid, - "stat events on existing process id"), - OPT_INTEGER('t', "tid", &target_tid, - "stat events on existing thread id"), + OPT_STRING('p', "pid", &target_pid, "pid", + "stat events on existing process id"), + OPT_STRING('t', "tid", &target_tid, "tid", + "stat events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('g', "group", &group, @@ -1190,7 +1190,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - if (!argc && target_pid == -1 && target_tid == -1) + if (!argc && !target_pid && !target_tid) usage_with_options(stat_usage, options); if (run_count <= 0) usage_with_options(stat_usage, options); @@ -1206,10 +1206,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) if (add_default_attributes()) goto out; - if (target_pid != -1) + if (target_pid) target_tid = target_pid; - evsel_list->threads = thread_map__new(target_pid, target_tid, UINT_MAX); + evsel_list->threads = thread_map__new_str(target_pid, + target_tid, UINT_MAX); if (evsel_list->threads == NULL) { pr_err("Problems finding threads of monitor\n"); usage_with_options(stat_usage, options); diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 70c4eb2bdf7..0f151952a77 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -1010,8 +1010,6 @@ realloc: static int test__PERF_RECORD(void) { struct perf_record_opts opts = { - .target_pid = -1, - .target_tid = -1, .no_delay = true, .freq = 10, .mmap_pages = 256, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d869b214ada..94d55cb2048 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -965,7 +965,7 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (top->target_tid != -1 || top->uid != UINT_MAX) + if (top->target_tid || top->uid != UINT_MAX) perf_event__synthesize_thread_map(&top->tool, top->evlist->threads, perf_event__process, &top->session->host_machine); @@ -1103,8 +1103,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) struct perf_top top = { .count_filter = 5, .delay_secs = 2, - .target_pid = -1, - .target_tid = -1, .uid = UINT_MAX, .freq = 1000, /* 1 KHz */ .sample_id_all_avail = true, @@ -1118,9 +1116,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) parse_events_option), OPT_INTEGER('c', "count", &top.default_interval, "event period to sample"), - OPT_INTEGER('p', "pid", &top.target_pid, + OPT_STRING('p', "pid", &top.target_pid, "pid", "profile events on existing process id"), - OPT_INTEGER('t', "tid", &top.target_tid, + OPT_STRING('t', "tid", &top.target_tid, "tid", "profile events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &top.system_wide, "system-wide collection from all CPUs"), @@ -1210,13 +1208,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) goto out_delete_evlist; /* CPU and PID are mutually exclusive */ - if (top.target_tid > 0 && top.cpu_list) { + if (top.target_tid && top.cpu_list) { printf("WARNING: PID switch overriding CPU\n"); sleep(1); top.cpu_list = NULL; } - if (top.target_pid != -1) + if (top.target_pid) top.target_tid = top.target_pid; if (perf_evlist__create_maps(top.evlist, top.target_pid, diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 92af1688bae..deb17dba4a5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -186,8 +186,8 @@ extern const char perf_version_string[]; void pthread__unblock_sigwinch(void); struct perf_record_opts { - pid_t target_pid; - pid_t target_tid; + const char *target_pid; + const char *target_tid; uid_t uid; bool call_graph; bool group; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a57a8cfc5d9..5c61dc57d7c 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -593,15 +593,15 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_per_cpu(evlist, prot, mask); } -int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, - pid_t target_tid, uid_t uid, const char *cpu_list) +int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid, + const char *target_tid, uid_t uid, const char *cpu_list) { - evlist->threads = thread_map__new(target_pid, target_tid, uid); + evlist->threads = thread_map__new_str(target_pid, target_tid, uid); if (evlist->threads == NULL) return -1; - if (uid != UINT_MAX || (cpu_list == NULL && target_tid != -1)) + if (uid != UINT_MAX || (cpu_list == NULL && target_tid)) evlist->cpus = cpu_map__dummy_new(); else evlist->cpus = cpu_map__new(cpu_list); @@ -820,7 +820,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, exit(-1); } - if (!opts->system_wide && opts->target_tid == -1 && opts->target_pid == -1) + if (!opts->system_wide && !opts->target_tid && !opts->target_pid) evlist->threads->map[0] = evlist->workload.pid; close(child_ready_pipe[1]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 1b4282be8fe..21f1c9e57f1 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -106,8 +106,8 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = threads; } -int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, - pid_t tid, uid_t uid, const char *cpu_list); +int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid, + const char *tid, uid_t uid, const char *cpu_list); void perf_evlist__delete_maps(struct perf_evlist *evlist); int perf_evlist__set_filters(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9a11f9edac1..f910f50136d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -130,7 +130,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) attr->mmap = track; attr->comm = track; - if (opts->target_pid == -1 && opts->target_tid == -1 && !opts->system_wide) { + if (!opts->target_pid && !opts->target_tid && !opts->system_wide) { attr->disabled = 1; attr->enable_on_exec = 1; } diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index ff606f482a7..2884e67ee62 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -15,3 +15,5 @@ util/util.c util/xyarray.c util/cgroup.c util/debugfs.c +util/strlist.c +../../lib/rbtree.c diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 3d4b6c5931b..e15983cf077 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -6,6 +6,8 @@ #include #include #include +#include "strlist.h" +#include #include "thread_map.h" /* Skip "." and ".." directories */ @@ -152,6 +154,132 @@ struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) return thread_map__new_by_tid(tid); } +static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) +{ + struct thread_map *threads = NULL, *nt; + char name[256]; + int items, total_tasks = 0; + struct dirent **namelist = NULL; + int i, j = 0; + pid_t pid, prev_pid = INT_MAX; + char *end_ptr; + struct str_node *pos; + struct strlist *slist = strlist__new(false, pid_str); + + if (!slist) + return NULL; + + strlist__for_each(pos, slist) { + pid = strtol(pos->s, &end_ptr, 10); + + if (pid == INT_MIN || pid == INT_MAX || + (*end_ptr != '\0' && *end_ptr != ',')) + goto out_free_threads; + + if (pid == prev_pid) + continue; + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, filter, NULL); + if (items <= 0) + goto out_free_threads; + + total_tasks += items; + nt = realloc(threads, (sizeof(*threads) + + sizeof(pid_t) * total_tasks)); + if (nt == NULL) + goto out_free_threads; + + threads = nt; + + if (threads) { + for (i = 0; i < items; i++) + threads->map[j++] = atoi(namelist[i]->d_name); + threads->nr = total_tasks; + } + + for (i = 0; i < items; i++) + free(namelist[i]); + free(namelist); + + if (!threads) + break; + } + +out: + strlist__delete(slist); + return threads; + +out_free_threads: + free(threads); + threads = NULL; + goto out; +} + +static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +{ + struct thread_map *threads = NULL, *nt; + int ntasks = 0; + pid_t tid, prev_tid = INT_MAX; + char *end_ptr; + struct str_node *pos; + struct strlist *slist; + + /* perf-stat expects threads to be generated even if tid not given */ + if (!tid_str) { + threads = malloc(sizeof(*threads) + sizeof(pid_t)); + if (threads != NULL) { + threads->map[1] = -1; + threads->nr = 1; + } + return threads; + } + + slist = strlist__new(false, tid_str); + if (!slist) + return NULL; + + strlist__for_each(pos, slist) { + tid = strtol(pos->s, &end_ptr, 10); + + if (tid == INT_MIN || tid == INT_MAX || + (*end_ptr != '\0' && *end_ptr != ',')) + goto out_free_threads; + + if (tid == prev_tid) + continue; + + ntasks++; + nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks); + + if (nt == NULL) + goto out_free_threads; + + threads = nt; + threads->map[ntasks - 1] = tid; + threads->nr = ntasks; + } +out: + return threads; + +out_free_threads: + free(threads); + threads = NULL; + goto out; +} + +struct thread_map *thread_map__new_str(const char *pid, const char *tid, + uid_t uid) +{ + if (pid) + return thread_map__new_by_pid_str(pid); + + if (!tid && uid != UINT_MAX) + return thread_map__new_by_uid(uid); + + return thread_map__new_by_tid_str(tid); +} + void thread_map__delete(struct thread_map *threads) { free(threads); diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index c75ddbaba00..7da80f14418 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -13,6 +13,10 @@ struct thread_map *thread_map__new_by_pid(pid_t pid); struct thread_map *thread_map__new_by_tid(pid_t tid); struct thread_map *thread_map__new_by_uid(uid_t uid); struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); + +struct thread_map *thread_map__new_str(const char *pid, + const char *tid, uid_t uid); + void thread_map__delete(struct thread_map *threads); size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index e4370ca2719..09fe579ccaf 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -69,11 +69,11 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) ret += SNPRINTF(bf + ret, size - ret, "], "); - if (top->target_pid != -1) - ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d", + if (top->target_pid) + ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s", top->target_pid); - else if (top->target_tid != -1) - ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d", + else if (top->target_tid) + ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", top->target_tid); else if (top->uid_str != NULL) ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", @@ -85,7 +85,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list); else { - if (top->target_tid != -1) + if (top->target_tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index def3e53e0fe..49eb8481f19 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -23,7 +23,7 @@ struct perf_top { u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; int freq; - pid_t target_pid, target_tid; + const char *target_pid, *target_tid; uid_t uid; bool hide_kernel_symbols, hide_user_symbols, zero; bool system_wide; diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index d0c013934f3..52bb07c6442 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -83,7 +83,7 @@ void warning(const char *warn, ...) va_end(params); } -uid_t parse_target_uid(const char *str, pid_t tid, pid_t pid) +uid_t parse_target_uid(const char *str, const char *tid, const char *pid) { struct passwd pwd, *result; char buf[1024]; @@ -91,8 +91,8 @@ uid_t parse_target_uid(const char *str, pid_t tid, pid_t pid) if (str == NULL) return UINT_MAX; - /* CPU and PID are mutually exclusive */ - if (tid > 0 || pid > 0) { + /* UID and PID are mutually exclusive */ + if (tid || pid) { ui__warning("PID/TID switch overriding UID\n"); sleep(1); return UINT_MAX; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 232d17ef3e6..7917b09430b 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -245,7 +245,7 @@ struct perf_event_attr; void event_attr_init(struct perf_event_attr *attr); -uid_t parse_target_uid(const char *str, pid_t tid, pid_t pid); +uid_t parse_target_uid(const char *str, const char *tid, const char *pid); #define _STR(x) #x #define STR(x) _STR(x) -- cgit v1.2.3-70-g09d2 From 6b1bee9035d430c4b4f586df6df4b3f840e89b5b Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 21 Feb 2012 15:54:25 +0100 Subject: perf tools: fix broken perf record -a mode The following commit: b52956c perf tools: Allow multiple threads or processes in record, stat, top introduced a bug in the thread_map code which caused perf record -a to not setup system-wide monitoring properly. $ taskset -c 1 noploop 1000 & $ perf record -a -C 1 sleep 10 $ perf report -D | tail -20 cycles stats: TOTAL events: 4413 MMAP events: 4025 COMM events: 340 SAMPLE events: 48 Here I was expecting about 10,000 samples and not 48. In system-wide mode, the PID passed to perf_event_open() must be -1 and it was 0. That caused the kernel to setup a per-process event on PID:0. Consequently, the number of samples captured does not correspond to the requested measurement. The following one-liner fixes the problem for me with or without -C. I would also suggest to change the malloc() to something that matches the struct definition. thread_map->map[] is declared as int map[] and not pid_t map[]. If map[] can only contain pids, then change the struct definition. Acked-by: David Ahern Cc: David Ahern Cc: Eric Dumazet Cc: Ingo Molnar Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120221145424.GA6757@quad Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread_map.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/thread_map.c') diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index e15983cf077..84d9bd78200 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -229,7 +229,7 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) if (!tid_str) { threads = malloc(sizeof(*threads) + sizeof(pid_t)); if (threads != NULL) { - threads->map[1] = -1; + threads->map[0] = -1; threads->nr = 1; } return threads; -- cgit v1.2.3-70-g09d2