From 08aa0d1f376e9b966568316bd2019b3c1274d885 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 21 Nov 2011 14:42:47 +0100 Subject: perf tools: Add x86 RDPMC, RDTSC test Implement a simple test for the self-monitoring data from the perf mmap data area control page: 6: x86 rdpmc test: 0: 6053 1: 60053 2: 600059 3: 6000059 4: 60000075 5: 600000247 Ok The counts are expected to increase monotonically - these are recovered via RDPMC, without calling into the kernel. It might be nice to add logic to automagically turn these numbers into OK/FAIL. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian Cc: Arun Sharma Link: http://lkml.kernel.org/n/tip-evf5yii88ljdgmaihccbxxw1@git.kernel.org [ various small improvements ] Signed-off-by: Ingo Molnar --- tools/perf/builtin-test.c | 177 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 175 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 2b9a7f497a20..439b5ed03e64 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -15,6 +15,8 @@ #include "util/thread_map.h" #include "../../include/linux/hw_breakpoint.h" +#include + static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym) { bool *visited = symbol__priv(sym); @@ -1296,6 +1298,173 @@ out: return (err < 0 || errs > 0) ? -1 : 0; } + +#if defined(__x86_64__) || defined(__i386__) + +#define barrier() asm volatile("" ::: "memory") + +static u64 rdpmc(unsigned int counter) +{ + unsigned int low, high; + + asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter)); + + return low | ((u64)high) << 32; +} + +static u64 rdtsc(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} + +static u64 mmap_read_self(void *addr) +{ + struct perf_event_mmap_page *pc = addr; + u32 seq, idx, time_mult = 0, time_shift = 0; + u64 count, cyc = 0, time_offset = 0, enabled, running, delta; + + do { + seq = pc->lock; + barrier(); + + enabled = pc->time_enabled; + running = pc->time_running; + + if (enabled != running) { + cyc = rdtsc(); + time_mult = pc->time_mult; + time_shift = pc->time_shift; + time_offset = pc->time_offset; + } + + idx = pc->index; + count = pc->offset; + if (idx) + count += rdpmc(idx - 1); + + barrier(); + } while (pc->lock != seq); + + if (enabled != running) { + u64 quot, rem; + + quot = (cyc >> time_shift); + rem = cyc & ((1 << time_shift) - 1); + delta = time_offset + quot * time_mult + + ((rem * time_mult) >> time_shift); + + enabled += delta; + if (idx) + running += delta; + + quot = count / running; + rem = count % running; + count = quot * enabled + (rem * enabled) / running; + } + + return count; +} + +/* + * If the RDPMC instruction faults then signal this back to the test parent task: + */ +static void segfault_handler(int sig __used, siginfo_t *info __used, void *uc __used) +{ + exit(-1); +} + +static int __test__rdpmc(void) +{ + long page_size = sysconf(_SC_PAGE_SIZE); + volatile int tmp = 0; + u64 i, loops = 1000; + int n; + int fd; + void *addr; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .exclude_kernel = 1, + }; + u64 delta_sum = 0; + struct sigaction sa; + + sigfillset(&sa.sa_mask); + sa.sa_sigaction = segfault_handler; + sigaction(SIGSEGV, &sa, NULL); + + fprintf(stderr, "\n\n"); + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd < 0) { + die("Error: sys_perf_event_open() syscall returned " + "with %d (%s)\n", fd, strerror(errno)); + } + + addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); + if (addr == (void *)(-1)) { + die("Error: mmap() syscall returned " + "with (%s)\n", strerror(errno)); + } + + for (n = 0; n < 6; n++) { + u64 stamp, now, delta; + + stamp = mmap_read_self(addr); + + for (i = 0; i < loops; i++) + tmp++; + + now = mmap_read_self(addr); + loops *= 10; + + delta = now - stamp; + fprintf(stderr, "%14d: %14Lu\n", n, (long long)delta); + + delta_sum += delta; + } + + munmap(addr, page_size); + close(fd); + + fprintf(stderr, " "); + + if (!delta_sum) + return -1; + + return 0; +} + +static int test__rdpmc(void) +{ + int status = 0; + int wret = 0; + int ret; + int pid; + + pid = fork(); + if (pid < 0) + return -1; + + if (!pid) { + ret = __test__rdpmc(); + + exit(ret); + } + + wret = waitpid(pid, &status, 0); + if (wret < 0 || status) + return -1; + + return 0; +} + +#endif + static struct test { const char *desc; int (*func)(void); @@ -1320,6 +1489,12 @@ static struct test { .desc = "parse events tests", .func = test__parse_events, }, +#if defined(__x86_64__) || defined(__i386__) + { + .desc = "x86 rdpmc test", + .func = test__rdpmc, + }, +#endif { .desc = "Validate PERF_RECORD_* events & perf_sample fields", .func = test__PERF_RECORD, @@ -1412,7 +1587,5 @@ int cmd_test(int argc, const char **argv, const char *prefix __used) if (symbol__init() < 0) return -1; - setup_pager(); - return __cmd_test(argc, argv); } -- cgit v1.2.3-70-g09d2 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/cpumap.c | 11 +++++++++++ tools/perf/util/cpumap.h | 4 ++++ tools/perf/util/thread_map.c | 11 +++++++++++ tools/perf/util/thread_map.h | 4 ++++ 4 files changed, 30 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 6893eec693ab..adc72f09914d 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -166,6 +166,17 @@ out: return cpus; } +size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) +{ + int i; + size_t printed = fprintf(fp, "%d cpu%s: ", + map->nr, map->nr > 1 ? "s" : ""); + for (i = 0; i < map->nr; ++i) + printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]); + + return printed + fprintf(fp, "\n"); +} + struct cpu_map *cpu_map__dummy_new(void) { struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 072c0a374794..c41518573c6a 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -1,6 +1,8 @@ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H +#include + struct cpu_map { int nr; int map[]; @@ -10,4 +12,6 @@ struct cpu_map *cpu_map__new(const char *cpu_list); struct cpu_map *cpu_map__dummy_new(void); void cpu_map__delete(struct cpu_map *map); +size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index a5df131b77c3..894d52f65166 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"); +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 3cb907311409..736ab4a26210 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -2,6 +2,7 @@ #define __PERF_THREAD_MAP_H #include +#include struct thread_map { int nr; @@ -12,4 +13,7 @@ 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); void thread_map__delete(struct thread_map *threads); + +size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); + #endif /* __PERF_THREAD_MAP_H */ -- 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') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 2937f7e14bb7..ff9a66e0d4e4 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 b1a5bbbfebef..ab1454ed450f 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 0abfb18b911f..32870eef952f 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 f5d2a63eba66..459b8620a5d9 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 3854e869dce1..3ce709e97462 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 8f80df896038..e8b033c074f9 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 64f8bee31ced..92af1688bae4 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 3f16e08a5c8d..a6d50e376257 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 8922aeed0467..9c516607ce20 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 f55f0a8d1f81..0d486135d10f 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 9dd47a4f2596..e03b58a48424 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 894d52f65166..3d4b6c5931b9 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 736ab4a26210..c75ddbaba005 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 500471dffa4f..e4370ca27193 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 a248f3c2c60d..def3e53e0fe0 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 1212a386a033..7b6669d1f11f 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 d76d1c0ff98f..d0c013934f30 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 b9c530cce79a..061dbf8c038d 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 9ea811973d49a1df0be04ff6e4df449e4fca4fb5 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 18 Jan 2012 13:28:13 +0000 Subject: perf bench: Make "default" memcpy() selection actually use glibc's implementation Since arch/x86/lib/memcpy_64.S implements not only __memcpy, but also memcpy, without further precautions this function will get chose by the static linker for resolving all references, and hence the "default" measurement didn't really measure anything else than the "x86-64-unrolled" one. Fix this by renaming (through the pre-processor) the conflicting symbol. On my Westmere system, the glibc variant turns out to require about 4% less instructions, but 15% more cycles for the default 1Mb block size measured. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4F16D6FD020000780006D72F@nat28.tlf.novell.com Signed-off-by: Jan Beulich Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/mem-memcpy-x86-64-asm.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index a57b66e853c2..384b60788ab9 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -1,2 +1,2 @@ - +#define memcpy MEMCPY /* don't hide glibc's memcpy() */ #include "../../../arch/x86/lib/memcpy_64.S" -- cgit v1.2.3-70-g09d2 From 800eb01484b3ca1eaf4eb5186df13fb24de2db19 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 18 Jan 2012 13:28:56 +0000 Subject: perf bench: Also allow measuring alternative memcpy implementations Intended to be able to support the current selection of the preferred memcpy() implementation, this patch adds the ability to also measure the two alternative implementations, again by way of using some pre-processsor replacement. While on my Westmere system this proves that the movsb based variant is worse than the movsq based one (since the ERMS feature isn't there), it also shows that here for the default as well as small sizes the unrolled variant outperforms the movsq one. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4F16D728020000780006D732@nat28.tlf.novell.com Signed-off-by: Jan Beulich Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/mem-memcpy-x86-64-asm-def.h | 8 ++++++++ tools/perf/bench/mem-memcpy-x86-64-asm.S | 4 ++++ 2 files changed, 12 insertions(+) (limited to 'tools') diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index d588b87696fc..d66ab799b35f 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -2,3 +2,11 @@ MEMCPY_FN(__memcpy, "x86-64-unrolled", "unrolled memcpy() in arch/x86/lib/memcpy_64.S") + +MEMCPY_FN(memcpy_c, + "x86-64-movsq", + "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") + +MEMCPY_FN(memcpy_c_e, + "x86-64-movsb", + "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 384b60788ab9..a20780bd0771 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -1,2 +1,6 @@ #define memcpy MEMCPY /* don't hide glibc's memcpy() */ +#define altinstr_replacement text +#define globl p2align 4; .globl +#define Lmemcpy_c globl memcpy_c; memcpy_c +#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e #include "../../../arch/x86/lib/memcpy_64.S" -- cgit v1.2.3-70-g09d2 From be3de80dc2e671d9ee15e69fe9cd84d2b71e2225 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 24 Jan 2012 10:03:22 -0200 Subject: perf bench: Also allow measuring memset() This simply clones the respective memcpy() implementation. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/4F16D743020000780006D735@nat28.tlf.novell.com Signed-off-by: Jan Beulich Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 4 +- tools/perf/bench/bench.h | 1 + tools/perf/bench/mem-memset-arch.h | 12 ++ tools/perf/bench/mem-memset-x86-64-asm-def.h | 12 ++ tools/perf/bench/mem-memset-x86-64-asm.S | 6 + tools/perf/bench/mem-memset.c | 291 +++++++++++++++++++++++++++ tools/perf/builtin-bench.c | 3 + tools/perf/util/include/asm/dwarf2.h | 4 +- 8 files changed, 331 insertions(+), 2 deletions(-) create mode 100644 tools/perf/bench/mem-memset-arch.h create mode 100644 tools/perf/bench/mem-memset-x86-64-asm-def.h create mode 100644 tools/perf/bench/mem-memset-x86-64-asm.S create mode 100644 tools/perf/bench/mem-memset.c (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index ac86d67b636e..599031ac69ac 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -61,7 +61,7 @@ ifeq ($(ARCH),x86_64) ifeq (${IS_X86_64}, 1) RAW_ARCH := x86_64 ARCH_CFLAGS := -DARCH_X86_64 - ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S + ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S endif endif @@ -362,8 +362,10 @@ BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o ifeq ($(RAW_ARCH),x86_64) BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o +BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o +BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o BUILTIN_OBJS += $(OUTPUT)builtin-diff.o BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index f7781c6267c0..a09bece6dad2 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -4,6 +4,7 @@ extern int bench_sched_messaging(int argc, const char **argv, const char *prefix); extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used); +extern int bench_mem_memset(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h new file mode 100644 index 000000000000..a040fa77665b --- /dev/null +++ b/tools/perf/bench/mem-memset-arch.h @@ -0,0 +1,12 @@ + +#ifdef ARCH_X86_64 + +#define MEMSET_FN(fn, name, desc) \ + extern void *fn(void *, int, size_t); + +#include "mem-memset-x86-64-asm-def.h" + +#undef MEMSET_FN + +#endif + diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h new file mode 100644 index 000000000000..a71dff97c1f5 --- /dev/null +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -0,0 +1,12 @@ + +MEMSET_FN(__memset, + "x86-64-unrolled", + "unrolled memset() in arch/x86/lib/memset_64.S") + +MEMSET_FN(memset_c, + "x86-64-stosq", + "movsq-based memset() in arch/x86/lib/memset_64.S") + +MEMSET_FN(memset_c_e, + "x86-64-stosb", + "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S new file mode 100644 index 000000000000..cb9217063776 --- /dev/null +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -0,0 +1,6 @@ +#define memset MEMSET /* don't hide glibc's memset() */ +#define altinstr_replacement text +#define globl p2align 4; .globl +#define Lmemset_c globl memset_c; memset_c +#define Lmemset_c_e globl memset_c_e; memset_c_e +#include "../../../arch/x86/lib/memset_64.S" diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c new file mode 100644 index 000000000000..9c0c6f0cba9b --- /dev/null +++ b/tools/perf/bench/mem-memset.c @@ -0,0 +1,291 @@ +/* + * mem-memset.c + * + * memset: Simple memory set in various ways + * + * Trivial clone of mem-memcpy.c. + */ +#include + +#include "../perf.h" +#include "../util/util.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "mem-memset-arch.h" + +#include +#include +#include +#include +#include + +#define K 1024 + +static const char *length_str = "1MB"; +static const char *routine = "default"; +static bool use_clock; +static int clock_fd; +static bool only_prefault; +static bool no_prefault; + +static const struct option options[] = { + OPT_STRING('l', "length", &length_str, "1MB", + "Specify length of memory to copy. " + "available unit: B, MB, GB (upper and lower)"), + OPT_STRING('r', "routine", &routine, "default", + "Specify routine to copy"), + OPT_BOOLEAN('c', "clock", &use_clock, + "Use CPU clock for measuring"), + OPT_BOOLEAN('o', "only-prefault", &only_prefault, + "Show only the result with page faults before memset()"), + OPT_BOOLEAN('n', "no-prefault", &no_prefault, + "Show only the result without page faults before memset()"), + OPT_END() +}; + +typedef void *(*memset_t)(void *, int, size_t); + +struct routine { + const char *name; + const char *desc; + memset_t fn; +}; + +static const struct routine routines[] = { + { "default", + "Default memset() provided by glibc", + memset }, +#ifdef ARCH_X86_64 + +#define MEMSET_FN(fn, name, desc) { name, desc, fn }, +#include "mem-memset-x86-64-asm-def.h" +#undef MEMSET_FN + +#endif + + { NULL, + NULL, + NULL } +}; + +static const char * const bench_mem_memset_usage[] = { + "perf bench mem memset ", + NULL +}; + +static struct perf_event_attr clock_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES +}; + +static void init_clock(void) +{ + clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + + if (clock_fd < 0 && errno == ENOSYS) + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + else + BUG_ON(clock_fd < 0); +} + +static u64 get_clock(void) +{ + int ret; + u64 clk; + + ret = read(clock_fd, &clk, sizeof(u64)); + BUG_ON(ret != sizeof(u64)); + + return clk; +} + +static double timeval2double(struct timeval *ts) +{ + return (double)ts->tv_sec + + (double)ts->tv_usec / (double)1000000; +} + +static void alloc_mem(void **dst, size_t length) +{ + *dst = zalloc(length); + if (!dst) + die("memory allocation failed - maybe length is too large?\n"); +} + +static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) +{ + u64 clock_start = 0ULL, clock_end = 0ULL; + void *dst = NULL; + + alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + clock_start = get_clock(); + fn(dst, 0, len); + clock_end = get_clock(); + + free(dst); + return clock_end - clock_start; +} + +static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) +{ + struct timeval tv_start, tv_end, tv_diff; + void *dst = NULL; + + alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + BUG_ON(gettimeofday(&tv_start, NULL)); + fn(dst, 0, len); + BUG_ON(gettimeofday(&tv_end, NULL)); + + timersub(&tv_end, &tv_start, &tv_diff); + + free(dst); + return (double)((double)len / timeval2double(&tv_diff)); +} + +#define pf (no_prefault ? 0 : 1) + +#define print_bps(x) do { \ + if (x < K) \ + printf(" %14lf B/Sec", x); \ + else if (x < K * K) \ + printf(" %14lfd KB/Sec", x / K); \ + else if (x < K * K * K) \ + printf(" %14lf MB/Sec", x / K / K); \ + else \ + printf(" %14lf GB/Sec", x / K / K / K); \ + } while (0) + +int bench_mem_memset(int argc, const char **argv, + const char *prefix __used) +{ + int i; + size_t len; + double result_bps[2]; + u64 result_clock[2]; + + argc = parse_options(argc, argv, options, + bench_mem_memset_usage, 0); + + if (use_clock) + init_clock(); + + len = (size_t)perf_atoll((char *)length_str); + + result_clock[0] = result_clock[1] = 0ULL; + result_bps[0] = result_bps[1] = 0.0; + + if ((s64)len <= 0) { + fprintf(stderr, "Invalid length:%s\n", length_str); + return 1; + } + + /* same to without specifying either of prefault and no-prefault */ + if (only_prefault && no_prefault) + only_prefault = no_prefault = false; + + for (i = 0; routines[i].name; i++) { + if (!strcmp(routines[i].name, routine)) + break; + } + if (!routines[i].name) { + printf("Unknown routine:%s\n", routine); + printf("Available routines...\n"); + for (i = 0; routines[i].name; i++) { + printf("\t%s ... %s\n", + routines[i].name, routines[i].desc); + } + return 1; + } + + if (bench_format == BENCH_FORMAT_DEFAULT) + printf("# Copying %s Bytes ...\n\n", length_str); + + if (!only_prefault && !no_prefault) { + /* show both of results */ + if (use_clock) { + result_clock[0] = + do_memset_clock(routines[i].fn, len, false); + result_clock[1] = + do_memset_clock(routines[i].fn, len, true); + } else { + result_bps[0] = + do_memset_gettimeofday(routines[i].fn, + len, false); + result_bps[1] = + do_memset_gettimeofday(routines[i].fn, + len, true); + } + } else { + if (use_clock) { + result_clock[pf] = + do_memset_clock(routines[i].fn, + len, only_prefault); + } else { + result_bps[pf] = + do_memset_gettimeofday(routines[i].fn, + len, only_prefault); + } + } + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + if (!only_prefault && !no_prefault) { + if (use_clock) { + printf(" %14lf Clock/Byte\n", + (double)result_clock[0] + / (double)len); + printf(" %14lf Clock/Byte (with prefault)\n ", + (double)result_clock[1] + / (double)len); + } else { + print_bps(result_bps[0]); + printf("\n"); + print_bps(result_bps[1]); + printf(" (with prefault)\n"); + } + } else { + if (use_clock) { + printf(" %14lf Clock/Byte", + (double)result_clock[pf] + / (double)len); + } else + print_bps(result_bps[pf]); + + printf("%s\n", only_prefault ? " (with prefault)" : ""); + } + break; + case BENCH_FORMAT_SIMPLE: + if (!only_prefault && !no_prefault) { + if (use_clock) { + printf("%lf %lf\n", + (double)result_clock[0] / (double)len, + (double)result_clock[1] / (double)len); + } else { + printf("%lf %lf\n", + result_bps[0], result_bps[1]); + } + } else { + if (use_clock) { + printf("%lf\n", (double)result_clock[pf] + / (double)len); + } else + printf("%lf\n", result_bps[pf]); + } + break; + default: + /* reaching this means there's some disaster: */ + die("unknown format: %d\n", bench_format); + break; + } + + return 0; +} diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index fcb96269852a..b0e74ab2d7a2 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -52,6 +52,9 @@ static struct bench_suite mem_suites[] = { { "memcpy", "Simple memory copy in various ways", bench_mem_memcpy }, + { "memset", + "Simple memory set in various ways", + bench_mem_memset }, suite_all, { NULL, NULL, diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h index bb4198e7837a..afe38199e922 100644 --- a/tools/perf/util/include/asm/dwarf2.h +++ b/tools/perf/util/include/asm/dwarf2.h @@ -2,10 +2,12 @@ #ifndef PERF_DWARF2_H #define PERF_DWARF2_H -/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */ +/* dwarf2.h ... dummy header file for including arch/x86/lib/mem{cpy,set}_64.S */ #define CFI_STARTPROC #define CFI_ENDPROC +#define CFI_REMEMBER_STATE +#define CFI_RESTORE_STATE #endif /* PERF_DWARF2_H */ -- cgit v1.2.3-70-g09d2 From e3e877e79b7c6a322f9f628e87052c13581238cc Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 18 Jan 2012 13:29:59 +0000 Subject: perf bench: Allow passing an iteration count to "bench mem mem{cpy,set}" "perf stat ... perf bench mem mem..." is pretty meaningless when using small block sizes (as the overhead of the invocation of each test run basically hides the actual test result in the noise). Repeating the actually interesting function's invocation a number of times allows the results to become meaningful. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4F16D767020000780006D738@nat28.tlf.novell.com Signed-off-by: Jan Beulich Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/mem-memcpy.c | 11 +++++++++-- tools/perf/bench/mem-memset.c | 11 +++++++++-- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index db82021f4b91..6ad2b1c6b27b 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -24,6 +24,7 @@ static const char *length_str = "1MB"; static const char *routine = "default"; +static int iterations = 1; static bool use_clock; static int clock_fd; static bool only_prefault; @@ -35,6 +36,8 @@ static const struct option options[] = { "available unit: B, MB, GB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", "Specify routine to copy"), + OPT_INTEGER('i', "iterations", &iterations, + "repeat memcpy() invocation this number of times"), OPT_BOOLEAN('c', "clock", &use_clock, "Use CPU clock for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, @@ -121,6 +124,7 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) { u64 clock_start = 0ULL, clock_end = 0ULL; void *src = NULL, *dst = NULL; + int i; alloc_mem(&src, &dst, len); @@ -128,7 +132,8 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) fn(dst, src, len); clock_start = get_clock(); - fn(dst, src, len); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); clock_end = get_clock(); free(src); @@ -140,6 +145,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) { struct timeval tv_start, tv_end, tv_diff; void *src = NULL, *dst = NULL; + int i; alloc_mem(&src, &dst, len); @@ -147,7 +153,8 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) fn(dst, src, len); BUG_ON(gettimeofday(&tv_start, NULL)); - fn(dst, src, len); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); BUG_ON(gettimeofday(&tv_end, NULL)); timersub(&tv_end, &tv_start, &tv_diff); diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index 9c0c6f0cba9b..59d4933eff44 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -24,6 +24,7 @@ static const char *length_str = "1MB"; static const char *routine = "default"; +static int iterations = 1; static bool use_clock; static int clock_fd; static bool only_prefault; @@ -35,6 +36,8 @@ static const struct option options[] = { "available unit: B, MB, GB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", "Specify routine to copy"), + OPT_INTEGER('i', "iterations", &iterations, + "repeat memset() invocation this number of times"), OPT_BOOLEAN('c', "clock", &use_clock, "Use CPU clock for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, @@ -117,6 +120,7 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) { u64 clock_start = 0ULL, clock_end = 0ULL; void *dst = NULL; + int i; alloc_mem(&dst, len); @@ -124,7 +128,8 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) fn(dst, -1, len); clock_start = get_clock(); - fn(dst, 0, len); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); clock_end = get_clock(); free(dst); @@ -135,6 +140,7 @@ static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) { struct timeval tv_start, tv_end, tv_diff; void *dst = NULL; + int i; alloc_mem(&dst, len); @@ -142,7 +148,8 @@ static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) fn(dst, -1, len); BUG_ON(gettimeofday(&tv_start, NULL)); - fn(dst, 0, len); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); BUG_ON(gettimeofday(&tv_end, NULL)); timersub(&tv_end, &tv_start, &tv_diff); -- cgit v1.2.3-70-g09d2 From 2ef1ea3826434bdebe17b2941356a8f764ff5fcd Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 17 Jan 2012 13:41:01 -0800 Subject: perf tools: Fix broken build by defining _GNU_SOURCE in Makefile When building on my Debian/mips system, util/util.c fails to build because commit 1aed2671738785e8f5aea663a6fda91aa7ef59b5 (perf kvm: Do guest-only counting by default) indirectly includes stdio.h before the feature selection in util.h is done. This prevents _GNU_SOURCE in util.h from enabling the declaration of getline(), from now second inclusion of stdio.h, and the build is broken. There is another breakage in util/evsel.c caused by include ordering, but I didn't fully track down the commit that caused it. The root cause of all this is an inconsistent definition of _GNU_SOURCE, so I move the definition into the Makefile so that it is passed to all invocations of the compiler and used uniformly for all system header files. All other #define and #undef of _GNU_SOURCE are removed as they cause conflicts with the definition passed to the compiler. All the features.h definitions (_LARGEFILE64_SOURCE _FILE_OFFSET_BITS=64 and _GNU_SOURCE) are needed by the python glue code too, so they are moved to BASIC_CFLAGS, and the misleading comments about BASIC_CFLAGS are removed. This gives me a clean build on x86_64 (fc12) and mips (Debian). Cc: David Daney Cc: Ingo Molnar Cc: Joerg Roedel Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1326836461-11952-1-git-send-email-ddaney.cavm@gmail.com Signed-off-by: David Daney Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 7 ++----- tools/perf/builtin-probe.c | 2 -- tools/perf/util/probe-event.c | 2 -- tools/perf/util/symbol.c | 1 - tools/perf/util/trace-event-parse.c | 3 +-- tools/perf/util/ui/browsers/hists.c | 2 -- tools/perf/util/ui/helpline.c | 1 - tools/perf/util/util.h | 1 - 8 files changed, 3 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 599031ac69ac..d64f5819a380 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -104,7 +104,7 @@ endif CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_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_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE ALL_LDFLAGS = $(LDFLAGS) STRIP ?= strip @@ -168,10 +168,7 @@ endif ### --- END CONFIGURATION SECTION --- -# Those must not be GNU-specific; they are shared with perl/ which may -# be built by a different compiler. (Note that this is an artifact now -# but it still might be nice to keep that distinction.) -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include +BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = # Guard against environment variables diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 59d43abfbfec..fb8566181f27 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -20,7 +20,6 @@ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * */ -#define _GNU_SOURCE #include #include #include @@ -31,7 +30,6 @@ #include #include -#undef _GNU_SOURCE #include "perf.h" #include "builtin.h" #include "util/util.h" diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index eb25900e2211..29cb65459811 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,7 +19,6 @@ * */ -#define _GNU_SOURCE #include #include #include @@ -33,7 +32,6 @@ #include #include -#undef _GNU_SOURCE #include "util.h" #include "event.h" #include "string.h" diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 215d50f2042e..0975438c3e72 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,4 +1,3 @@ -#define _GNU_SOURCE #include #include #include diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 6c164dc9ee95..1a8d4dc4f386 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -21,14 +21,13 @@ * The parts for function graph printing was taken and modified from the * Linux Kernel that were written by Frederic Weisbecker. */ -#define _GNU_SOURCE + #include #include #include #include #include -#undef _GNU_SOURCE #include "../perf.h" #include "util.h" #include "trace-event.h" diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 7b6669d1f11f..bfba0490c098 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -1,6 +1,4 @@ -#define _GNU_SOURCE #include -#undef _GNU_SOURCE #include "../libslang.h" #include #include diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c index 6ef3c5691762..4f48f5901b30 100644 --- a/tools/perf/util/ui/helpline.c +++ b/tools/perf/util/ui/helpline.c @@ -1,4 +1,3 @@ -#define _GNU_SOURCE #include #include #include diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 061dbf8c038d..232d17ef3e60 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -40,7 +40,6 @@ #define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) #define _ALL_SOURCE 1 -#define _GNU_SOURCE 1 #define _BSD_SOURCE 1 #define HAS_BOOL -- cgit v1.2.3-70-g09d2 From a844d1ef09872a8b8c66d431edd1b8a943e51c7a Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 20 Jan 2012 17:43:54 +0530 Subject: perf probe: Usability fixes Ingo pointed out few perf probe usability related errors during his review of uprobes. Since these issues are independent of uprobes, fixing them in a separate patch. Suggested-by: Ingo Molnar Acked-by: Masami Hiramatsu Cc: Masami Hiramatsu Link: http://lkml.kernel.org/r/20120120121354.GL15447@linux.vnet.ibm.com Signed-off-by: Srikar Dronamraju Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 29cb65459811..b9bbdd236357 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1729,7 +1729,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, } ret = 0; - printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":"); + printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; if (pev->event) @@ -1784,7 +1784,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret >= 0) { /* Show how to use the event. */ - printf("\nYou can now use it on all perf tools, such as:\n\n"); + printf("\nYou can now use it in all perf tools, such as:\n\n"); printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } @@ -1959,7 +1959,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) goto error; } - printf("Remove event: %s\n", ent->s); + printf("Removed event: %s\n", ent->s); return 0; error: pr_warning("Failed to delete event: %s\n", strerror(-ret)); -- cgit v1.2.3-70-g09d2 From f8f4b2872295dca88339ec0c403b2217b1197353 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Fri, 20 Jan 2012 10:49:12 +0100 Subject: perf tools: Fix strlen() bug in perf_event__synthesize_event_type() The event_type record has a max length for the event name. It's called MAX_EVENT_NAME. The name may be truncated to fit the max length. But the header.size still reflects the original name length. If that length is > MAX_EVENT_NAME, then the header.size field is bogus. Fix this by using the length of the name after the potential truncation. Cc: David Ahern Cc: Ingo Molnar Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120120094912.GA4882@quad Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 3e7e0b09c12c..ecd7f4dd7eea 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2105,7 +2105,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool, strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(name); + size = strlen(ev.event_type.event_type.name); size = ALIGN(size, sizeof(u64)); ev.event_type.header.size = sizeof(ev.event_type) - (sizeof(ev.event_type.event_type.name) - size); -- cgit v1.2.3-70-g09d2 From f9d36996564f91c517b75b02942015f7e09a6574 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Wed, 25 Jan 2012 15:20:40 +0100 Subject: perf evsel: Fix spelling typo Correct spelling "unsuported" to "unsupported" in tools/peft/util/evsel.c Cc: Peter Zijlstra Cc: standby24x7@gmail.com Cc: trivial@kernel.org Link: http://lkml.kernel.org/r/1327500312-9520-1-git-send-email-standby24x7@gmail.com Signed-off-by: Masanari Iida Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 667f3b78bb2c..dcfefab53e00 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -535,7 +535,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_READ) { - fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n"); + fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n"); return -1; } -- cgit v1.2.3-70-g09d2 From 547a92e0aedb88129e7fbd804697a11949de2e5a Mon Sep 17 00:00:00 2001 From: Akihiro Nagai Date: Mon, 30 Jan 2012 13:42:57 +0900 Subject: perf script: Unify the expressions indicating "unknown" The perf script command uses various expressions to indicate "unknown". It is unfriendly for user scripts to parse it. So, this patch unifies the expressions to "[unknown]". Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20120130044257.2384.62905.stgit@linux3 Signed-off-by: Akihiro Nagai Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 20 ++++++-------------- tools/perf/util/map.c | 12 ++++++++++++ tools/perf/util/map.h | 1 + tools/perf/util/session.c | 35 ++++++++++------------------------- tools/perf/util/symbol.c | 12 ++++++++++++ tools/perf/util/symbol.h | 1 + 6 files changed, 42 insertions(+), 39 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index bb68ddf257b7..add13ec15977 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -300,7 +300,7 @@ static void print_sample_start(struct perf_sample *sample, } else evname = __event_name(attr->type, attr->config); - printf("%s: ", evname ? evname : "(unknown)"); + printf("%s: ", evname ? evname : "[unknown]"); } } @@ -323,7 +323,6 @@ static void print_sample_addr(union perf_event *event, { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - const char *symname, *dsoname; printf("%16" PRIx64, sample->addr); @@ -343,21 +342,14 @@ static void print_sample_addr(union perf_event *event, al.sym = map__find_symbol(al.map, al.addr, NULL); if (PRINT_FIELD(SYM)) { - if (al.sym && al.sym->name) - symname = al.sym->name; - else - symname = ""; - - printf(" %16s", symname); + printf(" "); + symbol__fprintf_symname(al.sym, stdout); } if (PRINT_FIELD(DSO)) { - if (al.map && al.map->dso && al.map->dso->name) - dsoname = al.map->dso->name; - else - dsoname = ""; - - printf(" (%s)", dsoname); + printf(" ("); + map__fprintf_dsoname(al.map, stdout); + printf(")"); } } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 316aa0ab7122..11079607105b 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -212,6 +212,18 @@ size_t map__fprintf(struct map *self, FILE *fp) self->start, self->end, self->pgoff, self->dso->name); } +size_t map__fprintf_dsoname(struct map *map, FILE *fp) +{ + const char *dsoname; + + if (map && map->dso && map->dso->name) + dsoname = map->dso->name; + else + dsoname = "[unknown]"; + + return fprintf(fp, "%s", dsoname); +} + /* * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN. * map->dso->adjust_symbols==1 for ET_EXEC-like cases. diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 2b8017f8a930..b100c20b7f94 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -118,6 +118,7 @@ void map__delete(struct map *self); struct map *map__clone(struct map *self); int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *self, FILE *fp); +size_t map__fprintf_dsoname(struct map *map, FILE *fp); int map__load(struct map *self, symbol_filter_t filter); struct symbol *map__find_symbol(struct map *self, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index b5ca2558c7bb..e5334a976536 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1296,7 +1296,6 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, int print_sym, int print_dso) { struct addr_location al; - const char *symname, *dsoname; struct callchain_cursor *cursor = &evsel->hists.callchain_cursor; struct callchain_cursor_node *node; @@ -1324,20 +1323,13 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, printf("\t%16" PRIx64, node->ip); if (print_sym) { - if (node->sym && node->sym->name) - symname = node->sym->name; - else - symname = ""; - - printf(" %s", symname); + printf(" "); + symbol__fprintf_symname(node->sym, stdout); } if (print_dso) { - if (node->map && node->map->dso && node->map->dso->name) - dsoname = node->map->dso->name; - else - dsoname = ""; - - printf(" (%s)", dsoname); + printf(" ("); + map__fprintf_dsoname(al.map, stdout); + printf(")"); } printf("\n"); @@ -1347,21 +1339,14 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, } else { printf("%16" PRIx64, sample->ip); if (print_sym) { - if (al.sym && al.sym->name) - symname = al.sym->name; - else - symname = ""; - - printf(" %s", symname); + printf(" "); + symbol__fprintf_symname(al.sym, stdout); } if (print_dso) { - if (al.map && al.map->dso && al.map->dso->name) - dsoname = al.map->dso->name; - else - dsoname = ""; - - printf(" (%s)", dsoname); + printf(" ("); + map__fprintf_dsoname(al.map, stdout); + printf(")"); } } } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 0975438c3e72..b580fa82911a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -263,6 +263,18 @@ static size_t symbol__fprintf(struct symbol *sym, FILE *fp) sym->name); } +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) +{ + const char *symname; + + if (sym && sym->name) + symname = sym->name; + else + symname = "[unknown]"; + + return fprintf(fp, "%s", symname); +} + void dso__set_long_name(struct dso *dso, char *name) { if (name == NULL) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 123c2e14353e..d349c7a00b04 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -241,6 +241,7 @@ void machines__destroy_guest_kernel_maps(struct rb_root *machines); int symbol__init(void); void symbol__exit(void); +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); -- cgit v1.2.3-70-g09d2 From 9558259697b827106b464648e850e568e0b0c931 Mon Sep 17 00:00:00 2001 From: Akihiro Nagai Date: Mon, 30 Jan 2012 13:43:09 +0900 Subject: perf script: Print branch_from and branch_to of BTS events BTS records branch_from_addr and branch_to_addr in IP and ADDR field in perf_sample. This patch enables to print them in following format, () => () Sample: ffffffff814675d2 irq_return ([kernel.kallsyms]) => 3f03e016b0 _start (/lib64/ld-2.14.so) ffffffff814675d2 irq_return ([kernel.kallsyms]) => 3f03e016b0 _start (/lib64/ld-2.14.so) 3f03e016b3 _start (/lib64/ld-2.14.so) => 3f03e04b80 _dl_start (/lib64/ld-2.14.so) ffffffff814675d2 irq_return ([kernel.kallsyms]) => 3f03e04b80 _dl_start (/lib64/ld-2.14.so) ffffffff814675d2 irq_return ([kernel.kallsyms]) => 3f03e04ba6 _dl_start (/lib64/ld-2.14.so) ffffffff814675d2 irq_return ([kernel.kallsyms]) => 3f03e04bad _dl_start (/lib64/ld-2.14.so) 3f03e04bfb _dl_start (/lib64/ld-2.14.so) => 3f03e04c1d _dl_start (/lib64/ld-2.14.so) [snip] Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20120130044309.2384.44252.stgit@linux3 Signed-off-by: Akihiro Nagai Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index add13ec15977..414d49ad83de 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -304,6 +304,13 @@ static void print_sample_start(struct perf_sample *sample, } } +static bool is_bts_event(struct perf_event_attr *attr) +{ + return ((attr->type == PERF_TYPE_HARDWARE) && + (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && + (attr->sample_period == 1)); +} + static bool sample_addr_correlates_sym(struct perf_event_attr *attr) { if ((attr->type == PERF_TYPE_SOFTWARE) && @@ -312,6 +319,9 @@ static bool sample_addr_correlates_sym(struct perf_event_attr *attr) (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))) return true; + if (is_bts_event(attr)) + return true; + return false; } @@ -353,6 +363,33 @@ static void print_sample_addr(union perf_event *event, } } +static void print_sample_bts(union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine, + struct thread *thread) +{ + struct perf_event_attr *attr = &evsel->attr; + + /* print branch_from information */ + if (PRINT_FIELD(IP)) { + if (!symbol_conf.use_callchain) + printf(" "); + else + printf("\n"); + perf_event__print_ip(event, sample, machine, evsel, + PRINT_FIELD(SYM), PRINT_FIELD(DSO)); + } + + printf(" => "); + + /* print branch_to information */ + if (PRINT_FIELD(ADDR)) + print_sample_addr(event, sample, machine, thread, attr); + + printf("\n"); +} + static void process_event(union perf_event *event __unused, struct perf_sample *sample, struct perf_evsel *evsel, @@ -366,6 +403,11 @@ static void process_event(union perf_event *event __unused, print_sample_start(sample, thread, attr); + if (is_bts_event(attr)) { + print_sample_bts(event, sample, evsel, machine, thread); + return; + } + if (PRINT_FIELD(TRACE)) print_trace_event(sample->cpu, sample->raw_data, sample->raw_size); -- cgit v1.2.3-70-g09d2 From a978f2ab4166a84c77d0f846f59690f2a892d058 Mon Sep 17 00:00:00 2001 From: Akihiro Nagai Date: Mon, 30 Jan 2012 13:43:15 +0900 Subject: perf script: Add the offset field specifier Add the offset field specifier 'symoff' to show the offset from the symbols in the output of perf-script. We can get the more detailed address information. Output sample: ffffffff81467612 irq_return+0x0 => 301ec016b0 _start+0x0 ffffffff81467612 irq_return+0x0 => 301ec016b0 _start+0x0 301ec016b3 _start+0x3 => 301ec04b70 _dl_start+0x0 ffffffff81467612 irq_return+0x0 => 301ec04b70 _dl_start+0x0 ffffffff81467612 irq_return+0x0 => 301ec04b96 _dl_start+0x26 ffffffff81467612 irq_return+0x0 => 301ec04b9d _dl_start+0x2d 301ec04beb _dl_start+0x7b => 301ec04c0d _dl_start+0x9d 301ec04c11 _dl_start+0xa1 => 301ec04bf0 _dl_start+0x80 [snip] Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20120130044314.2384.67094.stgit@linux3 Signed-off-by: Akihiro Nagai Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 2 +- tools/perf/builtin-script.c | 23 +++++++++++++++++++---- tools/perf/util/session.c | 8 ++++++-- tools/perf/util/session.h | 2 +- tools/perf/util/symbol.c | 24 +++++++++++++++++------- tools/perf/util/symbol.h | 2 ++ 6 files changed, 46 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 2f6cef43da25..228c7bb0f0dd 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -115,7 +115,7 @@ OPTIONS -f:: --fields:: Comma separated list of fields to print. Options are: - comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr. + comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 414d49ad83de..752d4018d06d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -40,6 +40,7 @@ enum perf_output_field { PERF_OUTPUT_SYM = 1U << 8, PERF_OUTPUT_DSO = 1U << 9, PERF_OUTPUT_ADDR = 1U << 10, + PERF_OUTPUT_SYMOFFSET = 1U << 11, }; struct output_option { @@ -57,6 +58,7 @@ struct output_option { {.str = "sym", .field = PERF_OUTPUT_SYM}, {.str = "dso", .field = PERF_OUTPUT_DSO}, {.str = "addr", .field = PERF_OUTPUT_ADDR}, + {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET}, }; /* default set to maintain compatibility with current format */ @@ -193,6 +195,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "to symbols.\n"); return -EINVAL; } + if (PRINT_FIELD(SYMOFFSET) && !PRINT_FIELD(SYM)) { + pr_err("Display of offsets requested but symbol is not" + "selected.\n"); + return -EINVAL; + } if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { pr_err("Display of DSO requested but neither sample IP nor " "sample address\nis selected. Hence, no addresses to convert " @@ -353,7 +360,10 @@ static void print_sample_addr(union perf_event *event, if (PRINT_FIELD(SYM)) { printf(" "); - symbol__fprintf_symname(al.sym, stdout); + if (PRINT_FIELD(SYMOFFSET)) + symbol__fprintf_symname_offs(al.sym, &al, stdout); + else + symbol__fprintf_symname(al.sym, stdout); } if (PRINT_FIELD(DSO)) { @@ -378,7 +388,8 @@ static void print_sample_bts(union perf_event *event, else printf("\n"); perf_event__print_ip(event, sample, machine, evsel, - PRINT_FIELD(SYM), PRINT_FIELD(DSO)); + PRINT_FIELD(SYM), PRINT_FIELD(DSO), + PRINT_FIELD(SYMOFFSET)); } printf(" => "); @@ -421,7 +432,8 @@ static void process_event(union perf_event *event __unused, else printf("\n"); perf_event__print_ip(event, sample, machine, evsel, - PRINT_FIELD(SYM), PRINT_FIELD(DSO)); + PRINT_FIELD(SYM), PRINT_FIELD(DSO), + PRINT_FIELD(SYMOFFSET)); } printf("\n"); @@ -1131,7 +1143,10 @@ static const struct option options[] = { OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), OPT_CALLBACK('f', "fields", NULL, "str", - "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr", + "comma separated output fields prepend with 'type:'. " + "Valid types: hw,sw,trace,raw. " + "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," + "addr,symoff", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e5334a976536..552c1c50eea1 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1293,7 +1293,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso) + int print_sym, int print_dso, int print_symoffset) { struct addr_location al; struct callchain_cursor *cursor = &evsel->hists.callchain_cursor; @@ -1340,7 +1340,11 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, printf("%16" PRIx64, sample->ip); if (print_sym) { printf(" "); - symbol__fprintf_symname(al.sym, stdout); + if (print_symoffset) + symbol__fprintf_symname_offs(al.sym, &al, + stdout); + else + symbol__fprintf_symname(al.sym, stdout); } if (print_dso) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 37bc38381fb6..c8d90178e7de 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -147,7 +147,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso); + int print_sym, int print_dso, int print_symoffset); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index b580fa82911a..fc6e12fe4b44 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -263,16 +263,26 @@ static size_t symbol__fprintf(struct symbol *sym, FILE *fp) sym->name); } -size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, FILE *fp) { - const char *symname; + unsigned long offset; + size_t length; - if (sym && sym->name) - symname = sym->name; - else - symname = "[unknown]"; + if (sym && sym->name) { + length = fprintf(fp, "%s", sym->name); + if (al) { + offset = al->addr - sym->start; + length += fprintf(fp, "+0x%lx", offset); + } + return length; + } else + return fprintf(fp, "[unknown]"); +} - return fprintf(fp, "%s", symname); +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) +{ + return symbol__fprintf_symname_offs(sym, NULL, fp); } void dso__set_long_name(struct dso *dso, char *name) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index d349c7a00b04..ba909c9970e2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -241,6 +241,8 @@ void machines__destroy_guest_kernel_maps(struct rb_root *machines); int symbol__init(void); void symbol__exit(void); +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); -- cgit v1.2.3-70-g09d2 From 0bc8d20580af74c9a8a39c200e269261e5cded05 Mon Sep 17 00:00:00 2001 From: Akihiro Nagai Date: Mon, 30 Jan 2012 13:43:20 +0900 Subject: perf script: Add option resolving vmlinux path Add the option get the path of [kernel.kallsyms]. Specify '--show-kernel-path' option to use this function. This patch enables other applications to use this output easily. Without --show-kernel-path option ffffffff81467612 irq_return ([kernel.kallsyms]) ffffffff81467612 irq_return ([kernel.kallsyms]) 7f24fc02a6b3 _start (/lib64/ld-2.14.so) [snip] With --show-kernel-path option ffffffff81467612 irq_return (/lib/modules/3.2.0+/build/vmlinux) ffffffff81467612 irq_return (/lib/modules/3.2.0+/build/vmlinux) 7f24fc02a6b3 _start (/lib64/ld-2.14.so) [snip] Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20120130044320.2384.73322.stgit@linux3 Signed-off-by: Akihiro Nagai Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 3 +++ tools/perf/builtin-script.c | 3 +++ tools/perf/util/map.c | 9 ++++++--- tools/perf/util/symbol.h | 1 + 4 files changed, 13 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 228c7bb0f0dd..e9cbfcddfa3f 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -200,6 +200,9 @@ OPTIONS It currently includes: cpu and numa topology of the host system. It can only be used with the perf script report mode. +--show-kernel-path:: + Try to resolve the path of [kernel.kallsyms] + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 752d4018d06d..d4ce733b9eba 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1155,6 +1155,9 @@ static const struct option options[] = { "only display events for these comms"), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), + OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, + "Show the path of [kernel.kallsyms]"), + OPT_END() }; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 11079607105b..dea6d1c1a954 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -216,9 +216,12 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) { const char *dsoname; - if (map && map->dso && map->dso->name) - dsoname = map->dso->name; - else + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } else dsoname = "[unknown]"; return fprintf(fp, "%s", dsoname); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ba909c9970e2..2a683d4fc918 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -70,6 +70,7 @@ struct symbol_conf { unsigned short priv_size; unsigned short nr_events; bool try_vmlinux_path, + show_kernel_path, use_modules, sort_by_name, show_nr_samples, -- cgit v1.2.3-70-g09d2 From 008953dc6a3164b7ec2be2684a8fad1e636d5648 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 30 Jan 2012 11:50:37 +0100 Subject: perf top: Fix number of samples displayed In recent versions of perf top, pressing the 'e' key to change the number of displayed samples had no effect. The number of samples was still dictated by the size of the terminal (stdio mode). That was quite annoying because typically only the first dozen samples really matter. This patch fixes this. Cc: David Ahern Cc: Ingo Molnar Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120130105037.GA5160@quad Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e8b033c074f9..d869b214ada2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -88,8 +88,6 @@ void get_term_dimensions(struct winsize *ws) static void perf_top__update_print_entries(struct perf_top *top) { - top->print_entries = top->winsize.ws_row; - if (top->print_entries > 9) top->print_entries -= 9; } @@ -99,6 +97,13 @@ static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *ar struct perf_top *top = arg; get_term_dimensions(&top->winsize); + if (!top->print_entries + || (top->print_entries+4) > top->winsize.ws_row) { + top->print_entries = top->winsize.ws_row; + } else { + top->print_entries += 4; + top->winsize.ws_row = top->print_entries; + } perf_top__update_print_entries(top); } @@ -452,8 +457,10 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) }; perf_top__sig_winch(SIGWINCH, NULL, top); sigaction(SIGWINCH, &act, NULL); - } else + } else { + perf_top__sig_winch(SIGWINCH, NULL, top); signal(SIGWINCH, SIG_DFL); + } break; case 'E': if (top->evlist->nr_entries > 1) { -- cgit v1.2.3-70-g09d2 From d1eec3ecaef083affaf3210246b01b6e80d3a44e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 29 Jan 2012 17:55:56 +0900 Subject: perf lock: Document lock info subcommand The commit 26242d859c9be ("perf lock: Add "info" subcommand for dumping misc information") added the subcommand but missed documentation. Add it. Also update stale 'trace' subcommand to 'script'. Cc: Hitoshi Mitake Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1327827356-8786-5-git-send-email-namhyung@gmail.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-lock.txt | 20 +++++++++++++++++--- tools/perf/builtin-lock.c | 4 ++-- 2 files changed, 19 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index d6b2a4f2108b..c7f5f55634ac 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -8,7 +8,7 @@ perf-lock - Analyze lock events SYNOPSIS -------- [verse] -'perf lock' {record|report|trace} +'perf lock' {record|report|script|info} DESCRIPTION ----------- @@ -20,10 +20,13 @@ and statistics with this 'perf lock' command. produces the file "perf.data" which contains tracing results of lock events. - 'perf lock trace' shows raw lock events. - 'perf lock report' reports statistical data. + 'perf lock script' shows raw lock events. + + 'perf lock info' shows metadata like threads or addresses + of lock instances. + COMMON OPTIONS -------------- @@ -47,6 +50,17 @@ REPORT OPTIONS Sorting key. Possible values: acquired (default), contended, wait_total, wait_max, wait_min. +INFO OPTIONS +------------ + +-t:: +--threads:: + dump thread list in perf.data + +-m:: +--map:: + dump map of lock instances (address:name table) + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 2296c391d0f5..12c814838993 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -922,12 +922,12 @@ static const struct option info_options[] = { OPT_BOOLEAN('t', "threads", &info_threads, "dump thread list in perf.data"), OPT_BOOLEAN('m', "map", &info_map, - "map of lock instances (name:address table)"), + "map of lock instances (address:name table)"), OPT_END() }; static const char * const lock_usage[] = { - "perf lock [] {record|trace|report}", + "perf lock [] {record|report|script|info}", NULL }; -- cgit v1.2.3-70-g09d2 From d30d4a080d195892091ad7d014fc9293cc08ea0f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 29 Jan 2012 17:55:55 +0900 Subject: perf tools: Remove unnecessary ctype.h inclusion There are unnecessary #include out there, and they might cause a nasty build failure in some environment. As we already have most of ctype macros in util.h, just get rid of them. A few of exceptions are util/symbol.c which needs isupper() macro util.h doesn't provide and perl scripting support code which includes ctype.h internally. Suggested-by: Ingo Molnar Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1327827356-8786-4-git-send-email-namhyung@gmail.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/mem-memcpy.c | 1 - tools/perf/bench/mem-memset.c | 1 - tools/perf/util/probe-finder.c | 1 - tools/perf/util/scripting-engines/trace-event-python.c | 1 - tools/perf/util/trace-event-parse.c | 1 - tools/perf/util/trace-event-read.c | 1 - tools/perf/util/trace-event-scripting.c | 1 - tools/perf/util/ui/browsers/map.c | 2 +- 8 files changed, 1 insertion(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 6ad2b1c6b27b..71557225bf92 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -5,7 +5,6 @@ * * Written by Hitoshi Mitake */ -#include #include "../perf.h" #include "../util/util.h" diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index 59d4933eff44..e9079185bd72 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -5,7 +5,6 @@ * * Trivial clone of mem-memcpy.c. */ -#include #include "../perf.h" #include "../util/util.h" diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 5d732621a462..67dc4aed721c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 0b2a48783172..c2623c6f9b51 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include "../../perf.h" diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 1a8d4dc4f386..e0a4f652f289 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include "../perf.h" diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index f55cc3a765a1..b9592e0de8d7 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include "../perf.h" diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index a3fdf55f317b..18ae6c1831d3 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include "../perf.h" diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c index 6905bcc8be2d..eca6575abfd0 100644 --- a/tools/perf/util/ui/browsers/map.c +++ b/tools/perf/util/ui/browsers/map.c @@ -3,9 +3,9 @@ #include #include #include -#include #include #include +#include "../../util.h" #include "../../debug.h" #include "../../symbol.h" #include "../browser.h" -- cgit v1.2.3-70-g09d2 From cfeb1d90a1b1db96383b48888cb7a5f10ca12e12 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Jan 2012 14:43:21 -0200 Subject: perf python: Use attr.watermark in twatch.py We want to be woken up for every PERF_RECORD_ event, attr.wakeup_events is only for PERF_RECORD_SAMPLE, so also use attr.watermark = 1 to fix that. Suggested-by: Peter Zijlstra 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-v3lnpwgrr8mllcr3ntduuqvc@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/python/twatch.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py index df638c438a9f..b11cca584238 100755 --- a/tools/perf/python/twatch.py +++ b/tools/perf/python/twatch.py @@ -19,7 +19,7 @@ def main(): cpus = perf.cpu_map() threads = perf.thread_map() evsel = perf.evsel(task = 1, comm = 1, mmap = 0, - wakeup_events = 1, sample_period = 1, + wakeup_events = 1, watermark = 1, sample_id_all = 1, sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID) evsel.open(cpus = cpus, threads = threads); -- cgit v1.2.3-70-g09d2 From 0529bc1fe1e3e509a2fc06fe887b0c76b1eb01f9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 27 Jan 2012 15:34:20 +0100 Subject: perf evlist: Make splice_list_tail method public Making perf_evlist__splice_list_tail globaly accessible. It is used in the upcomming paches. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Corey Ashford Link: http://lkml.kernel.org/r/1327674868-10486-2-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 6 +++--- tools/perf/util/evlist.h | 5 +++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a6d50e376257..a57a8cfc5d90 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -97,9 +97,9 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) ++evlist->nr_entries; } -static void perf_evlist__splice_list_tail(struct perf_evlist *evlist, - struct list_head *list, - int nr_entries) +void perf_evlist__splice_list_tail(struct perf_evlist *evlist, + struct list_head *list, + int nr_entries) { list_splice_tail(list, &evlist->entries); evlist->nr_entries += nr_entries; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 9c516607ce20..1b4282be8fe7 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -117,4 +117,9 @@ u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist); bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist); bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist); + +void perf_evlist__splice_list_tail(struct perf_evlist *evlist, + struct list_head *list, + int nr_entries); + #endif /* __PERF_EVLIST_H */ -- cgit v1.2.3-70-g09d2 From 946d863cc0d2262080c8101c8e6299974e449fe3 Mon Sep 17 00:00:00 2001 From: John Kacur Date: Wed, 1 Feb 2012 23:16:31 +0100 Subject: perf tools: Remove distclean from Makefile help output distclean as an alias for clean was removed from the perf Makefile by commit a3d1ee10d1bf4520af3d44c1aa6cd46956ec4fd7 However, that commit neglected to remove it from the help output of the perf Makefile, which could result in a user trying the following. $ cd tools/perf/ $ make help | grep distclean distclean - alias to clean $ make distclean make: *** No rule to make target `distclean'. Stop. This patch removes it from the Makefile help output. Link: http://lkml.kernel.org/r/1328134591-19851-1-git-send-email-jkacur@redhat.com Signed-off-by: John Kacur Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 1 - 1 file changed, 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index d64f5819a380..64df5de12ca8 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -794,7 +794,6 @@ help: @echo ' quick-install-html - install the html documentation quickly' @echo '' @echo 'Perf maintainer targets:' - @echo ' distclean - alias to clean' @echo ' clean - clean all binary objects and build output' doc: -- cgit v1.2.3-70-g09d2 From 4eced2347c447c9409877368fc52478c356b4767 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Thu, 2 Feb 2012 19:50:40 +0530 Subject: perf probe: Rename target_module to target This is a precursor patch that modifies names that refer to kernel/module to also refer to user space names. Cc: Ananth N Mavinakayanahalli Cc: Andi Kleen Cc: Andrew Morton Cc: Anton Arapov Cc: Christoph Hellwig Cc: Ingo Molnar Cc: Jim Keniston Cc: Linus Torvalds Cc: Linux-mm Cc: Masami Hiramatsu Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Roland McGrath Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20120202142040.5967.64156.sendpatchset@srdronam.in.ibm.com Signed-off-by: Srikar Dronamraju Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-probe.c | 12 ++++++------ tools/perf/util/probe-event.c | 26 +++++++++++++------------- 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index fb8566181f27..4935c09dd5b5 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -58,7 +58,7 @@ static struct { struct perf_probe_event events[MAX_PROBES]; struct strlist *dellist; struct line_range line_range; - const char *target_module; + const char *target; int max_probe_points; struct strfilter *filter; } params; @@ -246,7 +246,7 @@ static const struct option options[] = { "file", "vmlinux pathname"), OPT_STRING('s', "source", &symbol_conf.source_prefix, "directory", "path to kernel source"), - OPT_STRING('m', "module", ¶ms.target_module, + OPT_STRING('m', "module", ¶ms.target, "modname|path", "target module name (for online) or path (for offline)"), #endif @@ -333,7 +333,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) if (!params.filter) params.filter = strfilter__new(DEFAULT_FUNC_FILTER, NULL); - ret = show_available_funcs(params.target_module, + ret = show_available_funcs(params.target, params.filter); strfilter__delete(params.filter); if (ret < 0) @@ -354,7 +354,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) usage_with_options(probe_usage, options); } - ret = show_line_range(¶ms.line_range, params.target_module); + ret = show_line_range(¶ms.line_range, params.target); if (ret < 0) pr_err(" Error: Failed to show lines. (%d)\n", ret); return ret; @@ -371,7 +371,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) ret = show_available_vars(params.events, params.nevents, params.max_probe_points, - params.target_module, + params.target, params.filter, params.show_ext_vars); strfilter__delete(params.filter); @@ -393,7 +393,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) if (params.nevents) { ret = add_perf_probe_events(params.events, params.nevents, params.max_probe_points, - params.target_module, + params.target, params.force_add); if (ret < 0) { pr_err(" Error: Failed to add events. (%d)\n", ret); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b9bbdd236357..c1a513e56764 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -273,10 +273,10 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs, - int max_tevs, const char *module) + int max_tevs, const char *target) { bool need_dwarf = perf_probe_event_need_dwarf(pev); - struct debuginfo *dinfo = open_debuginfo(module); + struct debuginfo *dinfo = open_debuginfo(target); int ntevs, ret = 0; if (!dinfo) { @@ -295,9 +295,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("find %d probe_trace_events.\n", ntevs); - if (module) + if (target) ret = add_module_to_probe_trace_events(*tevs, ntevs, - module); + target); return ret < 0 ? ret : ntevs; } @@ -1796,14 +1796,14 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, static int convert_to_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs, - int max_tevs, const char *module) + int max_tevs, const char *target) { struct symbol *sym; int ret = 0, i; struct probe_trace_event *tev; /* Convert perf_probe_event with debuginfo */ - ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, module); + ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); if (ret != 0) return ret; /* Found in debuginfo or got an error */ @@ -1819,8 +1819,8 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, goto error; } - if (module) { - tev->point.module = strdup(module); + if (target) { + tev->point.module = strdup(target); if (tev->point.module == NULL) { ret = -ENOMEM; goto error; @@ -1884,7 +1884,7 @@ struct __event_package { }; int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, - int max_tevs, const char *module, bool force_add) + int max_tevs, const char *target, bool force_add) { int i, j, ret; struct __event_package *pkgs; @@ -1907,7 +1907,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, ret = convert_to_probe_trace_events(pkgs[i].pev, &pkgs[i].tevs, max_tevs, - module); + target); if (ret < 0) goto end; pkgs[i].ntevs = ret; @@ -2063,7 +2063,7 @@ static int filter_available_functions(struct map *map __unused, return 1; } -int show_available_funcs(const char *module, struct strfilter *_filter) +int show_available_funcs(const char *target, struct strfilter *_filter) { struct map *map; int ret; @@ -2074,9 +2074,9 @@ int show_available_funcs(const char *module, struct strfilter *_filter) if (ret < 0) return ret; - map = kernel_get_module_map(module); + map = kernel_get_module_map(target); if (!map) { - pr_err("Failed to find %s map.\n", (module) ? : "kernel"); + pr_err("Failed to find %s map.\n", (target) ? : "kernel"); return -EINVAL; } available_func_filter = _filter; -- cgit v1.2.3-70-g09d2 From 781ba9d2ed9df07dbb413fb5ee80ef7d353841c9 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 15 Dec 2011 17:32:40 +0100 Subject: perf record: Make feature initialization generic Loop over all features to enable it instead of explicitly enabling every single feature. Reducing duplicate code and making it more robust to later changes e.g. when adding more features. Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1323966762-8574-3-git-send-email-robert.richter@amd.com Signed-off-by: Robert Richter Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 28 +++++++++------------------- tools/perf/util/header.h | 1 + 2 files changed, 10 insertions(+), 19 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 32870eef952f..f8d9a545dd6e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -386,7 +386,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) { struct stat st; int flags; - int err, output; + int err, output, feat; unsigned long waking = 0; const bool forks = argc > 0; struct machine *machine; @@ -453,8 +453,14 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) rec->session = session; - if (!rec->no_buildid) - perf_header__set_feat(&session->header, HEADER_BUILD_ID); + for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) + perf_header__set_feat(&session->header, feat); + + if (rec->no_buildid) + perf_header__clear_feat(&session->header, HEADER_BUILD_ID); + + if (!have_tracepoints(&evsel_list->entries)) + perf_header__clear_feat(&session->header, HEADER_TRACE_INFO); if (!rec->file_new) { err = perf_session__read_header(session, output); @@ -462,22 +468,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } - if (have_tracepoints(&evsel_list->entries)) - perf_header__set_feat(&session->header, HEADER_TRACE_INFO); - - perf_header__set_feat(&session->header, HEADER_HOSTNAME); - perf_header__set_feat(&session->header, HEADER_OSRELEASE); - perf_header__set_feat(&session->header, HEADER_ARCH); - perf_header__set_feat(&session->header, HEADER_CPUDESC); - perf_header__set_feat(&session->header, HEADER_NRCPUS); - perf_header__set_feat(&session->header, HEADER_EVENT_DESC); - perf_header__set_feat(&session->header, HEADER_CMDLINE); - perf_header__set_feat(&session->header, HEADER_VERSION); - perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); - perf_header__set_feat(&session->header, HEADER_TOTAL_MEM); - perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY); - perf_header__set_feat(&session->header, HEADER_CPUID); - if (forks) { err = perf_evlist__prepare_workload(evsel_list, opts, argv); if (err < 0) { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index ac4ec956024e..e68f617d082f 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -11,6 +11,7 @@ enum { HEADER_RESERVED = 0, /* always cleared */ + HEADER_FIRST_FEATURE = 1, HEADER_TRACE_INFO = 1, HEADER_BUILD_ID, -- cgit v1.2.3-70-g09d2 From e89cef136a8b56eef1acf702591fd3039fc3385d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 1 Feb 2012 13:54:08 +0100 Subject: perf tool: Fix perf stack to non executable on x86_64 By adding following objects: bench/mem-memset-x86-64-asm.o bench/mem-memcpy-x86-64-asm.o the x86_64 perf binary ended up with executable stack. The reason was that above objects are assembler sourced and are missing the GNU-stack note section. In such case the linker assumes that the final binary should not be restricted at all and mark the stack as RWX. Adding section ".note.GNU-stack" definition to mentioned objects, with all flags disabled, thus omiting those objects from linker stack flags decision. Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=783570 Reported-by: Clark Williams Acked-by: Eric Dumazet Cc: Corey Ashford Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328100848-5630-1-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa [ committer note: Remaining bits after what was already added to perf/urgent ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/mem-memset-x86-64-asm.S | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index cb9217063776..9e5af89ed13a 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -4,3 +4,10 @@ #define Lmemset_c globl memset_c; memset_c #define Lmemset_c_e globl memset_c_e; memset_c_e #include "../../../arch/x86/lib/memset_64.S" + +/* + * We need to provide note.GNU-stack section, saying that we want + * NOT executable stack. Otherwise the final linking will assume that + * the ELF stack should not be restricted at all and set it RWX. + */ +.section .note.GNU-stack,"",@progbits -- cgit v1.2.3-70-g09d2 From 762b2935fc0ea2eab3a0edc8333fedb95266c7a9 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Mon, 6 Feb 2012 16:17:23 +0100 Subject: perf doc: Allow producing documentation in a specified output directory Currently we can put the object files in a different directory by using 'O=' comand line argument. However the generated documentation files don't honor this directive, This patch fixes that. It's been tested for man target but the others seems currently broken so no tests have been done on them so far. Link: http://lkml.kernel.org/r/1328541443-18003-1-git-send-email-fbuihuu@gmail.com Signed-off-by: Franck Bui-Huu Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/Makefile | 86 +++++++++++++++++++++++---------------- 1 file changed, 52 insertions(+), 34 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 4626a398836a..ca600e09c8d4 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -1,3 +1,10 @@ +OUTPUT := ./ +ifeq ("$(origin O)", "command line") + ifneq ($(O),) + OUTPUT := $(O)/ + endif +endif + MAN1_TXT= \ $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \ $(wildcard perf-*.txt)) \ @@ -6,10 +13,11 @@ MAN5_TXT= MAN7_TXT= MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT) -MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT)) -MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT)) +_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT)) -DOC_HTML=$(MAN_HTML) +MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML)) ARTICLES = # with their own formatting rules. @@ -18,11 +26,17 @@ API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technica SP_ARTICLES += $(API_DOCS) SP_ARTICLES += technical/api-index -DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES)) +_DOC_HTML = $(_MAN_HTML) +_DOC_HTML+=$(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES)) +DOC_HTML=$(addprefix $(OUTPUT),$(_DOC_HTML)) -DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT)) -DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT)) -DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT)) +_DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT)) +_DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT)) +_DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT)) + +DOC_MAN1=$(addprefix $(OUTPUT),$(_DOC_MAN1)) +DOC_MAN5=$(addprefix $(OUTPUT),$(_DOC_MAN5)) +DOC_MAN7=$(addprefix $(OUTPUT),$(_DOC_MAN7)) # Make the path relative to DESTDIR, not prefix ifndef DESTDIR @@ -150,9 +164,9 @@ man1: $(DOC_MAN1) man5: $(DOC_MAN5) man7: $(DOC_MAN7) -info: perf.info perfman.info +info: $(OUTPUT)perf.info $(OUTPUT)perfman.info -pdf: user-manual.pdf +pdf: $(OUTPUT)user-manual.pdf install: install-man @@ -166,7 +180,7 @@ install-man: man install-info: info $(INSTALL) -d -m 755 $(DESTDIR)$(infodir) - $(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(infodir) + $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir) if test -r $(DESTDIR)$(infodir)/dir; then \ $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\ $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\ @@ -176,7 +190,7 @@ install-info: info install-pdf: pdf $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir) - $(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir) + $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir) #install-html: html # '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) @@ -189,14 +203,14 @@ install-pdf: pdf # # Determine "include::" file references in asciidoc files. # -doc.dep : $(wildcard *.txt) build-docdep.perl +$(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl $(QUIET_GEN)$(RM) $@+ $@ && \ $(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \ mv $@+ $@ --include doc.dep +-include $(OUPTUT)doc.dep -cmds_txt = cmds-ancillaryinterrogators.txt \ +_cmds_txt = cmds-ancillaryinterrogators.txt \ cmds-ancillarymanipulators.txt \ cmds-mainporcelain.txt \ cmds-plumbinginterrogators.txt \ @@ -205,32 +219,36 @@ cmds_txt = cmds-ancillaryinterrogators.txt \ cmds-synchelpers.txt \ cmds-purehelpers.txt \ cmds-foreignscminterface.txt +cmds_txt=$(addprefix $(OUTPUT),$(_cmds_txt)) -$(cmds_txt): cmd-list.made +$(cmds_txt): $(OUTPUT)cmd-list.made -cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT) +$(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT) $(QUIET_GEN)$(RM) $@ && \ $(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \ date >$@ clean: - $(RM) *.xml *.xml+ *.html *.html+ *.1 *.5 *.7 - $(RM) *.texi *.texi+ *.texi++ perf.info perfman.info - $(RM) howto-index.txt howto/*.html doc.dep - $(RM) technical/api-*.html technical/api-index.txt - $(RM) $(cmds_txt) *.made - -$(MAN_HTML): %.html : %.txt + $(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML)) + $(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) + $(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7) + $(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++ + $(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info + $(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep + $(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt + $(RM) $(cmds_txt) $(OUTPUT)*.made + +$(MAN_HTML): $(OUTPUT)%.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ -%.1 %.5 %.7 : %.xml +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(QUIET_XMLTO)$(RM) $@ && \ - xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + xmlto -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< -%.xml : %.txt +$(OUTPUT)%.xml : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ @@ -239,25 +257,25 @@ $(MAN_HTML): %.html : %.txt XSLT = docbook.xsl XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css -user-manual.html: user-manual.xml +$(OUTPUT)user-manual.html: $(OUTPUT)user-manual.xml $(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $< -perf.info: user-manual.texi - $(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ user-manual.texi +$(OUTPUT)perf.info: $(OUTPUT)user-manual.texi + $(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ $(OUTPUT)user-manual.texi -user-manual.texi: user-manual.xml +$(OUTPUT)user-manual.texi: $(OUTPUT)user-manual.xml $(QUIET_DB2TEXI)$(RM) $@+ $@ && \ - $(DOCBOOK2X_TEXI) user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \ + $(DOCBOOK2X_TEXI) $(OUTPUT)user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \ $(PERL_PATH) fix-texi.perl <$@++ >$@+ && \ rm $@++ && \ mv $@+ $@ -user-manual.pdf: user-manual.xml +$(OUTPUT)user-manual.pdf: $(OUTPUT)user-manual.xml $(QUIET_DBLATEX)$(RM) $@+ $@ && \ $(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \ mv $@+ $@ -perfman.texi: $(MAN_XML) cat-texi.perl +$(OUTPUT)perfman.texi: $(MAN_XML) cat-texi.perl $(QUIET_DB2TEXI)$(RM) $@+ $@ && \ ($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \ --to-stdout $(xml) &&) true) > $@++ && \ @@ -265,7 +283,7 @@ perfman.texi: $(MAN_XML) cat-texi.perl rm $@++ && \ mv $@+ $@ -perfman.info: perfman.texi +$(OUTPUT)perfman.info: $(OUTPUT)perfman.texi $(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi $(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml -- cgit v1.2.3-70-g09d2 From 5fde2523bddb71d96f12b6ee8d2a9a43cb99da96 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 6 Feb 2012 16:44:44 +0900 Subject: perf stat: Adjust print unit The default 'M/sec' unit is not useful if the result is small enough. Adjust it dynamically according to the value. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328514285-26232-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 459b8620a5d9..32d930eb754e 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -844,12 +844,18 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) fprintf(output, " # %8.3f GHz ", ratio); } else if (runtime_nsecs_stats[cpu].n != 0) { + char unit = 'M'; + total = avg_stats(&runtime_nsecs_stats[cpu]); if (total) ratio = 1000.0 * avg / total; + if (ratio < 0.001) { + ratio *= 1000; + unit = 'K'; + } - fprintf(output, " # %8.3f M/sec ", ratio); + fprintf(output, " # %8.3f %c/sec ", ratio, unit); } else { fprintf(output, " "); } -- cgit v1.2.3-70-g09d2 From 9dac6a29e0ce0cd9dec497baa123e216b00b525d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 6 Feb 2012 16:44:45 +0900 Subject: perf stat: Align scaled output of cpu-clock The output of cpu-clock event is controlled in nsec_printout(), but its alignment was broken: Performance counter stats for 'sleep 1': 6,038,774 instructions # 0.00 insns per cycle 180 faults # 0.007 K/sec [99.95%] 1,282,201 branches # 0.053 M/sec [99.84%] 24126.221811 cpu-clock [99.62%] 24121.689540 task-clock # 24.098 CPUs utilized [99.52%] 1.001001017 seconds time elapsed This patch fixes this: Performance counter stats for 'sleep 1': 13,540,843 instructions # 0.00 insns per cycle 180 faults # 0.007 K/sec [99.94%] 2,875,386 branches # 0.119 M/sec [99.82%] 24144.221137 cpu-clock [99.61%] 24133.515366 task-clock # 24.109 CPUs utilized [99.52%] 1.001020946 seconds time elapsed Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328514285-26232-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 32d930eb754e..d14b37ad7638 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -576,6 +576,8 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) fprintf(output, " # %8.3f CPUs utilized ", avg / avg_stats(&walltime_nsecs_stats)); + else + fprintf(output, " "); } /* used for get_ratio_color() */ -- cgit v1.2.3-70-g09d2 From 73323f541fe5f55a3b8a5c3d565bfc1efd64abf6 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 2 Feb 2012 13:54:44 +0100 Subject: perf tools: fix endianness detection in perf.data The current version of perf detects whether or not the perf.data file is written in a different endianness using the attr_size field in the header of the file. This field represents sizeof(struct perf_event_attr) as known to perf record. If the sizes do not match, then perf tries the byte-swapped version. If they match, then the tool assumes a different endianness. The issue with the approach is that it assumes the size of perf_event_attr always has to match between perf record and perf report. However, the kernel perf_event ABI is extensible. New fields can be added to struct perf_event_attr. Consequently, it is not possible to use attr_size to detect endianness. This patch takes another approach by using the magic number written at the beginning of the perf.data file to detect endianness. The magic number is an eight-byte signature. It's primary purpose is to identify (signature) a perf.data file. But it could also be used to encode the endianness. The patch introduces a new value for this signature. The key difference is that the signature is written differently in the file depending on the endianness. Thus, by comparing the signature from the file with the tool's own signature it is possible to detect endianness. The new signature is "PERFILE2". Backward compatiblity with existing perf.data file is ensured. Tested-by: David Ahern Acked-by: David Ahern Cc: Andi Kleen Cc: Anshuman Khandual Cc: Arun Sharma Cc: David Ahern Cc: Ingo Molnar Cc: Lin Ming Cc: Peter Zijlstra Cc: Roberto Agostino Vitillo Cc: Robert Richter Cc: Vince Weaver Link: http://lkml.kernel.org/r/1328187288-24395-15-git-send-email-eranian@google.com Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 77 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 64 insertions(+), 13 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index ecd7f4dd7eea..6f4187de4b72 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -63,9 +63,20 @@ char *perf_header__find_event(u64 id) return NULL; } -static const char *__perf_magic = "PERFFILE"; +/* + * magic2 = "PERFILE2" + * must be a numerical value to let the endianness + * determine the memory layout. That way we are able + * to detect endianness when reading the perf.data file + * back. + * + * we check for legacy (PERFFILE) format. + */ +static const char *__perf_magic1 = "PERFFILE"; +static const u64 __perf_magic2 = 0x32454c4946524550ULL; +static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; -#define PERF_MAGIC (*(u64 *)__perf_magic) +#define PERF_MAGIC __perf_magic2 struct perf_file_attr { struct perf_event_attr attr; @@ -1620,24 +1631,59 @@ out_free: return err; } +static int check_magic_endian(u64 *magic, struct perf_file_header *header, + struct perf_header *ph) +{ + int ret; + + /* check for legacy format */ + ret = memcmp(magic, __perf_magic1, sizeof(*magic)); + if (ret == 0) { + pr_debug("legacy perf.data format\n"); + if (!header) + return -1; + + if (header->attr_size != sizeof(struct perf_file_attr)) { + u64 attr_size = bswap_64(header->attr_size); + + if (attr_size != sizeof(struct perf_file_attr)) + return -1; + + ph->needs_swap = true; + } + return 0; + } + + /* check magic number with same endianness */ + if (*magic == __perf_magic2) + return 0; + + /* check magic number but opposite endianness */ + if (*magic != __perf_magic2_sw) + return -1; + + ph->needs_swap = true; + + return 0; +} + int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd) { + int ret; + lseek(fd, 0, SEEK_SET); - if (readn(fd, header, sizeof(*header)) <= 0 || - memcmp(&header->magic, __perf_magic, sizeof(header->magic))) + ret = readn(fd, header, sizeof(*header)); + if (ret <= 0) return -1; - if (header->attr_size != sizeof(struct perf_file_attr)) { - u64 attr_size = bswap_64(header->attr_size); - - if (attr_size != sizeof(struct perf_file_attr)) - return -1; + if (check_magic_endian(&header->magic, header, ph) < 0) + return -1; + if (ph->needs_swap) { mem_bswap_64(header, offsetof(struct perf_file_header, - adds_features)); - ph->needs_swap = true; + adds_features)); } if (header->size != sizeof(*header)) { @@ -1873,8 +1919,13 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, struct perf_header *ph, int fd, bool repipe) { - if (readn(fd, header, sizeof(*header)) <= 0 || - memcmp(&header->magic, __perf_magic, sizeof(header->magic))) + int ret; + + ret = readn(fd, header, sizeof(*header)); + if (ret <= 0) + return -1; + + if (check_magic_endian(&header->magic, NULL, ph) < 0) return -1; if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) -- cgit v1.2.3-70-g09d2 From d3665498955779e56453501a16f4ad084f798802 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 6 Feb 2012 15:27:52 -0700 Subject: perf record: No build id option fails A recent refactoring of perf-record introduced the following: perf record -a -B Couldn't generating buildids. Use --no-buildid to profile anyway. sleep: Terminated I believe the triple negative was meant to be only a double negative. :-) While I'm there, fixed the grammar on the error message. Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1328567272-13190-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f8d9a545dd6e..d6d1c6cdcfe6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -494,9 +494,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) return err; } - if (!!rec->no_buildid + if (!rec->no_buildid && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) { - pr_err("Couldn't generating buildids. " + pr_err("Couldn't generate buildids. " "Use --no-buildid to profile anyway.\n"); return -1; } -- cgit v1.2.3-70-g09d2 From 6a5c13aff49ac9b3fea38d5f84b436718cb2780d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 12 Feb 2012 19:45:24 +0900 Subject: perf tools: Fix build dependency of perf python extension The perf python extention (perf.so) file lacks its dependencies in the Makefile so that it cannot be refreshed if one of source files it depends is changed. Fix it by putting them in a separate file and processing it in both of Makefile and setup.py. Reported-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1329043524-12470-1-git-send-email-namhyung@gmail.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 5 ++++- tools/perf/util/python-ext-sources | 17 +++++++++++++++++ tools/perf/util/setup.py | 8 ++++---- 3 files changed, 25 insertions(+), 5 deletions(-) create mode 100644 tools/perf/util/python-ext-sources (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 64df5de12ca8..8359fa140d2d 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -183,7 +183,10 @@ SCRIPT_SH += perf-archive.sh grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) -$(OUTPUT)python/perf.so: $(PYRF_OBJS) +PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) +PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py + +$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ mkdir -p $(OUTPUT)python && \ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources new file mode 100644 index 000000000000..ff606f482a7c --- /dev/null +++ b/tools/perf/util/python-ext-sources @@ -0,0 +1,17 @@ +# +# List of files needed by perf python extention +# +# Each source file must be placed on its own line so that it can be +# processed by Makefile and util/setup.py accordingly. +# + +util/python.c +util/ctype.c +util/evlist.c +util/evsel.c +util/cpumap.c +util/thread_map.c +util/util.c +util/xyarray.c +util/cgroup.c +util/debugfs.c diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 36d4c5619575..d0f9f29cf181 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -24,11 +24,11 @@ cflags += getenv('CFLAGS', '').split() build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') +ext_sources = [f.strip() for f in file('util/python-ext-sources') + if len(f.strip()) > 0 and f[0] != '#'] + perf = Extension('perf', - sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c', - 'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c', - 'util/util.c', 'util/xyarray.c', 'util/cgroup.c', - 'util/debugfs.c'], + sources = ext_sources, include_dirs = ['util/include'], extra_compile_args = cflags, ) -- cgit v1.2.3-70-g09d2 From eca1c3e3f937307331fd1fd5ee5205e57f2131ca Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 13 Feb 2012 07:57:37 -0700 Subject: perf tools: Fix out of tree compiles For latest tip/perf/core tree Compiles are failing on: GEN common-cmds.h make: *** No rule to make target `../../arch/x86/lib/memset_64.S', needed by `builtin-annotate.o'. Stop. Resolve by adding memset.* to the tar file. Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1329145057-26302-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 1078c5fadd5b..5476bc0a1eac 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -9,6 +9,7 @@ lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h arch/*/lib/memcpy*.S +arch/*/lib/memset*.S include/linux/poison.h include/linux/magic.h include/linux/hw_breakpoint.h -- 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') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index ff9a66e0d4e4..a5766b4b0125 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 8966b9ab2014..2fa173b51970 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 ab1454ed450f..4a5680cb242e 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 d6d1c6cdcfe6..08ed24b66ffe 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 d14b37ad7638..ea40e4e8b227 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 70c4eb2bdf72..0f151952a770 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 d869b214ada2..94d55cb2048c 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 92af1688bae4..deb17dba4a5b 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 a57a8cfc5d90..5c61dc57d7c7 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 1b4282be8fe7..21f1c9e57f13 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 9a11f9edac12..f910f50136d0 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 ff606f482a7c..2884e67ee625 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 3d4b6c5931b9..e15983cf077d 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 c75ddbaba005..7da80f14418b 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 e4370ca27193..09fe579ccafb 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 def3e53e0fe0..49eb8481f19f 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 d0c013934f30..52bb07c6442a 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 232d17ef3e60..7917b09430bd 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 0c095715b388d19d7a0b7e8eaceeceb018f5b3d1 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 10 Feb 2012 18:05:04 +0100 Subject: perf top: Don't process samples with no valid machine object The perf sample processing code relies on a valid machine object. Make sure that this path is only entered when such a object exists. A counter for samples where no machine object exits is also introduced to give the user a message about these samples. Reported-by: David Ahern Reported-by: Jason Wang Cc: David Ahern Cc: Ingo Molnar Cc: Jason Wang Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328893505-4115-2-git-send-email-joerg.roedel@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 6 ++++++ tools/perf/util/hist.h | 1 + tools/perf/util/session.c | 10 ++++++++++ 3 files changed, 17 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 94d55cb2048c..5a88c0dadf15 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -677,6 +677,12 @@ static void perf_event__process_sample(struct perf_tool *tool, return; } + if (!machine) { + pr_err("%u unprocessable samples recorded.", + top->session->hists.stats.nr_unprocessable_samples++); + return; + } + if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) top->exact_samples++; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 0d486135d10f..48e5acd1e862 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -32,6 +32,7 @@ struct events_stats { u32 nr_unknown_events; u32 nr_invalid_chains; u32 nr_unknown_id; + u32 nr_unprocessable_samples; }; enum hist_column { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 552c1c50eea1..9f833cf9c6a9 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -796,6 +796,10 @@ static int perf_session_deliver_event(struct perf_session *session, ++session->hists.stats.nr_unknown_id; return -1; } + if (machine == NULL) { + ++session->hists.stats.nr_unprocessable_samples; + return -1; + } return tool->sample(tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); @@ -964,6 +968,12 @@ static void perf_session__warn_about_errors(const struct perf_session *session, session->hists.stats.nr_invalid_chains, session->hists.stats.nr_events[PERF_RECORD_SAMPLE]); } + + if (session->hists.stats.nr_unprocessable_samples != 0) { + ui__warning("%u unprocessable samples recorded.\n" + "Do you have a KVM guest running and not using 'perf kvm'?\n", + session->hists.stats.nr_unprocessable_samples); + } } #define session_done() (*(volatile int *)(&session_done)) -- cgit v1.2.3-70-g09d2 From c4a7dca92bbb9881a5d678720f1d0c2153499749 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 10 Feb 2012 18:05:05 +0100 Subject: perf tools: Change perf_guest default back to false Setting perf_guest to true by default makes no sense because the perf subcommands can not setup guest symbol information and thus not process and guest samples. The only exception is perf-kvm which changes the perf_guest value on its own. So change the default for perf_guest back to false. Cc: David Ahern Cc: Ingo Molnar Cc: Jason Wang Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328893505-4115-3-git-send-email-joerg.roedel@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 813141047fc2..fb25d1329218 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -6,7 +6,7 @@ * XXX We need to find a better place for these things... */ bool perf_host = true; -bool perf_guest = true; +bool perf_guest = false; void event_attr_init(struct perf_event_attr *attr) { -- cgit v1.2.3-70-g09d2 From 2cd13b0f7dd3a5df68ff4cd82af2e1f7bc2a43ab Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 10 Feb 2012 10:10:15 +0900 Subject: perf tools: Implement islower/isupper macro into util.h The util.h header provides various ctype macros but lacks those two. Add them. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328836217-9118-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/util.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 7917b09430bd..0f99f394d8e0 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -199,6 +199,8 @@ static inline int has_extension(const char *filename, const char *ext) #undef isalpha #undef isprint #undef isalnum +#undef islower +#undef isupper #undef tolower #undef toupper @@ -219,6 +221,8 @@ extern unsigned char sane_ctype[256]; #define isalpha(x) sane_istest(x,GIT_ALPHA) #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) #define isprint(x) sane_istest(x,GIT_PRINT) +#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20)) +#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20)) #define tolower(x) sane_case((unsigned char)(x), 0x20) #define toupper(x) sane_case((unsigned char)(x), 0) -- cgit v1.2.3-70-g09d2 From 3bd2b8d1095d41254d3bdc3d62622c7fd5e143b8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 10 Feb 2012 10:10:16 +0900 Subject: perf tools: ctype.c only wants util.h The implementation of sane ctype macros only depends on symbols in util.h not cache.h. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328836217-9118-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ctype.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index 35073621e5de..aada3ac5e891 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -3,7 +3,7 @@ * * No surprises, and works with signed and unsigned chars. */ -#include "cache.h" +#include "util.h" enum { S = GIT_SPACE, -- cgit v1.2.3-70-g09d2 From e334c726ca774d346cb7c4db487e80953a202b58 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 10 Feb 2012 10:10:17 +0900 Subject: perf tools: Get rid of ctype.h in symbol.c The ctype.h in symbol.c was needed because of isupper(). However we now have it in util.h, it can be changed to use our implementation. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328836217-9118-3-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index fc6e12fe4b44..5dd83c3e2c0c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,4 +1,3 @@ -#include #include #include #include @@ -12,6 +11,7 @@ #include #include #include "build-id.h" +#include "util.h" #include "debug.h" #include "symbol.h" #include "strlist.h" -- cgit v1.2.3-70-g09d2 From 2837609fefbfe8f1248bfce09d9f0b44d5eb713d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 27 Jan 2012 15:34:21 +0100 Subject: perf tools: Remove unused functions from debugfs object Following debugfs object functions are not referenced within the code: int debugfs_valid_entry(const char *path); int debugfs_umount(void); int debugfs_write(const char *entry, const char *value); int debugfs_read(const char *entry, char *buffer, size_t size); void debugfs_force_cleanup(void); int debugfs_make_path(const char *element, char *buffer, int size); Removing them. Cc: Corey Ashford Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1327674868-10486-3-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/debugfs.c | 141 ---------------------------------------------- tools/perf/util/debugfs.h | 6 -- 2 files changed, 147 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c index ffc35e748e89..dd8b19319c03 100644 --- a/tools/perf/util/debugfs.c +++ b/tools/perf/util/debugfs.c @@ -15,32 +15,6 @@ static const char *debugfs_known_mountpoints[] = { 0, }; -/* use this to force a umount */ -void debugfs_force_cleanup(void) -{ - debugfs_find_mountpoint(); - debugfs_premounted = 0; - debugfs_umount(); -} - -/* construct a full path to a debugfs element */ -int debugfs_make_path(const char *element, char *buffer, int size) -{ - int len; - - if (strlen(debugfs_mountpoint) == 0) { - buffer[0] = '\0'; - return -1; - } - - len = strlen(debugfs_mountpoint) + strlen(element) + 1; - if (len >= size) - return len+1; - - snprintf(buffer, size-1, "%s/%s", debugfs_mountpoint, element); - return 0; -} - static int debugfs_found; /* find the path to the mounted debugfs */ @@ -97,17 +71,6 @@ int debugfs_valid_mountpoint(const char *debugfs) return 0; } - -int debugfs_valid_entry(const char *path) -{ - struct stat st; - - if (stat(path, &st)) - return -errno; - - return 0; -} - static void debugfs_set_tracing_events_path(const char *mountpoint) { snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", @@ -149,107 +112,3 @@ void debugfs_set_path(const char *mountpoint) snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint); debugfs_set_tracing_events_path(mountpoint); } - -/* umount the debugfs */ - -int debugfs_umount(void) -{ - char umountcmd[128]; - int ret; - - /* if it was already mounted, leave it */ - if (debugfs_premounted) - return 0; - - /* make sure it's a valid mount point */ - ret = debugfs_valid_mountpoint(debugfs_mountpoint); - if (ret) - return ret; - - snprintf(umountcmd, sizeof(umountcmd), - "/bin/umount %s", debugfs_mountpoint); - return system(umountcmd); -} - -int debugfs_write(const char *entry, const char *value) -{ - char path[PATH_MAX + 1]; - int ret, count; - int fd; - - /* construct the path */ - snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); - - /* verify that it exists */ - ret = debugfs_valid_entry(path); - if (ret) - return ret; - - /* get how many chars we're going to write */ - count = strlen(value); - - /* open the debugfs entry */ - fd = open(path, O_RDWR); - if (fd < 0) - return -errno; - - while (count > 0) { - /* write it */ - ret = write(fd, value, count); - if (ret <= 0) { - if (ret == EAGAIN) - continue; - close(fd); - return -errno; - } - count -= ret; - } - - /* close it */ - close(fd); - - /* return success */ - return 0; -} - -/* - * read a debugfs entry - * returns the number of chars read or a negative errno - */ -int debugfs_read(const char *entry, char *buffer, size_t size) -{ - char path[PATH_MAX + 1]; - int ret; - int fd; - - /* construct the path */ - snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); - - /* verify that it exists */ - ret = debugfs_valid_entry(path); - if (ret) - return ret; - - /* open the debugfs entry */ - fd = open(path, O_RDONLY); - if (fd < 0) - return -errno; - - do { - /* read it */ - ret = read(fd, buffer, size); - if (ret == 0) { - close(fd); - return EOF; - } - } while (ret < 0 && errno == EAGAIN); - - /* close it */ - close(fd); - - /* make *sure* there's a null character at the end */ - buffer[ret] = '\0'; - - /* return the number of chars read */ - return ret; -} diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h index 4a878f735eb0..68f3e87ec57f 100644 --- a/tools/perf/util/debugfs.h +++ b/tools/perf/util/debugfs.h @@ -3,14 +3,8 @@ const char *debugfs_find_mountpoint(void); int debugfs_valid_mountpoint(const char *debugfs); -int debugfs_valid_entry(const char *path); char *debugfs_mount(const char *mountpoint); -int debugfs_umount(void); void debugfs_set_path(const char *mountpoint); -int debugfs_write(const char *entry, const char *value); -int debugfs_read(const char *entry, char *buffer, size_t size); -void debugfs_force_cleanup(void); -int debugfs_make_path(const char *element, char *buffer, int size); extern char debugfs_mountpoint[]; extern char tracing_events_path[]; -- cgit v1.2.3-70-g09d2 From e90fda0635401225ca7c2343bea2f6d279347d10 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 27 Jan 2012 15:34:22 +0100 Subject: perf tools: Add sysfs mountpoint interface Adding sysfs object to provide sysfs mount information in the same way as debugfs object does. The object provides following function: sysfs_find_mountpoint which returns the sysfs mount mount. Cc: Corey Ashford Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1327674868-10486-4-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 2 ++ tools/perf/util/sysfs.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/sysfs.h | 6 +++++ 3 files changed, 68 insertions(+) create mode 100644 tools/perf/util/sysfs.c create mode 100644 tools/perf/util/sysfs.h (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 8359fa140d2d..e011b5060f92 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -259,6 +259,7 @@ LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h LIB_H += util/debugfs.h +LIB_H += util/sysfs.h LIB_H += util/event.h LIB_H += util/evsel.h LIB_H += util/evlist.h @@ -305,6 +306,7 @@ LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o LIB_OBJS += $(OUTPUT)util/debugfs.o +LIB_OBJS += $(OUTPUT)util/sysfs.o LIB_OBJS += $(OUTPUT)util/environment.o LIB_OBJS += $(OUTPUT)util/event.o LIB_OBJS += $(OUTPUT)util/evlist.o diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c new file mode 100644 index 000000000000..48c6902e749f --- /dev/null +++ b/tools/perf/util/sysfs.c @@ -0,0 +1,60 @@ + +#include "util.h" +#include "sysfs.h" + +static const char * const sysfs_known_mountpoints[] = { + "/sys", + 0, +}; + +static int sysfs_found; +char sysfs_mountpoint[PATH_MAX]; + +static int sysfs_valid_mountpoint(const char *sysfs) +{ + struct statfs st_fs; + + if (statfs(sysfs, &st_fs) < 0) + return -ENOENT; + else if (st_fs.f_type != (long) SYSFS_MAGIC) + return -ENOENT; + + return 0; +} + +const char *sysfs_find_mountpoint(void) +{ + const char * const *ptr; + char type[100]; + FILE *fp; + + if (sysfs_found) + return (const char *) sysfs_mountpoint; + + ptr = sysfs_known_mountpoints; + while (*ptr) { + if (sysfs_valid_mountpoint(*ptr) == 0) { + sysfs_found = 1; + strcpy(sysfs_mountpoint, *ptr); + return sysfs_mountpoint; + } + ptr++; + } + + /* give up and parse /proc/mounts */ + fp = fopen("/proc/mounts", "r"); + if (fp == NULL) + return NULL; + + while (!sysfs_found && + fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", + sysfs_mountpoint, type) == 2) { + + if (strcmp(type, "sysfs") == 0) + sysfs_found = 1; + } + + fclose(fp); + + return sysfs_found ? sysfs_mountpoint : NULL; +} diff --git a/tools/perf/util/sysfs.h b/tools/perf/util/sysfs.h new file mode 100644 index 000000000000..a813b7203938 --- /dev/null +++ b/tools/perf/util/sysfs.h @@ -0,0 +1,6 @@ +#ifndef __SYSFS_H__ +#define __SYSFS_H__ + +const char *sysfs_find_mountpoint(void); + +#endif /* __DEBUGFS_H__ */ -- cgit v1.2.3-70-g09d2 From 850f8127fa3666737881aecb3b16e8ede85e58f4 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 27 Jan 2012 15:34:23 +0100 Subject: perf tools: Add bitmap_or function into bitmap object Adding implementation os bitmap_or function to the bitmap object. It is stolen from the kernel lib/bitmap.o object. It is used in upcomming patches. Cc: Corey Ashford Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1327674868-10486-5-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bitmap.c | 10 ++++++++++ tools/perf/util/include/linux/bitmap.h | 11 +++++++++++ 2 files changed, 21 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c index 5e230acae1e9..0a1adc1111fd 100644 --- a/tools/perf/util/bitmap.c +++ b/tools/perf/util/bitmap.c @@ -19,3 +19,13 @@ int __bitmap_weight(const unsigned long *bitmap, int bits) return w; } + +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] | bitmap2[k]; +} diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index eda4416efa0a..bb162e40c76c 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -5,6 +5,8 @@ #include int __bitmap_weight(const unsigned long *bitmap, int bits); +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ @@ -32,4 +34,13 @@ static inline int bitmap_weight(const unsigned long *src, int nbits) return __bitmap_weight(src, nbits); } +static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, int nbits) +{ + if (small_const_nbits(nbits)) + *dst = *src1 | *src2; + else + __bitmap_or(dst, src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ -- cgit v1.2.3-70-g09d2 From 08d95bd256277f914e525aeb292da52f15173e7d Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Fri, 10 Feb 2012 15:41:55 +0100 Subject: perf tools: Moving code in header.c Needed for later changes. No modified functionality. Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1328884916-5901-1-git-send-email-robert.richter@amd.com Signed-off-by: Robert Richter Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 300 +++++++++++++++++++++++------------------------ 1 file changed, 150 insertions(+), 150 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 6f4187de4b72..5bb2d752ab8f 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1316,6 +1316,156 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp) free(str); } +static int __event_process_build_id(struct build_id_event *bev, + char *filename, + struct perf_session *session) +{ + int err = -1; + struct list_head *head; + struct machine *machine; + u16 misc; + struct dso *dso; + enum dso_kernel_type dso_type; + + machine = perf_session__findnew_machine(session, bev->pid); + if (!machine) + goto out; + + misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + switch (misc) { + case PERF_RECORD_MISC_KERNEL: + dso_type = DSO_TYPE_KERNEL; + head = &machine->kernel_dsos; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + dso_type = DSO_TYPE_GUEST_KERNEL; + head = &machine->kernel_dsos; + break; + case PERF_RECORD_MISC_USER: + case PERF_RECORD_MISC_GUEST_USER: + dso_type = DSO_TYPE_USER; + head = &machine->user_dsos; + break; + default: + goto out; + } + + dso = __dsos__findnew(head, filename); + if (dso != NULL) { + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + dso__set_build_id(dso, &bev->build_id); + + if (filename[0] == '[') + dso->kernel = dso_type; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), + sbuild_id); + pr_debug("build id event received for %s: %s\n", + dso->long_name, sbuild_id); + } + + err = 0; +out: + return err; +} + +static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(header, struct perf_session, header); + struct { + struct perf_event_header header; + u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + char filename[0]; + } old_bev; + struct build_id_event bev; + char filename[PATH_MAX]; + u64 limit = offset + size; + + while (offset < limit) { + ssize_t len; + + if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) + return -1; + + if (header->needs_swap) + perf_event_header__bswap(&old_bev.header); + + len = old_bev.header.size - sizeof(old_bev); + if (read(input, filename, len) != len) + return -1; + + bev.header = old_bev.header; + + /* + * As the pid is the missing value, we need to fill + * it properly. The header.misc value give us nice hint. + */ + bev.pid = HOST_KERNEL_ID; + if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER || + bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL) + bev.pid = DEFAULT_GUEST_KERNEL_ID; + + memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id)); + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + + return 0; +} + +static int perf_header__read_build_ids(struct perf_header *header, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(header, struct perf_session, header); + struct build_id_event bev; + char filename[PATH_MAX]; + u64 limit = offset + size, orig_offset = offset; + int err = -1; + + while (offset < limit) { + ssize_t len; + + if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + goto out; + + if (header->needs_swap) + perf_event_header__bswap(&bev.header); + + len = bev.header.size - sizeof(bev); + if (read(input, filename, len) != len) + goto out; + /* + * The a1645ce1 changeset: + * + * "perf: 'perf kvm' tool for monitoring guest performance from host" + * + * Added a field to struct build_id_event that broke the file + * format. + * + * Since the kernel build-id is the first entry, process the + * table using the old format if the well known + * '[kernel.kallsyms]' string for the kernel build-id has the + * first 4 characters chopped off (where the pid_t sits). + */ + if (memcmp(filename, "nel.kallsyms]", 13) == 0) { + if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1) + return -1; + return perf_header__read_build_ids_abi_quirk(header, input, offset, size); + } + + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + err = 0; +out: + return err; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); @@ -1735,156 +1885,6 @@ int perf_file_header__read(struct perf_file_header *header, return 0; } -static int __event_process_build_id(struct build_id_event *bev, - char *filename, - struct perf_session *session) -{ - int err = -1; - struct list_head *head; - struct machine *machine; - u16 misc; - struct dso *dso; - enum dso_kernel_type dso_type; - - machine = perf_session__findnew_machine(session, bev->pid); - if (!machine) - goto out; - - misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - - switch (misc) { - case PERF_RECORD_MISC_KERNEL: - dso_type = DSO_TYPE_KERNEL; - head = &machine->kernel_dsos; - break; - case PERF_RECORD_MISC_GUEST_KERNEL: - dso_type = DSO_TYPE_GUEST_KERNEL; - head = &machine->kernel_dsos; - break; - case PERF_RECORD_MISC_USER: - case PERF_RECORD_MISC_GUEST_USER: - dso_type = DSO_TYPE_USER; - head = &machine->user_dsos; - break; - default: - goto out; - } - - dso = __dsos__findnew(head, filename); - if (dso != NULL) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - dso__set_build_id(dso, &bev->build_id); - - if (filename[0] == '[') - dso->kernel = dso_type; - - build_id__sprintf(dso->build_id, sizeof(dso->build_id), - sbuild_id); - pr_debug("build id event received for %s: %s\n", - dso->long_name, sbuild_id); - } - - err = 0; -out: - return err; -} - -static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, - int input, u64 offset, u64 size) -{ - struct perf_session *session = container_of(header, struct perf_session, header); - struct { - struct perf_event_header header; - u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; - char filename[0]; - } old_bev; - struct build_id_event bev; - char filename[PATH_MAX]; - u64 limit = offset + size; - - while (offset < limit) { - ssize_t len; - - if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) - return -1; - - if (header->needs_swap) - perf_event_header__bswap(&old_bev.header); - - len = old_bev.header.size - sizeof(old_bev); - if (read(input, filename, len) != len) - return -1; - - bev.header = old_bev.header; - - /* - * As the pid is the missing value, we need to fill - * it properly. The header.misc value give us nice hint. - */ - bev.pid = HOST_KERNEL_ID; - if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER || - bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL) - bev.pid = DEFAULT_GUEST_KERNEL_ID; - - memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id)); - __event_process_build_id(&bev, filename, session); - - offset += bev.header.size; - } - - return 0; -} - -static int perf_header__read_build_ids(struct perf_header *header, - int input, u64 offset, u64 size) -{ - struct perf_session *session = container_of(header, struct perf_session, header); - struct build_id_event bev; - char filename[PATH_MAX]; - u64 limit = offset + size, orig_offset = offset; - int err = -1; - - while (offset < limit) { - ssize_t len; - - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) - goto out; - - if (header->needs_swap) - perf_event_header__bswap(&bev.header); - - len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) - goto out; - /* - * The a1645ce1 changeset: - * - * "perf: 'perf kvm' tool for monitoring guest performance from host" - * - * Added a field to struct build_id_event that broke the file - * format. - * - * Since the kernel build-id is the first entry, process the - * table using the old format if the well known - * '[kernel.kallsyms]' string for the kernel build-id has the - * first 4 characters chopped off (where the pid_t sits). - */ - if (memcmp(filename, "nel.kallsyms]", 13) == 0) { - if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1) - return -1; - return perf_header__read_build_ids_abi_quirk(header, input, offset, size); - } - - __event_process_build_id(&bev, filename, session); - - offset += bev.header.size; - } - err = 0; -out: - return err; -} - static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, int feat, int fd, void *data __used) -- cgit v1.2.3-70-g09d2 From f1c67db7e351bf9fd328e368ba045cbeca11d513 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Fri, 10 Feb 2012 15:41:56 +0100 Subject: perf tools: Factor out feature op to process header sections There is individual code for each feature to process header sections. Adding a function pointer .process to struct feature_ops for keeping the implementation in separate functions. Code to process header sections is now a generic function. Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1328884916-5901-2-git-send-email-robert.richter@amd.com Signed-off-by: Robert Richter Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 44 +++++++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 5bb2d752ab8f..9f867d96c6a5 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1466,25 +1466,48 @@ out: return err; } +static int process_trace_info(struct perf_file_section *section __unused, + struct perf_header *ph __unused, + int feat __unused, int fd) +{ + trace_report(fd, false); + return 0; +} + +static int process_build_id(struct perf_file_section *section, + struct perf_header *ph, + int feat __unused, int fd) +{ + if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); + int (*process)(struct perf_file_section *section, + struct perf_header *h, int feat, int fd); const char *name; bool full_only; }; #define FEAT_OPA(n, func) \ [n] = { .name = #n, .write = write_##func, .print = print_##func } +#define FEAT_OPP(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func, \ + .process = process_##func } #define FEAT_OPF(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func, .full_only = true } + [n] = { .name = #n, .write = write_##func, .print = print_##func, \ + .full_only = true } /* feature_ops not implemented: */ #define print_trace_info NULL #define print_build_id NULL static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { - FEAT_OPA(HEADER_TRACE_INFO, trace_info), - FEAT_OPA(HEADER_BUILD_ID, build_id), + FEAT_OPP(HEADER_TRACE_INFO, trace_info), + FEAT_OPP(HEADER_BUILD_ID, build_id), FEAT_OPA(HEADER_HOSTNAME, hostname), FEAT_OPA(HEADER_OSRELEASE, osrelease), FEAT_OPA(HEADER_VERSION, version), @@ -1900,19 +1923,10 @@ static int perf_file_section__process(struct perf_file_section *section, return 0; } - switch (feat) { - case HEADER_TRACE_INFO: - trace_report(fd, false); - break; - case HEADER_BUILD_ID: - if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) - pr_debug("Failed to read buildids, continuing...\n"); - break; - default: - break; - } + if (!feat_ops[feat].process) + return 0; - return 0; + return feat_ops[feat].process(section, ph, feat, fd); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, -- cgit v1.2.3-70-g09d2 From 7e1ccd3804281fc0755eb726b654469c40a96d89 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 9 Feb 2012 16:12:38 +0100 Subject: perf tools: cleanup initialization of attr->size The perf_event_attr size needs to be initialized in all cases because it captures the ABI version. This patch moves the initialization of the field from the perf_event_open() syscall stub to its proper location in the event_attr_init(). Cc: Ingo Molnar Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120209151238.GA10272@quad Signed-off-by: Stephane Eranian Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.h | 1 - tools/perf/util/util.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/perf.h b/tools/perf/perf.h index deb17dba4a5b..03a045618148 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -167,7 +167,6 @@ sys_perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, int group_fd, unsigned long flags) { - attr->size = sizeof(*attr); return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index fb25d1329218..8109a907841e 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -14,6 +14,8 @@ void event_attr_init(struct perf_event_attr *attr) attr->exclude_host = 1; if (!perf_guest) attr->exclude_guest = 1; + /* to capture ABI version */ + attr->size = sizeof(*attr); } int mkdir_p(char *path, mode_t mode) -- cgit v1.2.3-70-g09d2 From 0c9781280fb672ca09c997df3f14ba506bbdb977 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Feb 2012 14:05:30 -0200 Subject: perf tools: Handle kernels that don't support attr.exclude_{guest,host} Just fall back to resetting those fields, if set, warning the user that that feature is not available. If guest samples appear they will just be discarded because no struct machine will be found and thus the event will be accounted as not handled and dropped, see 0c09571. Reported-by: Namhyung Kim Tested-by: Joerg Roedel Cc: David Ahern Cc: Frederic Weisbecker Cc: Joerg Roedel Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-vuwxig36mzprl5n7nzvnxxsh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 29 ++++++++++++++++++++--------- tools/perf/builtin-top.c | 23 +++++++++++++++++------ tools/perf/perf.h | 1 + tools/perf/util/top.h | 1 + 4 files changed, 39 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 08ed24b66ffe..d6c10e8ff6b6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -205,6 +205,9 @@ static void perf_record__open(struct perf_record *rec) if (opts->group && pos != first) group_fd = first->fd; +fallback_missing_features: + if (opts->exclude_guest_missing) + attr->exclude_guest = attr->exclude_host = 0; retry_sample_id: attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0; try_again: @@ -218,15 +221,23 @@ try_again: } else if (err == ENODEV && opts->cpu_list) { die("No such device - did you specify" " an out-of-range profile CPU?\n"); - } else if (err == EINVAL && opts->sample_id_all_avail) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - opts->sample_id_all_avail = false; - if (!opts->sample_time && !opts->raw_samples && !time_needed) - attr->sample_type &= ~PERF_SAMPLE_TIME; - - goto retry_sample_id; + } else if (err == EINVAL) { + if (!opts->exclude_guest_missing && + (attr->exclude_guest || attr->exclude_host)) { + pr_debug("Old kernel, cannot exclude " + "guest or host samples.\n"); + opts->exclude_guest_missing = true; + goto fallback_missing_features; + } else if (opts->sample_id_all_avail) { + /* + * Old kernel, no attr->sample_id_type_all field + */ + opts->sample_id_all_avail = false; + if (!opts->sample_time && !opts->raw_samples && !time_needed) + attr->sample_type &= ~PERF_SAMPLE_TIME; + + goto retry_sample_id; + } } /* diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5a88c0dadf15..02e11ff5a729 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -872,6 +872,9 @@ static void perf_top__start_counters(struct perf_top *top) attr->mmap = 1; attr->comm = 1; attr->inherit = top->inherit; +fallback_missing_features: + if (top->exclude_guest_missing) + attr->exclude_guest = attr->exclude_host = 0; retry_sample_id: attr->sample_id_all = top->sample_id_all_avail ? 1 : 0; try_again: @@ -883,12 +886,20 @@ try_again: if (err == EPERM || err == EACCES) { ui__error_paranoid(); goto out_err; - } else if (err == EINVAL && top->sample_id_all_avail) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - top->sample_id_all_avail = false; - goto retry_sample_id; + } else if (err == EINVAL) { + if (!top->exclude_guest_missing && + (attr->exclude_guest || attr->exclude_host)) { + pr_debug("Old kernel, cannot exclude " + "guest or host samples.\n"); + top->exclude_guest_missing = true; + goto fallback_missing_features; + } else if (top->sample_id_all_avail) { + /* + * Old kernel, no attr->sample_id_type_all field + */ + top->sample_id_all_avail = false; + goto retry_sample_id; + } } /* * If it's cycles then fall back to hrtimer diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 03a045618148..8b9c43635f4d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -199,6 +199,7 @@ struct perf_record_opts { bool sample_address; bool sample_time; bool sample_id_all_avail; + bool exclude_guest_missing; bool system_wide; bool period; unsigned int freq; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 49eb8481f19f..7dea8912aa97 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -35,6 +35,7 @@ struct perf_top { bool inherit; bool group; bool sample_id_all_avail; + bool exclude_guest_missing; bool dump_symtab; const char *cpu_list; struct hist_entry *sym_filter_entry; -- cgit v1.2.3-70-g09d2 From 808e122630d45a7f036d25582474d70548a87e2c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Feb 2012 14:18:57 -0200 Subject: perf tools: Invert the sample_id_all logic Instead of requiring that users of perf_record_opts set .sample_id_all_avail to true, just invert the logic, using .sample_id_all_missing, that doesn't need to be explicitely initialized since gcc will zero members ommitted in a struct initialization. Just like the newly introduced .exclude_{guest,host} feature test. 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-ab772uzk78cwybihf0vt7kxw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 7 +++---- tools/perf/builtin-test.c | 1 - tools/perf/builtin-top.c | 7 +++---- tools/perf/perf.h | 2 +- tools/perf/util/evsel.c | 4 ++-- tools/perf/util/top.h | 2 +- 6 files changed, 10 insertions(+), 13 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d6c10e8ff6b6..75d230fef202 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -209,7 +209,7 @@ fallback_missing_features: if (opts->exclude_guest_missing) attr->exclude_guest = attr->exclude_host = 0; retry_sample_id: - attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0; + attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(pos, evlist->cpus, evlist->threads, opts->group, group_fd) < 0) { @@ -228,11 +228,11 @@ try_again: "guest or host samples.\n"); opts->exclude_guest_missing = true; goto fallback_missing_features; - } else if (opts->sample_id_all_avail) { + } else if (!opts->sample_id_all_missing) { /* * Old kernel, no attr->sample_id_type_all field */ - opts->sample_id_all_avail = false; + opts->sample_id_all_missing = true; if (!opts->sample_time && !opts->raw_samples && !time_needed) attr->sample_type &= ~PERF_SAMPLE_TIME; @@ -660,7 +660,6 @@ static struct perf_record record = { .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .freq = 1000, - .sample_id_all_avail = true, }, .write_mode = WRITE_FORCE, .file_new = true, diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 0f151952a770..3e087ce8daa6 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -1013,7 +1013,6 @@ static int test__PERF_RECORD(void) .no_delay = true, .freq = 10, .mmap_pages = 256, - .sample_id_all_avail = true, }; cpu_set_t *cpu_mask = NULL; size_t cpu_mask_size = 0; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 02e11ff5a729..e3c63aef8efc 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -876,7 +876,7 @@ fallback_missing_features: if (top->exclude_guest_missing) attr->exclude_guest = attr->exclude_host = 0; retry_sample_id: - attr->sample_id_all = top->sample_id_all_avail ? 1 : 0; + attr->sample_id_all = top->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads, top->group, @@ -893,11 +893,11 @@ try_again: "guest or host samples.\n"); top->exclude_guest_missing = true; goto fallback_missing_features; - } else if (top->sample_id_all_avail) { + } else if (!top->sample_id_all_missing) { /* * Old kernel, no attr->sample_id_type_all field */ - top->sample_id_all_avail = false; + top->sample_id_all_missing = true; goto retry_sample_id; } } @@ -1122,7 +1122,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) .delay_secs = 2, .uid = UINT_MAX, .freq = 1000, /* 1 KHz */ - .sample_id_all_avail = true, .mmap_pages = 128, .sym_pcnt_filter = 5, }; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 8b9c43635f4d..f0227e93665d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -198,7 +198,7 @@ struct perf_record_opts { bool raw_samples; bool sample_address; bool sample_time; - bool sample_id_all_avail; + bool sample_id_all_missing; bool exclude_guest_missing; bool system_wide; bool period; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f910f50136d0..302d49a9f985 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -68,7 +68,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ - attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0; + attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; attr->inherit = !opts->no_inherit; attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | @@ -111,7 +111,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) if (opts->period) attr->sample_type |= PERF_SAMPLE_PERIOD; - if (opts->sample_id_all_avail && + if (!opts->sample_id_all_missing && (opts->sample_time || opts->system_wide || !opts->no_inherit || opts->cpu_list)) attr->sample_type |= PERF_SAMPLE_TIME; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 7dea8912aa97..ce61cb2d1acf 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -34,7 +34,7 @@ struct perf_top { bool vmlinux_warned; bool inherit; bool group; - bool sample_id_all_avail; + bool sample_id_all_missing; bool exclude_guest_missing; bool dump_symtab; const char *cpu_list; -- cgit v1.2.3-70-g09d2 From a5a178e1ae0192e405830f1bba84548992124e88 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Sun, 4 Sep 2011 16:08:59 +0100 Subject: perf tools: Allow expressions in __print_symbolic() fields The __print_symbolic() function takes a sequence of key-value pairs for pretty-printing a constant. The new kvm:kvm_exit print fmt uses the expression: __print_symbolic(..., { 0x040 + 1, "DB excp" }, ...) Currently only atoms are supported and this print fmt fails to parse. This patch adds support for expressions instead of just atoms so that 0x040 + 1 is parsed successfully. Also add arg_num_eval() support for the '+' operator. Acked-by: Steven Rostedt Cc: Ingo Molnar Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1315148939-14313-1-git-send-email-stefanha@linux.vnet.ibm.com Signed-off-by: Stefan Hajnoczi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/trace-event-parse.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index e0a4f652f289..a4088ced1e64 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -1423,6 +1423,11 @@ static long long arg_num_eval(struct print_arg *arg) die("unknown op '%s'", arg->op.op); } break; + case '+': + left = arg_num_eval(arg->op.left); + right = arg_num_eval(arg->op.right); + val = left + right; + break; default: die("unknown op '%s'", arg->op.op); } @@ -1483,6 +1488,13 @@ process_fields(struct event *event, struct print_flag_sym **list, char **tok) free_token(token); type = process_arg(event, arg, &token); + + if (type == EVENT_OP) + type = process_op(event, arg, &token); + + if (type == EVENT_ERROR) + goto out_free; + if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; -- cgit v1.2.3-70-g09d2 From dfd3b1e3e8a580bcbf854d46ae0f22c8333e82d8 Mon Sep 17 00:00:00 2001 From: Danny Kukawka Date: Thu, 16 Feb 2012 14:54:19 +0100 Subject: perf tools: Remove duplicated string.h includes tools/perf/util/probe-event.c included 'string.h' twice, remove the duplicate. Acked-by: Masami Hiramatsu Cc: Danny Kukawka Cc: Ingo Molnar Cc: Jovi Zhang Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1329400459-31570-1-git-send-email-danny.kukawka@bisect.de Signed-off-by: Danny Kukawka Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c1a513e56764..8379252e75c4 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -34,7 +34,6 @@ #include "util.h" #include "event.h" -#include "string.h" #include "strlist.h" #include "debug.h" #include "cache.h" -- 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') diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index e15983cf077d..84d9bd782004 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 From 41c21a68308f2f268a01ec1a7fa5f650e320a0f3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 12:13:36 +0900 Subject: perf evlist: Restore original errno after open failed If perf_evsel__open() failed, the errno was set and returned properly. However since the perf_evlist__open() called close() on fd's for all of evsel x cpu x thread after the failure, the errno was overridden by other code (EBADF). So the caller of the function ended up seeing different error message and getting confused. Fit it by restoring original return value. Because one of caller of the function is in the python extension, and it uses system errno internally, it'd be better restoring the original value rather than using the return value of the function directly, IMHO (i.e. I'm not a python expert :) Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329966816-23175-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f8da9fada002..159263d17c2d 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -765,6 +765,7 @@ out_err: list_for_each_entry_reverse(evsel, &evlist->entries, node) perf_evsel__close(evsel, ncpus, nthreads); + errno = -err; return err; } -- cgit v1.2.3-70-g09d2 From 67cbbd7f1838cc8f6900f39d860d6c2e1f86cf61 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 16:08:14 +0900 Subject: perf tools: Add descriptions of missing Makefile arguments There are some variable arguments can be specified on make invocation, but some of them are missing descriptions so that user cannot be informed easily. Fix it. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329980894-4289-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index e011b5060f92..fa043404479e 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -15,6 +15,16 @@ endif # Define V to have a more verbose compile. # +# Define O to save output files in a separate directory. +# +# Define ARCH as name of target architecture if you want cross-builds. +# +# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds. +# +# Define NO_LIBPERL to disable perl script extension. +# +# Define NO_LIBPYTHON to disable python script extension. +# # Define PYTHON to point to the python binary if the default # `python' is not correct; for example: PYTHON=python2 # @@ -32,6 +42,10 @@ endif # Define NO_DWARF if you do not want debug-info analysis feature at all. # # Define WERROR=0 to disable treating any warnings as errors. +# +# Define NO_NEWT if you do not want TUI support. +# +# Define NO_DEMANGLE if you do not want C++ symbol demangling. $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) -- cgit v1.2.3-70-g09d2 From 58e817d997d162682717dcaae39393dcadf5f296 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 17:46:20 +0900 Subject: perf annotate: Print asm code as blue when source code is displayed Print unselected asm code lines as blue. This is what we do now for --stdio. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329986784-4916-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ui/browsers/annotate.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 295a9c93f945..76caae95df39 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -69,14 +69,17 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro if (!self->navkeypressed) width += 1; + if (!ab->hide_src_code && ol->offset != -1) + if (!current_entry || (self->use_navkeypressed && + !self->navkeypressed)) + ui_browser__set_color(self, HE_COLORSET_CODE); + if (!*ol->line) slsmg_write_nstring(" ", width - 18); else slsmg_write_nstring(ol->line, width - 18); - if (!current_entry) - ui_browser__set_color(self, HE_COLORSET_CODE); - else + if (current_entry) ab->selection = ol; } -- cgit v1.2.3-70-g09d2 From ef7c537221160c285704997a913fb66ddc1fe6bc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 17:46:21 +0900 Subject: perf annotate: Handle lower case key code in annotate_browser__run() Accepting upper case character only is unconvenient since it requires SHIFT key too. Why not change to it accept a simple key stroke? Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329986784-4916-3-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ui/browsers/annotate.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 76caae95df39..374d3bc570b2 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -287,9 +287,11 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, nd = self->curr_hot; break; case 'H': + case 'h': nd = self->curr_hot; break; case 'S': + case 's': if (annotate_browser__toggle_source(self)) ui_helpline__puts(help); continue; -- cgit v1.2.3-70-g09d2 From 142cfbd0a0353bbcf4ce62f1d4b4ffaa5fe228f9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 17:46:22 +0900 Subject: perf annotate: Restore title when came back to original symbol On tui annotation, the title was set to name of the target symbol if user selects the target. However it remained after returning to original symbol from the target. Fix it. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329986784-4916-4-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ui/browsers/annotate.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 374d3bc570b2..e73357770d5d 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -343,6 +343,7 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, pthread_mutex_unlock(¬es->lock); symbol__tui_annotate(target, ms->map, evidx, timer, arg, delay_secs); + ui_browser__show_title(&self->b, sym->name); } continue; case K_LEFT: -- cgit v1.2.3-70-g09d2 From 824ac0e9838aadf5a398850c80ec2a43b9d0ca49 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 17:46:23 +0900 Subject: perf annotate: Fix help string on tui Separate multiple binding using /, capitalize descriptions, add missing key binding. Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329986784-4916-5-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ui/browsers/annotate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index e73357770d5d..57a4c6ef3fd2 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -233,9 +233,9 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, struct rb_node *nd = NULL; struct map_symbol *ms = self->b.priv; struct symbol *sym = ms->sym; - const char *help = "<-, ESC: exit, TAB/shift+TAB: cycle hottest lines, " - "H: Hottest, -> Line action, S -> Toggle source " - "code view"; + const char *help = "<-/ESC: Exit, TAB/shift+TAB: Cycle hot lines, " + "H: Go to hottest line, ->/ENTER: Line action, " + "S: Toggle source code view"; int key; if (ui_browser__show(&self->b, sym->name, help) < 0) -- cgit v1.2.3-70-g09d2 From ff2a6617c2acd6a8dc468c90ab8708a6ad112bb0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Feb 2012 17:46:24 +0900 Subject: perf annotate: Add missing newline on error message If perf.data couldn't find vmlinux image for the given build-id, it would print error message. However it lacked a newline at the end, so the output looked like below: $ perf annotate --stdio No vmlinux file with build id 63b554b2e90f14a4bced200008865e757d3e8b36 was found in the path. Please use: perf buildid-cache -av vmlinux or: --vmlinux vmlinux Percent | Source code & Disassembly of a.out ------------------------------------------------ : : : : Disassembly of section .text: : : 00000000004004f4 : 0.00 : 4004f4: push %rbp 0.00 : 4004f5: mov %rsp,%rbp 0.00 : 4004f8: movl $0x0,-0x4(%rbp) 0.00 : 4004ff: jmp 400517 14.70 : 400501: mov 0x200b28(%rip),%rax # 601030 0.02 : 400508: add $0x1,%rax 0.01 : 40050c: mov %rax,0x200b1d(%rip) # 601030 0.01 : 400513: addl $0x1,-0x4(%rbp) 13.92 : 400517: cmpl $0x98967f,-0x4(%rbp) 71.33 : 40051e: jle 400501 0.00 : 400520: leaveq 0.00 : 400521: retq Fix it by adding a newline at the end of the message. It doesn't affect the tui output AFAICS. New output will look like this: ... or: --vmlinux vmlinux Percent | Source code & Disassembly of a.out ------------------------------------------------ : : : : Disassembly of section .text: ... Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1329986784-4916-6-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 011ed2676604..e5a462f1d07c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -315,7 +315,7 @@ fallback: "Please use:\n\n" " perf buildid-cache -av vmlinux\n\n" "or:\n\n" - " --vmlinux vmlinux", + " --vmlinux vmlinux\n", sym->name, build_id_msg ?: ""); goto out_free_filename; } -- cgit v1.2.3-70-g09d2 From b5387528f31d98acedf06e930554b563d87e2383 Mon Sep 17 00:00:00 2001 From: Roberto Agostino Vitillo Date: Thu, 9 Feb 2012 23:21:01 +0100 Subject: perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK This patch adds: - ability to parse samples with PERF_SAMPLE_BRANCH_STACK - sort on branches (dso_from, symbol_from, dso_to, symbol_to, mispredict) - build histograms on branches Signed-off-by: Roberto Agostino Vitillo Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-12-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/perf.h | 17 +++ tools/perf/util/event.h | 1 + tools/perf/util/evsel.c | 10 ++ tools/perf/util/hist.c | 122 +++++++++++++++----- tools/perf/util/hist.h | 11 ++ tools/perf/util/session.c | 72 ++++++++++++ tools/perf/util/session.h | 4 + tools/perf/util/sort.c | 287 ++++++++++++++++++++++++++++++++++++++-------- tools/perf/util/sort.h | 9 ++ tools/perf/util/symbol.h | 13 +++ 10 files changed, 468 insertions(+), 78 deletions(-) (limited to 'tools') diff --git a/tools/perf/perf.h b/tools/perf/perf.h index f0227e93665d..358f40135c4d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -179,6 +179,23 @@ struct ip_callchain { u64 ips[0]; }; +struct branch_flags { + u64 mispred:1; + u64 predicted:1; + u64 reserved:62; +}; + +struct branch_entry { + u64 from; + u64 to; + struct branch_flags flags; +}; + +struct branch_stack { + u64 nr; + struct branch_entry entries[0]; +}; + extern bool perf_host, perf_guest; extern const char perf_version_string[]; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index cbdeaad9c5e5..1b197280c621 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -81,6 +81,7 @@ struct perf_sample { u32 raw_size; void *raw_data; struct ip_callchain *callchain; + struct branch_stack *branch_stack; }; #define BUILD_ID_SIZE 20 diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 302d49a9f985..a1fd1cd2a5af 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -576,6 +576,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, data->raw_data = (void *) pdata; } + if (type & PERF_SAMPLE_BRANCH_STACK) { + u64 sz; + + data->branch_stack = (struct branch_stack *)array; + array++; /* nr */ + + sz = data->branch_stack->nr * sizeof(struct branch_entry); + sz /= sizeof(u64); + array += sz; + } return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6f505d1abac7..8380c3db1c92 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists) hists__set_col_len(hists, col, 0); } +static void hists__set_unres_dso_col_len(struct hists *hists, int dso) +{ + const unsigned int unresolved_col_width = BITS_PER_LONG / 4; + + if (hists__col_len(hists, dso) < unresolved_col_width && + !symbol_conf.col_width_list_str && !symbol_conf.field_sep && + !symbol_conf.dso_list) + hists__set_col_len(hists, dso, unresolved_col_width); +} + static void hists__calc_col_len(struct hists *hists, struct hist_entry *h) { + const unsigned int unresolved_col_width = BITS_PER_LONG / 4; u16 len; if (h->ms.sym) - hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen); - else { - const unsigned int unresolved_col_width = BITS_PER_LONG / 4; - - if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width && - !symbol_conf.col_width_list_str && !symbol_conf.field_sep && - !symbol_conf.dso_list) - hists__set_col_len(hists, HISTC_DSO, - unresolved_col_width); - } + hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4); + else + hists__set_unres_dso_col_len(hists, HISTC_DSO); len = thread__comm_len(h->thread); if (hists__new_col_len(hists, HISTC_COMM, len)) @@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h) len = dso__name_len(h->ms.map->dso); hists__new_col_len(hists, HISTC_DSO, len); } + + if (h->branch_info) { + int symlen; + /* + * +4 accounts for '[x] ' priv level info + * +2 account of 0x prefix on raw addresses + */ + if (h->branch_info->from.sym) { + symlen = (int)h->branch_info->from.sym->namelen + 4; + hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); + + symlen = dso__name_len(h->branch_info->from.map->dso); + hists__new_col_len(hists, HISTC_DSO_FROM, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); + hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM); + } + + if (h->branch_info->to.sym) { + symlen = (int)h->branch_info->to.sym->namelen + 4; + hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); + + symlen = dso__name_len(h->branch_info->to.map->dso); + hists__new_col_len(hists, HISTC_DSO_TO, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); + hists__set_unres_dso_col_len(hists, HISTC_DSO_TO); + } + } } static void hist_entry__add_cpumode_period(struct hist_entry *he, @@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent) return 0; } -struct hist_entry *__hists__add_entry(struct hists *hists, +static struct hist_entry *add_hist_entry(struct hists *hists, + struct hist_entry *entry, struct addr_location *al, - struct symbol *sym_parent, u64 period) + u64 period) { struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = al->map, - .sym = al->sym, - }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, - .period = period, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - }; int cmp; pthread_mutex_lock(&hists->lock); @@ -225,7 +248,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, parent = *p; he = rb_entry(parent, struct hist_entry, rb_node_in); - cmp = hist_entry__cmp(&entry, he); + cmp = hist_entry__cmp(entry, he); if (!cmp) { he->period += period; @@ -239,7 +262,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, p = &(*p)->rb_right; } - he = hist_entry__new(&entry); + he = hist_entry__new(entry); if (!he) goto out_unlock; @@ -252,6 +275,51 @@ out_unlock: return he; } +struct hist_entry *__hists__add_branch_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + u64 period) +{ + struct hist_entry entry = { + .thread = al->thread, + .ms = { + .map = bi->to.map, + .sym = bi->to.sym, + }, + .cpu = al->cpu, + .ip = bi->to.addr, + .level = al->level, + .period = period, + .parent = sym_parent, + .filtered = symbol__parent_filter(sym_parent), + .branch_info = bi, + }; + + return add_hist_entry(self, &entry, al, period); +} + +struct hist_entry *__hists__add_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, u64 period) +{ + struct hist_entry entry = { + .thread = al->thread, + .ms = { + .map = al->map, + .sym = al->sym, + }, + .cpu = al->cpu, + .ip = al->addr, + .level = al->level, + .period = period, + .parent = sym_parent, + .filtered = symbol__parent_filter(sym_parent), + }; + + return add_hist_entry(self, &entry, al, period); +} + int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 48e5acd1e862..9413f3e31fea 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -42,6 +42,11 @@ enum hist_column { HISTC_COMM, HISTC_PARENT, HISTC_CPU, + HISTC_MISPREDICT, + HISTC_SYMBOL_FROM, + HISTC_SYMBOL_TO, + HISTC_DSO_FROM, + HISTC_DSO_TO, HISTC_NR_COLS, /* Last entry */ }; @@ -74,6 +79,12 @@ int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size, struct hists *hists); void hist_entry__free(struct hist_entry *); +struct hist_entry *__hists__add_branch_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + u64 period); + void hists__output_resort(struct hists *self); void hists__output_resort_threaded(struct hists *hists); void hists__collapse_resort(struct hists *self); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 9f833cf9c6a9..bec8a328b1b8 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -229,6 +229,63 @@ static bool symbol__match_parent_regex(struct symbol *sym) return 0; } +static const u8 cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL +}; +#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) + +static void ip__resolve_ams(struct machine *self, struct thread *thread, + struct addr_map_symbol *ams, + u64 ip) +{ + struct addr_location al; + size_t i; + u8 m; + + memset(&al, 0, sizeof(al)); + + for (i = 0; i < NCPUMODES; i++) { + m = cpumodes[i]; + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_addr_location(thread, self, m, MAP__FUNCTION, + ip, &al, NULL); + if (al.sym) + goto found; + } +found: + ams->addr = ip; + ams->sym = al.sym; + ams->map = al.map; +} + +struct branch_info *machine__resolve_bstack(struct machine *self, + struct thread *thr, + struct branch_stack *bs) +{ + struct branch_info *bi; + unsigned int i; + + bi = calloc(bs->nr, sizeof(struct branch_info)); + if (!bi) + return NULL; + + for (i = 0; i < bs->nr; i++) { + ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from); + bi[i].flags = bs->entries[i].flags; + } + return bi; +} + int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel, struct thread *thread, struct ip_callchain *chain, @@ -697,6 +754,18 @@ static void callchain__printf(struct perf_sample *sample) i, sample->callchain->ips[i]); } +static void branch_stack__printf(struct perf_sample *sample) +{ + uint64_t i; + + printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); + + for (i = 0; i < sample->branch_stack->nr; i++) + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n", + i, sample->branch_stack->entries[i].from, + sample->branch_stack->entries[i].to); +} + static void perf_session__print_tstamp(struct perf_session *session, union perf_event *event, struct perf_sample *sample) @@ -744,6 +813,9 @@ static void dump_sample(struct perf_session *session, union perf_event *event, if (session->sample_type & PERF_SAMPLE_CALLCHAIN) callchain__printf(sample); + + if (session->sample_type & PERF_SAMPLE_BRANCH_STACK) + branch_stack__printf(sample); } static struct machine * diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index c8d90178e7de..7a5434c00565 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -73,6 +73,10 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel struct ip_callchain *chain, struct symbol **parent); +struct branch_info *machine__resolve_bstack(struct machine *self, + struct thread *thread, + struct branch_stack *bs); + bool perf_session__has_traces(struct perf_session *self, const char *msg); void mem_bswap_64(void *src, int byte_size); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 16da30d8d765..2739ed10d5e6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -8,6 +8,7 @@ const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; int sort__need_collapse = 0; int sort__has_parent = 0; +bool sort__branch_mode; enum sort_type sort__first_dimension; @@ -94,6 +95,26 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); } +static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) +{ + struct dso *dso_l = map_l ? map_l->dso : NULL; + struct dso *dso_r = map_r ? map_r->dso : NULL; + const char *dso_name_l, *dso_name_r; + + if (!dso_l || !dso_r) + return cmp_null(dso_l, dso_r); + + if (verbose) { + dso_name_l = dso_l->long_name; + dso_name_r = dso_r->long_name; + } else { + dso_name_l = dso_l->short_name; + dso_name_r = dso_r->short_name; + } + + return strcmp(dso_name_l, dso_name_r); +} + struct sort_entry sort_comm = { .se_header = "Command", .se_cmp = sort__comm_cmp, @@ -107,36 +128,74 @@ struct sort_entry sort_comm = { static int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { - struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL; - struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL; - const char *dso_name_l, *dso_name_r; + return _sort__dso_cmp(left->ms.map, right->ms.map); +} - if (!dso_l || !dso_r) - return cmp_null(dso_l, dso_r); - if (verbose) { - dso_name_l = dso_l->long_name; - dso_name_r = dso_r->long_name; - } else { - dso_name_l = dso_l->short_name; - dso_name_r = dso_r->short_name; +static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r, + u64 ip_l, u64 ip_r) +{ + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + if (sym_l == sym_r) + return 0; + + if (sym_l) + ip_l = sym_l->start; + if (sym_r) + ip_r = sym_r->start; + + return (int64_t)(ip_r - ip_l); +} + +static int _hist_entry__dso_snprintf(struct map *map, char *bf, + size_t size, unsigned int width) +{ + if (map && map->dso) { + const char *dso_name = !verbose ? map->dso->short_name : + map->dso->long_name; + return repsep_snprintf(bf, size, "%-*s", width, dso_name); } - return strcmp(dso_name_l, dso_name_r); + return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); } static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width) { - if (self->ms.map && self->ms.map->dso) { - const char *dso_name = !verbose ? self->ms.map->dso->short_name : - self->ms.map->dso->long_name; - return repsep_snprintf(bf, size, "%-*s", width, dso_name); + return _hist_entry__dso_snprintf(self->ms.map, bf, size, width); +} + +static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, + u64 ip, char level, char *bf, size_t size, + unsigned int width __used) +{ + size_t ret = 0; + + if (verbose) { + char o = map ? dso__symtab_origin(map->dso) : '!'; + ret += repsep_snprintf(bf, size, "%-#*llx %c ", + BITS_PER_LONG / 4, ip, o); } - return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level); + if (sym) + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, + sym->name); + else { + size_t len = BITS_PER_LONG / 4; + ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", + len, ip); + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, ""); + } + + return ret; } + struct sort_entry sort_dso = { .se_header = "Shared Object", .se_cmp = sort__dso_cmp, @@ -144,8 +203,14 @@ struct sort_entry sort_dso = { .se_width_idx = HISTC_DSO, }; -/* --sort symbol */ +static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) +{ + return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, + self->level, bf, size, width); +} +/* --sort symbol */ static int64_t sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -163,31 +228,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) ip_l = left->ms.sym->start; ip_r = right->ms.sym->start; - return (int64_t)(ip_r - ip_l); -} - -static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) -{ - size_t ret = 0; - - if (verbose) { - char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!'; - ret += repsep_snprintf(bf, size, "%-#*llx %c ", - BITS_PER_LONG / 4, self->ip, o); - } - - if (!sort_dso.elide) - ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); - - if (self->ms.sym) - ret += repsep_snprintf(bf + ret, size - ret, "%s", - self->ms.sym->name); - else - ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx", - BITS_PER_LONG / 4, self->ip); - - return ret; + return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r); } struct sort_entry sort_sym = { @@ -246,19 +287,155 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +static int64_t +sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_cmp(left->branch_info->from.map, + right->branch_info->from.map); +} + +static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_snprintf(self->branch_info->from.map, + bf, size, width); +} + +struct sort_entry sort_dso_from = { + .se_header = "Source Shared Object", + .se_cmp = sort__dso_from_cmp, + .se_snprintf = hist_entry__dso_from_snprintf, + .se_width_idx = HISTC_DSO_FROM, +}; + +static int64_t +sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_cmp(left->branch_info->to.map, + right->branch_info->to.map); +} + +static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_snprintf(self->branch_info->to.map, + bf, size, width); +} + +static int64_t +sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct addr_map_symbol *from_l = &left->branch_info->from; + struct addr_map_symbol *from_r = &right->branch_info->from; + + if (!from_l->sym && !from_r->sym) + return right->level - left->level; + + return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr, + from_r->addr); +} + +static int64_t +sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct addr_map_symbol *to_l = &left->branch_info->to; + struct addr_map_symbol *to_r = &right->branch_info->to; + + if (!to_l->sym && !to_r->sym) + return right->level - left->level; + + return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr); +} + +static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) +{ + struct addr_map_symbol *from = &self->branch_info->from; + return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, + self->level, bf, size, width); + +} + +static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) +{ + struct addr_map_symbol *to = &self->branch_info->to; + return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, + self->level, bf, size, width); + +} + +struct sort_entry sort_dso_to = { + .se_header = "Target Shared Object", + .se_cmp = sort__dso_to_cmp, + .se_snprintf = hist_entry__dso_to_snprintf, + .se_width_idx = HISTC_DSO_TO, +}; + +struct sort_entry sort_sym_from = { + .se_header = "Source Symbol", + .se_cmp = sort__sym_from_cmp, + .se_snprintf = hist_entry__sym_from_snprintf, + .se_width_idx = HISTC_SYMBOL_FROM, +}; + +struct sort_entry sort_sym_to = { + .se_header = "Target Symbol", + .se_cmp = sort__sym_to_cmp, + .se_snprintf = hist_entry__sym_to_snprintf, + .se_width_idx = HISTC_SYMBOL_TO, +}; + +static int64_t +sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) +{ + const unsigned char mp = left->branch_info->flags.mispred != + right->branch_info->flags.mispred; + const unsigned char p = left->branch_info->flags.predicted != + right->branch_info->flags.predicted; + + return mp || p; +} + +static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width){ + static const char *out = "N/A"; + + if (self->branch_info->flags.predicted) + out = "N"; + else if (self->branch_info->flags.mispred) + out = "Y"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +struct sort_entry sort_mispredict = { + .se_header = "Branch Mispredicted", + .se_cmp = sort__mispredict_cmp, + .se_snprintf = hist_entry__mispredict_snprintf, + .se_width_idx = HISTC_MISPREDICT, +}; + struct sort_dimension { const char *name; struct sort_entry *entry; int taken; }; +#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } + static struct sort_dimension sort_dimensions[] = { - { .name = "pid", .entry = &sort_thread, }, - { .name = "comm", .entry = &sort_comm, }, - { .name = "dso", .entry = &sort_dso, }, - { .name = "symbol", .entry = &sort_sym, }, - { .name = "parent", .entry = &sort_parent, }, - { .name = "cpu", .entry = &sort_cpu, }, + DIM(SORT_PID, "pid", sort_thread), + DIM(SORT_COMM, "comm", sort_comm), + DIM(SORT_DSO, "dso", sort_dso), + DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), + DIM(SORT_DSO_TO, "dso_to", sort_dso_to), + DIM(SORT_SYM, "symbol", sort_sym), + DIM(SORT_SYM_TO, "symbol_from", sort_sym_from), + DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to), + DIM(SORT_PARENT, "parent", sort_parent), + DIM(SORT_CPU, "cpu", sort_cpu), + DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), }; int sort_dimension__add(const char *tok) @@ -270,7 +447,6 @@ int sort_dimension__add(const char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sd->entry == &sort_parent) { int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); if (ret) { @@ -302,6 +478,16 @@ int sort_dimension__add(const char *tok) sort__first_dimension = SORT_PARENT; else if (!strcmp(sd->name, "cpu")) sort__first_dimension = SORT_CPU; + else if (!strcmp(sd->name, "symbol_from")) + sort__first_dimension = SORT_SYM_FROM; + else if (!strcmp(sd->name, "symbol_to")) + sort__first_dimension = SORT_SYM_TO; + else if (!strcmp(sd->name, "dso_from")) + sort__first_dimension = SORT_DSO_FROM; + else if (!strcmp(sd->name, "dso_to")) + sort__first_dimension = SORT_DSO_TO; + else if (!strcmp(sd->name, "mispredict")) + sort__first_dimension = SORT_MISPREDICT; } list_add_tail(&sd->entry->list, &hist_entry__sort_list); @@ -309,7 +495,6 @@ int sort_dimension__add(const char *tok) return 0; } - return -ESRCH; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 3f67ae395752..7aa72a00bc8e 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -31,11 +31,14 @@ extern const char *parent_pattern; extern const char default_sort_order[]; extern int sort__need_collapse; extern int sort__has_parent; +extern bool sort__branch_mode; extern char *field_sep; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; extern struct sort_entry sort_parent; +extern struct sort_entry sort_lbr_dso; +extern struct sort_entry sort_lbr_sym; extern enum sort_type sort__first_dimension; /** @@ -72,6 +75,7 @@ struct hist_entry { struct hist_entry *pair; struct rb_root sorted_chain; }; + struct branch_info *branch_info; struct callchain_root callchain[0]; }; @@ -82,6 +86,11 @@ enum sort_type { SORT_SYM, SORT_PARENT, SORT_CPU, + SORT_DSO_FROM, + SORT_DSO_TO, + SORT_SYM_FROM, + SORT_SYM_TO, + SORT_MISPREDICT, }; /* diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2a683d4fc918..5866ce6b9c02 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -5,6 +5,7 @@ #include #include #include "map.h" +#include "../perf.h" #include #include #include @@ -120,6 +121,18 @@ struct map_symbol { bool has_children; }; +struct addr_map_symbol { + struct map *map; + struct symbol *sym; + u64 addr; +}; + +struct branch_info { + struct addr_map_symbol from; + struct addr_map_symbol to; + struct branch_flags flags; +}; + struct addr_location { struct thread *thread; struct map *map; -- cgit v1.2.3-70-g09d2 From bdfebd848f2a14e639031a0b0e61d7c7ee5e5fd2 Mon Sep 17 00:00:00 2001 From: Roberto Agostino Vitillo Date: Thu, 9 Feb 2012 23:21:02 +0100 Subject: perf record: Add support for sampling taken branch This patch adds a new option to enable taken branch stack sampling, i.e., leverage the PERF_SAMPLE_BRANCH_STACK feature of perf_events. There is a new option to active this mode: -b. It is possible to pass a set of filters to select the type of branches to sample. The following filters are available: - any : any type of branches - any_call : any function call or system call - any_ret : any function return or system call return - any_ind : any indirect branch - u: only when the branch target is at the user level - k: only when the branch target is in the kernel - hv: only when the branch target is in the hypervisor Filters can be combined by passing a comma separated list to the option: $ perf record -b any_call,u -e cycles:u branchy Signed-off-by: Roberto Agostino Vitillo Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-13-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/Documentation/perf-record.txt | 25 +++++++++++ tools/perf/builtin-record.c | 74 ++++++++++++++++++++++++++++++++ tools/perf/perf.h | 1 + tools/perf/util/evsel.c | 4 ++ 4 files changed, 104 insertions(+) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index a5766b4b0125..60bddaf0e5bd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -152,6 +152,31 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha corresponding events, i.e., they always refer to events defined earlier on the command line. +-b:: +--branch-stack:: +Enable taken branch stack sampling. Each sample captures a series of consecutive +taken branches. The number of branches captured with each sample depends on the +underlying hardware, the type of branches of interest, and the executed code. +It is possible to select the types of branches captured by enabling filters. The +following filters are defined: + + - any : any type of branches + - any_call: any function call or system call + - any_ret: any function return or system call return + - any_ind: any indirect branch + - u: only when the branch target is at the user level + - k: only when the branch target is in the kernel + - hv: only when the target is at the hypervisor level + ++ +At least one of any, any_call, any_ret, any_ind must be provided. The privilege levels may +be ommitted, in which case, the privilege levels of the associated event are applied to the +branch filter. Both kernel (k) and hypervisor (hv) privilege levels are subject to +permissions. When sampling on multiple events, branch stack sampling is enabled for all +the sampling events. The sampled branch type is the same for all events. +Note that taken branch sampling may not be available on all processors. +The various filters must be specified as a comma separated list: -b any_ret,u,k + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 75d230fef202..1c49d4e8767c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -638,6 +638,77 @@ out_delete_session: return err; } +#define BRANCH_OPT(n, m) \ + { .name = n, .mode = (m) } + +#define BRANCH_END { .name = NULL } + +struct branch_mode { + const char *name; + int mode; +}; + +static const struct branch_mode branch_modes[] = { + BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER), + BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL), + BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV), + BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY), + BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL), + BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN), + BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL), + BRANCH_END +}; + +static int +parse_branch_stack(const struct option *opt, const char *str, int unset __used) +{ +#define ONLY_PLM \ + (PERF_SAMPLE_BRANCH_USER |\ + PERF_SAMPLE_BRANCH_KERNEL |\ + PERF_SAMPLE_BRANCH_HV) + + uint64_t *mode = (uint64_t *)opt->value; + const struct branch_mode *br; + char *s, *os, *p; + int ret = -1; + + *mode = 0; + + /* because str is read-only */ + s = os = strdup(str); + if (!s) + return -1; + + for (;;) { + p = strchr(s, ','); + if (p) + *p = '\0'; + + for (br = branch_modes; br->name; br++) { + if (!strcasecmp(s, br->name)) + break; + } + if (!br->name) + goto error; + + *mode |= br->mode; + + if (!p) + break; + + s = p + 1; + } + ret = 0; + + if ((*mode & ~ONLY_PLM) == 0) { + error("need at least one branch type with -b\n"); + ret = -1; + } +error: + free(os); + return ret; +} + static const char * const record_usage[] = { "perf record [] []", "perf record [] -- []", @@ -727,6 +798,9 @@ const struct option record_options[] = { "monitor event in cgroup name only", parse_cgroups), OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"), + OPT_CALLBACK('b', "branch-stack", &record.opts.branch_stack, + "branch mode mask", "branch stack sampling modes", + parse_branch_stack), OPT_END() }; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 358f40135c4d..eec392e48067 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -222,6 +222,7 @@ struct perf_record_opts { unsigned int freq; unsigned int mmap_pages; unsigned int user_freq; + int branch_stack; u64 default_interval; u64 user_interval; const char *cpu_list; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a1fd1cd2a5af..f421f7cbc0d3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -126,6 +126,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) attr->watermark = 0; attr->wakeup_events = 1; } + if (opts->branch_stack) { + attr->sample_type |= PERF_SAMPLE_BRANCH_STACK; + attr->branch_sample_type = opts->branch_stack; + } attr->mmap = track; attr->comm = track; -- cgit v1.2.3-70-g09d2 From b50311dc2ac1c04ad19163c2359910b25e16caf6 Mon Sep 17 00:00:00 2001 From: Roberto Agostino Vitillo Date: Thu, 9 Feb 2012 23:21:03 +0100 Subject: perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/Documentation/perf-report.txt | 7 ++ tools/perf/builtin-report.c | 107 ++++++++++++++++++++++++++++--- 2 files changed, 105 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 9b430e98712e..19b9092cf8b7 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -153,6 +153,13 @@ OPTIONS information which may be very large and thus may clutter the display. It currently includes: cpu and numa topology of the host system. +-b:: +--branch-stack:: + Use the addresses of sampled taken branches instead of the instruction + address to build the histograms. To generate meaningful output, the + perf.data file must have been obtained using perf record -b xxx where + xxx is a branch filter option. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1] diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 25d34d483e49..528789f6c702 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -53,6 +53,50 @@ struct perf_report { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; +static int perf_report__add_branch_hist_entry(struct perf_tool *tool, + struct addr_location *al, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct perf_report *rep = container_of(tool, struct perf_report, tool); + struct symbol *parent = NULL; + int err = 0; + unsigned i; + struct hist_entry *he; + struct branch_info *bi; + + if ((sort__has_parent || symbol_conf.use_callchain) + && sample->callchain) { + err = machine__resolve_callchain(machine, evsel, al->thread, + sample->callchain, &parent); + if (err) + return err; + } + + bi = machine__resolve_bstack(machine, al->thread, + sample->branch_stack); + if (!bi) + return -ENOMEM; + + for (i = 0; i < sample->branch_stack->nr; i++) { + if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + continue; + /* + * The report shows the percentage of total branches captured + * and not events sampled. Thus we use a pseudo period of 1. + */ + he = __hists__add_branch_entry(&evsel->hists, al, parent, + &bi[i], 1); + if (he) { + evsel->hists.stats.total_period += 1; + hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + } else + return -ENOMEM; + } + return err; +} + static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample, @@ -126,14 +170,21 @@ static int process_sample_event(struct perf_tool *tool, if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; - if (al.map != NULL) - al.map->dso->hit = 1; + if (sort__branch_mode) { + if (perf_report__add_branch_hist_entry(tool, &al, sample, + evsel, machine)) { + pr_debug("problem adding lbr entry, skipping event\n"); + return -1; + } + } else { + if (al.map != NULL) + al.map->dso->hit = 1; - if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) { - pr_debug("problem incrementing symbol period, skipping event\n"); - return -1; + if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) { + pr_debug("problem incrementing symbol period, skipping event\n"); + return -1; + } } - return 0; } @@ -188,6 +239,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } } + if (sort__branch_mode) { + if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { + fprintf(stderr, "selected -b but no branch data." + " Did you call perf record without" + " -b?\n"); + return -1; + } + } + return 0; } @@ -477,7 +537,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) OPT_BOOLEAN(0, "stdio", &report.use_stdio, "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent"), + "sort by key(s): pid, comm, dso, symbol, parent, dso_to," + " dso_from, symbol_to, symbol_from, mispredict"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -517,6 +578,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), + OPT_BOOLEAN('b', "branch-stack", &sort__branch_mode, + "use branch records for histogram filling"), OPT_END() }; @@ -537,10 +600,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) report.input_name = "perf.data"; } - if (strcmp(report.input_name, "-") != 0) + if (sort__branch_mode) { + if (use_browser) + fprintf(stderr, "Warning: TUI interface not supported" + " in branch mode\n"); + if (symbol_conf.dso_list_str != NULL) + fprintf(stderr, "Warning: dso filtering not supported" + " in branch mode\n"); + if (symbol_conf.sym_list_str != NULL) + fprintf(stderr, "Warning: symbol filtering not" + " supported in branch mode\n"); + + report.use_stdio = true; + use_browser = 0; setup_browser(true); - else + symbol_conf.dso_list_str = NULL; + symbol_conf.sym_list_str = NULL; + + /* + * if no sort_order is provided, then specify branch-mode + * specific order + */ + if (sort_order == default_sort_order) + sort_order = "comm,dso_from,symbol_from," + "dso_to,symbol_to"; + + } else if (strcmp(report.input_name, "-") != 0) { + setup_browser(true); + } else { use_browser = 0; + } /* * Only in the newt browser we are doing integrated annotation, -- cgit v1.2.3-70-g09d2 From 69996df486fc3921bbaaa17fca0d68f537f9eabf Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 9 Feb 2012 23:21:06 +0100 Subject: perf tools: Enable reading of perf.data files from different ABI rev This patch allows perf to process perf.data files generated using an ABI that has a different perf_event_attr struct size, i.e., a different ABI version. The perf_event_attr can be extended, yet perf needs to cope with older perf.data files. Similarly, perf must be able to cope with a perf.data file which is using a newer version of the ABI than what it knows about. This patch adds read_attr(), a routine that reads a perf_event_attr struct from a file incrementally based on its advertised size. If the on-file struct is smaller than what perf knows, then the extra fields are zeroed. If the on-file struct is bigger, then perf only uses what it knows about, the rest is skipped. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-17-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/util/header.c | 53 ++++++++++++++++++++++++++++++++++++++++++----- tools/perf/util/session.c | 4 ++-- 2 files changed, 50 insertions(+), 7 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 9f867d96c6a5..666f18972fa3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1973,6 +1973,51 @@ static int perf_header__read_pipe(struct perf_session *session, int fd) return 0; } +static int read_attr(int fd, struct perf_header *ph, + struct perf_file_attr *f_attr) +{ + struct perf_event_attr *attr = &f_attr->attr; + size_t sz, left; + size_t our_sz = sizeof(f_attr->attr); + int ret; + + memset(f_attr, 0, sizeof(*f_attr)); + + /* read minimal guaranteed structure */ + ret = readn(fd, attr, PERF_ATTR_SIZE_VER0); + if (ret <= 0) { + pr_debug("cannot read %d bytes of header attr\n", + PERF_ATTR_SIZE_VER0); + return -1; + } + + /* on file perf_event_attr size */ + sz = attr->size; + if (ph->needs_swap) + sz = bswap_32(sz); + + if (sz == 0) { + /* assume ABI0 */ + sz = PERF_ATTR_SIZE_VER0; + } else if (sz > our_sz) { + pr_debug("file uses a more recent and unsupported ABI" + " (%zu bytes extra)\n", sz - our_sz); + return -1; + } + /* what we have not yet read and that we know about */ + left = sz - PERF_ATTR_SIZE_VER0; + if (left) { + void *ptr = attr; + ptr += PERF_ATTR_SIZE_VER0; + + ret = readn(fd, ptr, left); + } + /* read perf_file_section, ids are read in caller */ + ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids)); + + return ret <= 0 ? -1 : 0; +} + int perf_session__read_header(struct perf_session *session, int fd) { struct perf_header *header = &session->header; @@ -1988,19 +2033,17 @@ int perf_session__read_header(struct perf_session *session, int fd) if (session->fd_pipe) return perf_header__read_pipe(session, fd); - if (perf_file_header__read(&f_header, header, fd) < 0) { - pr_debug("incompatible file format\n"); + if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; - } - nr_attrs = f_header.attrs.size / sizeof(f_attr); + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); for (i = 0; i < nr_attrs; i++) { struct perf_evsel *evsel; off_t tmp; - if (readn(fd, &f_attr, sizeof(f_attr)) <= 0) + if (read_attr(fd, header, &f_attr) < 0) goto out_errno; if (header->needs_swap) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index bec8a328b1b8..e650de8f4396 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force) self->fd = STDIN_FILENO; if (perf_session__read_header(self, self->fd) < 0) - pr_err("incompatible file format"); + pr_err("incompatible file format (rerun with -v to learn more)"); return 0; } @@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force) } if (perf_session__read_header(self, self->fd) < 0) { - pr_err("incompatible file format"); + pr_err("incompatible file format (rerun with -v to learn more)"); goto out_close; } -- cgit v1.2.3-70-g09d2 From 62db90681c0db8c76e5db006b929a2edd5d12ae6 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 9 Feb 2012 23:21:07 +0100 Subject: perf tools: Fix ABI compatibility bug in print_event_desc() This patches cleans up local variable types for msz and ret. They need to be size_t and ssize_t respectively. It also fixes a bug whereby perf would not read attr struct with a different size than what it knows about. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-18-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/util/header.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 666f18972fa3..6d580267d043 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1144,8 +1144,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) uint64_t id; void *buf = NULL; char *str; - u32 nre, sz, nr, i, j, msz; - int ret; + u32 nre, sz, nr, i, j; + ssize_t ret; + size_t msz; /* number of events */ ret = read(fd, &nre, sizeof(nre)); @@ -1162,25 +1163,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) if (ph->needs_swap) sz = bswap_32(sz); - /* - * ensure it is at least to our ABI rev - */ - if (sz < (u32)sizeof(attr)) - goto error; - memset(&attr, 0, sizeof(attr)); - /* read entire region to sync up to next field */ + /* buffer to hold on file attr struct */ buf = malloc(sz); if (!buf) goto error; msz = sizeof(attr); - if (sz < msz) + if (sz < (ssize_t)msz) msz = sz; for (i = 0 ; i < nre; i++) { + /* + * must read entire on-file attr struct to + * sync up with layout. + */ ret = read(fd, buf, sz); if (ret != (ssize_t)sz) goto error; -- cgit v1.2.3-70-g09d2 From 114382a0aea97974803c942f106d462cbca5c64d Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 9 Feb 2012 23:21:08 +0100 Subject: perf tools: Make perf able to read files from older ABIs This patches provides a way to handle legacy perf.data files. Legacy files are those using the older PERFFILE signature. For those, it is still necessary to detect endianness but without comparing their header->attr_size with the tool's own version as it may be different. Instead, we use a reference table for all known sizes from the legacy era. We try all the combinations for sizes and endianness. If we find a match, we proceed, otherwise we return: "incompatible file format". This is also done for the pipe-mode file format. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-19-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/util/header.c | 122 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 94 insertions(+), 28 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 6d580267d043..c851495b9b48 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1803,35 +1803,101 @@ out_free: return err; } -static int check_magic_endian(u64 *magic, struct perf_file_header *header, - struct perf_header *ph) +static const int attr_file_abi_sizes[] = { + [0] = PERF_ATTR_SIZE_VER0, + [1] = PERF_ATTR_SIZE_VER1, + 0, +}; + +/* + * In the legacy file format, the magic number is not used to encode endianness. + * hdr_sz was used to encode endianness. But given that hdr_sz can vary based + * on ABI revisions, we need to try all combinations for all endianness to + * detect the endianness. + */ +static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph) { - int ret; + uint64_t ref_size, attr_size; + int i; - /* check for legacy format */ - ret = memcmp(magic, __perf_magic1, sizeof(*magic)); - if (ret == 0) { - pr_debug("legacy perf.data format\n"); - if (!header) - return -1; + for (i = 0 ; attr_file_abi_sizes[i]; i++) { + ref_size = attr_file_abi_sizes[i] + + sizeof(struct perf_file_section); + if (hdr_sz != ref_size) { + attr_size = bswap_64(hdr_sz); + if (attr_size != ref_size) + continue; - if (header->attr_size != sizeof(struct perf_file_attr)) { - u64 attr_size = bswap_64(header->attr_size); + ph->needs_swap = true; + } + pr_debug("ABI%d perf.data file detected, need_swap=%d\n", + i, + ph->needs_swap); + return 0; + } + /* could not determine endianness */ + return -1; +} - if (attr_size != sizeof(struct perf_file_attr)) - return -1; +#define PERF_PIPE_HDR_VER0 16 + +static const size_t attr_pipe_abi_sizes[] = { + [0] = PERF_PIPE_HDR_VER0, + 0, +}; + +/* + * In the legacy pipe format, there is an implicit assumption that endiannesss + * between host recording the samples, and host parsing the samples is the + * same. This is not always the case given that the pipe output may always be + * redirected into a file and analyzed on a different machine with possibly a + * different endianness and perf_event ABI revsions in the perf tool itself. + */ +static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) +{ + u64 attr_size; + int i; + + for (i = 0 ; attr_pipe_abi_sizes[i]; i++) { + if (hdr_sz != attr_pipe_abi_sizes[i]) { + attr_size = bswap_64(hdr_sz); + if (attr_size != hdr_sz) + continue; ph->needs_swap = true; } + pr_debug("Pipe ABI%d perf.data file detected\n", i); return 0; } + return -1; +} + +static int check_magic_endian(u64 magic, uint64_t hdr_sz, + bool is_pipe, struct perf_header *ph) +{ + int ret; + + /* check for legacy format */ + ret = memcmp(&magic, __perf_magic1, sizeof(magic)); + if (ret == 0) { + pr_debug("legacy perf.data format\n"); + if (is_pipe) + return try_all_pipe_abis(hdr_sz, ph); + + return try_all_file_abis(hdr_sz, ph); + } + /* + * the new magic number serves two purposes: + * - unique number to identify actual perf.data files + * - encode endianness of file + */ - /* check magic number with same endianness */ - if (*magic == __perf_magic2) + /* check magic number with one endianness */ + if (magic == __perf_magic2) return 0; - /* check magic number but opposite endianness */ - if (*magic != __perf_magic2_sw) + /* check magic number with opposite endianness */ + if (magic != __perf_magic2_sw) return -1; ph->needs_swap = true; @@ -1850,8 +1916,11 @@ int perf_file_header__read(struct perf_file_header *header, if (ret <= 0) return -1; - if (check_magic_endian(&header->magic, header, ph) < 0) + if (check_magic_endian(header->magic, + header->attr_size, false, ph) < 0) { + pr_debug("magic/endian check failed\n"); return -1; + } if (ph->needs_swap) { mem_bswap_64(header, offsetof(struct perf_file_header, @@ -1938,21 +2007,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, if (ret <= 0) return -1; - if (check_magic_endian(&header->magic, NULL, ph) < 0) + if (check_magic_endian(header->magic, header->size, true, ph) < 0) { + pr_debug("endian/magic failed\n"); return -1; + } + + if (ph->needs_swap) + header->size = bswap_64(header->size); if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) return -1; - if (header->size != sizeof(*header)) { - u64 size = bswap_64(header->size); - - if (size != sizeof(*header)) - return -1; - - ph->needs_swap = true; - } - return 0; } @@ -1992,6 +2057,7 @@ static int read_attr(int fd, struct perf_header *ph, /* on file perf_event_attr size */ sz = attr->size; + if (ph->needs_swap) sz = bswap_32(sz); -- cgit v1.2.3-70-g09d2 From a5aabdacde9caff54886ae454e0fad2f26929753 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 8 Mar 2012 23:47:45 +0100 Subject: perf record: Provide default branch stack sampling mode option This patch chanegs the logic of the -b, --branch-stack options of perf record. Based on users' request, the patch provides a default filter mode with the -b (or --branch-any) option. With the option, any type of taken branches is sampled. With -j (or --branch-filter), the user can specify any valid combination of branch types and privilege levels if supported by the underlying hardware. The -b (--branch any) is a shortcut for: --branch-filter any. $ perf record -b foo or: $ perf record --branch-filter any foo For more specific filtering: $ perf record --branch-filter ind_call,u foo Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/Documentation/perf-record.txt | 23 ++++++----- tools/perf/builtin-record.c | 68 ++++++++++++++++++++------------ 2 files changed, 57 insertions(+), 34 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 60bddaf0e5bd..a1386b2fff00 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -153,14 +153,19 @@ corresponding events, i.e., they always refer to events defined earlier on the c line. -b:: ---branch-stack:: +--branch-any:: +Enable taken branch stack sampling. Any type of taken branch may be sampled. +This is a shortcut for --branch-filter any. See --branch-filter for more infos. + +-j:: +--branch-filter:: Enable taken branch stack sampling. Each sample captures a series of consecutive taken branches. The number of branches captured with each sample depends on the underlying hardware, the type of branches of interest, and the executed code. It is possible to select the types of branches captured by enabling filters. The following filters are defined: - - any : any type of branches + - any: any type of branches - any_call: any function call or system call - any_ret: any function return or system call return - any_ind: any indirect branch @@ -169,13 +174,13 @@ following filters are defined: - hv: only when the target is at the hypervisor level + -At least one of any, any_call, any_ret, any_ind must be provided. The privilege levels may -be ommitted, in which case, the privilege levels of the associated event are applied to the -branch filter. Both kernel (k) and hypervisor (hv) privilege levels are subject to -permissions. When sampling on multiple events, branch stack sampling is enabled for all -the sampling events. The sampled branch type is the same for all events. -Note that taken branch sampling may not be available on all processors. -The various filters must be specified as a comma separated list: -b any_ret,u,k +The option requires at least one branch type among any, any_call, any_ret, ind_call. +The privilege levels may be ommitted, in which case, the privilege levels of the associated +event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege +levels are subject to permissions. When sampling on multiple events, branch stack sampling +is enabled for all the sampling events. The sampled branch type is the same for all events. +The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k +Note that this feature may not be available on all processors. SEE ALSO -------- diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 1c49d4e8767c..a7c53a9ef372 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -660,7 +660,7 @@ static const struct branch_mode branch_modes[] = { }; static int -parse_branch_stack(const struct option *opt, const char *str, int unset __used) +parse_branch_stack(const struct option *opt, const char *str, int unset) { #define ONLY_PLM \ (PERF_SAMPLE_BRANCH_USER |\ @@ -669,40 +669,53 @@ parse_branch_stack(const struct option *opt, const char *str, int unset __used) uint64_t *mode = (uint64_t *)opt->value; const struct branch_mode *br; - char *s, *os, *p; + char *s, *os = NULL, *p; int ret = -1; - *mode = 0; + if (unset) + return 0; - /* because str is read-only */ - s = os = strdup(str); - if (!s) + /* + * cannot set it twice, -b + --branch-filter for instance + */ + if (*mode) return -1; - for (;;) { - p = strchr(s, ','); - if (p) - *p = '\0'; - - for (br = branch_modes; br->name; br++) { - if (!strcasecmp(s, br->name)) - break; - } - if (!br->name) - goto error; + /* str may be NULL in case no arg is passed to -b */ + if (str) { + /* because str is read-only */ + s = os = strdup(str); + if (!s) + return -1; + + for (;;) { + p = strchr(s, ','); + if (p) + *p = '\0'; + + for (br = branch_modes; br->name; br++) { + if (!strcasecmp(s, br->name)) + break; + } + if (!br->name) { + ui__warning("unknown branch filter %s," + " check man page\n", s); + goto error; + } - *mode |= br->mode; + *mode |= br->mode; - if (!p) - break; + if (!p) + break; - s = p + 1; + s = p + 1; + } } ret = 0; + /* default to any branch */ if ((*mode & ~ONLY_PLM) == 0) { - error("need at least one branch type with -b\n"); - ret = -1; + *mode = PERF_SAMPLE_BRANCH_ANY; } error: free(os); @@ -798,8 +811,13 @@ const struct option record_options[] = { "monitor event in cgroup name only", parse_cgroups), OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"), - OPT_CALLBACK('b', "branch-stack", &record.opts.branch_stack, - "branch mode mask", "branch stack sampling modes", + + OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack, + "branch any", "sample any taken branches", + parse_branch_stack), + + OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack, + "branch filter mask", "branch stack filter modes", parse_branch_stack), OPT_END() }; -- cgit v1.2.3-70-g09d2 From 330aa675b4f92a422cb6d3acbbfd16a628017520 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 8 Mar 2012 23:47:46 +0100 Subject: perf record: Add HEADER_BRANCH_STACK tag This patch adds a new feature bit, namely, HEADER_BRANCH_STACK. When present, it indicates that sample records may contain branch stack. This could be useful to a viewer to switch to branch mode without having to parse all the samples or without a specific cmdline option. This will be used in a subsequent patch to enhance perf report with branch stacks. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/builtin-record.c | 3 +++ tools/perf/util/header.c | 13 +++++++++++++ tools/perf/util/header.h | 2 +- 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a7c53a9ef372..be4e1eee782e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -473,6 +473,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) if (!have_tracepoints(&evsel_list->entries)) perf_header__clear_feat(&session->header, HEADER_TRACE_INFO); + if (!rec->opts.branch_stack) + perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); + if (!rec->file_new) { err = perf_session__read_header(session, output); if (err < 0) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index c851495b9b48..0d9b6da86a39 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1023,6 +1023,12 @@ write_it: return do_write_string(fd, buffer); } +static int write_branch_stack(int fd __used, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + return 0; +} + static void print_hostname(struct perf_header *ph, int fd, FILE *fp) { char *str = do_read_string(fd, ph); @@ -1315,6 +1321,12 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp) free(str); } +static void print_branch_stack(struct perf_header *ph __used, int fd __used, + FILE *fp) +{ + fprintf(fp, "# contains samples with branch stack\n"); +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -1519,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPA(HEADER_CMDLINE, cmdline), FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), + FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index e68f617d082f..21a6be09c129 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -27,7 +27,7 @@ enum { HEADER_EVENT_DESC, HEADER_CPU_TOPOLOGY, HEADER_NUMA_TOPOLOGY, - + HEADER_BRANCH_STACK, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; -- cgit v1.2.3-70-g09d2 From 993ac88d5892629fbe1f8a54857f9947f49f0d96 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 8 Mar 2012 23:47:47 +0100 Subject: perf report: Auto-detect branch stack sampling mode This patch enhances perf report to auto-detect when the perf.data file contains samples with branch stacks. That way it is not necessary to use the -b option. To force branch view mode to off, simply use --no-branch-stack. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-4-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/Documentation/perf-report.txt | 7 +++-- tools/perf/builtin-report.c | 50 ++++++++++++++++++++++---------- tools/perf/util/sort.c | 2 +- tools/perf/util/sort.h | 2 +- 4 files changed, 41 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 19b9092cf8b7..87feeee8b90c 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -157,8 +157,11 @@ OPTIONS --branch-stack:: Use the addresses of sampled taken branches instead of the instruction address to build the histograms. To generate meaningful output, the - perf.data file must have been obtained using perf record -b xxx where - xxx is a branch filter option. + perf.data file must have been obtained using perf record -b or + perf record --branch-filter xxx where xxx is a branch filter option. + perf report is able to auto-detect whether a perf.data file contains + branch stacks and it will automatically switch to the branch view mode, + unless --no-branch-stack is used. SEE ALSO -------- diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 528789f6c702..66e852376a05 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -170,7 +170,7 @@ static int process_sample_event(struct perf_tool *tool, if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; - if (sort__branch_mode) { + if (sort__branch_mode == 1) { if (perf_report__add_branch_hist_entry(tool, &al, sample, evsel, machine)) { pr_debug("problem adding lbr entry, skipping event\n"); @@ -239,7 +239,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } } - if (sort__branch_mode) { + if (sort__branch_mode == 1) { if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { fprintf(stderr, "selected -b but no branch data." " Did you call perf record without" @@ -306,7 +306,7 @@ static int __cmd_report(struct perf_report *rep) { int ret = -EINVAL; u64 nr_samples; - struct perf_session *session; + struct perf_session *session = rep->session; struct perf_evsel *pos; struct map *kernel_map; struct kmap *kernel_kmap; @@ -314,13 +314,6 @@ static int __cmd_report(struct perf_report *rep) signal(SIGINT, sig_handler); - session = perf_session__new(rep->input_name, O_RDONLY, - rep->force, false, &rep->tool); - if (session == NULL) - return -ENOMEM; - - rep->session = session; - if (rep->cpu_list) { ret = perf_session__cpu_bitmap(session, rep->cpu_list, rep->cpu_bitmap); @@ -487,9 +480,19 @@ setup: return 0; } +static int +parse_branch_mode(const struct option *opt __used, const char *str __used, int unset) +{ + sort__branch_mode = !unset; + return 0; +} + int cmd_report(int argc, const char **argv, const char *prefix __used) { + struct perf_session *session; struct stat st; + bool has_br_stack = false; + int ret = -1; char callchain_default_opt[] = "fractal,0.5,callee"; const char * const report_usage[] = { "perf report []", @@ -578,8 +581,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), - OPT_BOOLEAN('b', "branch-stack", &sort__branch_mode, - "use branch records for histogram filling"), + OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "", + "use branch records for histogram filling", parse_branch_mode), OPT_END() }; @@ -599,8 +602,20 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) else report.input_name = "perf.data"; } + session = perf_session__new(report.input_name, O_RDONLY, + report.force, false, &report.tool); + if (session == NULL) + return -ENOMEM; + + report.session = session; + + has_br_stack = perf_header__has_feat(&session->header, + HEADER_BRANCH_STACK); - if (sort__branch_mode) { + if (sort__branch_mode == -1 && has_br_stack) + sort__branch_mode = 1; + + if (sort__branch_mode == 1) { if (use_browser) fprintf(stderr, "Warning: TUI interface not supported" " in branch mode\n"); @@ -657,13 +672,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) } if (symbol__init() < 0) - return -1; + goto error; setup_sorting(report_usage, options); if (parent_pattern != default_parent_pattern) { if (sort_dimension__add("parent") < 0) - return -1; + goto error; /* * Only show the parent fields if we explicitly @@ -685,5 +700,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout); sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); - return __cmd_report(&report); + ret = __cmd_report(&report); +error: + perf_session__delete(session); + return ret; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2739ed10d5e6..88dbcf6f9575 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -8,7 +8,7 @@ const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; int sort__need_collapse = 0; int sort__has_parent = 0; -bool sort__branch_mode; +int sort__branch_mode = -1; /* -1 = means not set */ enum sort_type sort__first_dimension; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7aa72a00bc8e..8505b9bcfa36 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -31,7 +31,7 @@ extern const char *parent_pattern; extern const char default_sort_order[]; extern int sort__need_collapse; extern int sort__has_parent; -extern bool sort__branch_mode; +extern int sort__branch_mode; extern char *field_sep; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; -- cgit v1.2.3-70-g09d2 From a68c2c58171391ef368fced32a555b2f0ff106e5 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 8 Mar 2012 23:47:48 +0100 Subject: perf report: Enable TUI in branch view mode This patch updates perf report to support TUI mode when the perf.data file contains samples with branch stacks. For each row in the report, it is possible to annotate either the source or target of each branch. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-5-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 73 +++++++++++++++++++++++++------------ tools/perf/util/session.c | 1 + tools/perf/util/sort.h | 6 ++- tools/perf/util/symbol.h | 7 +++- tools/perf/util/ui/browsers/hists.c | 62 +++++++++++++++++++++++++------ 5 files changed, 111 insertions(+), 38 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 66e852376a05..8e91c6eba18a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -64,7 +64,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, int err = 0; unsigned i; struct hist_entry *he; - struct branch_info *bi; + struct branch_info *bi, *bx; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { @@ -87,13 +87,45 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, * and not events sampled. Thus we use a pseudo period of 1. */ he = __hists__add_branch_entry(&evsel->hists, al, parent, - &bi[i], 1); + &bi[i], 1); if (he) { + struct annotation *notes; + err = -ENOMEM; + bx = he->branch_info; + if (bx->from.sym && use_browser > 0) { + notes = symbol__annotation(bx->from.sym); + if (!notes->src + && symbol__alloc_hist(bx->from.sym) < 0) + goto out; + + err = symbol__inc_addr_samples(bx->from.sym, + bx->from.map, + evsel->idx, + bx->from.al_addr); + if (err) + goto out; + } + + if (bx->to.sym && use_browser > 0) { + notes = symbol__annotation(bx->to.sym); + if (!notes->src + && symbol__alloc_hist(bx->to.sym) < 0) + goto out; + + err = symbol__inc_addr_samples(bx->to.sym, + bx->to.map, + evsel->idx, + bx->to.al_addr); + if (err) + goto out; + } evsel->hists.stats.total_period += 1; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + err = 0; } else return -ENOMEM; } +out: return err; } @@ -615,32 +647,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) if (sort__branch_mode == -1 && has_br_stack) sort__branch_mode = 1; + /* sort__branch_mode could be 0 if --no-branch-stack */ if (sort__branch_mode == 1) { - if (use_browser) - fprintf(stderr, "Warning: TUI interface not supported" - " in branch mode\n"); - if (symbol_conf.dso_list_str != NULL) - fprintf(stderr, "Warning: dso filtering not supported" - " in branch mode\n"); - if (symbol_conf.sym_list_str != NULL) - fprintf(stderr, "Warning: symbol filtering not" - " supported in branch mode\n"); - - report.use_stdio = true; - use_browser = 0; - setup_browser(true); - symbol_conf.dso_list_str = NULL; - symbol_conf.sym_list_str = NULL; - /* - * if no sort_order is provided, then specify branch-mode - * specific order + * if no sort_order is provided, then specify + * branch-mode specific order */ if (sort_order == default_sort_order) sort_order = "comm,dso_from,symbol_from," "dso_to,symbol_to"; - } else if (strcmp(report.input_name, "-") != 0) { + } + + if (strcmp(report.input_name, "-") != 0) { setup_browser(true); } else { use_browser = 0; @@ -696,9 +715,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) if (argc) usage_with_options(report_usage, options); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout); sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); + + if (sort__branch_mode == 1) { + sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout); + sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout); + sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout); + sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout); + } else { + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout); + sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); + } ret = __cmd_report(&report); error: diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e650de8f4396..002ebbf59f48 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -263,6 +263,7 @@ static void ip__resolve_ams(struct machine *self, struct thread *thread, } found: ams->addr = ip; + ams->al_addr = al.addr; ams->sym = al.sym; ams->map = al.map; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 8505b9bcfa36..472aa5a63a58 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -37,8 +37,10 @@ extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; extern struct sort_entry sort_parent; -extern struct sort_entry sort_lbr_dso; -extern struct sort_entry sort_lbr_sym; +extern struct sort_entry sort_dso_from; +extern struct sort_entry sort_dso_to; +extern struct sort_entry sort_sym_from; +extern struct sort_entry sort_sym_to; extern enum sort_type sort__first_dimension; /** diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 5866ce6b9c02..ac49ef208a5f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -97,7 +97,11 @@ struct symbol_conf { *col_width_list_str; struct strlist *dso_list, *comm_list, - *sym_list; + *sym_list, + *dso_from_list, + *dso_to_list, + *sym_from_list, + *sym_to_list; const char *symfs; }; @@ -125,6 +129,7 @@ struct addr_map_symbol { struct map *map; struct symbol *sym; u64 addr; + u64 al_addr; }; struct branch_info { diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index bfba0490c098..951e2e985c87 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -805,8 +805,11 @@ static struct hist_browser *hist_browser__new(struct hists *hists) self->hists = hists; self->b.refresh = hist_browser__refresh; self->b.seek = ui_browser__hists_seek; - self->b.use_navkeypressed = true, - self->has_symbols = sort_sym.list.next != NULL; + self->b.use_navkeypressed = true; + if (sort__branch_mode == 1) + self->has_symbols = sort_sym_from.list.next != NULL; + else + self->has_symbols = sort_sym.list.next != NULL; } return self; @@ -861,6 +864,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, { struct hists *self = &evsel->hists; struct hist_browser *browser = hist_browser__new(self); + struct branch_info *bi; struct pstack *fstack; int key = -1; @@ -879,7 +883,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, char *options[16]; int nr_options = 0, choice = 0, i, annotate = -2, zoom_dso = -2, zoom_thread = -2, - browse_map = -2; + annotate_f = -2, annotate_t = -2, browse_map = -2; key = hist_browser__run(browser, ev_name, timer, arg, delay_secs); @@ -887,7 +891,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, thread = hist_browser__selected_thread(browser); dso = browser->selection->map ? browser->selection->map->dso : NULL; } - switch (key) { case K_TAB: case K_UNTAB: @@ -902,7 +905,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (!browser->has_symbols) { ui_browser__warning(&browser->b, delay_secs * 2, "Annotation is only available for symbolic views, " - "include \"sym\" in --sort to use it."); + "include \"sym*\" in --sort to use it."); continue; } @@ -972,12 +975,32 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (!browser->has_symbols) goto add_exit_option; - if (browser->selection != NULL && - browser->selection->sym != NULL && - !browser->selection->map->dso->annotate_warned && - asprintf(&options[nr_options], "Annotate %s", - browser->selection->sym->name) > 0) - annotate = nr_options++; + if (sort__branch_mode == 1) { + bi = browser->he_selection->branch_info; + if (browser->selection != NULL && + bi && + bi->from.sym != NULL && + !bi->from.map->dso->annotate_warned && + asprintf(&options[nr_options], "Annotate %s", + bi->from.sym->name) > 0) + annotate_f = nr_options++; + + if (browser->selection != NULL && + bi && + bi->to.sym != NULL && + !bi->to.map->dso->annotate_warned && + asprintf(&options[nr_options], "Annotate %s", + bi->to.sym->name) > 0) + annotate_t = nr_options++; + } else { + + if (browser->selection != NULL && + browser->selection->sym != NULL && + !browser->selection->map->dso->annotate_warned && + asprintf(&options[nr_options], "Annotate %s", + browser->selection->sym->name) > 0) + annotate = nr_options++; + } if (thread != NULL && asprintf(&options[nr_options], "Zoom %s %s(%d) thread", @@ -1010,13 +1033,28 @@ add_exit_option: if (choice == -1) continue; - if (choice == annotate) { + if (choice == annotate || choice == annotate_t || choice == annotate_f) { struct hist_entry *he; int err; do_annotate: he = hist_browser__selected_entry(browser); if (he == NULL) continue; + + /* + * we stash the branch_info symbol + map into the + * the ms so we don't have to rewrite all the annotation + * code to use branch_info. + * in branch mode, the ms struct is not used + */ + if (choice == annotate_f) { + he->ms.sym = he->branch_info->from.sym; + he->ms.map = he->branch_info->from.map; + } else if (choice == annotate_t) { + he->ms.sym = he->branch_info->to.sym; + he->ms.map = he->branch_info->to.map; + } + /* * Don't let this be freed, say, by hists__decay_entry. */ -- cgit v1.2.3-70-g09d2 From 8bcd65fd29e9abfb633bfd6eedaf24b22e211f3a Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 12 Mar 2012 16:13:29 +0100 Subject: perf report: Remove duplicate annotate choice in branch view mode This patch removes the duplicated annotate selection when browsing in branch view mode. If the sym and dso oof the branch source and target are the same, then only one annotate choice is proposed. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331565210-10865-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/util/ui/browsers/hists.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 951e2e985c87..40fd42470447 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -989,6 +989,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, bi && bi->to.sym != NULL && !bi->to.map->dso->annotate_warned && + (bi->to.sym != bi->from.sym || + bi->to.map->dso != bi->from.map->dso) && asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) annotate_t = nr_options++; -- cgit v1.2.3-70-g09d2 From 24bff2dc0f77b1f186b7bdf30060caf3df191a68 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 12 Mar 2012 16:13:30 +0100 Subject: perf report: Fix annotate double quit issue in branch view mode This patch fixes perf report to not go back two levels when pressing the 'q' key while annotating in branch view mode. When pressing 'q' in annotate mode and if the branch source and target belong to different functions, perf now brings up the annotation popup menu again to offer the option to annotate the other branch source or target. As part of the code restructuring in perf_evsel__hists_browse() we also fix a memory leak on options[] in case of error. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331565210-10865-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- tools/perf/util/ui/browsers/hists.c | 38 ++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 40fd42470447..de8ece8bcce3 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -856,6 +856,16 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, return printed; } +static inline void free_popup_options(char **options, int n) +{ + int i; + + for (i = 0; i < n; ++i) { + free(options[i]); + options[i] = NULL; + } +} + static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, bool left_exits, @@ -866,6 +876,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, struct hist_browser *browser = hist_browser__new(self); struct branch_info *bi; struct pstack *fstack; + char *options[16]; + int nr_options = 0; int key = -1; if (browser == NULL) @@ -877,14 +889,17 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, ui_helpline__push(helpline); + memset(options, 0, sizeof(options)); + while (1) { const struct thread *thread = NULL; const struct dso *dso = NULL; - char *options[16]; - int nr_options = 0, choice = 0, i, + int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, annotate_f = -2, annotate_t = -2, browse_map = -2; + nr_options = 0; + key = hist_browser__run(browser, ev_name, timer, arg, delay_secs); if (browser->he_selection != NULL) { @@ -1023,17 +1038,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, browse_map = nr_options++; add_exit_option: options[nr_options++] = (char *)"Exit"; - +retry_popup_menu: choice = ui__popup_menu(nr_options, options); - for (i = 0; i < nr_options - 1; ++i) - free(options[i]); - if (choice == nr_options - 1) break; - if (choice == -1) + if (choice == -1) { + free_popup_options(options, nr_options - 1); continue; + } if (choice == annotate || choice == annotate_t || choice == annotate_f) { struct hist_entry *he; @@ -1064,9 +1078,18 @@ do_annotate: err = hist_entry__tui_annotate(he, evsel->idx, timer, arg, delay_secs); he->used = false; + /* + * offer option to annotate the other branch source or target + * (if they exists) when returning from annotate + */ + if ((err == 'q' || err == CTRL('c')) + && annotate_t != -2 && annotate_f != -2) + goto retry_popup_menu; + ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries); if (err) ui_browser__handle_resize(&browser->b); + } else if (choice == browse_map) map__browse(browser->selection->map); else if (choice == zoom_dso) { @@ -1112,6 +1135,7 @@ out_free_stack: pstack__delete(fstack); out: hist_browser__delete(browser); + free_popup_options(options, nr_options - 1); return key; } -- cgit v1.2.3-70-g09d2