From 55d43bcafe78b6da33f8a49be68ef168f3cbfec9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 19 Feb 2015 15:00:22 -0500 Subject: perf trace: Fix SIGBUS failures due to misaligned accesses On Sparc64 perf-trace is failing in many spots due to extended load instructions being used on misaligned accesses. (gdb) run trace ls Starting program: /tmp/perf/perf trace ls [Thread debugging using libthread_db enabled] Detaching after fork from child process 169460. Program received signal SIGBUS, Bus error. 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61 warning: Source file is more recent than executable. 61 TP_UINT_FIELD(64); (gdb) bt 0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61 1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000, sample=0x7feffffa098) at builtin-trace.c:1701 2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160 3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609 4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341 5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400 6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444 7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559 (gdb) p *sample $1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082, stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36, data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0, branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = { offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0, values = 0x0}, one = {value = 0, id = 0}}}} (gdb) p *field $2 = {offset = 16, {integer = 0x14f4a8 , pointer = 0x14f4a8 }} sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded by the size as a u3. So accessing raw data with an extended load instruction causes the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size. Signed-off-by: David Ahern Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 5cd8497445fe..d95a8f4d988c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -52,7 +52,9 @@ struct tp_field { #define TP_UINT_FIELD(bits) \ static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - return *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ + return value; \ } TP_UINT_FIELD(8); @@ -63,7 +65,8 @@ TP_UINT_FIELD(64); #define TP_UINT_FIELD__SWAPPED(bits) \ static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - u##bits value = *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ return bswap_##bits(value);\ } @@ -1517,11 +1520,22 @@ static int trace__read_syscall_info(struct trace *trace, int id) return syscall__set_arg_fmts(sc); } +/* + * args is to be interpreted as a series of longs but we need to handle + * 8-byte unaligned accesses. args points to raw_data within the event + * and raw_data is guaranteed to be 8-byte unaligned because it is + * preceded by raw_size which is a u32. So we need to copy args to a temp + * variable to read it. Most notably this avoids extended load instructions + * on unaligned addresses + */ + static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, - unsigned long *args, struct trace *trace, + unsigned char *args, struct trace *trace, struct thread *thread) { size_t printed = 0; + unsigned char *p; + unsigned long val; if (sc->tp_format != NULL) { struct format_field *field; @@ -1537,12 +1551,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, field = field->next, ++arg.idx, bit <<= 1) { if (arg.mask & bit) continue; + + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * arg.idx; + memcpy(&val, p, sizeof(val)); + /* * Suppress this argument if its value is zero and * and we don't have a string associated in an * strarray for it. */ - if (args[arg.idx] == 0 && + if (val == 0 && !(sc->arg_scnprintf && sc->arg_scnprintf[arg.idx] == SCA_STRARRAY && sc->arg_parm[arg.idx])) @@ -1551,23 +1570,26 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, printed += scnprintf(bf + printed, size - printed, "%s%s: ", printed ? ", " : "", field->name); if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) { - arg.val = args[arg.idx]; + arg.val = val; if (sc->arg_parm) arg.parm = sc->arg_parm[arg.idx]; printed += sc->arg_scnprintf[arg.idx](bf + printed, size - printed, &arg); } else { printed += scnprintf(bf + printed, size - printed, - "%ld", args[arg.idx]); + "%ld", val); } } } else { int i = 0; while (i < 6) { + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * i; + memcpy(&val, p, sizeof(val)); printed += scnprintf(bf + printed, size - printed, "%sarg%d: %ld", - printed ? ", " : "", i, args[i]); + printed ? ", " : "", i, val); ++i; } } -- cgit v1.2.3 From 9aaf5a5f479bd68699f2e6f6e5e5f1253377b6da Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 19 Feb 2015 23:31:13 +0900 Subject: perf probe: Check kprobes blacklist when adding new events Recent linux kernel provides a blacklist of the functions which can not be probed. perf probe can now check this blacklist before setting new events and indicate better error message for users. Without this patch, ---- # perf probe --add vmalloc_fault Added new event: Failed to write event: Invalid argument Error: Failed to add events. ---- With this patch ---- # perf probe --add vmalloc_fault Added new event: Warning: Skipped probing on blacklisted function: vmalloc_fault ---- Reported-by: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150219143113.14434.5387.stgit@localhost.localdomain Signed-off-by: Masami Hiramatsu Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 109 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 108 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9dfbed96bf39..662d454cb667 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1903,6 +1903,95 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) return sl; } +struct kprobe_blacklist_node { + struct list_head list; + unsigned long start; + unsigned long end; + char *symbol; +}; + +static void kprobe_blacklist__delete(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + + while (!list_empty(blacklist)) { + node = list_first_entry(blacklist, + struct kprobe_blacklist_node, list); + list_del(&node->list); + free(node->symbol); + free(node); + } +} + +static int kprobe_blacklist__load(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + const char *__debugfs = debugfs_find_mountpoint(); + char buf[PATH_MAX], *p; + FILE *fp; + int ret; + + if (__debugfs == NULL) + return -ENOTSUP; + + ret = e_snprintf(buf, PATH_MAX, "%s/kprobes/blacklist", __debugfs); + if (ret < 0) + return ret; + + fp = fopen(buf, "r"); + if (!fp) + return -errno; + + ret = 0; + while (fgets(buf, PATH_MAX, fp)) { + node = zalloc(sizeof(*node)); + if (!node) { + ret = -ENOMEM; + break; + } + INIT_LIST_HEAD(&node->list); + list_add_tail(&node->list, blacklist); + if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + ret = -EINVAL; + break; + } + p = strchr(buf, '\t'); + if (p) { + p++; + if (p[strlen(p) - 1] == '\n') + p[strlen(p) - 1] = '\0'; + } else + p = (char *)"unknown"; + node->symbol = strdup(p); + if (!node->symbol) { + ret = -ENOMEM; + break; + } + pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + node->start, node->end, node->symbol); + ret++; + } + if (ret < 0) + kprobe_blacklist__delete(blacklist); + fclose(fp); + + return ret; +} + +static struct kprobe_blacklist_node * +kprobe_blacklist__find_by_address(struct list_head *blacklist, + unsigned long address) +{ + struct kprobe_blacklist_node *node; + + list_for_each_entry(node, blacklist, list) { + if (node->start <= address && address <= node->end) + return node; + } + + return NULL; +} + /* Show an event */ static int show_perf_probe_event(struct perf_probe_event *pev, const char *module) @@ -2117,6 +2206,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, char buf[64]; const char *event, *group; struct strlist *namelist; + LIST_HEAD(blacklist); + struct kprobe_blacklist_node *node; if (pev->uprobes) fd = open_uprobe_events(true); @@ -2134,11 +2225,25 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, pr_debug("Failed to get current event list.\n"); return -EIO; } + /* Get kprobe blacklist if exists */ + if (!pev->uprobes) { + ret = kprobe_blacklist__load(&blacklist); + if (ret < 0) + pr_debug("No kprobe blacklist support, ignored\n"); + } ret = 0; pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; + /* Ensure that the address is NOT blacklisted */ + node = kprobe_blacklist__find_by_address(&blacklist, + tev->point.address); + if (node) { + pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol); + continue; + } + if (pev->event) event = pev->event; else @@ -2189,13 +2294,15 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, allow_suffix = true; } - if (ret >= 0) { + /* Note that it is possible to skip all events because of blacklist */ + if (ret >= 0 && tev->event) { /* Show how to use the event. */ pr_info("\nYou can now use it in all perf tools, such as:\n\n"); pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } + kprobe_blacklist__delete(&blacklist); strlist__delete(namelist); close(fd); return ret; -- cgit v1.2.3 From eb47cb2eb22dfacac9689708f5bd3cb0e975e290 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Feb 2015 17:25:04 +0900 Subject: perf probe: Fix get_real_path to free allocated memory in error path Fix get_real_path to free allocated memory when comp_dir is used for complementing path and getting an error. Signed-off-by: Masami Hiramatsu Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150226082504.28125.74506.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 662d454cb667..4a93bf433344 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -549,9 +549,11 @@ static int get_real_path(const char *raw_path, const char *comp_dir, if (access(*new_path, R_OK) == 0) return 0; - if (!symbol_conf.source_prefix) + if (!symbol_conf.source_prefix) { /* In case of searching comp_dir, don't retry */ + zfree(new_path); return -errno; + } switch (errno) { case ENAMETOOLONG: -- cgit v1.2.3 From 38ae502b1df196f712f6f5d3609afc36337b330b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Feb 2015 11:47:18 -0300 Subject: perf probe: Handle strdup() failure We could end up returning 0 (Ok) with a NULL raw_path. Fix it. Acked-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Link: http://lkml.kernel.org/n/tip-l0kcbcg5f4nnzqt01cv42vec@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4a93bf433344..9526cf37682e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -533,7 +533,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir, else { if (access(raw_path, R_OK) == 0) { *new_path = strdup(raw_path); - return 0; + return *new_path ? 0 : -ENOMEM; } else return -errno; } -- cgit v1.2.3 From a50d11a10c2db86d7383c281d4e249d5393661e9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Feb 2015 15:54:40 +0900 Subject: perf buildid-cache: Add new buildid cache if update target is not cached Add new buildid cache if the update target file is not cached. This can happen when an old binary is replaced by new one after caching the old one. In this case, user sees his operation just failed. But it does not look straight, since user just pass the binary "path", not "build-id". ---- # ./perf buildid-cache --add ./perf (update ./perf to new binary) # ./perf buildid-cache --update ./perf ./perf wasn't in the cache # ---- This patch adds given new binary to cache if the new binary is not cached. So we'll not see the above error. ---- # ./perf buildid-cache --add ./perf (update ./perf to new binary) # ./perf buildid-cache --update ./perf # ---- Signed-off-by: Masami Hiramatsu Cc: Adrian Hunter Cc: Borislav Petkov Cc: Hemant Kumar Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150226065440.23912.1494.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-buildid-cache.txt | 11 ++++++++--- tools/perf/builtin-buildid-cache.c | 6 ++++-- tools/perf/util/build-id.c | 12 ++++++++++++ tools/perf/util/build-id.h | 1 + 4 files changed, 25 insertions(+), 5 deletions(-) diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 0294c57b1f5e..cec6b57e8be6 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -41,9 +41,14 @@ OPTIONS --missing=:: List missing build ids in the cache for the specified file. -u:: ---update:: - Update specified file of the cache. It can be used to update kallsyms - kernel dso to vmlinux in order to support annotation. +--update=:: + Update specified file of the cache. Note that this doesn't remove + older entires since those may be still needed for annotating old + (or remote) perf.data. Only if there is already a cache which has + exactly same build-id, that is replaced by new one. It can be used + to update kallsyms and kernel dso to vmlinux in order to support + annotation. + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index d929d9544664..e7568f5844ad 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -255,7 +255,7 @@ static int build_id_cache__update_file(const char *filename) u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - int err; + int err = 0; if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); @@ -263,7 +263,9 @@ static int build_id_cache__update_file(const char *filename) } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__remove_s(sbuild_id); + if (build_id_cache__cached(sbuild_id)) + err = build_id_cache__remove_s(sbuild_id); + if (!err) err = build_id_cache__add_s(sbuild_id, filename, false, false); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index adbc36028636..0bc33be5a78c 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -352,6 +352,18 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); } +bool build_id_cache__cached(const char *sbuild_id) +{ + bool ret = false; + char *filename = build_id__filename(sbuild_id, NULL, 0); + + if (filename && !access(filename, F_OK)) + ret = true; + free(filename); + + return ret; +} + int build_id_cache__remove_s(const char *sbuild_id) { const size_t size = PATH_MAX; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 31b3c6332a1a..2a094982f954 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -22,6 +22,7 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); +bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); -- cgit v1.2.3 From 94ba462d69efeba2f97111321a9ba1aa8141da57 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 9 Feb 2015 05:39:44 +0000 Subject: perf diff: Support for different binaries Currently, the perf diff only works with same binaries. That's because it compares the symbol start address. It doesn't work if the perf.data comes from different binaries. This patch matches the symbol names. Actually, perf diff once intended to compare the symbol names. The commit as below can look for a pair by name. 604c5c92972d (perf diff: Change the default sort order to "dso,symbol") However, at that time, perf diff used a global list of dsos. That means the binaries which has same name can only be loaded once. That's a problem for comparing different binaries. For example, we have an old binary and an updated binary. They very likely have same name and most of the functions, so only dsos from old binary will be loaded. When processing the data from updated binary, perf still use the symbol information from old binary. That's wrong. Then the commit as below used IP to replace symbol name. 9c443dfdd31e ("perf diff: Fix support for all --sort combinations") >From that time, perf diff starts to compare the symbol address. The global dsos is discarded from a patch in 2010. a1645ce12adb ("perf: 'perf kvm' tool for monitoring guest performance from host") However, at that time, perf diff already compared by address. So perf diff cannot work for different binaries as well. This patch actually rolls back the perf diff to original design. The document is also changed, so everybody knows the original design is to compare the symbol names. Here are some examples: The only difference between example_v1.c and example_v2.c is the location of f2 and f3. There is no change in behavior, but the previous perf diff display the wrong differential profile. example_v1.c noinline void f3(void) { volatile int i; for (i = 0; i < 10000;) { if(i%2) i++; else i++; } } noinline void f2(void) { volatile int a = 100, b, c; for (b = 0; b < 10000; b++) c = a * b; } noinline void f1(void) { f2(); f3(); } int main() { int i; for (i = 0; i < 100000; i++) f1(); } example_v2.c noinline void f2(void) { volatile int a = 100, b, c; for (b = 0; b < 10000; b++) c = a * b; } noinline void f3(void) { volatile int i; for (i = 0; i < 10000;) { if(i%2) i++; else i++; } } noinline void f1(void) { f2(); f3(); } int main() { int i; for (i = 0; i < 100000; i++) f1(); } [lk@localhost perf_diff]$ gcc example_v1.c -o example [lk@localhost perf_diff]$ perf record -o example_v1.data ./example [ perf record: Woken up 4 times to write data ] [ perf record: Captured and wrote 0.813 MB example_v1.data (~35522 samples) ] [lk@localhost perf_diff]$ gcc example_v2.c -o example [lk@localhost perf_diff]$ perf record -o example_v2.data ./example [ perf record: Woken up 4 times to write data ] [ perf record: Captured and wrote 0.824 MB example_v2.data (~36015 samples) ] Old perf diff result: [lk@localhost perf_diff]$ perf diff example_v1.data example_v2.data Event 'cycles' Baseline Delta Shared Object Symbol ........ ....... ................ ............................... [kernel.vmlinux] [k] __perf_event_task_sched_out 0.00% [kernel.vmlinux] [k] apic_timer_interrupt [kernel.vmlinux] [k] idle_cpu [kernel.vmlinux] [k] intel_pstate_timer_func [kernel.vmlinux] [k] native_read_msr_safe 0.00% [kernel.vmlinux] [k] native_read_tsc 0.00% [kernel.vmlinux] [k] native_write_msr_safe [kernel.vmlinux] [k] ntp_tick_length 0.00% [kernel.vmlinux] [k] rb_erase 0.00% [kernel.vmlinux] [k] tick_sched_timer 0.00% [kernel.vmlinux] [k] unmap_single_vma 0.00% [kernel.vmlinux] [k] update_wall_time 0.00% example [.] f1 46.24% example [.] f2 53.71% -7.55% example [.] f3 +53.81% example [.] f3 0.02% example [.] main New perf diff result: [lk@localhost perf_diff]$ perf diff example_v1.data example_v2.data [kernel.vmlinux] [k] __perf_event_task_sched_out 0.00% [kernel.vmlinux] [k] apic_timer_interrupt [kernel.vmlinux] [k] idle_cpu [kernel.vmlinux] [k] intel_pstate_timer_func [kernel.vmlinux] [k] native_read_msr_safe 0.00% [kernel.vmlinux] [k] native_read_tsc 0.00% [kernel.vmlinux] [k] native_write_msr_safe [kernel.vmlinux] [k] ntp_tick_length 0.00% [kernel.vmlinux] [k] rb_erase 0.00% [kernel.vmlinux] [k] tick_sched_timer 0.00% [kernel.vmlinux] [k] unmap_single_vma 0.00% [kernel.vmlinux] [k] update_wall_time 0.00% example [.] f1 46.24% -0.08% example [.] f2 53.71% +0.11% example [.] f3 0.02% example [.] main Signed-off-by: Kan Liang Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Andi Kleen Link: http://lkml.kernel.org/r/1423460384-11645-1-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-diff.txt | 5 +++++ tools/perf/util/sort.c | 9 +++++++++ 2 files changed, 14 insertions(+) diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index e463caa3eb49..518266192d67 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -20,6 +20,11 @@ If no parameters are passed it will assume perf.data.old and perf.data. The differential profile is displayed only for events matching both specified perf.data files. +If no parameters are passed the samples will be sorted by dso and symbol. +As the perf.data files could come from different binaries, the symbols addresses +could vary. So perf diff is based on the comparison of the files and +symbols name. + OPTIONS ------- -D:: diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 7a39c1ed8d37..4593f36ecc4c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1463,6 +1463,15 @@ int sort_dimension__add(const char *tok) sort__has_parent = 1; } else if (sd->entry == &sort_sym) { sort__has_sym = 1; + /* + * perf diff displays the performance difference amongst + * two or more perf.data files. Those files could come + * from different binaries. So we should not compare + * their ips, but the name of symbol. + */ + if (sort__mode == SORT_MODE__DIFF) + sd->entry->se_collapse = sort__sym_sort; + } else if (sd->entry == &sort_dso) { sort__has_dso = 1; } -- cgit v1.2.3 From f56847c2e99810781f6941d01baff9ae223eeac3 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Fri, 27 Feb 2015 18:52:53 +0800 Subject: perf probe: Fix a precedence bug The minus operator has higher precedence than ?: Add parentheses around ?: fix this. Before this patch: $ echo 'p:myprobe do_sys_open' > /sys/kernel/debug/tracing/kprobe_events $ perf probe -l -k ../vmlinux kprobes:myprobe (on do_sys_open) After this patch: $ echo 'p:myprobe do_sys_open' > /sys/kernel/debug/tracing/kprobe_events $ perf probe -l -k ../vmlinux kprobes:myprobe (on do_sys_open@linux.git/fs/open.c) Signed-off-by: He Kuang Acked-by: Masami Hiramatsu Cc: Wang Nan Link: http://lkml.kernel.org/r/1425034373-14511-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9526cf37682e..7c0e765fa2e3 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -151,7 +151,7 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) sym = __find_kernel_function_by_name(name, &map); if (sym) return map->unmap_ip(map, sym->start) - - (reloc) ? 0 : map->reloc; + ((reloc) ? 0 : map->reloc); } return 0; } -- cgit v1.2.3 From 1f924c29b5ab2257be88a2a4075d0800573d8479 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 19:53:46 +0800 Subject: perf data: Fix sentinel setting for data_cmds array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The recent new patch "perf tools: Add new 'perf data' command" (commit 2245bf14 in acme's git repo perf/core) has caused a building error when compiling the source code of perf: cc1: warnings being treated as errors builtin-data.c:89: error: missing initializer builtin-data.c:89: error: (near initialization for ‘data_cmds[1].summary’) make[2]: *** [builtin-data.o] Error 1 make[2]: *** Waiting for unfinished jobs.... LD bench/perf-in.o LD tests/perf-in.o make[1]: *** [perf-in.o] Error 2 make: *** [all] Error 2 This patch fixes the building error above. Signed-off-by: Yunlong Song Cc: Peter Zijlstra Cc: Jiri Olsa Cc: Paul Mackerras Cc: Wang Nan Link: http://lkml.kernel.org/r/1425038026-27604-1-git-send-email-yunlong.song@huawei.com [ .name == NULL ends the loop, use it instead of seting all fields to NULL ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index 9705ba7e4c16..155cf75b8199 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -86,7 +86,7 @@ static int cmd_data_convert(int argc, const char **argv, static struct data_cmd data_cmds[] = { { "convert", "converts data file between formats", cmd_data_convert }, - { NULL }, + { .name = NULL, }, }; int cmd_data(int argc, const char **argv, const char *prefix) -- cgit v1.2.3 From ab0e48002db818c1937f105cd18001dfdd3ce056 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:25 +0800 Subject: perf list: Sort the output of 'perf list' to view more clearly Sort the output according to ASCII character list (using strcmp), which supports both number sequence and alphabet sequence. Example: Before this patch: $ perf list List of pre-defined events (to be used in -e): cpu-cycles OR cycles [Hardware event] instructions [Hardware event] cache-references [Hardware event] cache-misses [Hardware event] branch-instructions OR branches [Hardware event] branch-misses [Hardware event] bus-cycles [Hardware event] ... ... jbd2:jbd2_start_commit [Tracepoint event] jbd2:jbd2_commit_locking [Tracepoint event] jbd2:jbd2_run_stats [Tracepoint event] block:block_rq_issue [Tracepoint event] block:block_bio_complete [Tracepoint event] block:block_bio_backmerge [Tracepoint event] block:block_getrq [Tracepoint event] ... ... After this patch: $ perf list List of pre-defined events (to be used in -e): branch-instructions OR branches [Hardware event] branch-misses [Hardware event] bus-cycles [Hardware event] cache-misses [Hardware event] cache-references [Hardware event] cpu-cycles OR cycles [Hardware event] instructions [Hardware event] ... ... block:block_bio_backmerge [Tracepoint event] block:block_bio_complete [Tracepoint event] block:block_getrq [Tracepoint event] block:block_rq_issue [Tracepoint event] jbd2:jbd2_commit_locking [Tracepoint event] jbd2:jbd2_run_stats [Tracepoint event] jbd2:jbd2_start_commit [Tracepoint event] ... ... Signed-off-by: Yunlong Song Tested-by: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-2-git-send-email-yunlong.song@huawei.com [ Don't forget closedir({sys,evt}_dir) when handling errors ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 216 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 193 insertions(+), 23 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 109ba5c8c2e5..f6822d9b2b53 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1089,6 +1089,14 @@ static const char * const event_type_descriptors[] = { "Hardware breakpoint", }; +static int cmp_string(const void *a, const void *b) +{ + const char * const *as = a; + const char * const *bs = b; + + return strcmp(*as, *bs); +} + /* * Print the events from /tracing/events */ @@ -1100,11 +1108,21 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; + char **evt_list = NULL; + unsigned int evt_i = 0, evt_num = 0; + bool evt_num_known = false; +restart: sys_dir = opendir(tracing_events_path); if (!sys_dir) return; + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_close_sys_dir; + } + for_each_subsystem(sys_dir, sys_dirent, sys_next) { if (subsys_glob != NULL && !strglobmatch(sys_dirent.d_name, subsys_glob)) @@ -1121,19 +1139,56 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, !strglobmatch(evt_dirent.d_name, event_glob)) continue; - if (name_only) { - printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name); + if (!evt_num_known) { + evt_num++; continue; } snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - printf(" %-50s [%s]\n", evt_path, - event_type_descriptors[PERF_TYPE_TRACEPOINT]); + + evt_list[evt_i] = strdup(evt_path); + if (evt_list[evt_i] == NULL) + goto out_close_evt_dir; + evt_i++; } closedir(evt_dir); } closedir(sys_dir); + + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + } + if (evt_num) + printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_close_evt_dir: + closedir(evt_dir); +out_close_sys_dir: + closedir(sys_dir); + + printf("FATAL: not enough memory to print %s\n", + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + if (evt_list) + goto out_free; } /* @@ -1218,20 +1273,61 @@ static void __print_events_type(u8 type, struct event_symbol *syms, unsigned max) { char name[64]; - unsigned i; + unsigned int i, evt_i = 0, evt_num = 0; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + syms -= max; + } for (i = 0; i < max ; i++, syms++) { if (!is_event_supported(type, i)) continue; + if (!evt_num_known) { + evt_num++; + continue; + } + if (strlen(syms->alias)) snprintf(name, sizeof(name), "%s OR %s", syms->symbol, syms->alias); else snprintf(name, sizeof(name), "%s", syms->symbol); - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; + } + + if (!evt_num_known) { + evt_num_known = true; + goto restart; } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) + printf(" %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]); + if (evt_num) + printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]); + if (evt_list) + goto out_free; } void print_events_type(u8 type) @@ -1244,8 +1340,17 @@ void print_events_type(u8 type) int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, printed = 0; + unsigned int type, op, i, evt_i = 0, evt_num = 0; char name[64]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + } for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { @@ -1263,27 +1368,66 @@ int print_hwcache_events(const char *event_glob, bool name_only) type | (op << 8) | (i << 16))) continue; - if (name_only) - printf("%s ", name); - else - printf(" %-50s [%s]\n", name, - event_type_descriptors[PERF_TYPE_HW_CACHE]); - ++printed; + if (!evt_num_known) { + evt_num++; + continue; + } + + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } } } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_HW_CACHE]); + } + if (evt_num) printf("\n"); - return printed; + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return evt_num; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[PERF_TYPE_HW_CACHE]); + if (evt_list) + goto out_free; + return evt_num; } static void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) { - unsigned i, printed = 0; + unsigned int i, evt_i = 0, evt_num = 0; char name[MAX_NAME_LEN]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + syms -= max; + } for (i = 0; i < max; i++, syms++) { @@ -1295,23 +1439,49 @@ static void print_symbol_events(const char *event_glob, unsigned type, if (!is_event_supported(type, i)) continue; - if (name_only) { - printf("%s ", syms->symbol); + if (!evt_num_known) { + evt_num++; continue; } - if (strlen(syms->alias)) + if (!name_only && strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else strncpy(name, syms->symbol, MAX_NAME_LEN); - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); - - printed++; + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]); + } + if (evt_num) printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]); + if (evt_list) + goto out_free; } /* -- cgit v1.2.3 From 161149513b3570ebd7fe14fc2ddc42cb46557e37 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:26 +0800 Subject: perf list: Allow listing events with 'tracepoint' prefix If somebody happens to name an event with the beginning of 'tracepoint' (e.g. tracepoint_foo), then it will never be showed with perf list event_glob, thus we parse the argument 'tracepoint' more carefully for accuracy. Example: Before this patch: $ perf list tracepoint_foo:* jbd2:jbd2_start_commit [Tracepoint event] jbd2:jbd2_commit_locking [Tracepoint event] jbd2:jbd2_run_stats [Tracepoint event] block:block_rq_issue [Tracepoint event] block:block_bio_complete [Tracepoint event] block:block_bio_backmerge [Tracepoint event] block:block_getrq [Tracepoint event] ... ... As shown above, all of the tracepoint events are printed. In fact, the command's real intention is to print the events of tracepoint_foo. After this patch: $ perf list tracepoint_foo:* tracepoint_foo:tp_foo_enter [Tracepoint event] tracepoint_foo:tp_foo_exit [Tracepoint event] As shown above, only the events of tracepoint_foo are printed. Signed-off-by: Yunlong Song Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-3-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index ad8018e26aa0..2acbcf0b554f 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -50,9 +50,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) } for (i = 0; i < argc; ++i) { - if (i) - putchar('\n'); - if (strncmp(argv[i], "tracepoint", 10) == 0) + if (strcmp(argv[i], "tracepoint") == 0) print_tracepoint_events(NULL, NULL, false); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) -- cgit v1.2.3 From ed45752061be11a40f57df4304296147dbda2da9 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:29 +0800 Subject: perf list: Avoid confusion of perf output and the next command prompt Distinguish the output of 'perf list --list-opts' or 'perf --list-cmds' with the next command prompt, which also happens in other cases (e.g. record, report ...). Example: Before this patch: $perf list --list-opts --raw-dump $ <-- the output and the next command prompt are at the same line After this patch: $perf list --list-opts --raw-dump $ <-- the new line Signed-off-by: Yunlong Song Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-6-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.c | 1 + tools/perf/util/parse-options.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index f3c66b81c6be..3df2665022be 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -223,6 +223,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) struct cmd_struct *p = commands+i; printf("%s ", p->cmd); } + putchar('\n'); exit(0); } else if (!strcmp(cmd, "--debug")) { if (*argc < 2) { diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 4ee9a86705ed..b0ef2d813d2f 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -508,12 +508,14 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o printf("--%s ", options->long_name); options++; } + putchar('\n'); exit(130); case PARSE_OPT_LIST_SUBCMDS: if (subcommands) { for (int i = 0; subcommands[i]; i++) printf("%s ", subcommands[i]); } + putchar('\n'); exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { -- cgit v1.2.3 From 3ef1e65c829c86ffaa94a4ed59fed5da37f9610a Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:30 +0800 Subject: perf tools: Remove the '--(null)' long_name for --list-opts If the long_name of a 'struct option' is defined as NULL, --list-opts will incorrectly print '--(null)' in its output. As a result, '--(null)' will finally appear in the case of bash completion, e.g. 'perf record --'. Example: Before this patch: $ perf record --list-opts --event --filter --pid --tid --realtime --no-buffering --raw-samples --all-cpus --cpu --count --output --no-inherit --freq --mmap-pages --group --(null) --call-graph --verbose --quiet --stat --data --timestamp --period --no-samples --no-buildid-cache --no-buildid --cgroup --delay --uid --branch-any --branch-filter --weight --transaction --per-thread --intr-regs After this patch: $ perf record --list-opts --event --filter --pid --tid --realtime --no-buffering --raw-samples --all-cpus --cpu --count --output --no-inherit --freq --mmap-pages --group --call-graph --verbose --quiet --stat --data --timestamp --period --no-samples --no-buildid-cache --no-buildid --cgroup --delay --uid --branch-any --branch-filter --weight --transaction --per-thread --intr-regs Signed-off-by: Yunlong Song Tested-by: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-7-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-options.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index b0ef2d813d2f..1457d6639b60 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -505,7 +505,8 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o break; case PARSE_OPT_LIST_OPTS: while (options->type != OPTION_END) { - printf("--%s ", options->long_name); + if (options->long_name) + printf("--%s ", options->long_name); options++; } putchar('\n'); -- cgit v1.2.3 From 705750f2d6e283ba2856ba8eda60dce2d405b387 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:27 +0800 Subject: perf list: Clean up the printing functions of hardware/software events Do not need print_events_type or __print_events_type for listing hw/sw events, let print_symbol_events do its job instead. Moreover, print_symbol_events can also handle event_glob and name_only. Signed-off-by: Yunlong Song Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-4-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 6 ++-- tools/perf/util/parse-events.c | 80 ++---------------------------------------- tools/perf/util/parse-events.h | 11 +++++- 3 files changed, 17 insertions(+), 80 deletions(-) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 2acbcf0b554f..8b323e015458 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -54,10 +54,12 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_tracepoint_events(NULL, NULL, false); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) - print_events_type(PERF_TYPE_HARDWARE); + print_symbol_events(NULL, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX, false); else if (strcmp(argv[i], "sw") == 0 || strcmp(argv[i], "software") == 0) - print_events_type(PERF_TYPE_SOFTWARE); + print_symbol_events(NULL, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX, false); else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) print_hwcache_events(NULL, false); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f6822d9b2b53..fe07573d5ed4 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -20,11 +20,6 @@ #define MAX_NAME_LEN 100 -struct event_symbol { - const char *symbol; - const char *alias; -}; - #ifdef PARSER_DEBUG extern int parse_events_debug; #endif @@ -39,7 +34,7 @@ static struct perf_pmu_event_symbol *perf_pmu_events_list; */ static int perf_pmu_events_list_num; -static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { +struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { .symbol = "cpu-cycles", .alias = "cycles", @@ -82,7 +77,7 @@ static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { }, }; -static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { +struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { [PERF_COUNT_SW_CPU_CLOCK] = { .symbol = "cpu-clock", .alias = "", @@ -1269,75 +1264,6 @@ static bool is_event_supported(u8 type, unsigned config) return ret; } -static void __print_events_type(u8 type, struct event_symbol *syms, - unsigned max) -{ - char name[64]; - unsigned int i, evt_i = 0, evt_num = 0; - char **evt_list = NULL; - bool evt_num_known = false; - -restart: - if (evt_num_known) { - evt_list = zalloc(sizeof(char *) * evt_num); - if (!evt_list) - goto out_enomem; - syms -= max; - } - - for (i = 0; i < max ; i++, syms++) { - if (!is_event_supported(type, i)) - continue; - - if (!evt_num_known) { - evt_num++; - continue; - } - - if (strlen(syms->alias)) - snprintf(name, sizeof(name), "%s OR %s", - syms->symbol, syms->alias); - else - snprintf(name, sizeof(name), "%s", syms->symbol); - - evt_list[evt_i] = strdup(name); - if (evt_list[evt_i] == NULL) - goto out_enomem; - evt_i++; - } - - if (!evt_num_known) { - evt_num_known = true; - goto restart; - } - qsort(evt_list, evt_num, sizeof(char *), cmp_string); - evt_i = 0; - while (evt_i < evt_num) - printf(" %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]); - if (evt_num) - printf("\n"); - -out_free: - evt_num = evt_i; - for (evt_i = 0; evt_i < evt_num; evt_i++) - zfree(&evt_list[evt_i]); - zfree(&evt_list); - return; - -out_enomem: - printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]); - if (evt_list) - goto out_free; -} - -void print_events_type(u8 type) -{ - if (type == PERF_TYPE_SOFTWARE) - __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); - else - __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); -} - int print_hwcache_events(const char *event_glob, bool name_only) { unsigned int type, op, i, evt_i = 0, evt_num = 0; @@ -1412,7 +1338,7 @@ out_enomem: return evt_num; } -static void print_symbol_events(const char *event_glob, unsigned type, +void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) { diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 39c3b57965d1..52a2dda4f954 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -116,7 +116,16 @@ void parse_events_update_lists(struct list_head *list_event, void parse_events_error(void *data, void *scanner, char const *msg); void print_events(const char *event_glob, bool name_only); -void print_events_type(u8 type); + +struct event_symbol { + const char *symbol; + const char *alias; +}; +extern struct event_symbol event_symbols_hw[]; +extern struct event_symbol event_symbols_sw[]; +void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max, + bool name_only); void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); -- cgit v1.2.3 From 5ef803ee02d67ad0b49f357cb7feb7d5e6b0015d Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:28 +0800 Subject: perf list: Extend raw-dump to certain kind of events Extend 'perf list --raw-dump' to 'perf list --raw-dump [hw|sw|cache |tracepoint|pmu|event_glob]' in order to show the raw-dump of a certain kind of events rather than all of the events. Example: Before this patch: $ perf list --raw-dump hw branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions stalled-cycles-backend stalled-cycles-frontend alignment-faults context-switches cpu-clock cpu-migrations emulation-faults major-faults minor-faults page-faults task-clock ... ... writeback:writeback_thread_start writeback:writeback_thread_stop writeback:writeback_wait_iff_congested writeback:writeback_wake_background writeback:writeback_wake_thread As shown above, all of the events are printed. After this patch: $ perf list --raw-dump hw branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions stalled-cycles-backend stalled-cycles-frontend As shown above, only the hw events are printed. Signed-off-by: Yunlong Song Tested-by: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-5-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-list.txt | 6 ++++++ tools/perf/builtin-list.c | 21 ++++++++------------- 2 files changed, 14 insertions(+), 13 deletions(-) diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 3e2aec94f806..4692d277980b 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -127,6 +127,12 @@ To limit the list use: One or more types can be used at the same time, listing the events for the types specified. +Support raw format: + +. '--raw-dump', shows the raw-dump of all the events. +. '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of + a certain kind of events. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1], diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 8b323e015458..af5bd0514108 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -36,41 +36,36 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) setup_pager(); - if (raw_dump) { - print_events(NULL, true); - return 0; - } - if (!raw_dump) printf("\nList of pre-defined events (to be used in -e):\n\n"); if (argc == 0) { - print_events(NULL, false); + print_events(NULL, raw_dump); return 0; } for (i = 0; i < argc; ++i) { if (strcmp(argv[i], "tracepoint") == 0) - print_tracepoint_events(NULL, NULL, false); + print_tracepoint_events(NULL, NULL, raw_dump); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) print_symbol_events(NULL, PERF_TYPE_HARDWARE, - event_symbols_hw, PERF_COUNT_HW_MAX, false); + event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); else if (strcmp(argv[i], "sw") == 0 || strcmp(argv[i], "software") == 0) print_symbol_events(NULL, PERF_TYPE_SOFTWARE, - event_symbols_sw, PERF_COUNT_SW_MAX, false); + event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) - print_hwcache_events(NULL, false); + print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) - print_pmu_events(NULL, false); + print_pmu_events(NULL, raw_dump); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; if (sep == NULL) { - print_events(argv[i], false); + print_events(argv[i], raw_dump); continue; } sep_idx = sep - argv[i]; @@ -79,7 +74,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) return -1; s[sep_idx] = '\0'; - print_tracepoint_events(s, s + sep_idx + 1, false); + print_tracepoint_events(s, s + sep_idx + 1, raw_dump); free(s); } } -- cgit v1.2.3 From 7335399a6a4bead9ef8b59ce7d811fc4e99ca98c Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 27 Feb 2015 18:21:31 +0800 Subject: perf tools: Fix the bash completion problem of 'perf --*' The perf-completion.sh uses a predefined string '--help --version --exec-path --html-path --paginate --no-pager --perf-dir --work-tree --debugfs-dir' for the bash completion of 'perf --*', which has two problems: Problem 1: If the options of perf are changed (see handle_options() in perf.c), the perf-completion.sh has to be changed at the same time. If not, the bash completion of 'perf --*' and the options which perf really supports will be inconsistent. Problem 2: When typing another single character after 'perf --', e.g. 'h', and hit TAB key to get the bash completion of 'perf --h', the character 'h' disappears at once. This is not what we want, we wish the bash completion can return '--help --html-path' and then we can continue to choose one. To solve this problem, we add '--list-opts' to perf, which now supports 'perf --list-opts' directly, and its result can be used in bash completion now. Example: Before this patch: $ perf --h <-- hit TAB key after character 'h' $ perf -- <-- 'h' disappears and no required result After this patch: $ perf --h <-- hit TAB key after character 'h' --help --html-path <-- the required result Signed-off-by: Yunlong Song Tested-by: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425032491-20224-8-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf-completion.sh | 6 ++---- tools/perf/perf.c | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 33569847fdcc..c2595e9bd69b 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -110,13 +110,11 @@ __perf_main () # List perf subcommands or long options if [ $cword -eq 1 ]; then if [[ $cur == --* ]]; then - __perfcomp '--help --version \ - --exec-path --html-path --paginate --no-pager \ - --perf-dir --work-tree --debugfs-dir' -- "$cur" + cmds=$($cmd --list-opts) else cmds=$($cmd --list-cmds) - __perfcomp "$cmds" "$cur" fi + __perfcomp "$cmds" "$cur" # List possible events for -e option elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then evts=$($cmd list --raw-dump) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 3df2665022be..b857fcbd00cf 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,6 +13,7 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" +#include "util/parse-options.h" #include "util/debug.h" #include #include @@ -125,6 +126,23 @@ static void commit_pager_choice(void) } } +struct option options[] = { + OPT_ARGUMENT("help", "help"), + OPT_ARGUMENT("version", "version"), + OPT_ARGUMENT("exec-path", "exec-path"), + OPT_ARGUMENT("html-path", "html-path"), + OPT_ARGUMENT("paginate", "paginate"), + OPT_ARGUMENT("no-pager", "no-pager"), + OPT_ARGUMENT("perf-dir", "perf-dir"), + OPT_ARGUMENT("work-tree", "work-tree"), + OPT_ARGUMENT("debugfs-dir", "debugfs-dir"), + OPT_ARGUMENT("buildid-dir", "buildid-dir"), + OPT_ARGUMENT("list-cmds", "list-cmds"), + OPT_ARGUMENT("list-opts", "list-opts"), + OPT_ARGUMENT("debug", "debug"), + OPT_END() +}; + static int handle_options(const char ***argv, int *argc, int *envchanged) { int handled = 0; @@ -225,6 +243,15 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) } putchar('\n'); exit(0); + } else if (!strcmp(cmd, "--list-opts")) { + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(options)-1; i++) { + struct option *p = options+i; + printf("--%s ", p->long_name); + } + putchar('\n'); + exit(0); } else if (!strcmp(cmd, "--debug")) { if (*argc < 2) { fprintf(stderr, "No variable specified for --debug.\n"); -- cgit v1.2.3 From 8d8c8e4cb3014fcc51f0e127b4316043306f5bb0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 27 Feb 2015 13:50:26 +0900 Subject: perf buildid-cache: Add --purge FILE to remove all caches of FILE Add --purge FILE to remove all caches of FILE. Since the current --remove FILE removes a cache which has same build-id of given FILE. Since the command takes a FILE path, it can confuse user who tries to remove cache about FILE path. ----- # ./perf buildid-cache -v --add ./perf Adding 133b7b5486d987a5ab5c3ebf4ea14941f45d4d4f ./perf: Ok # (update the ./perf binary) # ./perf buildid-cache -v --remove ./perf Removing 305bbd1be68f66eca7e2d78db294653031edfa79 ./perf: FAIL ./perf wasn't in the cache ----- Actually, the --remove's FAIL is not shown, it just silently fails. So, this patch adds --purge FILE action for such usecase. perf buildid-cache --purge FILE removes all caches which has same FILE path. In other words, it removes all caches including old binaries. ----- # ./perf buildid-cache -v --add ./perf Adding 133b7b5486d987a5ab5c3ebf4ea14941f45d4d4f ./perf: Ok # (update the ./perf binary) # ./perf buildid-cache -v --purge ./perf Removing 133b7b5486d987a5ab5c3ebf4ea14941f45d4d4f ./perf: Ok ----- BTW, if you want to purge all the caches, remove ~/.debug/* . Signed-off-by: Masami Hiramatsu Cc: Adrian Hunter Cc: Borislav Petkov Cc: Hemant Kumar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150227045026.1999.64084.stgit@localhost.localdomain [ s/dirname/dir_name/g to fix build on fedora14, where dirname is a global ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-buildid-cache.txt | 13 ++-- tools/perf/builtin-buildid-cache.c | 48 +++++++++++++ tools/perf/util/build-id.c | 93 ++++++++++++++++++++----- tools/perf/util/build-id.h | 3 + 4 files changed, 136 insertions(+), 21 deletions(-) diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index cec6b57e8be6..dd07b55f58d8 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -12,9 +12,9 @@ SYNOPSIS DESCRIPTION ----------- -This command manages the build-id cache. It can add and remove files to/from -the cache. In the future it should as well purge older entries, set upper -limits for the space used by the cache, etc. +This command manages the build-id cache. It can add, remove, update and purge +files to/from the cache. In the future it should as well set upper limits for +the space used by the cache, etc. OPTIONS ------- @@ -36,7 +36,12 @@ OPTIONS actually made. -r:: --remove=:: - Remove specified file from the cache. + Remove a cached binary which has same build-id of specified file + from the cache. +-p:: +--purge=:: + Purge all cached binaries including older caches which have specified + path from the cache. -M:: --missing=:: List missing build ids in the cache for the specified file. diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index e7568f5844ad..86f9d78195a4 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -223,6 +223,33 @@ static int build_id_cache__remove_file(const char *filename) return err; } +static int build_id_cache__purge_path(const char *pathname) +{ + struct strlist *list; + struct str_node *pos; + int err; + + err = build_id_cache__list_build_ids(pathname, &list); + if (err) + goto out; + + strlist__for_each(pos, list) { + err = build_id_cache__remove_s(pos->s); + if (verbose) + pr_info("Removing %s %s: %s\n", pos->s, pathname, + err ? "FAIL" : "Ok"); + if (err) + break; + } + strlist__delete(list); + +out: + if (verbose) + pr_info("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok"); + + return err; +} + static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) { char filename[PATH_MAX]; @@ -285,6 +312,7 @@ int cmd_buildid_cache(int argc, const char **argv, bool force = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, + *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, *kcore_filename = NULL; @@ -302,6 +330,8 @@ int cmd_buildid_cache(int argc, const char **argv, "file", "kcore file to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), + OPT_STRING('p', "purge", &purge_name_list_str, "path list", + "path(s) to remove (remove old caches too)"), OPT_STRING('M', "missing", &missing_filename, "file", "to find missing build ids in the cache"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -368,6 +398,24 @@ int cmd_buildid_cache(int argc, const char **argv, } } + if (purge_name_list_str) { + list = strlist__new(true, purge_name_list_str); + if (list) { + strlist__for_each(pos, list) + if (build_id_cache__purge_path(pos->s)) { + if (errno == ENOENT) { + pr_debug("%s wasn't in the cache\n", + pos->s); + continue; + } + pr_warning("Couldn't remove %s: %s\n", + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); + } + + strlist__delete(list); + } + } + if (missing_filename) ret = build_id_cache__fprintf_missing(session, stdout); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0bc33be5a78c..ffdc338df925 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -281,35 +281,93 @@ void disable_buildid_cache(void) no_buildid_cache = true; } +static char *build_id_cache__dirname_from_path(const char *name, + bool is_kallsyms, bool is_vdso) +{ + char *realname = (char *)name, *filename; + bool slash = is_kallsyms || is_vdso; + + if (!slash) { + realname = realpath(name, NULL); + if (!realname) + return NULL; + } + + if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "", + is_vdso ? DSO__NAME_VDSO : realname) < 0) + filename = NULL; + + if (!slash) + free(realname); + + return filename; +} + +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result) +{ + struct strlist *list; + char *dir_name; + DIR *dir; + struct dirent *d; + int ret = 0; + + list = strlist__new(true, NULL); + dir_name = build_id_cache__dirname_from_path(pathname, false, false); + if (!list || !dir_name) { + ret = -ENOMEM; + goto out; + } + + /* List up all dirents */ + dir = opendir(dir_name); + if (!dir) { + ret = -errno; + goto out; + } + + while ((d = readdir(dir)) != NULL) { + if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) + continue; + strlist__add(list, d->d_name); + } + closedir(dir); + +out: + free(dir_name); + if (ret) + strlist__delete(list); + else + *result = list; + + return ret; +} + int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; - char *realname, *filename = zalloc(size), + char *realname = NULL, *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *targetname, *tmp; - int len, err = -1; - bool slash = is_kallsyms || is_vdso; + int err = -1; - if (is_kallsyms) { - if (symbol_conf.kptr_restrict) { - pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - err = 0; - goto out_free; - } - realname = (char *) name; - } else + if (!is_kallsyms) { realname = realpath(name, NULL); + if (!realname) + goto out_free; + } - if (realname == NULL || filename == NULL || linkname == NULL) + dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso); + if (!dir_name) goto out_free; - len = scnprintf(filename, size, "%s%s%s", - buildid_dir, slash ? "/" : "", - is_vdso ? DSO__NAME_VDSO : realname); - if (mkdir_p(filename, 0755)) + if (mkdir_p(dir_name, 0755)) goto out_free; - snprintf(filename + len, size - len, "/%s", sbuild_id); + if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) { + filename = NULL; + goto out_free; + } if (access(filename, F_OK)) { if (is_kallsyms) { @@ -337,6 +395,7 @@ out_free: if (!is_kallsyms) free(realname); free(filename); + free(dir_name); free(linkname); return err; } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 2a094982f954..85011222cc14 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -4,6 +4,7 @@ #define BUILD_ID_SIZE 20 #include "tool.h" +#include "strlist.h" #include extern struct perf_tool build_id__mark_dso_hit_ops; @@ -22,6 +23,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); -- cgit v1.2.3 From cc169c7c31253e80e0d504f0cd5dbb9f1e3d3ac5 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 27 Feb 2015 13:50:28 +0900 Subject: perf buildid-cache: Use pr_debug instead of verbose && pr_info Use pr_debug instead of the combination of verbose and pr_info. "if (verbose) pr_info(...)" is same as "pr_debug(...)", replace it. Signed-off-by: Masami Hiramatsu Suggested-by: Namhyung Kim Cc: Adrian Hunter Cc: Borislav Petkov Cc: Hemant Kumar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150227045028.1999.93137.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-buildid-cache.c | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 86f9d78195a4..04466c4ff9d7 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -196,9 +196,8 @@ static int build_id_cache__add_file(const char *filename) build_id__sprintf(build_id, sizeof(build_id), sbuild_id); err = build_id_cache__add_s(sbuild_id, filename, false, false); - if (verbose) - pr_info("Adding %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Adding %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } @@ -216,9 +215,8 @@ static int build_id_cache__remove_file(const char *filename) build_id__sprintf(build_id, sizeof(build_id), sbuild_id); err = build_id_cache__remove_s(sbuild_id); - if (verbose) - pr_info("Removing %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Removing %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } @@ -235,17 +233,15 @@ static int build_id_cache__purge_path(const char *pathname) strlist__for_each(pos, list) { err = build_id_cache__remove_s(pos->s); - if (verbose) - pr_info("Removing %s %s: %s\n", pos->s, pathname, - err ? "FAIL" : "Ok"); + pr_debug("Removing %s %s: %s\n", pos->s, pathname, + err ? "FAIL" : "Ok"); if (err) break; } strlist__delete(list); out: - if (verbose) - pr_info("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok"); + pr_debug("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok"); return err; } @@ -296,9 +292,8 @@ static int build_id_cache__update_file(const char *filename) if (!err) err = build_id_cache__add_s(sbuild_id, filename, false, false); - if (verbose) - pr_info("Updating %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Updating %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } -- cgit v1.2.3 From 0497d0a8201a38f0c95edc8a1fc0325f2f879ddb Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 27 Feb 2015 13:50:31 +0900 Subject: perf buildid-cache: Show usage with incorrect params Show usage if no action is specified or unexpected parameter is given. In other words, be more user friendly. Signed-off-by: Masami Hiramatsu Cc: Adrian Hunter Cc: Borislav Petkov Cc: Hemant Kumar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150227045030.1999.44006.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-buildid-cache.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 04466c4ff9d7..d47a0cdc71c9 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -343,6 +343,11 @@ int cmd_buildid_cache(int argc, const char **argv, argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); + if (argc || (!add_name_list_str && !kcore_filename && + !remove_name_list_str && !purge_name_list_str && + !missing_filename && !update_name_list_str)) + usage_with_options(buildid_cache_usage, buildid_cache_options); + if (missing_filename) { file.path = missing_filename; file.force = force; -- cgit v1.2.3 From fefd2d9619de3bf0bf02a8622e9f445c3d19cc3f Mon Sep 17 00:00:00 2001 From: He Kuang Date: Sun, 15 Feb 2015 10:33:37 +0800 Subject: perf report: Fix branch stack mode cannot be set When perf.data file is obtained using 'perf record -b', perf report should use branch stack mode to generate output. But this function is broken by improper comparison between boolean and constant -1. before this patch: $ perf report -b -i perf.data Samples: 16 of event 'cycles', Event count (approx.): 3171896 Overhead Command Shared Object Symbol 13.59% ls [kernel.kallsyms] [k] prio_tree_remove 13.16% ls [kernel.kallsyms] [k] change_pte_range 12.09% ls [kernel.kallsyms] [k] page_fault 12.02% ls [kernel.kallsyms] [k] zap_pte_range ... after this patch: $ perf report -b -i perf.data Samples: 256 of event 'cycles', Event count (approx.): 256 Overhead Command Source Shared Object Source Symbol Target Shared Object Target Symbol 9.38% ls [unknown] [k] 0000000000000000 [unknown] [k] 0000000000000000 6.25% ls libc-2.19.so [.] _dl_addr libc-2.19.so [.] _dl_addr 6.25% ls [kernel.kallsyms] [k] zap_pte_range [kernel.kallsyms] [k] zap_pte_range 6.25% ls [kernel.kallsyms] [k] change_pte_range [kernel.kallsyms] [k] change_pte_range 0.39% ls [kernel.kallsyms] [k] prio_tree_remove [kernel.kallsyms] [k] prio_tree_remove ... Signed-off-by: He Kuang Tested-by: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1423967617-28879-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0ba5f07906fb..fb350343b1d7 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -768,7 +768,7 @@ repeat: * 0/1 means the user chose a mode. */ if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) && - branch_call_mode == -1) { + !branch_call_mode) { sort__mode = SORT_MODE__BRANCH; symbol_conf.cumulate_callchain = false; } -- cgit v1.2.3