From a3c0cc2ac03bd9db032f590d59cdbf0b447503b8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 30 Jan 2015 11:33:29 +0900 Subject: perf tools: Fix a dso open fail message It's not related to mmap, remove it from the message. Signed-off-by: Namhyung Kim Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1422585209-32742-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index c2f7d3b..a8b3f18 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -240,7 +240,7 @@ static int do_open(char *name) if (fd >= 0) return fd; - pr_debug("dso open failed, mmap: %s\n", + pr_debug("dso open failed: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); if (!dso__data_open_cnt || errno != EMFILE) break; -- cgit v1.1 From e1ecbbc3fa834cc6b4b344edb1968e734d57189b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 30 Jan 2015 18:37:44 +0900 Subject: perf probe: Fix to handle optimized not-inlined functions Fix to handle optimized no-inline functions which have only function definition but no actual instance at that point. To fix this problem, we need to find actual instance of the function. Without this patch: ---- # perf probe -a __up Failed to get entry address of __up. Error: Failed to add events. # perf probe -L __up Specified source line is not found. Error: Failed to show lines. ---- With this patch: ---- # perf probe -a __up Added new event: probe:__up (on __up) You can now use it in all perf tools, such as: perf record -e probe:__up -aR sleep 1 # perf probe -L __up <__up@/home/fedora/ksrc/linux-3/kernel/locking/semaphore.c:0> 0 static noinline void __sched __up(struct semaphore *sem) { struct semaphore_waiter *waiter = list_first_entry(&sem->wait_ struct semaphore_waite 4 list_del(&waiter->list); 5 waiter->up = true; 6 wake_up_process(waiter->task); 7 } ---- Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150130093744.30575.43290.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 15 +++++++++++++++ tools/perf/util/dwarf-aux.h | 3 +++ tools/perf/util/probe-finder.c | 12 ++++-------- 3 files changed, 22 insertions(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index cc66c40..780b2bc 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -278,6 +278,21 @@ bool die_is_func_def(Dwarf_Die *dw_die) } /** + * die_is_func_instance - Ensure that this DIE is an instance of a subprogram + * @dw_die: a DIE + * + * Ensure that this DIE is an instance (which has an entry address). + * This returns true if @dw_die is a function instance. If not, you need to + * call die_walk_instances() to find actual instances. + **/ +bool die_is_func_instance(Dwarf_Die *dw_die) +{ + Dwarf_Addr tmp; + + /* Actually gcc optimizes non-inline as like as inlined */ + return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; +} +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index b4fe90c..af7dbcd 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -41,6 +41,9 @@ extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Ensure that this DIE is a subprogram and definition (not declaration) */ extern bool die_is_func_def(Dwarf_Die *dw_die); +/* Ensure that this DIE is an instance of a subprogram */ +extern bool die_is_func_instance(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index b5247d7..d141935 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -915,17 +915,13 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) dwarf_decl_line(sp_die, &pf->lno); pf->lno += pp->line; param->retval = find_probe_point_by_line(pf); - } else if (!dwarf_func_inline(sp_die)) { + } else if (die_is_func_instance(sp_die)) { + /* Instances always have the entry address */ + dwarf_entrypc(sp_die, &pf->addr); /* Real function */ if (pp->lazy_line) param->retval = find_probe_point_lazy(sp_die, pf); else { - if (dwarf_entrypc(sp_die, &pf->addr) != 0) { - pr_warning("Failed to get entry address of " - "%s.\n", dwarf_diename(sp_die)); - param->retval = -ENOENT; - return DWARF_CB_ABORT; - } pf->addr += pp->offset; /* TODO: Check the address in this function */ param->retval = call_probe_finder(sp_die, pf); @@ -1536,7 +1532,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e); lr->start = lf->lno_s; lr->end = lf->lno_e; - if (dwarf_func_inline(sp_die)) + if (!die_is_func_instance(sp_die)) param->retval = die_walk_instances(sp_die, line_range_inline_cb, lf); else -- cgit v1.1 From 4886f2ca19f6ff22ebfbe8e78c79c699e572b89f Mon Sep 17 00:00:00 2001 From: Victor Kamensky Date: Mon, 26 Jan 2015 22:34:01 -0800 Subject: perf symbols: Ignore mapping symbols on aarch64 Aarch64 ELF files use mapping symbols with special names $x, $d to identify regions of Aarch64 code (see Aarch64 ELF ABI - "ARM IHI 0056B", section "4.5.4 Mapping symbols"). The patch filters out these symbols at load time, similar to "696b97a perf symbols: Ignore mapping symbols on ARM" changes done for ARM before V8. Also added handling of mapping symbols that has format "$d." and similar for both cases. Note we are not making difference between EM_ARM and EM_AARCH64 mapping symbols instead code handles superset of both. Signed-off-by: Victor Kamensky Acked-by: Namhyung Kim Acked-by: Will Deacon Cc: Adrian Hunter Cc: Anton Blanchard Cc: Avi Kivity Cc: Dave Martin Cc: David Ahern Cc: Jiri Olsa Cc: linux-arm-kernel@lists.infradead.org Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Russell King Link: http://lkml.kernel.org/r/1422340442-4673-2-git-send-email-victor.kamensky@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b24f9d8..225eb73 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -859,10 +859,9 @@ int dso__load_sym(struct dso *dso, struct map *map, /* Reject ARM ELF "mapping symbols": these aren't unique and * don't identify functions, so will confuse the profile * output: */ - if (ehdr.e_machine == EM_ARM) { - if (!strcmp(elf_name, "$a") || - !strcmp(elf_name, "$d") || - !strcmp(elf_name, "$t")) + if (ehdr.e_machine == EM_ARM || ehdr.e_machine == EM_AARCH64) { + if (elf_name[0] == '$' && strchr("adtx", elf_name[1]) + && (elf_name[2] == '\0' || elf_name[2] == '.')) continue; } -- cgit v1.1 From dc6254cf870732804b76a83ff2d8a72fea4365f6 Mon Sep 17 00:00:00 2001 From: Victor Kamensky Date: Mon, 26 Jan 2015 22:34:02 -0800 Subject: perf symbols: debuglink should take symfs option into account Currently code that tries to read corresponding debug symbol file from .gnu_debuglink section (DSO_BINARY_TYPE__DEBUGLINK) does not take in account symfs option, so filename__read_debuglink function cannot open ELF file, if symfs option is used. Fix is to add proper handling of symfs as it is done in other places: use __symbol__join_symfs function to get real file name of target ELF file. Signed-off-by: Victor Kamensky Tested-by: David Ahern Acked-by: David Ahern Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Anton Blanchard Cc: Avi Kivity Cc: Dave Martin Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Russell King Cc: Waiman Long Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1422340442-4673-3-git-send-email-victor.kamensky@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index a8b3f18..814554d 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -45,13 +45,13 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__DEBUGLINK: { char *debuglink; - strncpy(filename, dso->long_name, size); - debuglink = filename + dso->long_name_len; + len = __symbol__join_symfs(filename, size, dso->long_name); + debuglink = filename + len; while (debuglink != filename && *debuglink != '/') debuglink--; if (*debuglink == '/') debuglink++; - ret = filename__read_debuglink(dso->long_name, debuglink, + ret = filename__read_debuglink(filename, debuglink, size - (debuglink - filename)); } break; -- cgit v1.1 From aa1aac17a15cbf64236bd6f3b855262dcfb845c9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Feb 2015 12:46:58 -0300 Subject: perf tools: Introduce event_format__fprintf method The existing one, event_format__print() uses stdout unconditionally, and 'perf trace' needs to use it to format into a file that may have been set by the user, i.e. 'trace -o file.output'. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt Link: http://lkml.kernel.org/n/tip-7l0mgm91hwg0bby00s5pse8r@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/trace-event-parse.c | 12 +++++++++--- tools/perf/util/trace-event.h | 3 +++ 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index c36636f..25d6c73 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -112,8 +112,8 @@ unsigned long long read_size(struct event_format *event, void *ptr, int size) return pevent_read_number(event->pevent, ptr, size); } -void event_format__print(struct event_format *event, - int cpu, void *data, int size) +void event_format__fprintf(struct event_format *event, + int cpu, void *data, int size, FILE *fp) { struct pevent_record record; struct trace_seq s; @@ -125,10 +125,16 @@ void event_format__print(struct event_format *event, trace_seq_init(&s); pevent_event_info(&s, event, &record); - trace_seq_do_printf(&s); + trace_seq_do_fprintf(&s, fp); trace_seq_destroy(&s); } +void event_format__print(struct event_format *event, + int cpu, void *data, int size) +{ + return event_format__fprintf(event, cpu, data, size, stdout); +} + void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size __maybe_unused) { diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 52aaa19..356629a 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -23,6 +23,9 @@ trace_event__tp_format(const char *sys, const char *name); int bigendian(void); +void event_format__fprintf(struct event_format *event, + int cpu, void *data, int size, FILE *fp); + void event_format__print(struct event_format *event, int cpu, void *data, int size); -- cgit v1.1 From 20f86fc1fde14c6d913ebf5f569ee85e058a7dbd Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Feb 2015 13:29:05 -0300 Subject: perf evlist: Fix typo in comment Link: http://lkml.kernel.org/n/tip-qzg2qrdgta6dmcrxqdeexthu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 28b8ce8..c602ebb 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1329,7 +1329,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar * writing exactly one byte, in workload.cork_fd, usually via * perf_evlist__start_workload(). * - * For cancelling the workload without actuallin running it, + * For cancelling the workload without actually running it, * the parent will just close workload.cork_fd, without writing * anything, i.e. read will return zero and we just exit() * here. -- cgit v1.1 From 5693c92660970851e95f769ff27397f5098a6296 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 2 Feb 2015 14:35:02 -0500 Subject: perf tools: Do not check debugfs MAGIC for tracing files It's rather strange to be checking the debugfs MAGIC number for the tracing directory. A system admin may want to have a custom set of events to trace and it should be allowed to let the admin make a temp file (even for tracing virtual boxes, this is useful). Also with the coming tracefs, the files may not even be under debugfs, so checking the debugfs MAGIC number is pointless. Signed-off-by: Steven Rostedt Acked-by: Jiri Olsa Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20150202193552.546175764@goodmis.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 7f8ec6c..ecf069b 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -175,9 +175,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) - return NULL; - sys_dir = opendir(tracing_events_path); if (!sys_dir) return NULL; @@ -473,12 +470,6 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event) { - int ret; - - ret = debugfs_valid_mountpoint(tracing_events_path); - if (ret) - return ret; - if (strpbrk(sys, "*?")) return add_tracepoint_multi_sys(list, idx, sys, event); else @@ -1109,13 +1100,6 @@ 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 sbuf[STRERR_BUFSIZE]; - - if (debugfs_valid_mountpoint(tracing_events_path)) { - printf(" [ Tracepoints not available: %s ]\n", - strerror_r(errno, sbuf, sizeof(sbuf))); - return; - } sys_dir = opendir(tracing_events_path); if (!sys_dir) @@ -1163,9 +1147,6 @@ int is_valid_tracepoint(const char *event_string) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) - return 0; - sys_dir = opendir(tracing_events_path); if (!sys_dir) return 0; -- cgit v1.1 From 23773ca18b399051eb94f98b689cf7a9173c795b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 2 Feb 2015 14:35:07 -0500 Subject: perf tools: Make perf aware of tracefs As tracefs may be mounted instead of debugfs to get to the event directories, have perf know about tracefs, and use that file system over debugfs if it is present. Signed-off-by: Steven Rostedt Acked-by: Jiri Olsa Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20150202193553.340946602@goodmis.org [ Fixed up error messages about tracefs pointed out by Namhyung ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cache.h | 1 + tools/perf/util/evlist.c | 1 - tools/perf/util/parse-events.h | 2 +- tools/perf/util/probe-event.c | 24 +++++++++++------ tools/perf/util/util.c | 60 ++++++++++++++++++++++++++++++++++-------- tools/perf/util/util.h | 1 + 6 files changed, 68 insertions(+), 21 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index d04d770..fbcca21 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -17,6 +17,7 @@ #define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH" #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR" +#define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c602ebb..a8b2c57 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -7,7 +7,6 @@ * Released under the GPL v2. (and only v2, not any later version) */ #include "util.h" -#include #include #include #include "cpumap.h" diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index ff6e1fa..39c3b57 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -122,6 +122,6 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, int print_hwcache_events(const char *event_glob, bool name_only); extern int is_valid_tracepoint(const char *event_string); -extern int valid_debugfs_mount(const char *debugfs); +int valid_event_mount(const char *eventfs); #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 919937e..9dfbed9 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -41,6 +41,7 @@ #include "symbol.h" #include "thread.h" #include +#include #include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" @@ -1805,7 +1806,7 @@ static void print_open_warning(int err, bool is_kprobe) " - please rebuild kernel with %s.\n", is_kprobe ? 'k' : 'u', config); } else if (err == -ENOTSUP) - pr_warning("Debugfs is not mounted.\n"); + pr_warning("Tracefs or debugfs is not mounted.\n"); else pr_warning("Failed to open %cprobe_events: %s\n", is_kprobe ? 'k' : 'u', @@ -1816,7 +1817,7 @@ static void print_both_open_warning(int kerr, int uerr) { /* Both kprobes and uprobes are disabled, warn it. */ if (kerr == -ENOTSUP && uerr == -ENOTSUP) - pr_warning("Debugfs is not mounted.\n"); + pr_warning("Tracefs or debugfs is not mounted.\n"); else if (kerr == -ENOENT && uerr == -ENOENT) pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " "or/and CONFIG_UPROBE_EVENTS.\n"); @@ -1833,13 +1834,20 @@ static int open_probe_events(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; const char *__debugfs; + const char *tracing_dir = ""; int ret; - __debugfs = debugfs_find_mountpoint(); - if (__debugfs == NULL) - return -ENOTSUP; + __debugfs = tracefs_find_mountpoint(); + if (__debugfs == NULL) { + tracing_dir = "tracing/"; - ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file); + __debugfs = debugfs_find_mountpoint(); + if (__debugfs == NULL) + return -ENOTSUP; + } + + ret = e_snprintf(buf, PATH_MAX, "%s/%s%s", + __debugfs, tracing_dir, trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) @@ -1855,12 +1863,12 @@ static int open_probe_events(const char *trace_file, bool readwrite) static int open_kprobe_events(bool readwrite) { - return open_probe_events("tracing/kprobe_events", readwrite); + return open_probe_events("kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("tracing/uprobe_events", readwrite); + return open_probe_events("uprobe_events", readwrite); } /* Get raw string list of current kprobe_events or uprobe_events */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index b86744f..92db3f1 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -303,13 +303,26 @@ void set_term_quiet_input(struct termios *old) tcsetattr(0, TCSANOW, &tc); } -static void set_tracing_events_path(const char *mountpoint) +static void set_tracing_events_path(const char *tracing, const char *mountpoint) { - snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", - mountpoint, "tracing/events"); + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s", + mountpoint, tracing, "events"); } -const char *perf_debugfs_mount(const char *mountpoint) +static const char *__perf_tracefs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = tracefs_mount(mountpoint); + if (!mnt) + return NULL; + + set_tracing_events_path("", mnt); + + return mnt; +} + +static const char *__perf_debugfs_mount(const char *mountpoint) { const char *mnt; @@ -317,7 +330,20 @@ const char *perf_debugfs_mount(const char *mountpoint) if (!mnt) return NULL; - set_tracing_events_path(mnt); + set_tracing_events_path("tracing/", mnt); + + return mnt; +} + +const char *perf_debugfs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = __perf_tracefs_mount(mountpoint); + if (mnt) + return mnt; + + mnt = __perf_debugfs_mount(mountpoint); return mnt; } @@ -325,12 +351,19 @@ const char *perf_debugfs_mount(const char *mountpoint) void perf_debugfs_set_path(const char *mntpt) { snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt); - set_tracing_events_path(mntpt); + set_tracing_events_path("tracing/", mntpt); +} + +static const char *find_tracefs(void) +{ + const char *path = __perf_tracefs_mount(NULL); + + return path; } static const char *find_debugfs(void) { - const char *path = perf_debugfs_mount(NULL); + const char *path = __perf_debugfs_mount(NULL); if (!path) fprintf(stderr, "Your kernel does not support the debugfs filesystem"); @@ -344,6 +377,7 @@ static const char *find_debugfs(void) */ const char *find_tracing_dir(void) { + const char *tracing_dir = ""; static char *tracing; static int tracing_found; const char *debugfs; @@ -351,11 +385,15 @@ const char *find_tracing_dir(void) if (tracing_found) return tracing; - debugfs = find_debugfs(); - if (!debugfs) - return NULL; + debugfs = find_tracefs(); + if (!debugfs) { + tracing_dir = "/tracing"; + debugfs = find_debugfs(); + if (!debugfs) + return NULL; + } - if (asprintf(&tracing, "%s/tracing", debugfs) < 0) + if (asprintf(&tracing, "%s%s", debugfs, tracing_dir) < 0) return NULL; tracing_found = 1; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 027a515..73c2f8e 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -75,6 +75,7 @@ #include #include #include +#include #include #include #include -- cgit v1.1 From 4e31050f482c02c822b150d71cf1ea5be7c9d6e4 Mon Sep 17 00:00:00 2001 From: Vinson Lee Date: Mon, 9 Feb 2015 16:29:37 -0800 Subject: perf symbols: Define STT_GNU_IFUNC for glibc 2.9 and older. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The token STT_GNU_IFUNC is not available with glibc 2.9 and older. Define this token if it is not already defined. This patch fixes this build errors with older versions of glibc. CC util/symbol-elf.o util/symbol-elf.c: In function ‘elf_sym__is_function’: util/symbol-elf.c:75: error: ‘STT_GNU_IFUNC’ undeclared (first use in this function) util/symbol-elf.c:75: error: (Each undeclared identifier is reported only once util/symbol-elf.c:75: error: for each function it appears in.) make: *** [util/symbol-elf.o] Error 1 Signed-off-by: Vinson Lee Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Anton Blanchard Cc: Avi Kivity Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Waiman Long Cc: stable@vger.kernel.org # 3.17+ Link: http://lkml.kernel.org/r/1423528286-13630-1-git-send-email-vlee@twopensource.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 225eb73..b02731a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -69,6 +69,10 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +#ifndef STT_GNU_IFUNC +#define STT_GNU_IFUNC 10 +#endif + static inline int elf_sym__is_function(const GElf_Sym *sym) { return (elf_sym__type(sym) == STT_FUNC || -- cgit v1.1 From e35f7362bab455fb5c13ea4ce53f959f3e1610b2 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 10 Feb 2015 18:18:51 +0900 Subject: perf buildid-cache: Remove unneeded debugdir parameters Functions related to buildid-cache subcommand use debugdir parameters for passing buildid cache directory path. However all callers just pass buildid_dir global variable. Moreover, other functions which refer buildid cache use buildid_dir directly. This removes unneeded debugdir parameters from those functions and use buildid_dir if needed. Signed-off-by: Masami Hiramatsu Acked-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/20150210091851.19264.72741.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 44 ++++++++++++++++++++------------------------ tools/perf/util/build-id.h | 4 ++-- 2 files changed, 22 insertions(+), 26 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0c72680..9f764f6 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -259,8 +259,8 @@ void disable_buildid_cache(void) no_buildid_cache = true; } -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms, bool is_vdso) +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), @@ -282,7 +282,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, goto out_free; len = scnprintf(filename, size, "%s%s%s", - debugdir, slash ? "/" : "", + buildid_dir, slash ? "/" : "", is_vdso ? DSO__NAME_VDSO : realname); if (mkdir_p(filename, 0755)) goto out_free; @@ -298,13 +298,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, } len = scnprintf(linkname, size, "%s/.build-id/%.2s", - debugdir, sbuild_id); + buildid_dir, sbuild_id); if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) goto out_free; snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); - targetname = filename + strlen(debugdir) - 5; + targetname = filename + strlen(buildid_dir) - 5; memcpy(targetname, "../..", 5); if (symlink(targetname, linkname) == 0) @@ -318,18 +318,17 @@ out_free: } static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, - const char *name, const char *debugdir, - bool is_kallsyms, bool is_vdso) + const char *name, bool is_kallsyms, + bool is_vdso) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, debugdir, name, - is_kallsyms, is_vdso); + return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); } -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) +int build_id_cache__remove_s(const char *sbuild_id) { const size_t size = PATH_MAX; char *filename = zalloc(size), @@ -340,7 +339,7 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) goto out_free; snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, sbuild_id + 2); + buildid_dir, sbuild_id, sbuild_id + 2); if (access(linkname, F_OK)) goto out_free; @@ -355,7 +354,7 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) * Since the link is relative, we must make it absolute: */ snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, filename); + buildid_dir, sbuild_id, filename); if (unlink(linkname)) goto out_free; @@ -367,8 +366,7 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, struct machine *machine, - const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = dso__is_vdso(dso); @@ -381,28 +379,26 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, name = nm; } return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - debugdir, is_kallsyms, is_vdso); + is_kallsyms, is_vdso); } static int __dsos__cache_build_ids(struct list_head *head, - struct machine *machine, const char *debugdir) + struct machine *machine) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, machine, debugdir)) + if (dso__cache_build_id(pos, machine)) err = -1; return err; } -static int machine__cache_build_ids(struct machine *machine, const char *debugdir) +static int machine__cache_build_ids(struct machine *machine) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine, - debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine, - debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine); + ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine); return ret; } @@ -417,11 +413,11 @@ int perf_session__cache_build_ids(struct perf_session *session) if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->machines.host, buildid_dir); + ret = machine__cache_build_ids(&session->machines.host); for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__cache_build_ids(pos, buildid_dir); + ret |= machine__cache_build_ids(pos); } return ret ? -1 : 0; } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 8236319..31b3c63 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -22,9 +22,9 @@ 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__add_s(const char *sbuild_id, const char *debugdir, +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, const char *debugdir); +int build_id_cache__remove_s(const char *sbuild_id); void disable_buildid_cache(void); #endif -- cgit v1.1 From 5cb113fd84f72b6e08c1970d612fd61327781d4e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 10 Feb 2015 18:18:53 +0900 Subject: perf buildid-cache: Consolidate .build-id cache path generators Consolidate .build-id cache path generating routines to build_id__filename() function. Other functions must use it to get the buildid cache path (link path) from build-id. This can reduce the risk of partial-update. Signed-off-by: Masami Hiramatsu Acked-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/20150210091853.19264.58513.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 58 ++++++++++++++++++++++++++++++++-------------- 1 file changed, 41 insertions(+), 17 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 9f764f6..adbc360 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -93,6 +93,35 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) return raw - build_id; } +/* asnprintf consolidates asprintf and snprintf */ +static int asnprintf(char **strp, size_t size, const char *fmt, ...) +{ + va_list ap; + int ret; + + if (!strp) + return -EINVAL; + + va_start(ap, fmt); + if (*strp) + ret = vsnprintf(*strp, size, fmt, ap); + else + ret = vasprintf(strp, fmt, ap); + va_end(ap); + + return ret; +} + +static char *build_id__filename(const char *sbuild_id, char *bf, size_t size) +{ + char *tmp = bf; + int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir, + sbuild_id, sbuild_id + 2); + if (ret < 0 || (tmp && size < (unsigned int)ret)) + return NULL; + return bf; +} + char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; @@ -101,14 +130,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) return NULL; build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); - if (bf == NULL) { - if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir, - build_id_hex, build_id_hex + 2) < 0) - return NULL; - } else - snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir, - build_id_hex, build_id_hex + 2); - return bf; + return build_id__filename(build_id_hex, bf, size); } #define dsos__for_each_with_build_id(pos, head) \ @@ -264,7 +286,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, { const size_t size = PATH_MAX; char *realname, *filename = zalloc(size), - *linkname = zalloc(size), *targetname; + *linkname = zalloc(size), *targetname, *tmp; int len, err = -1; bool slash = is_kallsyms || is_vdso; @@ -297,13 +319,15 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, goto out_free; } - len = scnprintf(linkname, size, "%s/.build-id/%.2s", - buildid_dir, sbuild_id); + if (!build_id__filename(sbuild_id, linkname, size)) + goto out_free; + tmp = strrchr(linkname, '/'); + *tmp = '\0'; if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) goto out_free; - snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); + *tmp = '/'; targetname = filename + strlen(buildid_dir) - 5; memcpy(targetname, "../..", 5); @@ -332,14 +356,14 @@ int build_id_cache__remove_s(const char *sbuild_id) { const size_t size = PATH_MAX; char *filename = zalloc(size), - *linkname = zalloc(size); + *linkname = zalloc(size), *tmp; int err = -1; if (filename == NULL || linkname == NULL) goto out_free; - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - buildid_dir, sbuild_id, sbuild_id + 2); + if (!build_id__filename(sbuild_id, linkname, size)) + goto out_free; if (access(linkname, F_OK)) goto out_free; @@ -353,8 +377,8 @@ int build_id_cache__remove_s(const char *sbuild_id) /* * Since the link is relative, we must make it absolute: */ - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - buildid_dir, sbuild_id, filename); + tmp = strrchr(linkname, '/') + 1; + snprintf(tmp, size - (tmp - linkname), "%s", filename); if (unlink(linkname)) goto out_free; -- cgit v1.1 From 885e00be17c07ffb517d471bf39c8acc44ef87a9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 11 Jan 2015 23:05:29 +0100 Subject: perf tools: Remove api fs object from python build It's already included in libapikfs.a library, which is already used to link perf.so. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-ijp7xkmj585rqajy4xmvjnar@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python-ext-sources | 1 - 1 file changed, 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 6c6a695..4d28624 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,6 +17,5 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -../lib/api/fs/fs.c util/trace-event.c ../../lib/rbtree.c -- cgit v1.1 From 9352aabad16af51c4c66fb2470ca01e4005bd282 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 29 Dec 2014 17:42:46 +0100 Subject: perf build: Add libperf objects building Move the util objects building under build framework. Add the new libperf build object so it's separated from the rest of the perf code and could be librarized. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-574tgt9t23tnxo9td8qjiibc@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 116 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 tools/perf/util/Build (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build new file mode 100644 index 0000000..c107f30 --- /dev/null +++ b/tools/perf/util/Build @@ -0,0 +1,116 @@ +libperf-y += abspath.o +libperf-y += alias.o +libperf-y += annotate.o +libperf-y += build-id.o +libperf-y += config.o +libperf-y += ctype.o +libperf-y += db-export.o +libperf-y += environment.o +libperf-y += event.o +libperf-y += evlist.o +libperf-y += evsel.o +libperf-y += exec_cmd.o +libperf-y += find_next_bit.o +libperf-y += help.o +libperf-y += kallsyms.o +libperf-y += levenshtein.o +libperf-y += parse-options.o +libperf-y += parse-events.o +libperf-y += path.o +libperf-y += rbtree.o +libperf-y += bitmap.o +libperf-y += hweight.o +libperf-y += run-command.o +libperf-y += quote.o +libperf-y += strbuf.o +libperf-y += string.o +libperf-y += strlist.o +libperf-y += strfilter.o +libperf-y += top.o +libperf-y += usage.o +libperf-y += wrapper.o +libperf-y += sigchain.o +libperf-y += dso.o +libperf-y += symbol.o +libperf-y += color.o +libperf-y += pager.o +libperf-y += header.o +libperf-y += callchain.o +libperf-y += values.o +libperf-y += debug.o +libperf-y += machine.o +libperf-y += map.o +libperf-y += pstack.o +libperf-y += session.o +libperf-y += ordered-events.o +libperf-y += comm.o +libperf-y += thread.o +libperf-y += thread_map.o +libperf-y += trace-event-parse.o +libperf-y += parse-events-flex.o +libperf-y += parse-events-bison.o +libperf-y += pmu.o +libperf-y += pmu-flex.o +libperf-y += pmu-bison.o +libperf-y += trace-event-read.o +libperf-y += trace-event-info.o +libperf-y += trace-event-scripting.o +libperf-y += trace-event.o +libperf-y += svghelper.o +libperf-y += sort.o +libperf-y += hist.o +libperf-y += util.o +libperf-y += xyarray.o +libperf-y += cpumap.o +libperf-y += cgroup.o +libperf-y += target.o +libperf-y += rblist.o +libperf-y += intlist.o +libperf-y += vdso.o +libperf-y += stat.o +libperf-y += record.o +libperf-y += srcline.o +libperf-y += data.o +libperf-y += tsc.o +libperf-y += cloexec.o +libperf-y += thread-stack.o + +CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" + +$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c + @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l + +$(OUTPUT)util/parse-events-bison.c: util/parse-events.y + @$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ + +$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c + @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l + +$(OUTPUT)util/pmu-bison.c: util/pmu.y + @$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_ + +CFLAGS_parse-events-flex.o += -w +CFLAGS_pmu-flex.o += -w +CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w +CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w + +$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c +$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c + +CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_parse-events.o += -Wno-redundant-decls + +$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE + $(call if_changed_dep,cc_o_c) -- cgit v1.1 From 709e679193c6e0e39222cd1fd51008225208cbc7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 29 Dec 2014 23:52:25 +0100 Subject: perf build: Add probe objects building Move the probe objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-p39iitiu2ltgmtbn48bsh7nz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index c107f30..73a0411 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -75,6 +75,13 @@ libperf-y += tsc.o libperf-y += cloexec.o libperf-y += thread-stack.o +libperf-$(CONFIG_LIBELF) += symbol-elf.o +libperf-$(CONFIG_LIBELF) += probe-event.o + +ifndef CONFIG_LIBELF +libperf-y += symbol-minimal.o +endif + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" -- cgit v1.1 From 8379fce485cc57daa42a06f4cf1ad822b794d95d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 00:06:25 +0100 Subject: perf build: Add dwarf objects building Move the dwarf objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-5ody6tnfnkt4rezvpem8n7rm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 73a0411..10630fb 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -82,6 +82,9 @@ ifndef CONFIG_LIBELF libperf-y += symbol-minimal.o endif +libperf-$(CONFIG_DWARF) += probe-finder.o +libperf-$(CONFIG_DWARF) += dwarf-aux.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" -- cgit v1.1 From b2e45c322e0298652fc05e65c671b2b88d30ae31 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 00:11:11 +0100 Subject: perf build: Add dwarf unwind objects building Move the dwarf unwind objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-7f7dmhkhs0e7jnqiu9ibzqia@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 10630fb..0401a80 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -85,6 +85,9 @@ endif libperf-$(CONFIG_DWARF) += probe-finder.o libperf-$(CONFIG_DWARF) += dwarf-aux.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" -- cgit v1.1 From c7355f842bf84ba7b1c9d6378f85bb53c99284b2 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 13:11:32 +0100 Subject: perf build: Add scripts objects building Move the scripts objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-ry8pd41ahwpq9h46i8te33c7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 ++ tools/perf/util/scripting-engines/Build | 6 ++++++ 2 files changed, 8 insertions(+) create mode 100644 tools/perf/util/scripting-engines/Build (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 0401a80..b0a6542 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -88,6 +88,8 @@ libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-y += scripting-engines/ + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build new file mode 100644 index 0000000..6516e22 --- /dev/null +++ b/tools/perf/util/scripting-engines/Build @@ -0,0 +1,6 @@ +libperf-$(CONFIG_LIBPERL) += trace-event-perl.o +libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o + +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default + +CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -- cgit v1.1 From 3bc3374cc50ce533259b7efed261f3d68307113c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 13:30:04 +0100 Subject: perf build: Add perf regs objects building Move the regs objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-hgny792g5x5iaklc34aa57uh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index b0a6542..f698432 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -90,6 +90,8 @@ libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o libperf-y += scripting-engines/ +libperf-$(CONFIG_PERF_REGS) += perf_regs.o + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" -- cgit v1.1 From 1571b695053c4ccad66c5151d78247a6590338d6 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 13:31:12 +0100 Subject: perf build: Add zlib objects building Move the zlib objects building under build framework to be included in the libperf build object. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-cpbb47g82ahpa4yqfr9dcobq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index f698432..4599188 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -91,6 +91,7 @@ libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o libperf-y += scripting-engines/ libperf-$(CONFIG_PERF_REGS) += perf_regs.o +libperf-$(CONFIG_ZLIB) += zlib.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" -- cgit v1.1 From 1999307b469bdfda97baa78c7f4ecf3800fdbacd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 30 Dec 2014 18:44:38 +0100 Subject: perf build: Add single target build framework support Add support to build single targets, like: $ make util/map.o # objects $ make util/map.i # preprocessor $ make util/map.s # assembly Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-tt10y0dmweq6rjaod937rpb4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 4599188..32f9327 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -97,15 +97,19 @@ CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c + $(call rule_mkdir) @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l $(OUTPUT)util/parse-events-bison.c: util/parse-events.y + $(call rule_mkdir) @$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c + $(call rule_mkdir) @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l $(OUTPUT)util/pmu-bison.c: util/pmu.y + $(call rule_mkdir) @$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_ CFLAGS_parse-events-flex.o += -w @@ -122,13 +126,17 @@ CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_parse-events.o += -Wno-redundant-decls $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE + $(call rule_mkdir) $(call if_changed_dep,cc_o_c) $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE + $(call rule_mkdir) $(call if_changed_dep,cc_o_c) $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE + $(call rule_mkdir) $(call if_changed_dep,cc_o_c) $(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE + $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -- cgit v1.1 From 285a8f247b08c2aff83633fb82c217f91455d10b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 10 Jan 2015 20:53:13 +0100 Subject: tools lib api: Rename libapikfs.a to libapi.a Renaming libapikfs.a to libapi.a, because it's not just 'fs' specific library now. Signed-off-by: Jiri Olsa Tested-by: Sukadev Bhattiprolu Tested-by: Will Deacon Cc: Alexis Berlemont Cc: Borislav Petkov Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-g1mk5oj2ayq4vn653ovfg3gv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index d0aee4b..1833103 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -25,7 +25,7 @@ cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') -libapikfs = getenv('LIBAPIKFS') +libapikfs = getenv('LIBAPI') ext_sources = [f.strip() for f in file('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] -- cgit v1.1 From 3a03005ff9445834f3d3b577a11bcbdbdf7a89cf Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 13 Feb 2015 21:11:52 +0800 Subject: perf tools: Fix a bug of segmentation fault Fix the 'segmentation fault' bug of 'perf list --list-cmds', which also happens in other cases (e.g. record, report ...). This bug happens when there are no cmds to list at all. Example: Before this patch: $ perf list --list-cmds Segmentation fault $ After this patch: $ perf list --list-cmds $ As shown above, the result prints nothing rather than a segmentation fault. The null result means 'perf list' has no cmds to display at this time. Signed-off-by: Yunlong Song Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1423833115-11199-5-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-options.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 4a015f7..4ee9a86 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -510,8 +510,10 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o } exit(130); case PARSE_OPT_LIST_SUBCMDS: - for (int i = 0; subcommands[i]; i++) - printf("%s ", subcommands[i]); + if (subcommands) { + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + } exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { -- cgit v1.1 From 619a303c1b8bd22abc549477d038ef9b5c1fe1bd Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Fri, 13 Feb 2015 21:11:55 +0800 Subject: perf list: Place the header text in its right position The hearer text 'List of pre-defined events (to be used in -e):' is placed in an improper function, which causes an abnormal output, e.g. 'perf list hw' shows no guiding text at all, and 'perf list hw L1-dcache*' shows the guiding text incorrectly in the middle of the output. Example Before this patch: $ perf list hw L1-dcache* 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] stalled-cycles-backend OR idle-cycles-backend [Hardware event] stalled-cycles-frontend OR idle-cycles-frontend [Hardware event] List of pre-defined events (to be used in -e): <-- incorrect position L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-prefetch-misses [Hardware cache event] L1-dcache-prefetches [Hardware cache event] L1-dcache-store-misses [Hardware cache event] L1-dcache-stores [Hardware cache event] After this patch: $ perf list hw L1-dcache* List of pre-defined events (to be used in -e): <-- correct position 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] stalled-cycles-backend OR idle-cycles-backend [Hardware event] stalled-cycles-frontend OR idle-cycles-frontend [Hardware event] L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-prefetch-misses [Hardware cache event] L1-dcache-prefetches [Hardware cache event] L1-dcache-store-misses [Hardware cache event] L1-dcache-stores [Hardware cache event] Signed-off-by: Yunlong Song Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Wang Nan Link: http://lkml.kernel.org/r/1423833115-11199-8-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ecf069b..109ba5c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1319,11 +1319,6 @@ static void print_symbol_events(const char *event_glob, unsigned type, */ void print_events(const char *event_glob, bool name_only) { - if (!name_only) { - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); - } - print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); -- cgit v1.1 From aad2b21c151273fa7abc419dac51a980eff1dd17 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 5 Jan 2015 13:23:04 -0500 Subject: perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Adrian Hunter Cc: Anshuman Khandual Cc: Arnaldo Carvalho de Melo Cc: Cody P Schafer Cc: David Ahern Cc: Don Zickus Cc: Jacob Shin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Masanari Iida Cc: Namhyung Kim Cc: Paul Mackerras Cc: Rodrigo Campos Cc: Stephane Eranian Cc: Sukadev Bhattiprolu Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- tools/perf/util/callchain.c | 8 ++++++++ tools/perf/util/callchain.h | 1 + tools/perf/util/evsel.c | 21 +++++++++++++++++++-- 3 files changed, 28 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 14e7a12..9f643ee 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -97,6 +97,14 @@ int parse_callchain_record_opt(const char *arg) callchain_param.dump_size = size; } #endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + callchain_param.record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; } else { pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c0ec1ac..6033a0a 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -11,6 +11,7 @@ enum perf_call_graph_mode { CALLCHAIN_NONE, CALLCHAIN_FP, CALLCHAIN_DWARF, + CALLCHAIN_LBR, CALLCHAIN_MAX }; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ea51a90..f93e520 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -537,13 +537,30 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) } static void -perf_evsel__config_callgraph(struct perf_evsel *evsel) +perf_evsel__config_callgraph(struct perf_evsel *evsel, + struct record_opts *opts) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); + if (callchain_param.record_mode == CALLCHAIN_LBR) { + if (!opts->branch_stack) { + if (attr->exclude_user) { + pr_warning("LBR callstack option is only available " + "to get user callchain information. " + "Falling back to framepointers.\n"); + } else { + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); + attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_CALL_STACK; + } + } else + pr_warning("Cannot use LBR callstack with branch stack. " + "Falling back to framepointers.\n"); + } + if (callchain_param.record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); @@ -667,7 +684,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) evsel->attr.exclude_callchain_user = 1; if (callchain_param.enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel); + perf_evsel__config_callgraph(evsel, opts); if (opts->sample_intr_regs) { attr->sample_regs_intr = PERF_REGS_MASK; -- cgit v1.1 From 384b60557b5522fcb99646f0eb6e7a344cdb94c6 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 5 Jan 2015 13:23:05 -0500 Subject: perf tools: Construct LBR call chain LBR call stack only has user-space callchains. It is output in the PERF_SAMPLE_BRANCH_STACK data format. For kernel callchains, it's still in the form of PERF_SAMPLE_CALLCHAIN. The perf tool has to handle both data sources to construct a complete callstack. For the "perf report -D" option, both lbr and fp information will be displayed. A new call chain recording option "lbr" is introduced into the perf tool for LBR call stack. The user can use --call-graph lbr to get the call stack information from hardware. Here are some examples. When profiling bc(1) on Fedora 19: echo 'scale=2000; 4*a(1)' > cmd; perf record --call-graph lbr bc -l < cmd If enabling LBR, perf report output looks like: 50.36% bc bc [.] bc_divide | --- bc_divide execute run_code yyparse main __libc_start_main _start 33.66% bc bc [.] _one_mult | --- _one_mult bc_divide execute run_code yyparse main __libc_start_main _start 7.62% bc bc [.] _bc_do_add | --- _bc_do_add | |--99.89%-- 0x2000186a8 --0.11%-- [...] 6.83% bc bc [.] _bc_do_sub | --- _bc_do_sub | |--99.94%-- bc_add | execute | run_code | yyparse | main | __libc_start_main | _start --0.06%-- [...] 0.46% bc libc-2.17.so [.] __memset_sse2 | --- __memset_sse2 | |--54.13%-- bc_new_num | | | |--51.00%-- bc_divide | | execute | | run_code | | yyparse | | main | | __libc_start_main | | _start | | | |--30.46%-- _bc_do_sub | | bc_add | | execute | | run_code | | yyparse | | main | | __libc_start_main | | _start | | | --18.55%-- _bc_do_add | bc_add | execute | run_code | yyparse | main | __libc_start_main | _start | --45.87%-- bc_divide execute run_code yyparse main __libc_start_main _start If using FP, perf report output looks like: echo 'scale=2000; 4*a(1)' > cmd; perf record --call-graph fp bc -l < cmd 50.49% bc bc [.] bc_divide | --- bc_divide 33.57% bc bc [.] _one_mult | --- _one_mult 7.61% bc bc [.] _bc_do_add | --- _bc_do_add 0x2000186a8 6.88% bc bc [.] _bc_do_sub | --- _bc_do_sub 0.42% bc libc-2.17.so [.] __memcpy_ssse3_back | --- __memcpy_ssse3_back If using LBR, perf report -D output looks like: 3458145275743 0x2fd750 [0xd8]: PERF_RECORD_SAMPLE(IP, 0x2): 9748/9748: 0x408ea8 period: 609644 addr: 0 ... LBR call chain: nr:8 ..... 0: fffffffffffffe00 ..... 1: 0000000000408e50 ..... 2: 000000000040a458 ..... 3: 000000000040562e ..... 4: 0000000000408590 ..... 5: 00000000004022c0 ..... 6: 00000000004015dd ..... 7: 0000003d1cc21b43 ... FP chain: nr:2 ..... 0: fffffffffffffe00 ..... 1: 0000000000408ea8 ... thread: bc:9748 ...... dso: /usr/bin/bc The LBR call stack has the following known limitations: - Zero length calls are not filtered out by the hardware - Exception handing such as setjmp/longjmp will have calls/returns not match - Pushing different return address onto the stack will have calls/returns not match - If callstack is deeper than the LBR, only the last entries are captured Tested-by: Jiri Olsa Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Linus Torvalds Cc: Namhyung Kim Cc: Paul Mackerras Cc: Simon Que Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1420482185-29830-3-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- tools/perf/util/evsel.h | 4 ++ tools/perf/util/machine.c | 102 +++++++++++++++++++++++++++++++++++++++++----- tools/perf/util/session.c | 64 ++++++++++++++++++++++++++--- 3 files changed, 153 insertions(+), 17 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3862274..dcf202a 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -355,4 +355,8 @@ for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ (_evsel) && (_evsel)->leader == (_leader); \ (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) +static inline bool has_branch_callstack(struct perf_evsel *evsel) +{ + return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; +} #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1bca3a9..9e0f60a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1502,18 +1502,100 @@ static int remove_loops(struct branch_entry *l, int nr) return nr; } -static int thread__resolve_callchain_sample(struct thread *thread, - struct ip_callchain *chain, - struct branch_stack *branch, - struct symbol **parent, - struct addr_location *root_al, - int max_stack) +/* + * Recolve LBR callstack chain sample + * Return: + * 1 on success get LBR callchain information + * 0 no available LBR callchain information, should try fp + * negative error code on other errors. + */ +static int resolve_lbr_callchain_sample(struct thread *thread, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { + struct ip_callchain *chain = sample->callchain; + int chain_nr = min(max_stack, (int)chain->nr); + int i, j, err; + u64 ip; + + for (i = 0; i < chain_nr; i++) { + if (chain->ips[i] == PERF_CONTEXT_USER) + break; + } + + /* LBR only affects the user callchain */ + if (i != chain_nr) { + struct branch_stack *lbr_stack = sample->branch_stack; + int lbr_nr = lbr_stack->nr; + /* + * LBR callstack can only get user call chain. + * The mix_chain_nr is kernel call chain + * number plus LBR user call chain number. + * i is kernel call chain number, + * 1 is PERF_CONTEXT_USER, + * lbr_nr + 1 is the user call chain number. + * For details, please refer to the comments + * in callchain__printf + */ + int mix_chain_nr = i + 1 + lbr_nr + 1; + + if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) { + pr_warning("corrupted callchain. skipping...\n"); + return 0; + } + + for (j = 0; j < mix_chain_nr; j++) { + if (callchain_param.order == ORDER_CALLEE) { + if (j < i + 1) + ip = chain->ips[j]; + else if (j > i + 1) + ip = lbr_stack->entries[j - i - 2].from; + else + ip = lbr_stack->entries[0].to; + } else { + if (j < lbr_nr) + ip = lbr_stack->entries[lbr_nr - j - 1].from; + else if (j > lbr_nr) + ip = chain->ips[i + 1 - (j - lbr_nr)]; + else + ip = lbr_stack->entries[0].to; + } + + err = add_callchain_ip(thread, parent, root_al, false, ip); + if (err) + return (err < 0) ? err : 0; + } + return 1; + } + + return 0; +} + +static int thread__resolve_callchain_sample(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) +{ + struct branch_stack *branch = sample->branch_stack; + struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr); int i, j, err; int skip_idx = -1; int first_call = 0; + callchain_cursor_reset(&callchain_cursor); + + if (has_branch_callstack(evsel)) { + err = resolve_lbr_callchain_sample(thread, sample, parent, + root_al, max_stack); + if (err) + return (err < 0) ? err : 0; + } + /* * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. @@ -1521,8 +1603,6 @@ static int thread__resolve_callchain_sample(struct thread *thread, if (chain->nr < PERF_MAX_STACK_DEPTH) skip_idx = arch_skip_callchain_idx(thread, chain); - callchain_cursor_reset(&callchain_cursor); - /* * Add branches to call stack for easier browsing. This gives * more context for a sample than just the callers. @@ -1623,9 +1703,9 @@ int thread__resolve_callchain(struct thread *thread, struct addr_location *root_al, int max_stack) { - int ret = thread__resolve_callchain_sample(thread, sample->callchain, - sample->branch_stack, - parent, root_al, max_stack); + int ret = thread__resolve_callchain_sample(thread, evsel, + sample, parent, + root_al, max_stack); if (ret) return ret; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0baf75f..504b7e6 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -553,15 +553,67 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, return 0; } -static void callchain__printf(struct perf_sample *sample) +static void callchain__lbr_callstack_printf(struct perf_sample *sample) { + struct ip_callchain *callchain = sample->callchain; + struct branch_stack *lbr_stack = sample->branch_stack; + u64 kernel_callchain_nr = callchain->nr; unsigned int i; - printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr); + for (i = 0; i < kernel_callchain_nr; i++) { + if (callchain->ips[i] == PERF_CONTEXT_USER) + break; + } + + if ((i != kernel_callchain_nr) && lbr_stack->nr) { + u64 total_nr; + /* + * LBR callstack can only get user call chain, + * i is kernel call chain number, + * 1 is PERF_CONTEXT_USER. + * + * The user call chain is stored in LBR registers. + * LBR are pair registers. The caller is stored + * in "from" register, while the callee is stored + * in "to" register. + * For example, there is a call stack + * "A"->"B"->"C"->"D". + * The LBR registers will recorde like + * "C"->"D", "B"->"C", "A"->"B". + * So only the first "to" register and all "from" + * registers are needed to construct the whole stack. + */ + total_nr = i + 1 + lbr_stack->nr + 1; + kernel_callchain_nr = i + 1; + + printf("... LBR call chain: nr:%" PRIu64 "\n", total_nr); + + for (i = 0; i < kernel_callchain_nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + i, callchain->ips[i]); + + printf("..... %2d: %016" PRIx64 "\n", + (int)(kernel_callchain_nr), lbr_stack->entries[0].to); + for (i = 0; i < lbr_stack->nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from); + } +} + +static void callchain__printf(struct perf_evsel *evsel, + struct perf_sample *sample) +{ + unsigned int i; + struct ip_callchain *callchain = sample->callchain; + + if (has_branch_callstack(evsel)) + callchain__lbr_callstack_printf(sample); + + printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr); - for (i = 0; i < sample->callchain->nr; i++) + for (i = 0; i < callchain->nr; i++) printf("..... %2d: %016" PRIx64 "\n", - i, sample->callchain->ips[i]); + i, callchain->ips[i]); } static void branch_stack__printf(struct perf_sample *sample) @@ -718,9 +770,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_type = evsel->attr.sample_type; if (sample_type & PERF_SAMPLE_CALLCHAIN) - callchain__printf(sample); + callchain__printf(evsel, sample); - if (sample_type & PERF_SAMPLE_BRANCH_STACK) + if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel)) branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) -- cgit v1.1 From cfd70a26aadf0a9af80bbce035e5760736727a94 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 21 Feb 2015 10:09:55 -0800 Subject: perf evlist: Introduce set_filter_pid method To filter out events for a certain pid, for instance, when tracing system wide, so that the tracer itself doesn't creates an event loop. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-byoia9dzu4gmkdv87etnd9zf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 13 +++++++++++++ tools/perf/util/evlist.h | 1 + 2 files changed, 14 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a8b2c57..39302a4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1085,6 +1085,19 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) return err; } +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid) +{ + char *filter; + int ret; + + if (asprintf(&filter, "common_pid != %d", pid) < 0) + return -1; + + ret = perf_evlist__set_filter(evlist, filter); + free(filter); + return ret; +} + bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { struct perf_evsel *pos; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c94a9e0..715fa3a 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -77,6 +77,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); -- cgit v1.1 From be199ada4fbbe5f742f854dce8e455cfcfcf7adb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 21 Feb 2015 11:33:47 -0800 Subject: perf evlist: Introduce set_filter_pids method We need to filter multiple pids in trace, i.e. trace itself, gnome-terminal, X.org, etc. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-frtpkg7qapqwf7asa35wf8am@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 27 +++++++++++++++++++++++---- tools/perf/util/evlist.h | 1 + 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 39302a4..8d0b623 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1085,19 +1085,38 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) return err; } -int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid) +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids) { char *filter; - int ret; + int ret = -1; + size_t i; - if (asprintf(&filter, "common_pid != %d", pid) < 0) - return -1; + for (i = 0; i < npids; ++i) { + if (i == 0) { + if (asprintf(&filter, "common_pid != %d", pids[i]) < 0) + return -1; + } else { + char *tmp; + + if (asprintf(&tmp, "%s && common_pid != %d", filter, pids[i]) < 0) + goto out_free; + + free(filter); + filter = tmp; + } + } ret = perf_evlist__set_filter(evlist, filter); +out_free: free(filter); return ret; } +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid) +{ + return perf_evlist__set_filter_pids(evlist, 1, &pid); +} + bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { struct perf_evsel *pos; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 715fa3a..c19ff45 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -78,6 +78,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); -- cgit v1.1 From 54245fdc357613633954bfd38cffb71cb9def067 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 14 Feb 2015 14:26:15 -0300 Subject: perf session: Remove wrappers to machines__find Start to untangle session from delivering samples, as there are tools that want to use ordered_events and don't use perf_session at all. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-rn4pk3pjxd78sgzrkn19tktp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 504b7e6..fac08e1 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -797,8 +797,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->attr.read_format); } -static struct machine * - perf_session__find_machine_for_cpumode(struct perf_session *session, +static struct machine *machines__find_for_cpumode(struct machines *machines, union perf_event *event, struct perf_sample *sample) { @@ -816,14 +815,13 @@ static struct machine * else pid = sample->pid; - machine = perf_session__find_machine(session, pid); + machine = machines__find(machines, pid); if (!machine) - machine = perf_session__findnew_machine(session, - DEFAULT_GUEST_KERNEL_ID); + machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } - return &session->machines.host; + return &machines->host; } static int deliver_sample_value(struct perf_session *session, @@ -907,8 +905,7 @@ int perf_session__deliver_event(struct perf_session *session, evsel = perf_evlist__id2evsel(session->evlist, sample->id); - machine = perf_session__find_machine_for_cpumode(session, event, - sample); + machine = machines__find_for_cpumode(&session->machines, event, sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: -- cgit v1.1 From 75be989a7a18e9666efd92b846ee48bed79e8086 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 14 Feb 2015 14:50:11 -0300 Subject: perf evlist: Adopt events_stats from perf_session For tools that don't deal with perf.data files, thus do not need to use perf_session. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-kglq67gvauq9tak02a4se00r@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.h | 1 + tools/perf/util/session.c | 54 +++++++++++++++++++++++------------------------ tools/perf/util/session.h | 1 - 3 files changed, 28 insertions(+), 28 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c19ff45..d4768a3 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -51,6 +51,7 @@ struct perf_evlist { struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; + struct events_stats stats; }; struct perf_evsel_str_handler { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index fac08e1..06ef1c3 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -537,7 +537,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", oe->last_flush_type); - s->stats.nr_unordered_events++; + s->evlist->stats.nr_unordered_events++; } new = ordered_events__new(oe, timestamp, event); @@ -841,7 +841,7 @@ static int deliver_sample_value(struct perf_session *session, } if (!sid || sid->evsel == NULL) { - ++session->stats.nr_unknown_id; + ++session->evlist->stats.nr_unknown_id; return 0; } @@ -911,11 +911,11 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->stats.nr_unknown_id; + ++session->evlist->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->stats.nr_unprocessable_samples; + ++session->evlist->stats.nr_unprocessable_samples; return 0; } return perf_session__deliver_sample(session, tool, event, @@ -932,7 +932,7 @@ int perf_session__deliver_event(struct perf_session *session, return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->stats.total_lost += event->lost.lost; + session->evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); @@ -941,7 +941,7 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->stats.nr_unknown_events; + ++session->evlist->stats.nr_unknown_events; return -1; } } @@ -991,7 +991,7 @@ int perf_session__deliver_synth_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool) { - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&session->evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, 0); @@ -1077,7 +1077,7 @@ static s64 perf_session__process_event(struct perf_session *session, if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&session->evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, file_offset); @@ -1129,43 +1129,43 @@ static void perf_session__warn_about_errors(const struct perf_session *session, const struct perf_tool *tool) { if (tool->lost == perf_event__process_lost && - session->stats.nr_events[PERF_RECORD_LOST] != 0) { + session->evlist->stats.nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->stats.nr_events[0], - session->stats.nr_events[PERF_RECORD_LOST]); + session->evlist->stats.nr_events[0], + session->evlist->stats.nr_events[PERF_RECORD_LOST]); } - if (session->stats.nr_unknown_events != 0) { + if (session->evlist->stats.nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_unknown_events); + session->evlist->stats.nr_unknown_events); } - if (session->stats.nr_unknown_id != 0) { + if (session->evlist->stats.nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->stats.nr_unknown_id); + session->evlist->stats.nr_unknown_id); } - if (session->stats.nr_invalid_chains != 0) { - ui__warning("Found invalid callchains!\n\n" - "%u out of %u events were discarded for this reason.\n\n" - "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_invalid_chains, - session->stats.nr_events[PERF_RECORD_SAMPLE]); - } + if (session->evlist->stats.nr_invalid_chains != 0) { + ui__warning("Found invalid callchains!\n\n" + "%u out of %u events were discarded for this reason.\n\n" + "Consider reporting to linux-kernel@vger.kernel.org.\n\n", + session->evlist->stats.nr_invalid_chains, + session->evlist->stats.nr_events[PERF_RECORD_SAMPLE]); + } - if (session->stats.nr_unprocessable_samples != 0) { + if (session->evlist->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->stats.nr_unprocessable_samples); + session->evlist->stats.nr_unprocessable_samples); } - if (session->stats.nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); + if (session->evlist->stats.nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", session->evlist->stats.nr_unordered_events); } volatile int session_done; @@ -1485,7 +1485,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { size_t ret = fprintf(fp, "Aggregated stats:\n"); - ret += events_stats__fprintf(&session->stats, fp); + ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 6d663dc..fe859f3 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -20,7 +20,6 @@ struct perf_session { struct machines machines; struct perf_evlist *evlist; struct trace_event tevent; - struct events_stats stats; bool repipe; bool one_mmap; void *one_mmap_addr; -- cgit v1.1 From ccda068f96138734eb40e9202ea9562566b43c12 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 14 Feb 2015 14:57:13 -0300 Subject: perf session: Remove perf_session from warn_errors signature Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-pxxm1liohog3d6i826x8sud8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 06ef1c3..34dd749 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1125,47 +1125,47 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } -static void perf_session__warn_about_errors(const struct perf_session *session, - const struct perf_tool *tool) +static void perf_tool__warn_about_errors(const struct perf_tool *tool, + const struct events_stats *stats) { if (tool->lost == perf_event__process_lost && - session->evlist->stats.nr_events[PERF_RECORD_LOST] != 0) { + stats->nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->evlist->stats.nr_events[0], - session->evlist->stats.nr_events[PERF_RECORD_LOST]); + stats->nr_events[0], + stats->nr_events[PERF_RECORD_LOST]); } - if (session->evlist->stats.nr_unknown_events != 0) { + if (stats->nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->evlist->stats.nr_unknown_events); + stats->nr_unknown_events); } - if (session->evlist->stats.nr_unknown_id != 0) { + if (stats->nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->evlist->stats.nr_unknown_id); + stats->nr_unknown_id); } - if (session->evlist->stats.nr_invalid_chains != 0) { + if (stats->nr_invalid_chains != 0) { ui__warning("Found invalid callchains!\n\n" "%u out of %u events were discarded for this reason.\n\n" "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->evlist->stats.nr_invalid_chains, - session->evlist->stats.nr_events[PERF_RECORD_SAMPLE]); + stats->nr_invalid_chains, + stats->nr_events[PERF_RECORD_SAMPLE]); } - if (session->evlist->stats.nr_unprocessable_samples != 0) { + if (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->evlist->stats.nr_unprocessable_samples); + stats->nr_unprocessable_samples); } - if (session->evlist->stats.nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", session->evlist->stats.nr_unordered_events); + if (stats->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", stats->nr_unordered_events); } volatile int session_done; @@ -1255,7 +1255,7 @@ done: err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: free(buf); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); return err; } @@ -1400,7 +1400,7 @@ out: err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: ui_progress__finish(); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); session->one_mmap = false; return err; -- cgit v1.1 From 313e53b08e99b1dacf9ea2b0fbe97890db1ea95f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 14 Feb 2015 15:05:28 -0300 Subject: perf session: Remove perf_session from some deliver event routines Further untangling perf_session from plain event delivery routines. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-cvz8e6pwyogs4w14582iis9w@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 34dd749..0133d01 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -824,16 +824,15 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, return &machines->host; } -static int deliver_sample_value(struct perf_session *session, +static int deliver_sample_value(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, struct machine *machine) { - struct perf_sample_id *sid; + struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); - sid = perf_evlist__id2sid(session->evlist, v->id); if (sid) { sample->id = v->id; sample->period = v->value - sid->period; @@ -841,14 +840,14 @@ static int deliver_sample_value(struct perf_session *session, } if (!sid || sid->evsel == NULL) { - ++session->evlist->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } return tool->sample(tool, event, sample, sid->evsel, machine); } -static int deliver_sample_group(struct perf_session *session, +static int deliver_sample_group(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -858,7 +857,7 @@ static int deliver_sample_group(struct perf_session *session, u64 i; for (i = 0; i < sample->read.group.nr; i++) { - ret = deliver_sample_value(session, tool, event, sample, + ret = deliver_sample_value(evlist, tool, event, sample, &sample->read.group.values[i], machine); if (ret) @@ -869,7 +868,7 @@ static int deliver_sample_group(struct perf_session *session, } static int -perf_session__deliver_sample(struct perf_session *session, + perf_evlist__deliver_sample(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -886,10 +885,10 @@ perf_session__deliver_sample(struct perf_session *session, /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) - return deliver_sample_group(session, tool, event, sample, + return deliver_sample_group(evlist, tool, event, sample, machine); else - return deliver_sample_value(session, tool, event, sample, + return deliver_sample_value(evlist, tool, event, sample, &sample->read.one, machine); } @@ -898,12 +897,13 @@ int perf_session__deliver_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; struct machine *machine; dump_event(session, event, file_offset, sample); - evsel = perf_evlist__id2evsel(session->evlist, sample->id); + evsel = perf_evlist__id2evsel(evlist, sample->id); machine = machines__find_for_cpumode(&session->machines, event, sample); @@ -911,15 +911,14 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->evlist->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->evlist->stats.nr_unprocessable_samples; + ++evlist->stats.nr_unprocessable_samples; return 0; } - return perf_session__deliver_sample(session, tool, event, - sample, evsel, machine); + return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: @@ -932,7 +931,7 @@ int perf_session__deliver_event(struct perf_session *session, return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->evlist->stats.total_lost += event->lost.lost; + evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); @@ -941,7 +940,7 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->evlist->stats.nr_unknown_events; + ++evlist->stats.nr_unknown_events; return -1; } } @@ -1068,16 +1067,17 @@ static s64 perf_session__process_event(struct perf_session *session, struct perf_tool *tool, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; struct perf_sample sample; int ret; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(session->evlist)); + event_swap(event, perf_evlist__sample_id_all(evlist)); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - events_stats__inc(&session->evlist->stats, event->header.type); + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, file_offset); @@ -1085,7 +1085,7 @@ static s64 perf_session__process_event(struct perf_session *session, /* * For all kernel events we get the sample data */ - ret = perf_evlist__parse_sample(session->evlist, event, &sample); + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) return ret; -- cgit v1.1 From 9fa8727aa4d98d35ca50ef9cd8a50c6468af921d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 14 Feb 2015 15:08:51 -0300 Subject: perf session: Remove perf_session from dump_event All it wants is session->evlist. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-6w9663gka3jb1j1rfxxd5jcq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0133d01..e4f1669 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -688,14 +688,14 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_session__print_tstamp(struct perf_session *session, +static void perf_evlist__print_tstamp(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(evlist); if (event->header.type != PERF_RECORD_SAMPLE && - !perf_evlist__sample_id_all(session->evlist)) { + !perf_evlist__sample_id_all(evlist)) { fputs("-1 -1 ", stdout); return; } @@ -737,7 +737,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.one.id, sample->read.one.value); } -static void dump_event(struct perf_session *session, union perf_event *event, +static void dump_event(struct perf_evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -749,7 +749,7 @@ static void dump_event(struct perf_session *session, union perf_event *event, trace_event(event); if (sample) - perf_session__print_tstamp(session, event, sample); + perf_evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); @@ -901,7 +901,7 @@ int perf_session__deliver_event(struct perf_session *session, struct perf_evsel *evsel; struct machine *machine; - dump_event(session, event, file_offset, sample); + dump_event(evlist, event, file_offset, sample); evsel = perf_evlist__id2evsel(evlist, sample->id); @@ -953,7 +953,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, int fd = perf_data_file__fd(session->file); int err; - dump_event(session, event, file_offset, NULL); + dump_event(session->evlist, event, file_offset, NULL); /* These events are processed right away */ switch (event->header.type) { -- cgit v1.1 From 280836812f5f821d26393268010f211160874810 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 22 Feb 2015 13:52:47 -0800 Subject: perf ordered_events: Stop using tool->ordered_events To figure out if ordered_events are being used when doing a flush operation, it is enough to check if there were in fact some events queued, i.e. look at oe->nr_events. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-1c5r404vy766kt5nflv88uag@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index fd4be94..077ddd2 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -166,7 +166,7 @@ static int __ordered_events__flush(struct perf_session *s, struct ui_progress prog; int ret; - if (!tool->ordered_events || !limit) + if (!limit) return 0; if (show_progress) @@ -216,6 +216,9 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, }; int err; + if (oe->nr_events == 0) + return 0; + switch (how) { case OE_FLUSH__FINAL: oe->next_flush = ULLONG_MAX; -- cgit v1.1 From 07c1a0dadfce976e9877c55ce5212dd14753c91d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Feb 2015 15:34:23 -0300 Subject: perf tools: Introduce dump_stack signal helper To use in stdio based tools, like 'trace'. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-79kjmerlw6d88csyx1afzwvn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/util.c | 7 +++++++ tools/perf/util/util.h | 1 + 2 files changed, 8 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 92db3f1..4ee6d0d 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -269,6 +269,13 @@ void dump_stack(void) void dump_stack(void) {} #endif +void sighandler_dump_stack(int sig) +{ + psignal(sig, "perf"); + dump_stack(); + exit(sig); +} + void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 73c2f8e..fbd598a 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -277,6 +277,7 @@ char *ltrim(char *s); char *rtrim(char *s); void dump_stack(void); +void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; -- cgit v1.1 From 506740654db4fa5b6e1229147cee3cf8c7e07eca Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Feb 2015 17:20:31 -0300 Subject: perf tools: Print the thread's tid on PERF_RECORD_COMM events when -D is asked Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-fmto8ft6jrtwz09dxn5d4z8w@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6c6d044..9e806d8 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -615,7 +615,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) else s = ""; - return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); + return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, -- cgit v1.1 From 85c273d2b6569706762cf400079ca0699e007d81 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 24 Feb 2015 15:13:40 -0800 Subject: perf record: Support recording running/enabled time Add an option to perf record to record running/enabled time for read events, similar to what stat does. This is useful to understand multiplexing problems. Right now the report support is not great, but at least report -D already supports it. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1424819620-16043-1-git-send-email-andi@firstfloor.org [ Fixed the Documentation entry to match the OPT_BOOLEAN one ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f93e520..bb4eff2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -734,6 +734,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_transaction) perf_evsel__set_sample_bit(evsel, TRANSACTION); + if (opts->running_time) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + } + /* * XXX see the function comment above * -- cgit v1.1 From edbe9817aeb540aa1494aa20276a2bfc7f4ab816 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 20 Feb 2015 23:17:00 +0100 Subject: perf data: Add perf data to CTF conversion support Adding 'perf data convert' to convert perf data file into different format. This patch adds support for CTF format conversion. To convert perf.data into CTF run: $ perf data convert --to-ctf=./ctf-data/ [ perf data convert: Converted 'perf.data' into CTF data './ctf-data/' ] [ perf data convert: Converted and wrote 11.268 MB (100230 samples) ] The command will create CTF metadata out of perf.data file (or one specified via -i option) and then convert all sample events into single CTF stream. Each sample_type bit is translated into separated CTF event field apart from following exceptions: PERF_SAMPLE_RAW - added in next patch PERF_SAMPLE_READ - TODO PERF_SAMPLE_CALLCHAIN - TODO PERF_SAMPLE_BRANCH_STACK - TODO PERF_SAMPLE_REGS_USER - TODO PERF_SAMPLE_STACK_USER - TODO $ perf --debug=data-convert=2 data convert ... The converted CTF data could be analyzed by CTF tools, like babletrace or tracecompass [1]. $ babeltrace ./ctf-data/ [03:19:13.962125533] (+?.?????????) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 1 } [03:19:13.962130001] (+0.000004468) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 1 } [03:19:13.962131936] (+0.000001935) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 8 } [03:19:13.962133732] (+0.000001796) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 114 } [03:19:13.962135557] (+0.000001825) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 2087 } [03:19:13.962137627] (+0.000002070) cycles: { }, { ip = 0xFFFFFFFF81361938, tid = 20714, pid = 20714, period = 37582 } [03:19:13.962161091] (+0.000023464) cycles: { }, { ip = 0xFFFFFFFF8124218F, tid = 20714, pid = 20714, period = 600246 } [03:19:13.962517569] (+0.000356478) cycles: { }, { ip = 0xFFFFFFFF811A75DB, tid = 20714, pid = 20714, period = 1325731 } [03:19:13.969518008] (+0.007000439) cycles: { }, { ip = 0x34080917B2, tid = 20714, pid = 20714, period = 1144298 } The following members to the ctf-environment were decided to be added to distinguish and specify perf CTF data: - domain It says "kernel" because it contains a kernel trace (not to be confused with a user space like lttng-ust does) - tracer_name It says perf. This can be used to distinguish between lttng and perf CTF based trace. - version The kernel version from stream. In addition to release, this is what it looks like on a Debian kernel: release = "3.14-1-amd64"; version = "3.14.0"; [1] http://projects.eclipse.org/projects/tools.tracecompass Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Reviewed-by: David Ahern Tested-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Jeremie Galarneau Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Tom Zanussi Cc: Wang Nan Link: http://lkml.kernel.org/r/1424470628-5969-4-git-send-email-jolsa@kernel.org Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 + tools/perf/util/data-convert-bt.c | 612 ++++++++++++++++++++++++++++++++++++++ tools/perf/util/data-convert-bt.h | 8 + tools/perf/util/debug.c | 2 + tools/perf/util/debug.h | 1 + 5 files changed, 625 insertions(+) create mode 100644 tools/perf/util/data-convert-bt.c create mode 100644 tools/perf/util/data-convert-bt.h (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 32f9327..a2c8047 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -88,6 +88,8 @@ libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o + libperf-y += scripting-engines/ libperf-$(CONFIG_PERF_REGS) += perf_regs.o diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c new file mode 100644 index 0000000..ff4826c --- /dev/null +++ b/tools/perf/util/data-convert-bt.c @@ -0,0 +1,612 @@ +/* + * CTF writing support via babeltrace. + * + * Copyright (C) 2014, Jiri Olsa + * Copyright (C) 2014, Sebastian Andrzej Siewior + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "asm/bug.h" +#include "data-convert-bt.h" +#include "session.h" +#include "util.h" +#include "debug.h" +#include "tool.h" +#include "evlist.h" +#include "evsel.h" +#include "machine.h" + +#define pr_N(n, fmt, ...) \ + eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) + +#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__) +#define pr2(fmt, ...) pr_N(2, pr_fmt(fmt), ##__VA_ARGS__) + +#define pr_time2(t, fmt, ...) pr_time_N(2, debug_data_convert, t, pr_fmt(fmt), ##__VA_ARGS__) + +struct evsel_priv { + struct bt_ctf_event_class *event_class; +}; + +struct ctf_writer { + /* writer primitives */ + struct bt_ctf_writer *writer; + struct bt_ctf_stream *stream; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_clock *clock; + + /* data types */ + union { + struct { + struct bt_ctf_field_type *s64; + struct bt_ctf_field_type *u64; + struct bt_ctf_field_type *s32; + struct bt_ctf_field_type *u32; + struct bt_ctf_field_type *string; + struct bt_ctf_field_type *u64_hex; + }; + struct bt_ctf_field_type *array[6]; + } data; +}; + +struct convert { + struct perf_tool tool; + struct ctf_writer writer; + + u64 events_size; + u64 events_count; +}; + +static int value_set(struct bt_ctf_field_type *type, + struct bt_ctf_event *event, + const char *name, u64 val) +{ + struct bt_ctf_field *field; + bool sign = bt_ctf_field_type_integer_get_signed(type); + int ret; + + field = bt_ctf_field_create(type); + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + if (sign) { + ret = bt_ctf_field_signed_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } else { + ret = bt_ctf_field_unsigned_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } + + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) { + pr_err("failed to set payload %s\n", name); + goto err; + } + + pr2(" SET [%s = %" PRIu64 "]\n", name, val); + +err: + bt_ctf_field_put(field); + return ret; +} + +#define __FUNC_VALUE_SET(_name, _val_type) \ +static __maybe_unused int value_set_##_name(struct ctf_writer *cw, \ + struct bt_ctf_event *event, \ + const char *name, \ + _val_type val) \ +{ \ + struct bt_ctf_field_type *type = cw->data._name; \ + return value_set(type, event, name, (u64) val); \ +} + +#define FUNC_VALUE_SET(_name) __FUNC_VALUE_SET(_name, _name) + +FUNC_VALUE_SET(s32) +FUNC_VALUE_SET(u32) +FUNC_VALUE_SET(s64) +FUNC_VALUE_SET(u64) +__FUNC_VALUE_SET(u64_hex, u64) + +static int add_generic_values(struct ctf_writer *cw, + struct bt_ctf_event *event, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 type = evsel->attr.sample_type; + int ret; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + + if (type & PERF_SAMPLE_IP) { + ret = value_set_u64_hex(cw, event, "ip", sample->ip); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TID) { + ret = value_set_s32(cw, event, "tid", sample->tid); + if (ret) + return -1; + + ret = value_set_s32(cw, event, "pid", sample->pid); + if (ret) + return -1; + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) { + ret = value_set_u64(cw, event, "id", sample->id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + ret = value_set_u64(cw, event, "stream_id", sample->stream_id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_CPU) { + ret = value_set_u32(cw, event, "cpu", sample->cpu); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_PERIOD) { + ret = value_set_u64(cw, event, "period", sample->period); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_WEIGHT) { + ret = value_set_u64(cw, event, "weight", sample->weight); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + ret = value_set_u64(cw, event, "data_src", sample->data_src); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + ret = value_set_u64(cw, event, "transaction", sample->transaction); + if (ret) + return -1; + } + + return 0; +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *_event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __maybe_unused) +{ + struct convert *c = container_of(tool, struct convert, tool); + struct evsel_priv *priv = evsel->priv; + struct ctf_writer *cw = &c->writer; + struct bt_ctf_event_class *event_class; + struct bt_ctf_event *event; + int ret; + + if (WARN_ONCE(!priv, "Failed to setup all events.\n")) + return 0; + + event_class = priv->event_class; + + /* update stats */ + c->events_count++; + c->events_size += _event->header.size; + + pr_time2(sample->time, "sample %" PRIu64 "\n", c->events_count); + + event = bt_ctf_event_create(event_class); + if (!event) { + pr_err("Failed to create an CTF event\n"); + return -1; + } + + bt_ctf_clock_set_time(cw->clock, sample->time); + + ret = add_generic_values(cw, event, evsel, sample); + if (ret) + return -1; + + bt_ctf_stream_append_event(cw->stream, event); + bt_ctf_event_put(event); + return 0; +} + +static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, + struct bt_ctf_event_class *event_class) +{ + u64 type = evsel->attr.sample_type; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + +#define ADD_FIELD(cl, t, n) \ + do { \ + pr2(" field '%s'\n", n); \ + if (bt_ctf_event_class_add_field(cl, t, n)) { \ + pr_err("Failed to add field '%s;\n", n); \ + return -1; \ + } \ + } while (0) + + if (type & PERF_SAMPLE_IP) + ADD_FIELD(event_class, cw->data.u64_hex, "ip"); + + if (type & PERF_SAMPLE_TID) { + ADD_FIELD(event_class, cw->data.s32, "tid"); + ADD_FIELD(event_class, cw->data.s32, "pid"); + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) + ADD_FIELD(event_class, cw->data.u64, "id"); + + if (type & PERF_SAMPLE_STREAM_ID) + ADD_FIELD(event_class, cw->data.u64, "stream_id"); + + if (type & PERF_SAMPLE_CPU) + ADD_FIELD(event_class, cw->data.u32, "cpu"); + + if (type & PERF_SAMPLE_PERIOD) + ADD_FIELD(event_class, cw->data.u64, "period"); + + if (type & PERF_SAMPLE_WEIGHT) + ADD_FIELD(event_class, cw->data.u64, "weight"); + + if (type & PERF_SAMPLE_DATA_SRC) + ADD_FIELD(event_class, cw->data.u64, "data_src"); + + if (type & PERF_SAMPLE_TRANSACTION) + ADD_FIELD(event_class, cw->data.u64, "transaction"); + +#undef ADD_FIELD + return 0; +} + +static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) +{ + struct bt_ctf_event_class *event_class; + struct evsel_priv *priv; + const char *name = perf_evsel__name(evsel); + int ret; + + pr("Adding event '%s' (type %d)\n", name, evsel->attr.type); + + event_class = bt_ctf_event_class_create(name); + if (!event_class) + return -1; + + ret = add_generic_types(cw, evsel, event_class); + if (ret) + goto err; + + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class); + if (ret) { + pr("Failed to add event class into stream.\n"); + goto err; + } + + priv = malloc(sizeof(*priv)); + if (!priv) + goto err; + + priv->event_class = event_class; + evsel->priv = priv; + return 0; + +err: + bt_ctf_event_class_put(event_class); + pr_err("Failed to add event '%s'.\n", name); + return -1; +} + +static int setup_events(struct ctf_writer *cw, struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel; + int ret; + + evlist__for_each(evlist, evsel) { + ret = add_event(cw, evsel); + if (ret) + return ret; + } + return 0; +} + +static int ctf_writer__setup_env(struct ctf_writer *cw, + struct perf_session *session) +{ + struct perf_header *header = &session->header; + struct bt_ctf_writer *writer = cw->writer; + +#define ADD(__n, __v) \ +do { \ + if (bt_ctf_writer_add_environment_field(writer, __n, __v)) \ + return -1; \ +} while (0) + + ADD("host", header->env.hostname); + ADD("sysname", "Linux"); + ADD("release", header->env.os_release); + ADD("version", header->env.version); + ADD("machine", header->env.arch); + ADD("domain", "kernel"); + ADD("tracer_name", "perf"); + +#undef ADD + return 0; +} + +static int ctf_writer__setup_clock(struct ctf_writer *cw) +{ + struct bt_ctf_clock *clock = cw->clock; + + bt_ctf_clock_set_description(clock, "perf clock"); + +#define SET(__n, __v) \ +do { \ + if (bt_ctf_clock_set_##__n(clock, __v)) \ + return -1; \ +} while (0) + + SET(frequency, 1000000000); + SET(offset_s, 0); + SET(offset, 0); + SET(precision, 10); + SET(is_absolute, 0); + +#undef SET + return 0; +} + +static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex) +{ + struct bt_ctf_field_type *type; + + type = bt_ctf_field_type_integer_create(size); + if (!type) + return NULL; + + if (sign && + bt_ctf_field_type_integer_set_signed(type, 1)) + goto err; + + if (hex && + bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL)) + goto err; + + pr2("Created type: INTEGER %d-bit %ssigned %s\n", + size, sign ? "un" : "", hex ? "hex" : ""); + return type; + +err: + bt_ctf_field_type_put(type); + return NULL; +} + +static void ctf_writer__cleanup_data(struct ctf_writer *cw) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cw->data.array); i++) + bt_ctf_field_type_put(cw->data.array[i]); +} + +static int ctf_writer__init_data(struct ctf_writer *cw) +{ +#define CREATE_INT_TYPE(type, size, sign, hex) \ +do { \ + (type) = create_int_type(size, sign, hex); \ + if (!(type)) \ + goto err; \ +} while (0) + + CREATE_INT_TYPE(cw->data.s64, 64, true, false); + CREATE_INT_TYPE(cw->data.u64, 64, false, false); + CREATE_INT_TYPE(cw->data.s32, 32, true, false); + CREATE_INT_TYPE(cw->data.u32, 32, false, false); + CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true); + + cw->data.string = bt_ctf_field_type_string_create(); + if (cw->data.string) + return 0; + +err: + ctf_writer__cleanup_data(cw); + pr_err("Failed to create data types.\n"); + return -1; +} + +static void ctf_writer__cleanup(struct ctf_writer *cw) +{ + ctf_writer__cleanup_data(cw); + + bt_ctf_clock_put(cw->clock); + bt_ctf_stream_put(cw->stream); + bt_ctf_stream_class_put(cw->stream_class); + bt_ctf_writer_put(cw->writer); + + /* and NULL all the pointers */ + memset(cw, 0, sizeof(*cw)); +} + +static int ctf_writer__init(struct ctf_writer *cw, const char *path) +{ + struct bt_ctf_writer *writer; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_stream *stream; + struct bt_ctf_clock *clock; + + /* CTF writer */ + writer = bt_ctf_writer_create(path); + if (!writer) + goto err; + + cw->writer = writer; + + /* CTF clock */ + clock = bt_ctf_clock_create("perf_clock"); + if (!clock) { + pr("Failed to create CTF clock.\n"); + goto err_cleanup; + } + + cw->clock = clock; + + if (ctf_writer__setup_clock(cw)) { + pr("Failed to setup CTF clock.\n"); + goto err_cleanup; + } + + /* CTF stream class */ + stream_class = bt_ctf_stream_class_create("perf_stream"); + if (!stream_class) { + pr("Failed to create CTF stream class.\n"); + goto err_cleanup; + } + + cw->stream_class = stream_class; + + /* CTF clock stream setup */ + if (bt_ctf_stream_class_set_clock(stream_class, clock)) { + pr("Failed to assign CTF clock to stream class.\n"); + goto err_cleanup; + } + + if (ctf_writer__init_data(cw)) + goto err_cleanup; + + /* CTF stream instance */ + stream = bt_ctf_writer_create_stream(writer, stream_class); + if (!stream) { + pr("Failed to create CTF stream.\n"); + goto err_cleanup; + } + + cw->stream = stream; + + /* CTF clock writer setup */ + if (bt_ctf_writer_add_clock(writer, clock)) { + pr("Failed to assign CTF clock to writer.\n"); + goto err_cleanup; + } + + return 0; + +err_cleanup: + ctf_writer__cleanup(cw); +err: + pr_err("Failed to setup CTF writer.\n"); + return -1; +} + +int bt_convert__perf2ctf(const char *input, const char *path) +{ + struct perf_session *session; + struct perf_data_file file = { + .path = input, + .mode = PERF_DATA_MODE_READ, + }; + struct convert c = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .comm = perf_event__process_comm, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, + .lost = perf_event__process_lost, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_events = true, + .ordering_requires_timestamps = true, + }, + }; + struct ctf_writer *cw = &c.writer; + int err = -1; + + /* CTF writer */ + if (ctf_writer__init(cw, path)) + return -1; + + /* perf.data session */ + session = perf_session__new(&file, 0, NULL); + if (!session) + goto free_writer; + + /* CTF writer env/clock setup */ + if (ctf_writer__setup_env(cw, session)) + goto free_session; + + /* CTF events setup */ + if (setup_events(cw, session)) + goto free_session; + + err = perf_session__process_events(session, &c.tool); + if (!err) + err = bt_ctf_stream_flush(cw->stream); + + fprintf(stderr, + "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", + file.path, path); + + fprintf(stderr, + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + (double) c.events_size / 1024.0 / 1024.0, + c.events_count); + + /* its all good */ +free_session: + perf_session__delete(session); + +free_writer: + ctf_writer__cleanup(cw); + return err; +} diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h new file mode 100644 index 0000000..dda30c5 --- /dev/null +++ b/tools/perf/util/data-convert-bt.h @@ -0,0 +1,8 @@ +#ifndef __DATA_CONVERT_BT_H +#define __DATA_CONVERT_BT_H +#ifdef HAVE_LIBBABELTRACE_SUPPORT + +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf); + +#endif /* HAVE_LIBBABELTRACE_SUPPORT */ +#endif /* __DATA_CONVERT_BT_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index ad60b2f..2da5581 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -20,6 +20,7 @@ int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; +int debug_data_convert; static int _eprintf(int level, int var, const char *fmt, va_list args) { @@ -147,6 +148,7 @@ static struct debug_variable { { .name = "verbose", .ptr = &verbose }, { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = "stderr", .ptr = &redirect_to_stderr}, + { .name = "data-convert", .ptr = &debug_data_convert }, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index be264d6..caac2fd 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -12,6 +12,7 @@ extern int verbose; extern bool quiet, dump_trace; extern int debug_ordered_events; +extern int debug_data_convert; #ifndef pr_fmt #define pr_fmt(fmt) fmt -- cgit v1.1 From 54cf776a9c5c2e6a91de31954bba4d3bad6c657c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 20 Feb 2015 23:17:01 +0100 Subject: perf data: Add a 'perf' prefix to the generic fields Some of the tracers bring their own id or pid fields and we can end up having two of them. This patch adds a "perf_" prefix to the 'generic' fields so we avoid a clash of the member names. The change is visible in the babeltrace output: Before: $ babeltrace ./ctf-data/ [03:19:13.962131936] (+0.000001935) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 8 } [03:19:13.962133732] (+0.000001796) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 114 } ... Now: $ babeltrace ./ctf-data/ [03:19:13.962131936] (+0.000001935) cycles: { }, { perf_ip = 0xFFFFFFFF8105443A, perf_tid = 20714, perf_pid = 20714, perf_period = 8 } [03:19:13.962133732] (+0.000001796) cycles: { }, { perf_ip = 0xFFFFFFFF8105443A, perf_tid = 20714, perf_pid = 20714, perf_period = 114 } ... Signed-off-by: Sebastian Andrzej Siewior Acked-by: Namhyung Kim Reviewed-by: David Ahern Tested-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Jeremie Galarneau Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi Cc: Wang Nan Link: http://lkml.kernel.org/r/1424470628-5969-5-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data-convert-bt.c | 42 ++++++++++++++++++++------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index ff4826c..e372e03 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -147,60 +147,62 @@ static int add_generic_values(struct ctf_writer *cw, */ if (type & PERF_SAMPLE_IP) { - ret = value_set_u64_hex(cw, event, "ip", sample->ip); + ret = value_set_u64_hex(cw, event, "perf_ip", sample->ip); if (ret) return -1; } if (type & PERF_SAMPLE_TID) { - ret = value_set_s32(cw, event, "tid", sample->tid); + ret = value_set_s32(cw, event, "perf_tid", sample->tid); if (ret) return -1; - ret = value_set_s32(cw, event, "pid", sample->pid); + ret = value_set_s32(cw, event, "perf_pid", sample->pid); if (ret) return -1; } if ((type & PERF_SAMPLE_ID) || (type & PERF_SAMPLE_IDENTIFIER)) { - ret = value_set_u64(cw, event, "id", sample->id); + ret = value_set_u64(cw, event, "perf_id", sample->id); if (ret) return -1; } if (type & PERF_SAMPLE_STREAM_ID) { - ret = value_set_u64(cw, event, "stream_id", sample->stream_id); + ret = value_set_u64(cw, event, "perf_stream_id", sample->stream_id); if (ret) return -1; } if (type & PERF_SAMPLE_CPU) { - ret = value_set_u32(cw, event, "cpu", sample->cpu); + ret = value_set_u32(cw, event, "perf_cpu", sample->cpu); if (ret) return -1; } if (type & PERF_SAMPLE_PERIOD) { - ret = value_set_u64(cw, event, "period", sample->period); + ret = value_set_u64(cw, event, "perf_period", sample->period); if (ret) return -1; } if (type & PERF_SAMPLE_WEIGHT) { - ret = value_set_u64(cw, event, "weight", sample->weight); + ret = value_set_u64(cw, event, "perf_weight", sample->weight); if (ret) return -1; } if (type & PERF_SAMPLE_DATA_SRC) { - ret = value_set_u64(cw, event, "data_src", sample->data_src); + ret = value_set_u64(cw, event, "perf_data_src", + sample->data_src); if (ret) return -1; } if (type & PERF_SAMPLE_TRANSACTION) { - ret = value_set_u64(cw, event, "transaction", sample->transaction); + ret = value_set_u64(cw, event, "perf_transaction", + sample->transaction); if (ret) return -1; } @@ -276,34 +278,34 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, } while (0) if (type & PERF_SAMPLE_IP) - ADD_FIELD(event_class, cw->data.u64_hex, "ip"); + ADD_FIELD(event_class, cw->data.u64_hex, "perf_ip"); if (type & PERF_SAMPLE_TID) { - ADD_FIELD(event_class, cw->data.s32, "tid"); - ADD_FIELD(event_class, cw->data.s32, "pid"); + ADD_FIELD(event_class, cw->data.s32, "perf_tid"); + ADD_FIELD(event_class, cw->data.s32, "perf_pid"); } if ((type & PERF_SAMPLE_ID) || (type & PERF_SAMPLE_IDENTIFIER)) - ADD_FIELD(event_class, cw->data.u64, "id"); + ADD_FIELD(event_class, cw->data.u64, "perf_id"); if (type & PERF_SAMPLE_STREAM_ID) - ADD_FIELD(event_class, cw->data.u64, "stream_id"); + ADD_FIELD(event_class, cw->data.u64, "perf_stream_id"); if (type & PERF_SAMPLE_CPU) - ADD_FIELD(event_class, cw->data.u32, "cpu"); + ADD_FIELD(event_class, cw->data.u32, "perf_cpu"); if (type & PERF_SAMPLE_PERIOD) - ADD_FIELD(event_class, cw->data.u64, "period"); + ADD_FIELD(event_class, cw->data.u64, "perf_period"); if (type & PERF_SAMPLE_WEIGHT) - ADD_FIELD(event_class, cw->data.u64, "weight"); + ADD_FIELD(event_class, cw->data.u64, "perf_weight"); if (type & PERF_SAMPLE_DATA_SRC) - ADD_FIELD(event_class, cw->data.u64, "data_src"); + ADD_FIELD(event_class, cw->data.u64, "perf_data_src"); if (type & PERF_SAMPLE_TRANSACTION) - ADD_FIELD(event_class, cw->data.u64, "transaction"); + ADD_FIELD(event_class, cw->data.u64, "perf_transaction"); #undef ADD_FIELD return 0; -- cgit v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9dfbed9..662d454 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 v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 662d454..4a93bf4 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 v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4a93bf4..9526cf3 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 v1.1 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/util/build-id.c | 12 ++++++++++++ tools/perf/util/build-id.h | 1 + 2 files changed, 13 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index adbc360..0bc33be 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 31b3c63..2a09498 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 v1.1 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/util/sort.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 7a39c1e..4593f36 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 v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9526cf3..7c0e765 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 v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 109ba5c..f6822d9 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 v1.1 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/util/parse-options.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 4ee9a86..b0ef2d8 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 v1.1 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(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index b0ef2d8..1457d66 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 v1.1 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/util/parse-events.c | 80 ++---------------------------------------- tools/perf/util/parse-events.h | 11 +++++- 2 files changed, 13 insertions(+), 78 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f6822d9..fe07573 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 39c3b57..52a2dda 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 v1.1 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/util/build-id.c | 93 +++++++++++++++++++++++++++++++++++++--------- tools/perf/util/build-id.h | 3 ++ 2 files changed, 79 insertions(+), 17 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0bc33be..ffdc338 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 2a09498..8501122 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 v1.1 From ecefde629fadd3fcca2ea4c6a799d6e6aab8781f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 19 Feb 2015 13:22:33 -0500 Subject: perf tools: Only include tsc file for x86 The perf_time_to_tsc and tsc_to_perf_time functions are only used for x86. Make inclusion of tsc.c dependent on x86 as well. Signed-off-by: David Ahern Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1424370153-128274-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index a2c8047..972a6e0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -71,7 +71,7 @@ libperf-y += stat.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o -libperf-y += tsc.o +libperf-$(CONFIG_X86) += tsc.o libperf-y += cloexec.o libperf-y += thread-stack.o -- cgit v1.1 From 4aa5f4f7bb8bc41cba15bcd0d80c4fb085027d6b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 27 Feb 2015 19:52:10 -0300 Subject: perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads In this commit: commit 363b785f3805a2632eb09a8b430842461c21a640 Author: Don Zickus Date: Fri Mar 14 10:43:44 2014 -0400 perf tools: Speed up thread map generation We ended up emitting PERF_RECORD_FORK events after their corresponding PERF_RECORD_COMM, so the code below will remove the "existing thread" and then recreates it, unnecessarily: [root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event 0 int machine__process_fork_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) 2 { 3 struct thread *thread = machine__find_thread(machine, event->fork.pid, event->fork.tid); 6 struct thread *parent = machine__findnew_thread(machine, event->fork.ppid, event->fork.ptid); /* if a thread currently exists for the thread id remove it */ if (thread != NULL) 12 machine__remove_thread(machine, thread); 14 thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); 16 if (dump_trace) 17 perf_event__fprintf_task(event, stdout); 19 if (thread == NULL || parent == NULL || 20 thread__fork(thread, parent, sample->time) < 0) { 21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); 22 return -1; } 25 return 0; 26 } [root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12 Added new event: probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:fork_after_comm -aR sleep 1 [root@ssdandy ~]# [root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ] Terminated [root@ssdandy ~]# [root@ssdandy ~]# perf report --no-children --show-total-period --stdio # To display the perf.data header info, please use --header/--header-only options. # # Samples: 30 of event 'probe_perf:fork_after_comm' # Event count (approx.): 30 # # Overhead Period Command Shared Object Symbol # ........ ............ ....... ............. ............................... # 100.00% 30 trace trace [.] machine__process_fork_event | ---machine__process_fork_event __event__synthesize_thread.part.2 perf_event__synthesize_threads cmd_trace main __libc_start_main [root@ssdandy ~]# And Looking at 'perf report -D' output we see it: 0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707 0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703) Fix it by more closely mimicking how the kernel generates those records when a new fork happens, i.e. first a PERF_RECORD_FORK, then a PERF_RECORD_COMM. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9e806d8..d5efa50 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -95,9 +95,7 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) return tgid; } -static pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, +static pid_t perf_event__prepare_comm(union perf_event *event, pid_t pid, struct machine *machine) { size_t size; @@ -124,6 +122,19 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, (sizeof(event->comm.comm) - size) + machine->id_hdr_size); event->comm.tid = pid; +out: + return tgid; +} + +static pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + pid_t tgid = perf_event__prepare_comm(event, pid, machine); + + if (tgid == -1) + goto out; if (process(tool, event, &synth_sample, machine) != 0) return -1; @@ -139,7 +150,6 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, { memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - /* this is really a clone event but we use fork to synthesize it */ event->fork.ppid = tgid; event->fork.ptid = tgid; event->fork.pid = tgid; @@ -368,19 +378,23 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (*end) continue; - tgid = perf_event__synthesize_comm(tool, comm_event, _pid, - process, machine); + tgid = perf_event__prepare_comm(comm_event, _pid, machine); if (tgid == -1) return -1; + if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + process, machine) < 0) + return -1; + /* + * Send the prepared comm event + */ + if (process(tool, comm_event, &synth_sample, machine) != 0) + return -1; + if (_pid == pid) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); - } else { - /* only fork the tid's map, to save time */ - rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - process, machine); } if (rc) -- cgit v1.1 From 79702f614187f652a814061e8f5875ddcc9e732d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 28 Feb 2015 11:53:29 +0900 Subject: perf probe: Warn if given uprobe event accesses memory on older kernel Warn if given uprobe event accesses memory on older kernel. Until 3.14, uprobe event only supports accessing registers so this warns to upgrade kernel if uprobe-event returns -EINVAL and an argument of the event accesses memory ($stack, @+offset, and +|-offs() symtax). With this patch (on 3.10.0-123.13.2.el7.x86_64); ----- # ./perf probe -x ./perf warn_uprobe_event_compat stack=-0\(%sp\) Added new event: Failed to write event: Invalid argument Please upgrade your kernel to at least 3.14 to have access to feature -0(%sp) Error: Failed to add events. ----- Suggested-by: Arnaldo Carvalho de Melo Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20150228025329.32106.70581.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 7c0e765..1c570c2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2199,6 +2199,27 @@ static int get_new_event_name(char *buf, size_t len, const char *base, return ret; } +/* Warn if the current kernel's uprobe implementation is old */ +static void warn_uprobe_event_compat(struct probe_trace_event *tev) +{ + int i; + char *buf = synthesize_probe_trace_command(tev); + + /* Old uprobe event doesn't support memory dereference */ + if (!tev->uprobes || tev->nargs == 0 || !buf) + goto out; + + for (i = 0; i < tev->nargs; i++) + if (strglobmatch(tev->args[i].value, "[$@+-]*")) { + pr_warning("Please upgrade your kernel to at least " + "3.14 to have access to feature %s\n", + tev->args[i].value); + break; + } +out: + free(buf); +} + static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs, bool allow_suffix) @@ -2295,6 +2316,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, */ allow_suffix = true; } + if (ret == -EINVAL && pev->uprobes) + warn_uprobe_event_compat(tev); /* Note that it is possible to skip all events because of blacklist */ if (ret >= 0 && tev->event) { -- cgit v1.1 From 0104fe69e0287cf3635657b4c6b26a18e0091697 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 2 Mar 2015 21:49:46 +0900 Subject: perf probe: Remove bias offset to find probe point by address Remove bias offset to find probe point by address. Without this patch, probe points on kernel and executables are shown correctly, but do not work with libraries: # ./perf probe -l probe:do_fork (on do_fork@kernel/fork.c) probe_libc:malloc (on malloc in /usr/lib64/libc-2.17.so) probe_perf:strlist__new (on strlist__new@util/strlist.c in /home/mhiramat/ksrc/linux-3/tools/perf/perf) Removing bias allows it to show it as real place: # ./perf probe -l probe:do_fork (on do_fork@kernel/fork.c) probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.17.so) probe_perf:strlist__new (on strlist__new@util/strlist.c in /home/mhiramat/ksrc/linux-3/tools/perf/perf) Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150302124946.9191.64085.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-finder.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index d141935..46f009a 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1345,11 +1345,8 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; - /* Adjust address with bias */ - addr += dbg->bias; - /* Find cu die */ - if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) { + if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; -- cgit v1.1 From f3b623b8490af7a9b819cbcf2d99ab4597ece94b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2015 22:21:35 -0300 Subject: perf tools: Reference count struct thread We need to do that to stop accumulating entries in the dead_threads linked list, i.e. we were keeping references to threads in struct hists that continue to exist even after a thread exited and was removed from the machine threads rbtree. We still keep the dead_threads list, but just for debugging, allowing us to iterate at any given point over the threads that still are referenced by things like struct hist_entry. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-3ejvfyed0r7ue61dkurzjux4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 5 +++-- tools/perf/util/hist.c | 2 ++ tools/perf/util/hist.h | 2 +- tools/perf/util/machine.c | 44 +++++++++++++++++++++++--------------------- tools/perf/util/machine.h | 1 - tools/perf/util/session.c | 6 ------ tools/perf/util/thread.c | 14 ++++++++++++++ tools/perf/util/thread.h | 13 +++++++++++++ 8 files changed, 56 insertions(+), 31 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index ffdc338..a196746 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -61,8 +61,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, if (thread) { rb_erase(&thread->rb_node, &machine->threads); - machine->last_match = NULL; - thread__delete(thread); + if (machine->last_match == thread) + thread__zput(machine->last_match); + thread__put(thread); } return 0; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 70b48a6..95f5ab7 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -355,6 +355,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, callchain_init(he->callchain); INIT_LIST_HEAD(&he->pairs.node); + thread__get(he->thread); } return he; @@ -941,6 +942,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__delete(struct hist_entry *he) { + thread__zput(he->thread); zfree(&he->branch_info); zfree(&he->mem_info); zfree(&he->stat_acc); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2b690d0..e988c9f 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -60,7 +60,7 @@ struct hists { struct rb_root entries_collapsed; u64 nr_entries; u64 nr_non_filtered_entries; - const struct thread *thread_filter; + struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9e0f60a..24f8c97 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -14,6 +14,8 @@ #include "unwind.h" #include "linux/hash.h" +static void machine__remove_thread(struct machine *machine, struct thread *th); + static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -89,16 +91,6 @@ static void dsos__delete(struct dsos *dsos) } } -void machine__delete_dead_threads(struct machine *machine) -{ - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &machine->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } -} - void machine__delete_threads(struct machine *machine) { struct rb_node *nd = rb_first(&machine->threads); @@ -106,9 +98,8 @@ void machine__delete_threads(struct machine *machine) while (nd) { struct thread *t = rb_entry(nd, struct thread, rb_node); - rb_erase(&t->rb_node, &machine->threads); nd = rb_next(nd); - thread__delete(t); + machine__remove_thread(machine, t); } } @@ -361,9 +352,13 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * the full rbtree: */ th = machine->last_match; - if (th && th->tid == tid) { - machine__update_thread_pid(machine, th, pid); - return th; + if (th != NULL) { + if (th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; + } + + thread__zput(machine->last_match); } while (*p != NULL) { @@ -371,7 +366,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - machine->last_match = th; + machine->last_match = thread__get(th); machine__update_thread_pid(machine, th, pid); return th; } @@ -403,8 +398,11 @@ static struct thread *__machine__findnew_thread(struct machine *machine, thread__delete(th); return NULL; } - - machine->last_match = th; + /* + * It is now in the rbtree, get a ref + */ + thread__get(th); + machine->last_match = thread__get(th); } return th; @@ -1238,13 +1236,17 @@ out_problem: static void machine__remove_thread(struct machine *machine, struct thread *th) { - machine->last_match = NULL; + if (machine->last_match == th) + thread__zput(machine->last_match); + rb_erase(&th->rb_node, &machine->threads); /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. + * Move it first to the dead_threads list, then drop the reference, + * if this is the last reference, then the thread__delete destructor + * will be called and we will remove it from the dead_threads list. */ list_add_tail(&th->node, &machine->dead_threads); + thread__put(th); } int machine__process_fork_event(struct machine *machine, union perf_event *event, diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index e8b7779..e2faf3b 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -118,7 +118,6 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); -void machine__delete_dead_threads(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e4f1669..ed4e5cf 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -138,11 +138,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, return NULL; } -static void perf_session__delete_dead_threads(struct perf_session *session) -{ - machine__delete_dead_threads(&session->machines.host); -} - static void perf_session__delete_threads(struct perf_session *session) { machine__delete_threads(&session->machines.host); @@ -167,7 +162,6 @@ static void perf_session_env__delete(struct perf_session_env *env) void perf_session__delete(struct perf_session *session) { perf_session__destroy_kernel_maps(session); - perf_session__delete_dead_threads(session); perf_session__delete_threads(session); perf_session_env__delete(&session->header.env); machines__exit(&session->machines); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 9ebc8b1..a5dbba9 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -82,6 +82,20 @@ void thread__delete(struct thread *thread) free(thread); } +struct thread *thread__get(struct thread *thread) +{ + ++thread->refcnt; + return thread; +} + +void thread__put(struct thread *thread) +{ + if (thread && --thread->refcnt == 0) { + list_del_init(&thread->node); + thread__delete(thread); + } +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 160fd06..783b668 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -20,6 +20,7 @@ struct thread { pid_t tid; pid_t ppid; int cpu; + int refcnt; char shortname[3]; bool comm_set; bool dead; /* if set thread has exited */ @@ -37,6 +38,18 @@ struct comm; struct thread *thread__new(pid_t pid, pid_t tid); int thread__init_map_groups(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); + +struct thread *thread__get(struct thread *thread); +void thread__put(struct thread *thread); + +static inline void __thread__zput(struct thread **thread) +{ + thread__put(*thread); + *thread = NULL; +} + +#define thread__zput(thread) __thread__zput(&thread) + static inline void thread__exited(struct thread *thread) { thread->dead = true; -- cgit v1.1 From fa713a4eb9cebe5dec71b1bd11429603e17d841d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Mar 2015 11:48:12 -0300 Subject: perf ordered_events: Untangle from perf_session For use by tools that are not perf.data based, as maybe 'perf trace' in live mode. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-nedqe7cmii5w82etfi36urfz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 17 +++++++++-------- tools/perf/util/ordered-events.h | 8 +++++--- tools/perf/util/session.c | 37 ++++++++++++++++++++++++++----------- tools/perf/util/session.h | 3 ++- 4 files changed, 42 insertions(+), 23 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 077ddd2..e6ab630 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -153,10 +153,11 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve free_dup_event(oe, event->event); } -static int __ordered_events__flush(struct perf_session *s, +static int __ordered_events__flush(struct ordered_events *oe, + struct machines *machines, + struct perf_evlist *evlist, struct perf_tool *tool) { - struct ordered_events *oe = &s->ordered_events; struct list_head *head = &oe->events; struct ordered_event *tmp, *iter; struct perf_sample sample; @@ -179,12 +180,12 @@ static int __ordered_events__flush(struct perf_session *s, if (iter->timestamp > limit) break; - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); + ret = perf_evlist__parse_sample(evlist, iter->event, &sample); if (ret) pr_err("Can't parse sample, err = %d\n", ret); else { - ret = perf_session__deliver_event(s, iter->event, &sample, tool, - iter->file_offset); + ret = machines__deliver_event(machines, evlist, iter->event, + &sample, tool, iter->file_offset); if (ret) return ret; } @@ -204,10 +205,10 @@ static int __ordered_events__flush(struct perf_session *s, return 0; } -int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, +int ordered_events__flush(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlist, struct perf_tool *tool, enum oe_flush how) { - struct ordered_events *oe = &s->ordered_events; static const char * const str[] = { "NONE", "FINAL", @@ -251,7 +252,7 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, str[how], oe->nr_events); pr_oe_time(oe->max_timestamp, "max_timestamp\n"); - err = __ordered_events__flush(s, tool); + err = __ordered_events__flush(oe, machines, evlist, tool); if (!err) { if (how == OE_FLUSH__ROUND) diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index 7b8f9b0..e09f243 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -2,9 +2,10 @@ #define __ORDERED_EVENTS_H #include -#include "tool.h" -struct perf_session; +struct perf_tool; +struct perf_evlist; +struct machines; struct ordered_event { u64 timestamp; @@ -40,7 +41,8 @@ struct ordered_events { struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, union perf_event *event); void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); -int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, +int ordered_events__flush(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlist, struct perf_tool *tool, enum oe_flush how); void ordered_events__init(struct ordered_events *oe); void ordered_events__free(struct ordered_events *oe); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ed4e5cf..23be146 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -512,7 +512,11 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event __maybe_unused, struct perf_session *session) { - return ordered_events__flush(session, tool, OE_FLUSH__ROUND); + struct ordered_events *oe = &session->ordered_events; + struct perf_evlist *evlist = session->evlist; + struct machines *machines = &session->machines; + + return ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__ROUND); } int perf_session_queue_event(struct perf_session *s, union perf_event *event, @@ -520,6 +524,9 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, u64 file_offset) { struct ordered_events *oe = &s->ordered_events; + struct perf_evlist *evlist = s->evlist; + struct machines *machines = &s->machines; + u64 timestamp = sample->time; struct ordered_event *new; @@ -536,7 +543,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, new = ordered_events__new(oe, timestamp, event); if (!new) { - ordered_events__flush(s, tool, OE_FLUSH__HALF); + ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__HALF); new = ordered_events__new(oe, timestamp, event); } @@ -886,12 +893,12 @@ static int &sample->read.one, machine); } -int perf_session__deliver_event(struct perf_session *session, +int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset) { - struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; struct machine *machine; @@ -899,7 +906,7 @@ int perf_session__deliver_event(struct perf_session *session, evsel = perf_evlist__id2evsel(evlist, sample->id); - machine = machines__find_for_cpumode(&session->machines, event, sample); + machine = machines__find_for_cpumode(machines, event, sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: @@ -984,12 +991,14 @@ int perf_session__deliver_synth_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool) { - events_stats__inc(&session->evlist->stats, event->header.type); + struct perf_evlist *evlist = session->evlist; + + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, 0); - return perf_session__deliver_event(session, event, sample, tool, 0); + return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0); } static void event_swap(union perf_event *event, bool sample_id_all) @@ -1090,8 +1099,8 @@ static s64 perf_session__process_event(struct perf_session *session, return ret; } - return perf_session__deliver_event(session, event, &sample, tool, - file_offset); + return machines__deliver_event(&session->machines, evlist, event, + &sample, tool, file_offset); } void perf_event_header__bswap(struct perf_event_header *hdr) @@ -1167,6 +1176,9 @@ volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *session, struct perf_tool *tool) { + struct ordered_events *oe = &session->ordered_events; + struct perf_evlist *evlist = session->evlist; + struct machines *machines = &session->machines; int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; @@ -1246,7 +1258,7 @@ more: goto more; done: /* do the final flush for ordered samples */ - err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__FINAL); out_err: free(buf); perf_tool__warn_about_errors(tool, &session->evlist->stats); @@ -1298,6 +1310,9 @@ static int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 file_size, struct perf_tool *tool) { + struct ordered_events *oe = &session->ordered_events; + struct perf_evlist *evlist = session->evlist; + struct machines *machines = &session->machines; int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; @@ -1391,7 +1406,7 @@ more: out: /* do the final flush for ordered samples */ - err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__FINAL); out_err: ui_progress__finish(); perf_tool__warn_about_errors(tool, &session->evlist->stats); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index fe859f3..c08fa6b 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -57,7 +57,8 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, void perf_tool__fill_defaults(struct perf_tool *tool); -int perf_session__deliver_event(struct perf_session *session, +int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset); -- cgit v1.1 From b7b61cbebd789a3dbca522e3fdb727fe5c95593f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Mar 2015 11:58:45 -0300 Subject: perf ordered_events: Shorten function signatures By keeping pointers to machines, evlist and tool in ordered_events. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-0c6huyaf59mqtm2ek9pmposl@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data-convert-bt.c | 4 +-- tools/perf/util/ordered-events.c | 23 +++++++------- tools/perf/util/ordered-events.h | 10 +++--- tools/perf/util/session.c | 65 ++++++++++++++++----------------------- tools/perf/util/session.h | 11 +++---- 5 files changed, 49 insertions(+), 64 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index e372e03..1afd381 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -579,7 +579,7 @@ int bt_convert__perf2ctf(const char *input, const char *path) return -1; /* perf.data session */ - session = perf_session__new(&file, 0, NULL); + session = perf_session__new(&file, 0, &c.tool); if (!session) goto free_writer; @@ -591,7 +591,7 @@ int bt_convert__perf2ctf(const char *input, const char *path) if (setup_events(cw, session)) goto free_session; - err = perf_session__process_events(session, &c.tool); + err = perf_session__process_events(session); if (!err) err = bt_ctf_stream_flush(cw->stream); diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index e6ab630..bad46ce 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -153,10 +153,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve free_dup_event(oe, event->event); } -static int __ordered_events__flush(struct ordered_events *oe, - struct machines *machines, - struct perf_evlist *evlist, - struct perf_tool *tool) +static int __ordered_events__flush(struct ordered_events *oe) { struct list_head *head = &oe->events; struct ordered_event *tmp, *iter; @@ -180,12 +177,12 @@ static int __ordered_events__flush(struct ordered_events *oe, if (iter->timestamp > limit) break; - ret = perf_evlist__parse_sample(evlist, iter->event, &sample); + ret = perf_evlist__parse_sample(oe->evlist, iter->event, &sample); if (ret) pr_err("Can't parse sample, err = %d\n", ret); else { - ret = machines__deliver_event(machines, evlist, iter->event, - &sample, tool, iter->file_offset); + ret = machines__deliver_event(oe->machines, oe->evlist, iter->event, + &sample, oe->tool, iter->file_offset); if (ret) return ret; } @@ -205,9 +202,7 @@ static int __ordered_events__flush(struct ordered_events *oe, return 0; } -int ordered_events__flush(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlist, struct perf_tool *tool, - enum oe_flush how) +int ordered_events__flush(struct ordered_events *oe, enum oe_flush how) { static const char * const str[] = { "NONE", @@ -252,7 +247,7 @@ int ordered_events__flush(struct ordered_events *oe, struct machines *machines, str[how], oe->nr_events); pr_oe_time(oe->max_timestamp, "max_timestamp\n"); - err = __ordered_events__flush(oe, machines, evlist, tool); + err = __ordered_events__flush(oe); if (!err) { if (how == OE_FLUSH__ROUND) @@ -268,13 +263,17 @@ int ordered_events__flush(struct ordered_events *oe, struct machines *machines, return err; } -void ordered_events__init(struct ordered_events *oe) +void ordered_events__init(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlist, struct perf_tool *tool) { INIT_LIST_HEAD(&oe->events); INIT_LIST_HEAD(&oe->cache); INIT_LIST_HEAD(&oe->to_free); oe->max_alloc_size = (u64) -1; oe->cur_alloc_size = 0; + oe->evlist = evlist; + oe->machines = machines; + oe->tool = tool; } void ordered_events__free(struct ordered_events *oe) diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index e09f243..ef7d73e 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -32,6 +32,9 @@ struct ordered_events { struct list_head to_free; struct ordered_event *buffer; struct ordered_event *last; + struct machines *machines; + struct perf_evlist *evlist; + struct perf_tool *tool; int buffer_idx; unsigned int nr_events; enum oe_flush last_flush_type; @@ -41,10 +44,9 @@ struct ordered_events { struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, union perf_event *event); void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); -int ordered_events__flush(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlist, struct perf_tool *tool, - enum oe_flush how); -void ordered_events__init(struct ordered_events *oe); +int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); +void ordered_events__init(struct ordered_events *oe, struct machines *machines, + struct perf_evlist *evlsit, struct perf_tool *tool); void ordered_events__free(struct ordered_events *oe); static inline diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 23be146..c6dd89f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -95,7 +95,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out; session->repipe = repipe; - ordered_events__init(&session->ordered_events); machines__init(&session->machines); if (file) { @@ -126,7 +125,8 @@ struct perf_session *perf_session__new(struct perf_data_file *file, tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; - } + } else + ordered_events__init(&session->ordered_events, &session->machines, session->evlist, tool); return session; @@ -508,24 +508,19 @@ static perf_event__swap_op perf_event__swap_ops[] = { * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(struct perf_tool *tool, +static int process_finished_round(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; - struct perf_evlist *evlist = session->evlist; - struct machines *machines = &session->machines; - return ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__ROUND); + return ordered_events__flush(oe, OE_FLUSH__ROUND); } -int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_tool *tool, struct perf_sample *sample, - u64 file_offset) +int perf_session__queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset) { struct ordered_events *oe = &s->ordered_events; - struct perf_evlist *evlist = s->evlist; - struct machines *machines = &s->machines; u64 timestamp = sample->time; struct ordered_event *new; @@ -543,7 +538,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, new = ordered_events__new(oe, timestamp, event); if (!new) { - ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__HALF); + ordered_events__flush(oe, OE_FLUSH__HALF); new = ordered_events__new(oe, timestamp, event); } @@ -948,9 +943,9 @@ int machines__deliver_event(struct machines *machines, static s64 perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) { + struct perf_tool *tool = session->ordered_events.tool; int fd = perf_data_file__fd(session->file); int err; @@ -988,15 +983,15 @@ static s64 perf_session__process_user_event(struct perf_session *session, int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool) + struct perf_sample *sample) { struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->ordered_events.tool; events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, tool, 0); + return perf_session__process_user_event(session, event, 0); return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0); } @@ -1066,11 +1061,10 @@ out_parse_sample: } static s64 perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - u64 file_offset) + union perf_event *event, u64 file_offset) { struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->ordered_events.tool; struct perf_sample sample; int ret; @@ -1083,7 +1077,7 @@ static s64 perf_session__process_event(struct perf_session *session, events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, tool, file_offset); + return perf_session__process_user_event(session, event, file_offset); /* * For all kernel events we get the sample data @@ -1093,8 +1087,7 @@ static s64 perf_session__process_event(struct perf_session *session, return ret; if (tool->ordered_events) { - ret = perf_session_queue_event(session, event, tool, &sample, - file_offset); + ret = perf_session__queue_event(session, event, &sample, file_offset); if (ret != -ETIME) return ret; } @@ -1173,12 +1166,10 @@ static void perf_tool__warn_about_errors(const struct perf_tool *tool, volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *session, - struct perf_tool *tool) +static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; - struct perf_evlist *evlist = session->evlist; - struct machines *machines = &session->machines; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; @@ -1242,7 +1233,7 @@ more: } } - if ((skip = perf_session__process_event(session, event, tool, head)) < 0) { + if ((skip = perf_session__process_event(session, event, head)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", head, event->header.size, event->header.type); err = -EINVAL; @@ -1258,7 +1249,7 @@ more: goto more; done: /* do the final flush for ordered samples */ - err = ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: free(buf); perf_tool__warn_about_errors(tool, &session->evlist->stats); @@ -1308,11 +1299,10 @@ fetch_mmaped_event(struct perf_session *session, static int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, - u64 file_size, struct perf_tool *tool) + u64 file_size) { struct ordered_events *oe = &session->ordered_events; - struct perf_evlist *evlist = session->evlist; - struct machines *machines = &session->machines; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; @@ -1381,8 +1371,7 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, tool, file_pos)) - < 0) { + (skip = perf_session__process_event(session, event, file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1406,7 +1395,7 @@ more: out: /* do the final flush for ordered samples */ - err = ordered_events__flush(oe, machines, evlist, tool, OE_FLUSH__FINAL); + err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: ui_progress__finish(); perf_tool__warn_about_errors(tool, &session->evlist->stats); @@ -1415,8 +1404,7 @@ out_err: return err; } -int perf_session__process_events(struct perf_session *session, - struct perf_tool *tool) +int perf_session__process_events(struct perf_session *session) { u64 size = perf_data_file__size(session->file); int err; @@ -1427,10 +1415,9 @@ int perf_session__process_events(struct perf_session *session, if (!perf_data_file__is_pipe(session->file)) err = __perf_session__process_events(session, session->header.data_offset, - session->header.data_size, - size, tool); + session->header.data_size, size); else - err = __perf_session__process_pipe_events(session, tool); + err = __perf_session__process_pipe_events(session); return err; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index c08fa6b..06e0777 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -48,12 +48,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, union perf_event **event_ptr, struct perf_sample *sample); -int perf_session__process_events(struct perf_session *session, - struct perf_tool *tool); +int perf_session__process_events(struct perf_session *session); -int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_tool *tool, struct perf_sample *sample, - u64 file_offset); +int perf_session__queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset); void perf_tool__fill_defaults(struct perf_tool *tool); @@ -126,8 +124,7 @@ extern volatile int session_done; int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool); + struct perf_sample *sample); int perf_event__process_id_index(struct perf_tool *tool, union perf_event *event, -- cgit v1.1 From d10eb1eb76a86266354ecab6e42c1606e3b8bc4c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Mar 2015 12:20:38 -0300 Subject: perf ordered_events: Allow tools to specify a deliver method So that we can simplify the deliver method to pass just: (ordered_events, ordered_event, sample); Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-j0s4bpxs5qza5tnkvjwom9rw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 7 ++++--- tools/perf/util/ordered-events.h | 11 ++++++++++- tools/perf/util/session.c | 30 +++++++++++++++++++++++------- tools/perf/util/session.h | 6 ------ 4 files changed, 37 insertions(+), 17 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index bad46ce..0d8cea9 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -181,8 +181,7 @@ static int __ordered_events__flush(struct ordered_events *oe) if (ret) pr_err("Can't parse sample, err = %d\n", ret); else { - ret = machines__deliver_event(oe->machines, oe->evlist, iter->event, - &sample, oe->tool, iter->file_offset); + ret = oe->deliver(oe, iter, &sample); if (ret) return ret; } @@ -264,7 +263,8 @@ int ordered_events__flush(struct ordered_events *oe, enum oe_flush how) } void ordered_events__init(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlist, struct perf_tool *tool) + struct perf_evlist *evlist, struct perf_tool *tool, + ordered_events__deliver_t deliver) { INIT_LIST_HEAD(&oe->events); INIT_LIST_HEAD(&oe->cache); @@ -274,6 +274,7 @@ void ordered_events__init(struct ordered_events *oe, struct machines *machines, oe->evlist = evlist; oe->machines = machines; oe->tool = tool; + oe->deliver = deliver; } void ordered_events__free(struct ordered_events *oe) diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index ef7d73e..c6cf0ba 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -5,6 +5,7 @@ struct perf_tool; struct perf_evlist; +struct perf_sample; struct machines; struct ordered_event { @@ -21,6 +22,12 @@ enum oe_flush { OE_FLUSH__HALF, }; +struct ordered_events; + +typedef int (*ordered_events__deliver_t)(struct ordered_events *oe, + struct ordered_event *event, + struct perf_sample *sample); + struct ordered_events { u64 last_flush; u64 next_flush; @@ -35,6 +42,7 @@ struct ordered_events { struct machines *machines; struct perf_evlist *evlist; struct perf_tool *tool; + ordered_events__deliver_t deliver; int buffer_idx; unsigned int nr_events; enum oe_flush last_flush_type; @@ -46,7 +54,8 @@ struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timesta void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); void ordered_events__init(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlsit, struct perf_tool *tool); + struct perf_evlist *evlsit, struct perf_tool *tool, + ordered_events__deliver_t deliver); void ordered_events__free(struct ordered_events *oe); static inline diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c6dd89f..e2f318a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -16,6 +16,12 @@ #include "perf_regs.h" #include "asm/bug.h" +static int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset); + static int perf_session__open(struct perf_session *session) { struct perf_data_file *file = session->file; @@ -86,6 +92,14 @@ static void perf_session__set_comm_exec(struct perf_session *session) machines__set_comm_exec(&session->machines, comm_exec); } +static int ordered_events__deliver_event(struct ordered_events *oe, + struct ordered_event *event, + struct perf_sample *sample) +{ + return machines__deliver_event(oe->machines, oe->evlist, event->event, + sample, oe->tool, event->file_offset); +} + struct perf_session *perf_session__new(struct perf_data_file *file, bool repipe, struct perf_tool *tool) { @@ -125,8 +139,10 @@ struct perf_session *perf_session__new(struct perf_data_file *file, tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; - } else - ordered_events__init(&session->ordered_events, &session->machines, session->evlist, tool); + } else { + ordered_events__init(&session->ordered_events, &session->machines, + session->evlist, tool, ordered_events__deliver_event); + } return session; @@ -888,11 +904,11 @@ static int &sample->read.one, machine); } -int machines__deliver_event(struct machines *machines, - struct perf_evlist *evlist, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, u64 file_offset) +static int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; struct machine *machine; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 06e0777..1310998 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -55,12 +55,6 @@ int perf_session__queue_event(struct perf_session *s, union perf_event *event, void perf_tool__fill_defaults(struct perf_tool *tool); -int machines__deliver_event(struct machines *machines, - struct perf_evlist *evlist, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, u64 file_offset); - int perf_session__resolve_callchain(struct perf_session *session, struct perf_evsel *evsel, struct thread *thread, -- cgit v1.1 From d704ebdae4aaeec89180dcfd0ca74e5bba318853 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Mar 2015 12:37:54 -0300 Subject: perf tools: tool->finished_round() doesn't need perf_session It is all about flushing the ordered queue or piping it thru, no need for a perf_session pointer. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-g47fx3ys0t9271cp0dcabjc7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 24 +++++++++++++++--------- tools/perf/util/tool.h | 8 ++++++-- 2 files changed, 21 insertions(+), 11 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e2f318a..703a370 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -225,10 +225,17 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused, return 0; } +static int process_build_id_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) + struct ordered_events *oe __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -236,7 +243,7 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, static int process_finished_round(struct perf_tool *tool, union perf_event *event, - struct perf_session *session); + struct ordered_events *oe); static int process_id_index_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, @@ -274,7 +281,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) - tool->build_id = process_finished_round_stub; + tool->build_id = process_build_id_stub; if (tool->finished_round == NULL) { if (tool->ordered_events) tool->finished_round = process_finished_round; @@ -526,10 +533,8 @@ static perf_event__swap_op perf_event__swap_ops[] = { */ static int process_finished_round(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_session *session) + struct ordered_events *oe) { - struct ordered_events *oe = &session->ordered_events; - return ordered_events__flush(oe, OE_FLUSH__ROUND); } @@ -961,7 +966,8 @@ static s64 perf_session__process_user_event(struct perf_session *session, union perf_event *event, u64 file_offset) { - struct perf_tool *tool = session->ordered_events.tool; + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = oe->tool; int fd = perf_data_file__fd(session->file); int err; @@ -989,7 +995,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, session); + return tool->finished_round(tool, event, oe); case PERF_RECORD_ID_INDEX: return tool->id_index(tool, event, session); default: diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index bb2708b..51d9e56 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -10,6 +10,7 @@ struct perf_evsel; struct perf_sample; struct perf_tool; struct machine; +struct ordered_events; typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -25,6 +26,9 @@ typedef int (*event_attr_op)(struct perf_tool *tool, typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, + struct ordered_events *oe); + struct perf_tool { event_sample sample, read; @@ -38,8 +42,8 @@ struct perf_tool { unthrottle; event_attr_op attr; event_op2 tracing_data; - event_op2 finished_round, - build_id, + event_oe finished_round; + event_op2 build_id, id_index; bool ordered_events; bool ordering_requires_timestamps; -- cgit v1.1 From 01fbc1fee926888f7c256ada95fa5fa3b06cba94 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 3 Mar 2015 16:29:28 +0100 Subject: perf tools: Remove superfluous thread->comm_set setting It is set by calling thread__set_comm right before the removed line. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1425396581-17716-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index a5dbba9..1c8fbc9 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -206,7 +206,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) err = thread__set_comm(thread, comm, timestamp); if (err) return err; - thread->comm_set = true; } thread->ppid = parent->tid; -- cgit v1.1 From 4a6b362f36e68618ee4d3cdb361d05a5e80af023 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Mar 2015 13:02:24 -0300 Subject: perf ordered_events: Adopt queue() method From perf_session, will be used in 'trace'. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-mfihndzaumx44h6y37ng2irb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 34 ++++++++++++++++++++++++++++++++-- tools/perf/util/ordered-events.h | 4 ++-- tools/perf/util/session.c | 28 +--------------------------- 3 files changed, 35 insertions(+), 31 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 0d8cea9..6002fa3 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -131,8 +131,8 @@ static struct ordered_event *alloc_event(struct ordered_events *oe, return new; } -struct ordered_event * -ordered_events__new(struct ordered_events *oe, u64 timestamp, +static struct ordered_event * +ordered_events__new_event(struct ordered_events *oe, u64 timestamp, union perf_event *event) { struct ordered_event *new; @@ -153,6 +153,36 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve free_dup_event(oe, event->event); } +int ordered_events__queue(struct ordered_events *oe, union perf_event *event, + struct perf_sample *sample, u64 file_offset) +{ + u64 timestamp = sample->time; + struct ordered_event *oevent; + + if (!timestamp || timestamp == ~0ULL) + return -ETIME; + + if (timestamp < oe->last_flush) { + pr_oe_time(timestamp, "out of order event\n"); + pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", + oe->last_flush_type); + + oe->evlist->stats.nr_unordered_events++; + } + + oevent = ordered_events__new_event(oe, timestamp, event); + if (!oevent) { + ordered_events__flush(oe, OE_FLUSH__HALF); + oevent = ordered_events__new_event(oe, timestamp, event); + } + + if (!oevent) + return -ENOMEM; + + oevent->file_offset = file_offset; + return 0; +} + static int __ordered_events__flush(struct ordered_events *oe) { struct list_head *head = &oe->events; diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index c6cf0ba..173e13f 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -49,8 +49,8 @@ struct ordered_events { bool copy_on_queue; }; -struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, - union perf_event *event); +int ordered_events__queue(struct ordered_events *oe, union perf_event *event, + struct perf_sample *sample, u64 file_offset); void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); void ordered_events__init(struct ordered_events *oe, struct machines *machines, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 703a370..adf0740 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -541,33 +541,7 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused, int perf_session__queue_event(struct perf_session *s, union perf_event *event, struct perf_sample *sample, u64 file_offset) { - struct ordered_events *oe = &s->ordered_events; - - u64 timestamp = sample->time; - struct ordered_event *new; - - if (!timestamp || timestamp == ~0ULL) - return -ETIME; - - if (timestamp < oe->last_flush) { - pr_oe_time(timestamp, "out of order event\n"); - pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", - oe->last_flush_type); - - s->evlist->stats.nr_unordered_events++; - } - - new = ordered_events__new(oe, timestamp, event); - if (!new) { - ordered_events__flush(oe, OE_FLUSH__HALF); - new = ordered_events__new(oe, timestamp, event); - } - - if (!new) - return -ENOMEM; - - new->file_offset = file_offset; - return 0; + return ordered_events__queue(&s->ordered_events, event, sample, file_offset); } static void callchain__lbr_callstack_printf(struct perf_sample *sample) -- cgit v1.1 From 9b118acae310f57baee770b5db402500d8695e50 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2015 16:31:20 +0900 Subject: perf probe: Fix to handle aliased symbols in glibc Fix perf probe to handle aliased symbols correctly in glibc. In the glibc, several symbols are defined as an alias of __libc_XXX, e.g. malloc is an alias of __libc_malloc. In such cases, dwarf has no subroutine instances of the alias functions (e.g. no "malloc" instance), but the map has that symbol and its address. Thus, if we search the alieased symbol in debuginfo, we always fail to find it, but it is in the map. To solve this problem, this fails back to address-based alternative search, which searches the symbol in the map, translates its address to alternative (correct) function name by using debuginfo, and retry to find the alternative function point from debuginfo. This adds fail-back process to --vars, --lines and --add options. So, now you can use those on malloc@libc :) Without this patch; ----- # ./perf probe -x /usr/lib64/libc-2.17.so -V malloc Failed to find the address of malloc Error: Failed to show vars. # ./perf probe -x /usr/lib64/libc-2.17.so -a "malloc bytes" Probe point 'malloc' not found in debuginfo. Error: Failed to add events. ----- With this patch; ----- # ./perf probe -x /usr/lib64/libc-2.17.so -V malloc Available variables at malloc @<__libc_malloc+0> size_t bytes # ./perf probe -x /usr/lib64/libc-2.17.so -a "malloc bytes" Added new event: probe_libc:malloc (on malloc in /usr/lib64/libc-2.17.so with bytes) You can now use it in all perf tools, such as: perf record -e probe_libc:malloc -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150306073120.6904.13779.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 140 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 124 insertions(+), 16 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 1c570c2..b8f4578 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -178,6 +178,25 @@ static struct map *kernel_get_module_map(const char *module) return NULL; } +static struct map *get_target_map(const char *target, bool user) +{ + /* Init maps of given executable or kernel */ + if (user) + return dso__new_map(target); + else + return kernel_get_module_map(target); +} + +static void put_target_map(struct map *map, bool user) +{ + if (map && user) { + /* Only the user map needs to be released */ + dso__delete(map->dso); + map__delete(map); + } +} + + static struct dso *kernel_get_module_dso(const char *module) { struct dso *dso; @@ -249,6 +268,13 @@ out: return ret; } +static void clear_perf_probe_point(struct perf_probe_point *pp) +{ + free(pp->file); + free(pp->function); + free(pp->lazy_line); +} + static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) { int i; @@ -258,6 +284,74 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) } #ifdef HAVE_DWARF_SUPPORT +/* + * Some binaries like glibc have special symbols which are on the symbol + * table, but not in the debuginfo. If we can find the address of the + * symbol from map, we can translate the address back to the probe point. + */ +static int find_alternative_probe_point(struct debuginfo *dinfo, + struct perf_probe_point *pp, + struct perf_probe_point *result, + const char *target, bool uprobes) +{ + struct map *map = NULL; + struct symbol *sym; + u64 address = 0; + int ret = -ENOENT; + + /* This can work only for function-name based one */ + if (!pp->function || pp->file) + return -ENOTSUP; + + map = get_target_map(target, uprobes); + if (!map) + return -EINVAL; + + /* Find the address of given function */ + map__for_each_symbol_by_name(map, pp->function, sym) { + if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) { + address = sym->start; + break; + } + } + if (!address) { + ret = -ENOENT; + goto out; + } + pr_debug("Symbol %s address found : %lx\n", pp->function, address); + + ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, + result); + if (ret <= 0) + ret = (!ret) ? -ENOENT : ret; + else { + result->offset += pp->offset; + result->line += pp->line; + ret = 0; + } + +out: + put_target_map(map, uprobes); + return ret; + +} + +static int get_alternative_probe_event(struct debuginfo *dinfo, + struct perf_probe_event *pev, + struct perf_probe_point *tmp, + const char *target) +{ + int ret; + + memcpy(tmp, &pev->point, sizeof(*tmp)); + memset(&pev->point, 0, sizeof(pev->point)); + ret = find_alternative_probe_point(dinfo, tmp, &pev->point, + target, pev->uprobes); + if (ret < 0) + memcpy(&pev->point, tmp, sizeof(*tmp)); + + return ret; +} /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module, bool silent) @@ -466,6 +560,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, int max_tevs, const char *target) { bool need_dwarf = perf_probe_event_need_dwarf(pev); + struct perf_probe_point tmp; struct debuginfo *dinfo; int ntevs, ret = 0; @@ -482,6 +577,20 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, /* Searching trace events corresponding to a probe event */ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs); + if (ntevs == 0) { /* Not found, retry with an alternative */ + ret = get_alternative_probe_event(dinfo, pev, &tmp, target); + if (!ret) { + ntevs = debuginfo__find_trace_events(dinfo, pev, + tevs, max_tevs); + /* + * Write back to the original probe_event for + * setting appropriate (user given) event name + */ + clear_perf_probe_point(&pev->point); + memcpy(&pev->point, &tmp, sizeof(tmp)); + } + } + debuginfo__delete(dinfo); if (ntevs > 0) { /* Succeeded to find trace events */ @@ -719,12 +828,13 @@ int show_line_range(struct line_range *lr, const char *module, bool user) static int show_available_vars_at(struct debuginfo *dinfo, struct perf_probe_event *pev, int max_vls, struct strfilter *_filter, - bool externs) + bool externs, const char *target) { char *buf; int ret, i, nvars; struct str_node *node; struct variable_list *vls = NULL, *vl; + struct perf_probe_point tmp; const char *var; buf = synthesize_perf_probe_point(&pev->point); @@ -734,6 +844,15 @@ static int show_available_vars_at(struct debuginfo *dinfo, ret = debuginfo__find_available_vars_at(dinfo, pev, &vls, max_vls, externs); + if (!ret) { /* Not found, retry with an alternative */ + ret = get_alternative_probe_event(dinfo, pev, &tmp, target); + if (!ret) { + ret = debuginfo__find_available_vars_at(dinfo, pev, + &vls, max_vls, externs); + /* Release the old probe_point */ + clear_perf_probe_point(&tmp); + } + } if (ret <= 0) { if (ret == 0 || ret == -ENOENT) { pr_err("Failed to find the address of %s\n", buf); @@ -796,7 +915,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, for (i = 0; i < npevs && ret >= 0; i++) ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter, - externs); + externs, module); debuginfo__delete(dinfo); out: @@ -1742,15 +1861,12 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, void clear_perf_probe_event(struct perf_probe_event *pev) { - struct perf_probe_point *pp = &pev->point; struct perf_probe_arg_field *field, *next; int i; free(pev->event); free(pev->group); - free(pp->file); - free(pp->function); - free(pp->lazy_line); + clear_perf_probe_point(&pev->point); for (i = 0; i < pev->nargs; i++) { free(pev->args[i].name); @@ -2367,11 +2483,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int num_matched_functions; int ret, i; - /* Init maps of given executable or kernel */ - if (pev->uprobes) - map = dso__new_map(target); - else - map = kernel_get_module_map(target); + map = get_target_map(target, pev->uprobes); if (!map) { ret = -EINVAL; goto out; @@ -2464,11 +2576,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } out: - if (map && pev->uprobes) { - /* Only when using uprobe(exec) map needs to be released */ - dso__delete(map->dso); - map__delete(map); - } + put_target_map(map, pev->uprobes); return ret; nomem_out: -- cgit v1.1 From 811dd2ae7cd670fefbb3b220b529bb9876edde70 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2015 16:31:22 +0900 Subject: perf probe: Fix --line to handle aliased symbols in glibc Fix perf probe --line to handle aliased symbols correctly in glibc. This makes line_range search failing back to address-based alternative search as same as --add and --vars. Without this patch; ----- # ./perf probe -x /usr/lib64/libc-2.17.so -L malloc Specified source line is not found. Error: Failed to show lines. ----- With this patch; ----- # ./perf probe -x /usr/lib64/libc-2.17.so -L malloc <__libc_malloc@/usr/src/debug/glibc-2.17-c758a686/malloc/malloc.c:0> 0 __libc_malloc(size_t bytes) 1 { mstate ar_ptr; void *victim; __malloc_ptr_t (*hook) (size_t, const __malloc_ptr_t) 6 = force_reg (__malloc_hook); 7 if (__builtin_expect (hook != NULL, 0)) 8 return (*hook)(bytes, RETURN_ADDRESS (0)); 10 arena_lookup(ar_ptr); 12 arena_lock(ar_ptr, bytes); ----- Note that this actually shows __libc_malloc, since it is the real instance of malloc. User can use both __libc_malloc and malloc for --line. Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150306073122.6904.18540.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b8f4578..4cfd121 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -353,6 +353,31 @@ static int get_alternative_probe_event(struct debuginfo *dinfo, return ret; } +static int get_alternative_line_range(struct debuginfo *dinfo, + struct line_range *lr, + const char *target, bool user) +{ + struct perf_probe_point pp = { 0 }, result = { 0 }; + int ret, len = 0; + + pp.function = lr->function; + pp.file = lr->file; + pp.line = lr->start; + if (lr->end != INT_MAX) + len = lr->end - lr->start; + ret = find_alternative_probe_point(dinfo, &pp, &result, + target, user); + if (!ret) { + lr->function = result.function; + lr->file = result.file; + lr->start = result.line; + if (lr->end != INT_MAX) + lr->end = lr->start + len; + clear_perf_probe_point(&pp); + } + return ret; +} + /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module, bool silent) { @@ -734,7 +759,8 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) * Show line-range always requires debuginfo to find source file and * line number. */ -static int __show_line_range(struct line_range *lr, const char *module) +static int __show_line_range(struct line_range *lr, const char *module, + bool user) { int l = 1; struct int_node *ln; @@ -750,6 +776,11 @@ static int __show_line_range(struct line_range *lr, const char *module) return -ENOENT; ret = debuginfo__find_line_range(dinfo, lr); + if (!ret) { /* Not found, retry with an alternative */ + ret = get_alternative_line_range(dinfo, lr, module, user); + if (!ret) + ret = debuginfo__find_line_range(dinfo, lr); + } debuginfo__delete(dinfo); if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); @@ -819,7 +850,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user) ret = init_symbol_maps(user); if (ret < 0) return ret; - ret = __show_line_range(lr, module); + ret = __show_line_range(lr, module, user); exit_symbol_maps(); return ret; -- cgit v1.1 From 0687eba7872d7dbe01b074c54359315e97502360 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2015 16:31:25 +0900 Subject: Revert "perf probe: Fix to fall back to find probe point in symbols" This reverts commit 906451b98b67 ("perf probe: Fix to fall back to find probe point in symbols"). Since 'perf probe' now retries with the address of given symbol searched from map before this path, this fall back routine isn't needed anymore. Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150306073124.6904.1751.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4cfd121..c379ea0 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -630,11 +630,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } if (ntevs == 0) { /* No error but failed to find probe point. */ - pr_warning("Probe point '%s' not found in debuginfo.\n", + pr_warning("Probe point '%s' not found.\n", synthesize_perf_probe_point(&pev->point)); - if (need_dwarf) - return -ENOENT; - return 0; + return -ENOENT; } /* Error path : ntevs < 0 */ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); -- cgit v1.1 From 680d926a8cb08dd9cf173e2bb93d4a4477771949 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 6 Mar 2015 16:31:27 +0900 Subject: perf symbols: Allow symbol alias when loading map for symbol name When perf probe tries to add a probe in a binary using symbol name, it sometimes failed since some symbols were discard during loading dso. When it resolves an address to symbol, it'd be better to have just one symbol at given address. But for finding address from symbol, it'd be better to keep all names (including aliases). So allow tools to state that they want to allow aliases via symbol_conf.allow_aliases. Signed-off-by: Namhyung Kim Acked-by: Masami Hiramatsu Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150306073127.6904.3232.stgit@localhost.localdomain [ Original patch passwd allow_alias to many functions, use symbol_conf.allow_aliases instead ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 1 + tools/perf/util/symbol-elf.c | 3 ++- tools/perf/util/symbol.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c379ea0..9feba0e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -80,6 +80,7 @@ static int init_symbol_maps(bool user_only) int ret; symbol_conf.sort_by_name = true; + symbol_conf.allow_aliases = true; ret = symbol__init(NULL); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index ada1676..62742e46 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1048,7 +1048,8 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_duplicate(&dso->symbols[map->type]); + if (!symbol_conf.allow_aliases) + symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); if (kmap) { /* diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 1650dcb..efdaaa5 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -87,6 +87,7 @@ struct symbol_conf { ignore_vmlinux_buildid, show_kernel_path, use_modules, + allow_aliases, sort_by_name, show_nr_samples, show_total_period, -- cgit v1.1 From e578da3b2009da2a9ae2d25fd0f78c7b76ca5e56 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 6 Mar 2015 16:31:29 +0900 Subject: perf probe: Allow weak symbols to be probed It currently prevents adding probes in weak symbols. But there're cases that given name is an only weak symbol so that we cannot add probe. $ perf probe -x /usr/lib/libc.so.6 -a calloc Failed to find symbol calloc in /usr/lib/libc-2.21.so Error: Failed to add events. $ nm /usr/lib/libc.so.6 | grep calloc 000000000007b1f0 t __calloc 000000000007b1f0 T __libc_calloc 000000000007b1f0 W calloc This change will result in duplicate probes when strong and weak symbols co-exist in a binary. But I think it's not a big problem since probes at the weak symbol will never be hit anyway. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150306073129.6904.41078.stgit@localhost.localdomain Signed-off-by: Masami Hiramatsu Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9feba0e..8af8e7f 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -310,10 +310,8 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, /* Find the address of given function */ map__for_each_symbol_by_name(map, pp->function, sym) { - if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) { - address = sym->start; - break; - } + address = sym->start; + break; } if (!address) { ret = -ENOENT; @@ -2485,8 +2483,7 @@ static int find_probe_functions(struct map *map, char *name) struct symbol *sym; map__for_each_symbol_by_name(map, name, sym) { - if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) - found++; + found++; } return found; @@ -2846,8 +2843,7 @@ static struct strfilter *available_func_filter; static int filter_available_functions(struct map *map __maybe_unused, struct symbol *sym) { - if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && - strfilter__compare(available_func_filter, sym->name)) + if (strfilter__compare(available_func_filter, sym->name)) return 0; return 1; } -- cgit v1.1 From a78604defffbc1da1497a8c8b48275b723eb5946 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Wed, 4 Mar 2015 18:01:42 +0800 Subject: perf probe: Fix possible double free on error A double free occurred when get source file path failed. If lr->path failed to assign a new value, it will be freed as the old path and then be freed again during line_range__clear(), and causes this: $ perf probe -L do_execve -k vmlinux *** Error in `/usr/bin/perf': double free or corruption (fasttop): 0x0000000000a9ac50 *** ======= Backtrace: ========= ../lib64/libc.so.6(+0x6eeef)[0x7ffff5e44eef] ../lib64/libc.so.6(+0x78cae)[0x7ffff5e4ecae] ../lib64/libc.so.6(+0x79987)[0x7ffff5e4f987] ../bin/perf[0x4ab41f] ... This patch fix this problem. Signed-off-by: He Kuang Acked-by: Masami Hiramatsu Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1425463302-1687-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8af8e7f..e2bf620 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -790,7 +790,11 @@ static int __show_line_range(struct line_range *lr, const char *module, /* Convert source file path */ tmp = lr->path; ret = get_real_path(tmp, lr->comp_dir, &lr->path); - free(tmp); /* Free old path */ + + /* Free old path when new path is assigned */ + if (tmp != lr->path) + free(tmp); + if (ret < 0) { pr_warning("Failed to find source file path.\n"); return ret; -- cgit v1.1 From a8cd1f4393032cd87e98803346865cdbceb15ad3 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Wed, 11 Mar 2015 20:36:03 +0800 Subject: perf hists browser: Fix UI bug after zoom into thread/dso/symbol When zoom into thread/dso/symbol, the fold/unfold stat is cleared in hists__filter_by_thread/dso/symbol(), but h->nr_rows is not cleared. So if we toggle fold stat on the unfold entires, nr_entries got a wrong value. This bug can be reproduced as follows: $ perf record -g -e syscalls:sys_enter_open ls $ perf report Children Self Command Shared Object Symbol ================================================================ + 50.00% 0.00% ls ld64.so [.] _dl_get_ready_to_run - 50.00% 0.00% ls ld64.so [.] _dl_load_shared_library _dl_load_shared_library <= [Zoom into thread/dso] _dl_get_ready_to_run _start ... In the new thread hists, all entries reset to fold, if we unfold the same entry as we previously unfolded, nr_entries got wrong value, and we can't move down cursor to bottom row. Thread: ls Children Self Command Shared Object Symbol ================================================================ + 50.00% 0.00% ls ld64.so [.] _dl_get_ready_to_run - 50.00% 0.00% ls ld64.so [.] _dl_load_shared_library _dl_load_shared_library _dl_get_ready_to_run <= [cursor may stop here, can't move down] _start ... This patch clear h->nr_rows to fix this bug. Signed-off-by: He Kuang Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1426077363-855-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 95f5ab7..d9a6d35 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1171,6 +1171,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h /* force fold unfiltered entry for simplicity */ h->ms.unfolded = false; h->row_offset = 0; + h->nr_rows = 0; hists->stats.nr_non_filtered_samples += h->stat.nr_events; -- cgit v1.1 From 6d4a48968bfb5c67002f253fbaeb5acd41d7897a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 11 Mar 2015 10:36:20 -0400 Subject: perf probe: Fix compiles due to declarations using perf_probe_point MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit perf fails to build with gcc "(GCC) 4.4.7 20120313 (Red Hat 4.4.7-4.0.9)" (a.k.a., RHEL6 / CentOS 6 / OL 6): cc1: warnings being treated as errors util/probe-event.c: In function ‘get_alternative_line_range’: util/probe-event.c:359: error: missing initializer util/probe-event.c:359: error: (near initialization for ‘pp.file’) util/probe-event.c:359: error: missing initializer util/probe-event.c:359: error: (near initialization for ‘result.function’) Fix by bringing in initializers to declaration. Signed-off-by: David Ahern Cc: Masami Hiramatsu Link: http://lkml.kernel.org/r/1426084580-60780-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e2bf620..f272a71 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -356,12 +356,14 @@ static int get_alternative_line_range(struct debuginfo *dinfo, struct line_range *lr, const char *target, bool user) { - struct perf_probe_point pp = { 0 }, result = { 0 }; + struct perf_probe_point pp = { .function = lr->function, + .file = lr->file, + .line = lr->start }; + struct perf_probe_point result; int ret, len = 0; - pp.function = lr->function; - pp.file = lr->file; - pp.line = lr->start; + memset(&result, 0, sizeof(result)); + if (lr->end != INT_MAX) len = lr->end - lr->start; ret = find_alternative_probe_point(dinfo, &pp, &result, -- cgit v1.1 From 69364727be2f3dc71a046771965c3c9d5ccce699 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 20 Feb 2015 23:17:02 +0100 Subject: perf data: Add tracepoint events fields CTF conversion support Adding support to convert tracepoint event fields into CTF event fields. We parse each tracepoint event for CTF conversion and add tracepoint fields as regular CTF event fields, so they appear in babeltrace output like: $ babeltrace ./ctf-data/ ... [09:02:00.950703057] (+?.?????????) sched:sched_stat_runtime: { }, { perf_ip = ... SNIP ... common_type = 298, common_flags = 1, \ common_preempt_count = 0, common_pid = 31813, comm = "perf", pid = 31813, runtime = 458800, vruntime = 52059858071 } ... Signed-off-by: Sebastian Andrzej Siewior Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Frederic Weisbecker Cc: Jeremie Galarneau Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi Cc: Wang Nan Link: http://lkml.kernel.org/r/1424470628-5969-6-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data-convert-bt.c | 242 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 242 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 1afd381..c6d6226 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -126,6 +126,177 @@ FUNC_VALUE_SET(s64) FUNC_VALUE_SET(u64) __FUNC_VALUE_SET(u64_hex, u64) +static struct bt_ctf_field_type* +get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field) +{ + unsigned long flags = field->flags; + + if (flags & FIELD_IS_STRING) + return cw->data.string; + + if (!(flags & FIELD_IS_SIGNED)) { + /* unsigned long are mostly pointers */ + if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER) + return cw->data.u64_hex; + } + + if (flags & FIELD_IS_SIGNED) { + if (field->size == 8) + return cw->data.s64; + else + return cw->data.s32; + } + + if (field->size == 8) + return cw->data.u64; + else + return cw->data.u32; +} + +static int add_tracepoint_field_value(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct perf_sample *sample, + struct format_field *fmtf) +{ + struct bt_ctf_field_type *type; + struct bt_ctf_field *array_field; + struct bt_ctf_field *field; + const char *name = fmtf->name; + void *data = sample->raw_data; + unsigned long long value_int; + unsigned long flags = fmtf->flags; + unsigned int n_items; + unsigned int i; + unsigned int offset; + unsigned int len; + int ret; + + offset = fmtf->offset; + len = fmtf->size; + if (flags & FIELD_IS_STRING) + flags &= ~FIELD_IS_ARRAY; + + if (flags & FIELD_IS_DYNAMIC) { + unsigned long long tmp_val; + + tmp_val = pevent_read_number(fmtf->event->pevent, + data + offset, len); + offset = tmp_val; + len = offset >> 16; + offset &= 0xffff; + } + + if (flags & FIELD_IS_ARRAY) { + + type = bt_ctf_event_class_get_field_by_name( + event_class, name); + array_field = bt_ctf_field_create(type); + bt_ctf_field_type_put(type); + if (!array_field) { + pr_err("Failed to create array type %s\n", name); + return -1; + } + + len = fmtf->size / fmtf->arraylen; + n_items = fmtf->arraylen; + } else { + n_items = 1; + array_field = NULL; + } + + type = get_tracepoint_field_type(cw, fmtf); + + for (i = 0; i < n_items; i++) { + if (!(flags & FIELD_IS_STRING)) + value_int = pevent_read_number( + fmtf->event->pevent, + data + offset + i * len, len); + + if (flags & FIELD_IS_ARRAY) + field = bt_ctf_field_array_get_field(array_field, i); + else + field = bt_ctf_field_create(type); + + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + if (flags & FIELD_IS_STRING) + ret = bt_ctf_field_string_set_value(field, + data + offset + i * len); + else if (!(flags & FIELD_IS_SIGNED)) + ret = bt_ctf_field_unsigned_integer_set_value( + field, value_int); + else + ret = bt_ctf_field_signed_integer_set_value( + field, value_int); + if (ret) { + pr_err("failed to set file value %s\n", name); + goto err_put_field; + } + if (!(flags & FIELD_IS_ARRAY)) { + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) { + pr_err("failed to set payload %s\n", name); + goto err_put_field; + } + } + bt_ctf_field_put(field); + } + if (flags & FIELD_IS_ARRAY) { + ret = bt_ctf_event_set_payload(event, name, array_field); + if (ret) { + pr_err("Failed add payload array %s\n", name); + return -1; + } + bt_ctf_field_put(array_field); + } + return 0; + +err_put_field: + bt_ctf_field_put(field); + return -1; +} + +static int add_tracepoint_fields_values(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct format_field *fields, + struct perf_sample *sample) +{ + struct format_field *field; + int ret; + + for (field = fields; field; field = field->next) { + ret = add_tracepoint_field_value(cw, event_class, event, sample, + field); + if (ret) + return -1; + } + return 0; +} + +static int add_tracepoint_values(struct ctf_writer *cw, + struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + struct format_field *common_fields = evsel->tp_format->format.common_fields; + struct format_field *fields = evsel->tp_format->format.fields; + int ret; + + ret = add_tracepoint_fields_values(cw, event_class, event, + common_fields, sample); + if (!ret) + ret = add_tracepoint_fields_values(cw, event_class, event, + fields, sample); + + return ret; +} + static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, struct perf_evsel *evsel, @@ -246,11 +417,76 @@ static int process_sample_event(struct perf_tool *tool, if (ret) return -1; + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + ret = add_tracepoint_values(cw, event_class, event, + evsel, sample); + if (ret) + return -1; + } + bt_ctf_stream_append_event(cw->stream, event); bt_ctf_event_put(event); return 0; } +static int add_tracepoint_fields_types(struct ctf_writer *cw, + struct format_field *fields, + struct bt_ctf_event_class *event_class) +{ + struct format_field *field; + int ret; + + for (field = fields; field; field = field->next) { + struct bt_ctf_field_type *type; + unsigned long flags = field->flags; + + pr2(" field '%s'\n", field->name); + + type = get_tracepoint_field_type(cw, field); + if (!type) + return -1; + + /* + * A string is an array of chars. For this we use the string + * type and don't care that it is an array. What we don't + * support is an array of strings. + */ + if (flags & FIELD_IS_STRING) + flags &= ~FIELD_IS_ARRAY; + + if (flags & FIELD_IS_ARRAY) + type = bt_ctf_field_type_array_create(type, field->arraylen); + + ret = bt_ctf_event_class_add_field(event_class, type, + field->name); + + if (flags & FIELD_IS_ARRAY) + bt_ctf_field_type_put(type); + + if (ret) { + pr_err("Failed to add field '%s\n", field->name); + return -1; + } + } + + return 0; +} + +static int add_tracepoint_types(struct ctf_writer *cw, + struct perf_evsel *evsel, + struct bt_ctf_event_class *class) +{ + struct format_field *common_fields = evsel->tp_format->format.common_fields; + struct format_field *fields = evsel->tp_format->format.fields; + int ret; + + ret = add_tracepoint_fields_types(cw, common_fields, class); + if (!ret) + ret = add_tracepoint_fields_types(cw, fields, class); + + return ret; +} + static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, struct bt_ctf_event_class *event_class) { @@ -328,6 +564,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) if (ret) goto err; + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + ret = add_tracepoint_types(cw, evsel, event_class); + if (ret) + goto err; + } + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class); if (ret) { pr("Failed to add event class into stream.\n"); -- cgit v1.1 From 4c47f4fcd60a2f4153d6fe0c31650fbec112a1bd Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 Mar 2015 17:18:58 -0300 Subject: perf hists: Remove hist_entry->used, not used anymore Since hist_entry__delete() nowadays doesn't actually frees anything that may be in use by the annotation code. Eventually we will solve this for good by reference counting struct symbol. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-uldtgljymtrkns0knpiso5op@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 8 +------- tools/perf/util/sort.h | 1 - 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index d9a6d35..cc22b91 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -263,15 +263,9 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) while (next) { n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - /* - * We may be annotating this, for instance, so keep it here in - * case some it gets new samples, we'll eventually free it when - * the user stops browsing and it agains gets fully decayed. - */ if (((zap_user && n->level == '.') || (zap_kernel && n->level != '.') || - hists__decay_entry(hists, n)) && - !n->used) { + hists__decay_entry(hists, n))) { hists__delete_entry(hists, n); } } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index c03e4ff..9c01b83 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -102,7 +102,6 @@ struct hist_entry { bool init_have_children; char level; - bool used; u8 filtered; char *srcline; struct symbol *parent; -- cgit v1.1 From d5dbc518cd8fbc7cf54b91d5b506eb4d67e4047d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 Mar 2015 18:27:28 -0300 Subject: perf hists browser: Allow annotating entries in callchains Instead of annotating just the top level hist_entry, allow instead annotating a map_symbol, i.e. the top level hist_entry or one of the callchains for which there were samples. Suggested-by: Stephane Eranian Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/n/tip-k1zxj5564je9jei4yd15ouwn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index e988c9f..9f31b89 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -303,6 +303,9 @@ struct hist_browser_timer { #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" +int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, + struct hist_browser_timer *hbt); + int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -321,6 +324,12 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, { return 0; } +static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused) +{ + return 0; +} static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct perf_evsel *evsel __maybe_unused, -- cgit v1.1 From 303cb89a6d708da9c24f6f3390ff68a2bd822a13 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 13 Mar 2015 15:02:56 +0800 Subject: perf callchain: Separate eh/debug frame offset cache. Commit f1f13af99a90 ("perf callchain: Cache eh/debug frame offset for dwarf unwind") introduces a cache for .debug_frame and .eh_frame_hdr. Unfortunately, it makes them share a same cache (dso->frame_offset). Which causes unwind failure on ARM: $ perf test unwind Test dwarf unwind: FAILED! The reason is that, if a dso has '.debug_frame' but doesn't have '.eh_frame_hdr' (like ARM), dso->frame_offset will be filled by offset of '.debug_frame' during the first time calling of find_proc_info() -> read_unwind_spec_debug_frame(), and be regarded to '.eh_frame_hdr' when the second time calling of find_proc_info() -> read_unwind_spec_eh_frame(), since '.eh_frame_hdr' is checked prior to '.debug_frame'. This patch solves the problem by creating two cache fields for '.eh_frame_hdr' and '.debug_frame'. Signed-off-by: Wang Nan Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Li Zefan Link: http://lkml.kernel.org/r/55028BA0.1030701@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.h | 3 ++- tools/perf/util/unwind-libunwind.c | 8 ++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ced9284..408c65f 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -139,7 +139,8 @@ struct dso { u32 status_seen; size_t file_size; struct list_head open_entry; - u64 frame_offset; + u64 debug_frame_offset; + u64 eh_frame_hdr_offset; } data; union { /* Tool specific area */ diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e3c40a5..7b09a44 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -266,7 +266,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, u64 *fde_count) { int ret = -EINVAL, fd; - u64 offset = dso->data.frame_offset; + u64 offset = dso->data.eh_frame_hdr_offset; if (offset == 0) { fd = dso__data_fd(dso, machine); @@ -275,7 +275,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, /* Check the .eh_frame section for unwinding info */ offset = elf_section_offset(fd, ".eh_frame_hdr"); - dso->data.frame_offset = offset; + dso->data.eh_frame_hdr_offset = offset; } if (offset) @@ -291,7 +291,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, struct machine *machine, u64 *offset) { int fd; - u64 ofs = dso->data.frame_offset; + u64 ofs = dso->data.debug_frame_offset; if (ofs == 0) { fd = dso__data_fd(dso, machine); @@ -300,7 +300,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, /* Check the .debug_frame section for unwinding info */ ofs = elf_section_offset(fd, ".debug_frame"); - dso->data.frame_offset = ofs; + dso->data.debug_frame_offset = ofs; } *offset = ofs; -- cgit v1.1 From 0c8c20779c5d56b93b8cb4cd30ba129a927ab437 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 13 Mar 2015 12:51:54 +0000 Subject: perf report: Don't allow empty argument for '-t'. Without this patch, perf report cause segfault if pass "" as '-t': $ perf report -t "" # To display the perf.data header info, please use --header/--header-only options. # # Samples: 37 of event 'syscalls:sys_enter_write' # Event count (approx.): 37 # # Children SelfCommand Shared Object Symbol Segmentation fault Since -t is used to add field-separator for generate table, -t "" is actually meanless. This patch defines a new OPT_STRING_NOEMPTY() option generator to ensure user never pass empty string to that option. Signed-off-by: Wang Nan Acked-by: Namhyung Kim Cc: pi3orama@163.com Cc: Jiri Olsa Cc: Zefan Li Link: http://lkml.kernel.org/r/1426251114-198991-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-options.c | 21 +++++++++++++++++++-- tools/perf/util/parse-options.h | 2 ++ 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 1457d66..01626be 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -37,6 +37,7 @@ static int get_value(struct parse_opt_ctx_t *p, { const char *s, *arg = NULL; const int unset = flags & OPT_UNSET; + int err; if (unset && p->opt) return opterror(opt, "takes no value", flags); @@ -114,13 +115,29 @@ static int get_value(struct parse_opt_ctx_t *p, return 0; case OPTION_STRING: + err = 0; if (unset) *(const char **)opt->value = NULL; else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) *(const char **)opt->value = (const char *)opt->defval; else - return get_arg(p, opt, flags, (const char **)opt->value); - return 0; + err = get_arg(p, opt, flags, (const char **)opt->value); + + /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */ + if (opt->flags & PARSE_OPT_NOEMPTY) { + const char *val = *(const char **)opt->value; + + if (!val) + return err; + + /* Similar to unset if we are given an empty string. */ + if (val[0] == '\0') { + *(const char **)opt->value = NULL; + return 0; + } + } + + return err; case OPTION_CALLBACK: if (unset) diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 97b153f..59561fd 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -40,6 +40,7 @@ enum parse_opt_option_flags { PARSE_OPT_LASTARG_DEFAULT = 16, PARSE_OPT_DISABLED = 32, PARSE_OPT_EXCLUSIVE = 64, + PARSE_OPT_NOEMPTY = 128, }; struct option; @@ -122,6 +123,7 @@ struct option { #define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) } #define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) } #define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) } +#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ -- cgit v1.1 From 0635b0f71424be7706793ac260d063491a2889a0 Mon Sep 17 00:00:00 2001 From: Milos Vyletel Date: Fri, 20 Mar 2015 11:37:25 +0100 Subject: perf tools: Fix race in build_id_cache__add_s() int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms, bool is_vdso) { ... if (access(filename, F_OK)) { ^--------------------------------------------------------- [1] if (is_kallsyms) { if (copyfile("/proc/kallsyms", filename)) goto out_free; } else if (link(realname, filename) && copyfile(name, filename)) ^-----------------------------^------------- [2] \------------ [3] goto out_free; } ... When multiple instances of perf record get to [1] at more or less same time and run access() one or more may get failure because the file does not exist yet (since the first instance did not have chance to link it yet). At this point the race moves to link() at [2] where first thread to get there links file and goes on but second one gets -EEXIST so it runs copyfile [3] which truncates the file. reproducer: rm -rf /root/.debug for cpu in $(awk '/processor/ {print $3}' /proc/cpuinfo); do perf record -a -v -T -F 1000 -C $cpu \ -o perf-${cpu}.data sleep 5 2> /dev/null & done wait and simply search for empty files by: find /lib/modules/`uname -r`/kernel/* -size 0 Signed-off-by: Milos Vyletel Acked-by: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1426847846-11112-1-git-send-email-milos@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a196746..f7fb258 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -374,7 +374,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, if (is_kallsyms) { if (copyfile("/proc/kallsyms", filename)) goto out_free; - } else if (link(realname, filename) && copyfile(name, filename)) + } else if (link(realname, filename) && errno != EEXIST && + copyfile(name, filename)) goto out_free; } -- cgit v1.1 From 0560a0c4a12a45def9700e7ec3215da102cf914b Mon Sep 17 00:00:00 2001 From: He Kuang Date: Fri, 20 Mar 2015 09:56:56 +0800 Subject: perf probe: Fix failure to add multiple probes without debuginfo Perf tries to find probe function addresses from map when debuginfo could not be found. To the first added function, the value of ref_reloc_sym was set in maps__set_kallsyms_ref_reloc_sym() and can be obtained from host_machine->kmaps->maps. After that, new maps are added to host_machine->kmaps->maps in dso__load_kcore(), all these new added maps do not have a valid ref_reloc_sym. When adding a second function, get_target_map() may get a map without valid ref_reloc_sym, and raise the error "Relocated base symbol is not found". Fix this by using kernel_get_ref_reloc_sym() to get ref_reloc_sym. This problem can be reproduced as following: $ perf probe --add='sys_write' --add='sys_open' Relocated base symbol is not found! Error: Failed to add events. After this patch: $ perf probe --add='sys_write' --add='sys_open' Added new event: probe:sys_write (on sys_write) You can now use it in all perf tools, such as: perf record -e probe:sys_write -aR sleep 1 Added new event: probe:sys_open (on sys_open) You can now use it in all perf tools, such as: perf record -e probe:sys_open -aR sleep 1 Signed-off-by: He Kuang Tested-by: Arnaldo Carvalho de Melo Tested-by: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1426816616-2394-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index f272a71..6b95985 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2507,7 +2507,6 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int max_tevs, const char *target) { struct map *map = NULL; - struct kmap *kmap = NULL; struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; struct probe_trace_event *tev; @@ -2540,8 +2539,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } if (!pev->uprobes && !pp->retprobe) { - kmap = map__kmap(map); - reloc_sym = kmap->ref_reloc_sym; + reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); ret = -EINVAL; -- cgit v1.1 From 80a32e5b498a7547073e5e4b2b804edc7219979d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 29 Jan 2015 13:29:39 +0100 Subject: perf tools: Add lzma decompression support for kernel module In short, Fedora compresses kernel modules now (since version 21) with lzma compression. Adding lzma decompress support into the dso.c:compressions array introduced by Namhyung earlier. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-2glp65kdtbrk0gblmirsjsnt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 1 + tools/perf/util/dso.c | 3 ++ tools/perf/util/lzma.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/util.h | 4 +++ 4 files changed, 103 insertions(+) create mode 100644 tools/perf/util/lzma.c (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 972a6e0..797490a 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -94,6 +94,7 @@ libperf-y += scripting-engines/ libperf-$(CONFIG_PERF_REGS) += perf_regs.o libperf-$(CONFIG_ZLIB) += zlib.o +libperf-$(CONFIG_LZMA) += lzma.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 814554d..be36841 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -148,6 +148,9 @@ static const struct { #ifdef HAVE_ZLIB_SUPPORT { "gz", gzip_decompress_to_file }, #endif +#ifdef HAVE_LZMA_SUPPORT + { "xz", lzma_decompress_to_file }, +#endif { NULL, NULL }, }; diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c new file mode 100644 index 0000000..95a1acb --- /dev/null +++ b/tools/perf/util/lzma.c @@ -0,0 +1,95 @@ +#include +#include +#include +#include "util.h" +#include "debug.h" + +#define BUFSIZE 8192 + +static const char *lzma_strerror(lzma_ret ret) +{ + switch ((int) ret) { + case LZMA_MEM_ERROR: + return "Memory allocation failed"; + case LZMA_OPTIONS_ERROR: + return "Unsupported decompressor flags"; + case LZMA_FORMAT_ERROR: + return "The input is not in the .xz format"; + case LZMA_DATA_ERROR: + return "Compressed file is corrupt"; + case LZMA_BUF_ERROR: + return "Compressed file is truncated or otherwise corrupt"; + default: + return "Unknown error, possibly a bug"; + } +} + +int lzma_decompress_to_file(const char *input, int output_fd) +{ + lzma_action action = LZMA_RUN; + lzma_stream strm = LZMA_STREAM_INIT; + lzma_ret ret; + + u8 buf_in[BUFSIZE]; + u8 buf_out[BUFSIZE]; + FILE *infile; + + infile = fopen(input, "rb"); + if (!infile) { + pr_err("lzma: fopen failed on %s: '%s'\n", + input, strerror(errno)); + return -1; + } + + ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED); + if (ret != LZMA_OK) { + pr_err("lzma: lzma_stream_decoder failed %s (%d)\n", + lzma_strerror(ret), ret); + return -1; + } + + strm.next_in = NULL; + strm.avail_in = 0; + strm.next_out = buf_out; + strm.avail_out = sizeof(buf_out); + + while (1) { + if (strm.avail_in == 0 && !feof(infile)) { + strm.next_in = buf_in; + strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile); + + if (ferror(infile)) { + pr_err("lzma: read error: %s\n", strerror(errno)); + return -1; + } + + if (feof(infile)) + action = LZMA_FINISH; + } + + ret = lzma_code(&strm, action); + + if (strm.avail_out == 0 || ret == LZMA_STREAM_END) { + ssize_t write_size = sizeof(buf_out) - strm.avail_out; + + if (writen(output_fd, buf_out, write_size) != write_size) { + pr_err("lzma: write error: %s\n", strerror(errno)); + return -1; + } + + strm.next_out = buf_out; + strm.avail_out = sizeof(buf_out); + } + + if (ret != LZMA_OK) { + if (ret == LZMA_STREAM_END) + return 0; + + pr_err("lzma: failed %s\n", lzma_strerror(ret)); + return -1; + } + } + + fclose(infile); + return 0; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index fbd598a..1ff23e0 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -329,4 +329,8 @@ bool find_process(const char *name); int gzip_decompress_to_file(const char *input, int output_fd); #endif +#ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_to_file(const char *input, int output_fd); +#endif + #endif /* GIT_COMPAT_UTIL_H */ -- cgit v1.1 From 3c8a67f50a1e68b912d1d74db6b455cac54ec4b4 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 5 Feb 2015 15:40:25 +0100 Subject: perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/dso.h | 14 +++++++++++ 2 files changed, 80 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index be36841..3e6863f 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -212,6 +212,72 @@ bool dso__needs_decompress(struct dso *dso) } /* + * Parses kernel module specified in @path and updates + * @m argument like: + * + * @comp - true if @path contains supported compression suffix, + * false otherwise + * @kmod - true if @path contains '.ko' suffix in right position, + * false otherwise + * @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name + * of the kernel module without suffixes, otherwise strudup-ed + * base name of @path + * @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string + * the compression suffix + * + * Returns 0 if there's no strdup error, -ENOMEM otherwise. + */ +int __kmod_path__parse(struct kmod_path *m, const char *path, + bool alloc_name, bool alloc_ext) +{ + const char *name = strrchr(path, '/'); + const char *ext = strrchr(path, '.'); + + memset(m, 0x0, sizeof(*m)); + name = name ? name + 1 : path; + + /* No extension, just return name. */ + if (ext == NULL) { + if (alloc_name) { + m->name = strdup(name); + return m->name ? 0 : -ENOMEM; + } + return 0; + } + + if (is_supported_compression(ext + 1)) { + m->comp = true; + ext -= 3; + } + + /* Check .ko extension only if there's enough name left. */ + if (ext > name) + m->kmod = !strncmp(ext, ".ko", 3); + + if (alloc_name) { + if (m->kmod) { + if (asprintf(&m->name, "[%.*s]", (int) (ext - name), name) == -1) + return -ENOMEM; + } else { + if (asprintf(&m->name, "%s", name) == -1) + return -ENOMEM; + } + + strxfrchar(m->name, '-', '_'); + } + + if (alloc_ext && m->comp) { + m->ext = strdup(ext + 4); + if (!m->ext) { + free((void *) m->name); + return -ENOMEM; + } + } + + return 0; +} + +/* * Global list of open DSOs and the counter. */ static LIST_HEAD(dso__data_open); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 408c65f..384cd29 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -195,6 +195,20 @@ bool is_kernel_module(const char *pathname, bool *compressed); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); +struct kmod_path { + char *name; + char *ext; + bool comp; + bool kmod; +}; + +int __kmod_path__parse(struct kmod_path *m, const char *path, + bool alloc_name, bool alloc_ext); + +#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) +#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) +#define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) + /* * The dso__data_* external interface provides following functions: * dso__data_fd -- cgit v1.1 From 701d8d7f861ec36f3bc60d1ddb185cceb7919c79 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:06:09 +0100 Subject: perf tools: Add dsos__addnew function Separate the creation of new dso object and its addition to the dsos list. It will be used in following patch. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-8j43jod97fdt5dwdsushwwae@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 21 ++++++++++++--------- tools/perf/util/dso.h | 1 + 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 3e6863f..7a7c54b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1071,21 +1071,24 @@ struct dso *dsos__find(const struct dsos *dsos, const char *name, return dso__find_by_longname(&dsos->root, name); } -struct dso *__dsos__findnew(struct dsos *dsos, const char *name) +struct dso *dsos__addnew(struct dsos *dsos, const char *name) { - struct dso *dso = dsos__find(dsos, name, false); + struct dso *dso = dso__new(name); - if (!dso) { - dso = dso__new(name); - if (dso != NULL) { - dsos__add(dsos, dso); - dso__set_basename(dso); - } + if (dso != NULL) { + dsos__add(dsos, dso); + dso__set_basename(dso); } - return dso; } +struct dso *__dsos__findnew(struct dsos *dsos, const char *name) +{ + struct dso *dso = dsos__find(dsos, name, false); + + return dso ? dso : dsos__addnew(dsos, name); +} + size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 384cd29..3c81d83 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -264,6 +264,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name, const char *short_name, int dso_type); void dsos__add(struct dsos *dsos, struct dso *dso); +struct dso *dsos__addnew(struct dsos *dsos, const char *name); struct dso *dsos__find(const struct dsos *dsos, const char *name, bool cmp_short); struct dso *__dsos__findnew(struct dsos *dsos, const char *name); -- cgit v1.1 From da17ea33e5a5d0c5226a37c375575d689f6a741b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:10:52 +0100 Subject: perf tools: Add machine__module_dso function Separate the dso object addition and update when adding new kernel module. Currently we update dso's symtab_type any time we find it in the list, because we can't distinguish between new and found dso from __dsos__findnew function. Adding machine__module_dso that separates finding and adding new dso objects, so there's no superfluous update of dso. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-uvqgs5tyq4wssnq6fm43hgvk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 24f8c97..dbb5f03 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -460,12 +460,35 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, return 0; } +static struct dso *machine__module_dso(struct machine *machine, const char *filename) +{ + struct dso *dso; + bool compressed; + + dso = dsos__find(&machine->kernel_dsos, filename, false); + if (!dso) { + dso = dsos__addnew(&machine->kernel_dsos, filename); + if (dso == NULL) + return NULL; + + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (is_kernel_module(filename, &compressed) && compressed) + dso->symtab_type++; + } + + return dso; +} + struct map *machine__new_module(struct machine *machine, u64 start, const char *filename) { struct map *map; - struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); - bool compressed; + struct dso *dso = machine__module_dso(machine, filename); if (dso == NULL) return NULL; @@ -474,15 +497,6 @@ struct map *machine__new_module(struct machine *machine, u64 start, if (map == NULL) return NULL; - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; - - /* _KMODULE_COMP should be next to _KMODULE */ - if (is_kernel_module(filename, &compressed) && compressed) - dso->symtab_type++; - map_groups__insert(&machine->kmaps, map); return map; } -- cgit v1.1 From ca33380adf74afb985bf7aab09ec46707a5d2d57 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 17 Feb 2015 17:29:57 +0100 Subject: perf tools: Use kmod_path__parse for machine__new_dso Using kmod_path__parse to get the module name and update the dso short name within machine__new_dso function. This way it's done only first time when dso is created, unlike the current way when we update it all the time we process memory map of the kernel module. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-8gjmt1ggf5ls1xkk7qi2ko4k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 59 +++++++++++++++++------------------------------ 1 file changed, 21 insertions(+), 38 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index dbb5f03..eb95b88 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -460,14 +460,15 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, return 0; } -static struct dso *machine__module_dso(struct machine *machine, const char *filename) +static struct dso* +machine__module_dso(struct machine *machine, struct kmod_path *m, + const char *filename) { struct dso *dso; - bool compressed; - dso = dsos__find(&machine->kernel_dsos, filename, false); + dso = dsos__find(&machine->kernel_dsos, m->name, true); if (!dso) { - dso = dsos__addnew(&machine->kernel_dsos, filename); + dso = dsos__addnew(&machine->kernel_dsos, m->name); if (dso == NULL) return NULL; @@ -477,8 +478,11 @@ static struct dso *machine__module_dso(struct machine *machine, const char *file dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; /* _KMODULE_COMP should be next to _KMODULE */ - if (is_kernel_module(filename, &compressed) && compressed) + if (m->kmod && m->comp) dso->symtab_type++; + + dso__set_short_name(dso, strdup(m->name), true); + dso__set_long_name(dso, strdup(filename), true); } return dso; @@ -487,17 +491,25 @@ static struct dso *machine__module_dso(struct machine *machine, const char *file struct map *machine__new_module(struct machine *machine, u64 start, const char *filename) { - struct map *map; - struct dso *dso = machine__module_dso(machine, filename); + struct map *map = NULL; + struct dso *dso; + struct kmod_path m; - if (dso == NULL) + if (kmod_path__parse_name(&m, filename)) return NULL; + dso = machine__module_dso(machine, &m, filename); + if (dso == NULL) + goto out; + map = map__new2(start, dso, MAP__FUNCTION); if (map == NULL) - return NULL; + goto out; map_groups__insert(&machine->kmaps, map); + +out: + free(m.name); return map; } @@ -1058,40 +1070,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine, strlen(kmmap_prefix) - 1) == 0; if (event->mmap.filename[0] == '/' || (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - - char short_module_name[1024]; - char *name, *dot; - - if (event->mmap.filename[0] == '/') { - name = strrchr(event->mmap.filename, '/'); - if (name == NULL) - goto out_problem; - - ++name; /* skip / */ - dot = strrchr(name, '.'); - if (dot == NULL) - goto out_problem; - /* On some system, modules are compressed like .ko.gz */ - if (is_supported_compression(dot + 1)) - dot -= 3; - if (!is_kmodule_extension(dot + 1)) - goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); - strxfrchar(short_module_name, '-', '_'); - } else - strcpy(short_module_name, event->mmap.filename); - map = machine__new_module(machine, event->mmap.start, event->mmap.filename); if (map == NULL) goto out_problem; - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - dso__set_short_name(map->dso, name, true); map->end = map->start + event->mmap.len; } else if (is_kernel_mmap) { const char *symbol_name = (event->mmap.filename + -- cgit v1.1 From bb58a8a459c322196613ad4af8801de41469cebb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:20:01 +0100 Subject: perf tools: Use kmod_path__parse in map_groups__set_modules_path_dir Replacing the file name parsing with kmod_path__parse and moving the dso update into new separate function. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-q0ed76ajcyoaofotntrg5sla@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 65 ++++++++++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 24 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index eb95b88..6ca61a3 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -851,6 +851,39 @@ static char *get_kernel_version(const char *root_dir) return strdup(name); } +static bool is_kmod_dso(struct dso *dso) +{ + return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; +} + +static int map_groups__set_module_path(struct map_groups *mg, const char *path, + struct kmod_path *m) +{ + struct map *map; + char *long_name; + + map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name); + if (map == NULL) + return 0; + + long_name = strdup(path); + if (long_name == NULL) + return -ENOMEM; + + dso__set_long_name(map->dso, long_name, true); + dso__kernel_module_get_build_id(map->dso, ""); + + /* + * Full name could reveal us kmod compression, so + * we need to update the symtab_type if needed. + */ + if (m->comp && is_kmod_dso(map->dso)) + map->dso->symtab_type++; + + return 0; +} + static int map_groups__set_modules_path_dir(struct map_groups *mg, const char *dir_name, int depth) { @@ -889,35 +922,19 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, if (ret < 0) goto out; } else { - char *dot = strrchr(dent->d_name, '.'), - dso_name[PATH_MAX]; - struct map *map; - char *long_name; + struct kmod_path m; - if (dot == NULL) - continue; + ret = kmod_path__parse_name(&m, dent->d_name); + if (ret) + goto out; - /* On some system, modules are compressed like .ko.gz */ - if (is_supported_compression(dot + 1) && - is_kmodule_extension(dot - 2)) - dot -= 3; + if (m.kmod) + ret = map_groups__set_module_path(mg, path, &m); - snprintf(dso_name, sizeof(dso_name), "[%.*s]", - (int)(dot - dent->d_name), dent->d_name); + free(m.name); - strxfrchar(dso_name, '-', '_'); - map = map_groups__find_by_name(mg, MAP__FUNCTION, - dso_name); - if (map == NULL) - continue; - - long_name = strdup(path); - if (long_name == NULL) { - ret = -1; + if (ret) goto out; - } - dso__set_long_name(map->dso, long_name, true); - dso__kernel_module_get_build_id(map->dso, ""); } } -- cgit v1.1 From 914f85c4a2db34429b146a57652d2db24d063379 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:27:50 +0100 Subject: perf tools: Use kmod_path__parse in decompress_kmodule Replacing the file name parsing with kmod_path__parse. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-zpyyitlte7lwe2ywi51rj4n5@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 62742e46..78ffde9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -579,32 +579,34 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) static int decompress_kmodule(struct dso *dso, const char *name, enum dso_binary_type type) { - int fd; - const char *ext = strrchr(name, '.'); + int fd = -1; char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; + struct kmod_path m; if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && type != DSO_BINARY_TYPE__BUILD_ID_CACHE) return -1; - if (!ext || !is_supported_compression(ext + 1)) { - ext = strrchr(dso->name, '.'); - if (!ext || !is_supported_compression(ext + 1)) - return -1; - } + if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE) + name = dso->long_name; + + if (kmod_path__parse_ext(&m, name) || !m.comp) + return -1; fd = mkstemp(tmpbuf); if (fd < 0) - return -1; + goto out; - if (!decompress_to_file(ext + 1, name, fd)) { + if (!decompress_to_file(m.ext, name, fd)) { close(fd); fd = -1; } unlink(tmpbuf); +out: + free(m.ext); return fd; } -- cgit v1.1 From 8dee9ff110f11fa536caef3cd2da23b74dceaf5b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 15:56:21 +0100 Subject: perf tools: Use kmod_path__parse in is_kernel_module Replacing the current parsing code with kmod_path__parse function call. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-r9mpbbgkp39wp1cdmv13ddq0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 7a7c54b..f375483 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -178,19 +178,15 @@ bool is_kmodule_extension(const char *ext) bool is_kernel_module(const char *pathname, bool *compressed) { - const char *ext = strrchr(pathname, '.'); + struct kmod_path m; - if (ext == NULL) - return false; + if (kmod_path__parse(&m, pathname)) + return NULL; - if (is_supported_compression(ext + 1)) { - if (compressed) - *compressed = true; - ext -= 3; - } else if (compressed) - *compressed = false; + if (compressed) + *compressed = m.comp; - return is_kmodule_extension(ext + 1); + return m.kmod; } bool decompress_to_file(const char *ext, const char *filename, int output_fd) -- cgit v1.1 From e746b3ea0d414b3382bb61c8cecc45cefb370fbf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:16:34 +0100 Subject: perf tools: Remove compressed argument from is_kernel_module We no longer need the 'compressed' argument, because all current users use 'NULL' for it. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-d72q2s7ggbmy2yzhumux4zzw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 5 +---- tools/perf/util/dso.h | 2 +- tools/perf/util/header.c | 2 +- tools/perf/util/machine.c | 2 +- 4 files changed, 4 insertions(+), 7 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index f375483..8803a69 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -176,16 +176,13 @@ bool is_kmodule_extension(const char *ext) return false; } -bool is_kernel_module(const char *pathname, bool *compressed) +bool is_kernel_module(const char *pathname) { struct kmod_path m; if (kmod_path__parse(&m, pathname)) return NULL; - if (compressed) - *compressed = m.comp; - return m.kmod; } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 3c81d83..54dd03a49 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -191,7 +191,7 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t char *root_dir, char *filename, size_t size); bool is_supported_compression(const char *ext); bool is_kmodule_extension(const char *ext); -bool is_kernel_module(const char *pathname, bool *compressed); +bool is_kernel_module(const char *pathname); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1f407f7..fb43215 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1266,7 +1266,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (!is_kernel_module(filename, NULL)) + if (!is_kernel_module(filename)) dso->kernel = dso_type; build_id__sprintf(dso->build_id, sizeof(dso->build_id), diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 6ca61a3..1de5438 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1104,7 +1104,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, struct dso *dso; list_for_each_entry(dso, &machine->kernel_dsos.head, node) { - if (is_kernel_module(dso->long_name, NULL)) + if (is_kernel_module(dso->long_name)) continue; kernel = dso; -- cgit v1.1 From 907fb509f0f1e35848d9e20b00176319af79101c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 12 Feb 2015 22:49:41 +0100 Subject: perf tools: Remove is_kmodule_extension function Because it's no longer needed. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-bb84vlg76t78q8y8fdeed2qn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 11 ----------- tools/perf/util/dso.h | 1 - 2 files changed, 12 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 8803a69..0d3667f 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -165,17 +165,6 @@ bool is_supported_compression(const char *ext) return false; } -bool is_kmodule_extension(const char *ext) -{ - if (strncmp(ext, "ko", 2)) - return false; - - if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3))) - return true; - - return false; -} - bool is_kernel_module(const char *pathname) { struct kmod_path m; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 54dd03a49..88f345c 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -190,7 +190,6 @@ char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); bool is_supported_compression(const char *ext); -bool is_kmodule_extension(const char *ext); bool is_kernel_module(const char *pathname); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); -- cgit v1.1 From bc84f464862489e687c98dea1a8ff20dc4413f93 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 17 Feb 2015 17:31:18 +0100 Subject: perf tools: Try to lookup kernel module map before creating one Currently we assume machine__new_module is called only once for each module so we create its map&dso unconditionally. However it's possible that it's called multiple times for same module. Like for perf record: 1) via machine__create_module during machine init 2) via kernel MMAP event processing Trying to lookup kernel module map before creating one. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-kx76xfqpnrpho5hdaapbqm09@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1de5438..e335330 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -498,6 +498,11 @@ struct map *machine__new_module(struct machine *machine, u64 start, if (kmod_path__parse_name(&m, filename)) return NULL; + map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION, + m.name); + if (map) + goto out; + dso = machine__module_dso(machine, &m, filename); if (dso == NULL) goto out; -- cgit v1.1 From 2c7da8c590ad719796f46c875a096eb45ef971c7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 2 Mar 2015 12:56:12 -0500 Subject: perf annotate: Allow annotation for decompressed kernel modules Decompressing kernel module file for objdump command if needed. Annotation commands now display annotation for compressed kernel modules. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-x4jcytk2d5qjmnjvb0w75q3f@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 61bf912..b72086e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1008,6 +1008,32 @@ fallback: } filename = symfs_filename; } + } else if (dso__needs_decompress(dso)) { + char tmp[PATH_MAX]; + struct kmod_path m; + int fd; + bool ret; + + if (kmod_path__parse_ext(&m, symfs_filename)) + goto out_free_filename; + + snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX"); + + fd = mkstemp(tmp); + if (fd < 0) { + free(m.ext); + goto out_free_filename; + } + + ret = decompress_to_file(m.ext, symfs_filename, fd); + + free(m.ext); + close(fd); + + if (!ret) + goto out_free_filename; + + strcpy(symfs_filename, tmp); } snprintf(command, sizeof(command), @@ -1027,7 +1053,7 @@ fallback: file = popen(command, "r"); if (!file) - goto out_free_filename; + goto out_remove_tmp; while (!feof(file)) if (symbol__parse_objdump_line(sym, map, file, privsize, @@ -1042,6 +1068,10 @@ fallback: delete_last_nop(sym); pclose(file); + +out_remove_tmp: + if (dso__needs_decompress(dso)) + unlink(symfs_filename); out_free_filename: if (delete_extract) kcore_extract__delete(&kce); -- cgit v1.1 From 228f14f2cbf481e0ec0bd0c7f947383cfa2d5167 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Mon, 23 Mar 2015 11:50:05 +0800 Subject: perf tools: Remove (null) value of "Sort order" for perf mem report When '--sort' is not set, 'perf mem report" will print a null pointer as the output value of sort order, so fix it. Example: Before this patch: $ perf mem report # To display the perf.data header info, please use --header/--header-only options. # # Samples: 18 of event 'cpu/mem-loads/pp' # Total weight : 188 # Sort order : (null) # ... After this patch: $ perf mem report # To display the perf.data header info, please use --header/--header-only options. # # Samples: 18 of event 'cpu/mem-loads/pp' # Total weight : 188 # Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked # ... Signed-off-by: Yunlong Song Acked-by: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1427082605-12881-1-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 9c01b83..846036a 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -44,6 +44,7 @@ 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; +extern const char default_mem_sort_order[]; struct he_stat { u64 period; -- cgit v1.1 From e6d7c91c8c5ea532584056f3e8bf1643310c8ef7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 22 Mar 2015 20:40:22 +0900 Subject: perf probe: Fix to get ummapped symbol address on kernel Fix to get correctly unmapped symbol address on kernel. This allows us to probe on syscall symbols which are aliases of SyS_ functions with using debuginfo. Without this fix: ---- # ./perf probe -a sys_write Failed to find debug information for address 3b0100 Probe point 'sys_write' not found. Error: Failed to add events. ---- The address 0x3b0100 is a mapped address, and not usable in debuginfo. With this fix: ---- # ./perf probe -a sys_write Added new event: probe:sys_write (on sys_write) You can now use it in all perf tools, such as: perf record -e probe:sys_write -aR sleep 1 ---- Signed-off-by: Masami Hiramatsu Cc: He Kuang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/20150322114022.32639.19096.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6b95985..8feac07 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -310,7 +310,10 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, /* Find the address of given function */ map__for_each_symbol_by_name(map, pp->function, sym) { - address = sym->start; + if (uprobes) + address = sym->start; + else + address = map->unmap_ip(map, sym->start); break; } if (!address) { -- cgit v1.1 From e1e455f4f4d35850c30235747620d0d078fe9f64 Mon Sep 17 00:00:00 2001 From: Vinson Lee Date: Mon, 23 Mar 2015 12:09:16 -0700 Subject: perf tools: Work around lack of sched_getcpu in glibc < 2.6. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes this build error with glibc < 2.6. CC util/cloexec.o cc1: warnings being treated as errors util/cloexec.c: In function ‘perf_flag_probe’: util/cloexec.c:24: error: implicit declaration of function ‘sched_getcpu’ util/cloexec.c:24: error: nested extern declaration of ‘sched_getcpu’ make: *** [util/cloexec.o] Error 1 Signed-off-by: Vinson Lee Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Yann Droneaud Cc: stable@vger.kernel.org # 3.18+ Link: http://lkml.kernel.org/r/1427137761-16119-1-git-send-email-vlee@twopensource.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cloexec.c | 6 ++++++ tools/perf/util/cloexec.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 6da965b..85b5238 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -7,6 +7,12 @@ static unsigned long flag = PERF_FLAG_FD_CLOEXEC; +int __weak sched_getcpu(void) +{ + errno = ENOSYS; + return -1; +} + static int perf_flag_probe(void) { /* use 'safest' configuration as used in perf_evsel__fallback() */ diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index 94a5a7d..68888c2 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -3,4 +3,10 @@ unsigned long perf_event_open_cloexec_flag(void); +#ifdef __GLIBC_PREREQ +#if !__GLIBC_PREREQ(2, 6) +extern int sched_getcpu(void) __THROW; +#endif +#endif + #endif /* __PERF_CLOEXEC_H */ -- cgit v1.1 From 17e44dc46f035ca27847bbf75ffd3072ed49f13c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 23 Mar 2015 18:23:02 -0300 Subject: perf target: Simplify handling of strerror_r return To deal with forwarding the strerror_r (GNU) return we need to check if the returned value is the buffer we passed or maybe some constant (unknown error), simplify that action by using scnprintf, that will do all the buflen size checks, trimming if needed. Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-d0ik6i5gjew56j0qphql28ou@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/target.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index e74c596..a53603b 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -123,11 +123,8 @@ int target__strerror(struct target *target, int errnum, if (errnum >= 0) { const char *err = strerror_r(errnum, buf, buflen); - if (err != buf) { - size_t len = strlen(err); - memcpy(buf, err, min(buflen - 1, len)); - *(buf + min(buflen - 1, len)) = '\0'; - } + if (err != buf) + scnprintf(buf, buflen, "%s", err); return 0; } -- cgit v1.1 From 18425f13a0890ac1e88a64276771c1ae10030b4a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Mar 2015 11:49:02 -0300 Subject: perf symbols: Save DSO loading errno to better report errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before, when some problem happened while trying to load the kernel symtab, 'perf top' would show: ┌─Warning:───────────────────────────┐ │The vmlinux file can't be used. │ │Kernel samples will not be resolved.│ │ │ │ │ │Press any key... │ └────────────────────────────────────┘ Now, it reports: # perf top --vmlinux /dev/null ┌─Warning:───────────────────────────────────────────┐ │The /tmp/passwd file can't be used: Invalid ELF file│ │Kernel samples will not be resolved. │ │ │ │ │ │Press any key... │ └────────────────────────────────────────────────────┘ This is possible because we now register the reason for not being able to load the symtab in the dso->load_errno member, and provide a dso__strerror_load() routine to format this error into a strerror like string with a short reason for the error while loading. That can be just forwarding the dso__strerror_load() call to strerror_r(), or, for a separate errno range providing a custom message. Reported-by: Ingo Molnar Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-u5rb5uq63xqhkfb8uv2lxd5u@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 33 +++++++++++++++++++++++++++++++++ tools/perf/util/dso.h | 28 ++++++++++++++++++++++++++++ tools/perf/util/symbol-elf.c | 37 +++++++++++++++++++++++++++---------- tools/perf/util/symbol-minimal.c | 7 ++++--- 4 files changed, 92 insertions(+), 13 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 0d3667f..fc0ddd5 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1137,3 +1137,36 @@ enum dso_type dso__type(struct dso *dso, struct machine *machine) return dso__type_fd(fd); } + +int dso__strerror_load(struct dso *dso, char *buf, size_t buflen) +{ + int idx, errnum = dso->load_errno; + /* + * This must have a same ordering as the enum dso_load_errno. + */ + static const char *dso_load__error_str[] = { + "Internal tools/perf/ library error", + "Invalid ELF file", + "Can not read build id", + "Mismatching build id", + "Decompression failure", + }; + + BUG_ON(buflen == 0); + + if (errnum >= 0) { + const char *err = strerror_r(errnum, buf, buflen); + + if (err != buf) + scnprintf(buf, buflen, "%s", err); + + return 0; + } + + if (errnum < __DSO_LOAD_ERRNO__START || errnum >= __DSO_LOAD_ERRNO__END) + return -1; + + idx = errnum - __DSO_LOAD_ERRNO__START; + scnprintf(buf, buflen, "%s", dso_load__error_str[idx]); + return 0; +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 88f345c..e0901b4 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -60,6 +60,31 @@ enum dso_type { DSO__TYPE_X32BIT, }; +enum dso_load_errno { + DSO_LOAD_ERRNO__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __DSO_LOAD_ERRNO__START = -10000, + + DSO_LOAD_ERRNO__INTERNAL_ERROR = __DSO_LOAD_ERRNO__START, + + /* for symsrc__init() */ + DSO_LOAD_ERRNO__INVALID_ELF, + DSO_LOAD_ERRNO__CANNOT_READ_BUILDID, + DSO_LOAD_ERRNO__MISMATCHING_BUILDID, + + /* for decompress_kmodule */ + DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE, + + __DSO_LOAD_ERRNO__END, +}; + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -113,6 +138,7 @@ struct dso { enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; enum dso_binary_type binary_type; + enum dso_load_errno load_errno; u8 adjust_symbols:1; u8 has_build_id:1; u8 has_srcline:1; @@ -294,4 +320,6 @@ void dso__free_a2l(struct dso *dso); enum dso_type dso__type(struct dso *dso, struct machine *machine); +int dso__strerror_load(struct dso *dso, char *buf, size_t buflen); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 78ffde9..476268c 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -595,10 +595,13 @@ static int decompress_kmodule(struct dso *dso, const char *name, return -1; fd = mkstemp(tmpbuf); - if (fd < 0) + if (fd < 0) { + dso->load_errno = errno; goto out; + } if (!decompress_to_file(m.ext, name, fd)) { + dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } @@ -635,37 +638,49 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, Elf *elf; int fd; - if (dso__needs_decompress(dso)) + if (dso__needs_decompress(dso)) { fd = decompress_kmodule(dso, name, type); - else + if (fd < 0) + return -1; + } else { fd = open(name, O_RDONLY); - - if (fd < 0) - return -1; + if (fd < 0) { + dso->load_errno = errno; + return -1; + } + } elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); if (elf == NULL) { pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF; goto out_close; } if (gelf_getehdr(elf, &ehdr) == NULL) { + dso->load_errno = DSO_LOAD_ERRNO__INVALID_ELF; pr_debug("%s: cannot get elf header.\n", __func__); goto out_elf_end; } - if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) + if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) { + dso->load_errno = DSO_LOAD_ERRNO__INTERNAL_ERROR; goto out_elf_end; + } /* Always reject images with a mismatched build-id: */ if (dso->has_build_id) { u8 build_id[BUILD_ID_SIZE]; - if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) { + dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID; goto out_elf_end; + } - if (!dso__build_id_equal(dso, build_id)) + if (!dso__build_id_equal(dso, build_id)) { + dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID; goto out_elf_end; + } } ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); @@ -701,8 +716,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, } ss->name = strdup(name); - if (!ss->name) + if (!ss->name) { + dso->load_errno = errno; goto out_elf_end; + } ss->elf = elf; ss->fd = fd; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index d7efb03..fd8477c 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -246,13 +246,12 @@ out: return ret; } -int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, - const char *name, +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type) { int fd = open(name, O_RDONLY); if (fd < 0) - return -1; + goto out_errno; ss->name = strdup(name); if (!ss->name) @@ -264,6 +263,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, return 0; out_close: close(fd); +out_errno: + dso->load_errno = errno; return -1; } -- cgit v1.1 From b839e1e846edb15cff322e262e8ce412d298232e Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Tue, 24 Mar 2015 11:07:19 +0000 Subject: tools lib traceevent: Add support for __print_array() Since 6ea22486ba46 ("tracing: Add array printing helper") trace can generate traces with variable element size arrays. Add support to parse them. Signed-off-by: Javi Merino Acked-by: Namhyung Kim Acked-by: Steven Rostedt Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1427195239-15730-1-git-send-email-javi.merino@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/scripting-engines/trace-event-perl.c | 5 +++++ tools/perf/util/scripting-engines/trace-event-python.c | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 22ebc46..8171fed 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -214,6 +214,11 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; + case PRINT_INT_ARRAY: + define_event_symbols(event, ev_name, args->int_array.field); + define_event_symbols(event, ev_name, args->int_array.count); + define_event_symbols(event, ev_name, args->int_array.el_size); + break; case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 0c815a4..2ec5dfb 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -231,6 +231,11 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; + case PRINT_INT_ARRAY: + define_event_symbols(event, ev_name, args->int_array.field); + define_event_symbols(event, ev_name, args->int_array.count); + define_event_symbols(event, ev_name, args->int_array.el_size); + break; case PRINT_STRING: break; case PRINT_TYPE: -- cgit v1.1 From e03eaa400cf8b8bded86cc5c41018a1c69152f16 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 24 Mar 2015 09:52:41 -0600 Subject: perf tools: Add pid/tid filtering to report and script commands The 'record' and 'top' tools already allow a user to specify a CSV of pids and/or tids of tasks to collect data. Add those options to the 'report' and 'script' analysis commands to only consider samples related to the given pids/tids. This is also inline with the existing comm option. Signed-off-by: David Ahern Cc: Adrian Hunter Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1427212361-7066-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 31 ++++++++++++++++++++++++++++++- tools/perf/util/symbol.h | 7 +++++++ tools/perf/util/thread.h | 11 +++++++++++ 3 files changed, 48 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a690668..fddeb90 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -15,6 +15,7 @@ #include "machine.h" #include "symbol.h" #include "strlist.h" +#include "intlist.h" #include "header.h" #include @@ -1859,6 +1860,20 @@ int setup_list(struct strlist **list, const char *list_str, return 0; } +int setup_intlist(struct intlist **list, const char *list_str, + const char *list_name) +{ + if (list_str == NULL) + return 0; + + *list = intlist__new(list_str); + if (!*list) { + pr_err("problems parsing %s list\n", list_name); + return -1; + } + return 0; +} + static bool symbol__read_kptr_restrict(void) { bool value = false; @@ -1909,9 +1924,17 @@ int symbol__init(struct perf_session_env *env) symbol_conf.comm_list_str, "comm") < 0) goto out_free_dso_list; + if (setup_intlist(&symbol_conf.pid_list, + symbol_conf.pid_list_str, "pid") < 0) + goto out_free_comm_list; + + if (setup_intlist(&symbol_conf.tid_list, + symbol_conf.tid_list_str, "tid") < 0) + goto out_free_pid_list; + if (setup_list(&symbol_conf.sym_list, symbol_conf.sym_list_str, "symbol") < 0) - goto out_free_comm_list; + goto out_free_tid_list; /* * A path to symbols of "/" is identical to "" @@ -1930,6 +1953,10 @@ int symbol__init(struct perf_session_env *env) symbol_conf.initialized = true; return 0; +out_free_tid_list: + intlist__delete(symbol_conf.tid_list); +out_free_pid_list: + intlist__delete(symbol_conf.pid_list); out_free_comm_list: strlist__delete(symbol_conf.comm_list); out_free_dso_list: @@ -1944,6 +1971,8 @@ void symbol__exit(void) strlist__delete(symbol_conf.sym_list); strlist__delete(symbol_conf.dso_list); strlist__delete(symbol_conf.comm_list); + intlist__delete(symbol_conf.tid_list); + intlist__delete(symbol_conf.pid_list); vmlinux_path__exit(); symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index efdaaa5..0956150 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -78,6 +78,7 @@ static inline size_t symbol__size(const struct symbol *sym) } struct strlist; +struct intlist; struct symbol_conf { unsigned short priv_size; @@ -115,6 +116,8 @@ struct symbol_conf { const char *guestmount; const char *dso_list_str, *comm_list_str, + *pid_list_str, + *tid_list_str, *sym_list_str, *col_width_list_str; struct strlist *dso_list, @@ -124,6 +127,8 @@ struct symbol_conf { *dso_to_list, *sym_from_list, *sym_to_list; + struct intlist *pid_list, + *tid_list; const char *symfs; }; @@ -295,5 +300,7 @@ int compare_proc_modules(const char *from, const char *to); int setup_list(struct strlist **list, const char *list_str, const char *list_name); +int setup_intlist(struct intlist **list, const char *list_str, + const char *list_name); #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 783b668..9b8a54d 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -7,6 +7,7 @@ #include #include "symbol.h" #include +#include struct thread_stack; @@ -100,6 +101,16 @@ static inline bool thread__is_filtered(struct thread *thread) return true; } + if (symbol_conf.pid_list && + !intlist__has_entry(symbol_conf.pid_list, thread->pid_)) { + return true; + } + + if (symbol_conf.tid_list && + !intlist__has_entry(symbol_conf.tid_list, thread->tid)) { + return true; + } + return false; } -- cgit v1.1 From e94eedab3ab8201fd41480171b2fabbf3c5b1ae0 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 24 Mar 2015 16:14:09 -0400 Subject: perf timechart: Fix SIBGUS error on sparc64 perf timechart -T on sparc64 is terminating due to SIGBUS. Backtrace: Program received signal SIGBUS, Bus error. 0x0000000000173d7c in perf_evsel__intval (evsel=, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1918 util/evsel.c: No such file or directory. in util/evsel.c Missing separate debuginfos, use: debuginfo-install audit-libs-2.3.7-1.0.1.el6.sparc64 bzip2-libs-1.0.5-7.el6_0.sparc64 elfutils-libelf-0.155-2.0.3.el6.sparc64 elfutils-libs-0.155-2.0.3.el6.sparc64 glibc-2.12-1.132.0.8.el6_5.sparc64 numactl-2.0.7-8.el6.sparc64 python-libs-2.6.6-52.0.2.el6.sparc64 slang-2.2.1-1.el6.sparc64 xz-libs-4.999.9-0.3.beta.20091007git.el6.sparc64 zlib-1.2.3-29.el6.sparc64 (gdb) bt 0 0x0000000000173d7c in perf_evsel__intval (evsel=, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1 0x0000000000123b94 in process_sample_sched_switch (tchart=0x7feffffe040, evsel=0x4ca850, sample=0x7feffffda28, backtrace=0xc39010 "") at builtin-timechart.c:627 2 0x0000000000122828 in process_sample_event (tool=0x7feffffe040, event=, sample=0x7feffffda28, evsel=0x4ca850, machine=0x4c9c88) at builtin-timechart.c:569 Another extended load on unaligned pointer. As before fix by copying to a temporary variable using memcpy. Signed-off-by: David Ahern Link: http://lkml.kernel.org/r/1427228049-51893-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index bb4eff2..358e595 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1915,7 +1915,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, value = *(u32 *)ptr; break; case 8: - value = *(u64 *)ptr; + memcpy(&value, ptr, sizeof(u64)); break; default: return 0; -- cgit v1.1 From 23d4aad48e31d3269af484dd2f9bd251278cd667 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 24 Mar 2015 19:23:47 -0300 Subject: perf evlist: Return the first evsel with an invalid filter in apply_filters() Use of a bad filter currently generates the message: Error: failed to set filter with 22 (Invalid argument) Add the event name to make it clear to which event the filter failed to apply: Error: Failed to set filter "foo" on event sched:sg_lb_stats: 22: Invalid argument To test it use something like: # perf record -e sched:sched_switch -e sched:*fork --filter parent_pid==1 -e sched:*wait* --filter bla usleep 1 Error: failed to set filter "bla" on event sched:sched_stat_iowait with 22 (Invalid argument) # Based-on-a-patch-by: David Ahern Acked-by: David Ahern Cc: Adrian Hunter Cc: Borislav Petkov Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-d7gq2fjvaecozp9o2i0siifu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 6 ++++-- tools/perf/util/evlist.h | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 8d0b623..82bf224 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1050,7 +1050,7 @@ out_delete_threads: return -1; } -int perf_evlist__apply_filters(struct perf_evlist *evlist) +int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) { struct perf_evsel *evsel; int err = 0; @@ -1062,8 +1062,10 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist) continue; err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter); - if (err) + if (err) { + *err_evsel = evsel; break; + } } return err; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index f07c984..fb19c47 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -152,7 +152,7 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct perf_evlist *evlist); +int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); -- cgit v1.1 From 73dbcd6537f0ef6bf98d84f8fd7f8ab9994c6cd8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 30 Mar 2015 10:11:00 +0200 Subject: perf callchain: Fix kernel symbol resolution by remembering the cpumode Commit 2e77784bb7d8 ("perf callchain: Move cpumode resolve code to add_callchain_ip") promised "No change in behavior.". As this commit breaks callchains on s390x (symbols not getting resolved, observed when profiling the kernel), this statement is wrong. The cpumode must be kept when iterating over all ips, otherwise the default (PERF_RECORD_MISC_USER) will be used by error. Signed-off-by: David Hildenbrand Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Hildenbrand Cc: Hendrik Brueckner Cc: Kan Liang Cc: Martin Schwidefsky Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1427703060-59883-1-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e335330..e45c8f3 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1408,29 +1408,27 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, static int add_callchain_ip(struct thread *thread, struct symbol **parent, struct addr_location *root_al, - bool branch_history, + u8 *cpumode, u64 ip) { struct addr_location al; al.filtered = 0; al.sym = NULL; - if (branch_history) + if (!cpumode) { thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); - else { - u8 cpumode = PERF_RECORD_MISC_USER; - + } else { if (ip >= PERF_CONTEXT_MAX) { switch (ip) { case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; + *cpumode = PERF_RECORD_MISC_HYPERVISOR; break; case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; + *cpumode = PERF_RECORD_MISC_KERNEL; break; case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; + *cpumode = PERF_RECORD_MISC_USER; break; default: pr_debug("invalid callchain context: " @@ -1444,8 +1442,8 @@ static int add_callchain_ip(struct thread *thread, } return 0; } - thread__find_addr_location(thread, cpumode, MAP__FUNCTION, - ip, &al); + thread__find_addr_location(thread, *cpumode, MAP__FUNCTION, + ip, &al); } if (al.sym != NULL) { @@ -1538,6 +1536,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, { struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr); + u8 cpumode = PERF_RECORD_MISC_USER; int i, j, err; u64 ip; @@ -1584,7 +1583,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; } - err = add_callchain_ip(thread, parent, root_al, false, ip); + err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; } @@ -1604,6 +1603,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, struct branch_stack *branch = sample->branch_stack; struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr); + u8 cpumode = PERF_RECORD_MISC_USER; int i, j, err; int skip_idx = -1; int first_call = 0; @@ -1669,10 +1669,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < nr; i++) { err = add_callchain_ip(thread, parent, root_al, - true, be[i].to); + NULL, be[i].to); if (!err) err = add_callchain_ip(thread, parent, root_al, - true, be[i].from); + NULL, be[i].from); if (err == -EINVAL) break; if (err) @@ -1701,7 +1701,7 @@ check_calls: #endif ip = chain->ips[j]; - err = add_callchain_ip(thread, parent, root_al, false, ip); + err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; -- cgit v1.1 From 5aa0b030e8d29d6719c144818814b519cfcb105c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 30 Mar 2015 14:35:57 -0600 Subject: perf tools: Refactor comm/tgid lookup Rather than parsing /proc/pid/status file one line at a time, read it into a buffer in one shot and search for all strings in one pass. tgid conversion also simplified -- removing the isspace walk. As noted by Arnaldo those are not needed for atoi == strtol calls. Signed-off-by: David Ahern Acked-by: Don Zickus Acked-by: Jiri Olsa Cc: Joe Mario Link: http://lkml.kernel.org/r/1427747758-18510-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 72 ++++++++++++++++++++++++++++++------------------- 1 file changed, 44 insertions(+), 28 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index d5efa50..023dd35 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -49,48 +49,64 @@ static struct perf_sample synth_sample = { .period = 1, }; +/* + * Assumes that the first 4095 bytes of /proc/pid/stat contains + * the comm and tgid. + */ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) { char filename[PATH_MAX]; - char bf[BUFSIZ]; - FILE *fp; - size_t size = 0; + char bf[4096]; + int fd; + size_t size = 0, n; pid_t tgid = -1; + char *nl, *name, *tgids; snprintf(filename, sizeof(filename), "/proc/%d/status", pid); - fp = fopen(filename, "r"); - if (fp == NULL) { + fd = open(filename, O_RDONLY); + if (fd < 0) { pr_debug("couldn't open %s\n", filename); return 0; } - while (!comm[0] || (tgid < 0)) { - if (fgets(bf, sizeof(bf), fp) == NULL) { - pr_warning("couldn't get COMM and pgid, malformed %s\n", - filename); - break; - } + n = read(fd, bf, sizeof(bf) - 1); + close(fd); + if (n <= 0) { + pr_warning("Couldn't get COMM and tgid for pid %d\n", + pid); + return -1; + } + bf[n] = '\0'; - if (memcmp(bf, "Name:", 5) == 0) { - char *name = bf + 5; - while (*name && isspace(*name)) - ++name; - size = strlen(name) - 1; - if (size >= len) - size = len - 1; - memcpy(comm, name, size); - comm[size] = '\0'; - - } else if (memcmp(bf, "Tgid:", 5) == 0) { - char *tgids = bf + 5; - while (*tgids && isspace(*tgids)) - ++tgids; - tgid = atoi(tgids); - } + name = strstr(bf, "Name:"); + tgids = strstr(bf, "Tgid:"); + + if (name) { + name += 5; /* strlen("Name:") */ + + while (*name && isspace(*name)) + ++name; + + nl = strchr(name, '\n'); + if (nl) + *nl = '\0'; + + size = strlen(name); + if (size >= len) + size = len - 1; + memcpy(comm, name, size); + comm[size] = '\0'; + } else { + pr_debug("Name: string not found for pid %d\n", pid); } - fclose(fp); + if (tgids) { + tgids += 5; /* strlen("Tgid:") */ + tgid = atoi(tgids); + } else { + pr_debug("Tgid: string not found for pid %d\n", pid); + } return tgid; } -- cgit v1.1 From ca6c41c59b964d362823e80442e9e32c31106b29 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 30 Mar 2015 14:35:58 -0600 Subject: perf tools: Fix ppid for synthesized fork events 363b785f38 added synthesized fork events and set a thread's parent id to itself. Since we are already processing /proc//status the ppid can be determined properly. Make it so. Signed-off-by: David Ahern Acked-by: Don Zickus Acked-by: Jiri Olsa Cc: Joe Mario Link: http://lkml.kernel.org/r/1427747758-18510-2-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 83 +++++++++++++++++++++++++++++-------------------- 1 file changed, 50 insertions(+), 33 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 023dd35..5516236 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -51,29 +51,32 @@ static struct perf_sample synth_sample = { /* * Assumes that the first 4095 bytes of /proc/pid/stat contains - * the comm and tgid. + * the comm, tgid and ppid. */ -static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) +static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, + pid_t *tgid, pid_t *ppid) { char filename[PATH_MAX]; char bf[4096]; int fd; size_t size = 0, n; - pid_t tgid = -1; - char *nl, *name, *tgids; + char *nl, *name, *tgids, *ppids; + + *tgid = -1; + *ppid = -1; snprintf(filename, sizeof(filename), "/proc/%d/status", pid); fd = open(filename, O_RDONLY); if (fd < 0) { pr_debug("couldn't open %s\n", filename); - return 0; + return -1; } n = read(fd, bf, sizeof(bf) - 1); close(fd); if (n <= 0) { - pr_warning("Couldn't get COMM and tgid for pid %d\n", + pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", pid); return -1; } @@ -81,6 +84,7 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) name = strstr(bf, "Name:"); tgids = strstr(bf, "Tgid:"); + ppids = strstr(bf, "PPid:"); if (name) { name += 5; /* strlen("Name:") */ @@ -103,32 +107,45 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) if (tgids) { tgids += 5; /* strlen("Tgid:") */ - tgid = atoi(tgids); + *tgid = atoi(tgids); } else { pr_debug("Tgid: string not found for pid %d\n", pid); } - return tgid; + if (ppids) { + ppids += 5; /* strlen("PPid:") */ + *ppid = atoi(ppids); + } else { + pr_debug("PPid: string not found for pid %d\n", pid); + } + + return 0; } -static pid_t perf_event__prepare_comm(union perf_event *event, pid_t pid, - struct machine *machine) +static int perf_event__prepare_comm(union perf_event *event, pid_t pid, + struct machine *machine, + pid_t *tgid, pid_t *ppid) { size_t size; - pid_t tgid; + + *ppid = -1; memset(&event->comm, 0, sizeof(event->comm)); - if (machine__is_host(machine)) - tgid = perf_event__get_comm_tgid(pid, event->comm.comm, - sizeof(event->comm.comm)); - else - tgid = machine->pid; + if (machine__is_host(machine)) { + if (perf_event__get_comm_ids(pid, event->comm.comm, + sizeof(event->comm.comm), + tgid, ppid) != 0) { + return -1; + } + } else { + *tgid = machine->pid; + } - if (tgid < 0) - goto out; + if (*tgid < 0) + return -1; - event->comm.pid = tgid; + event->comm.pid = *tgid; event->comm.header.type = PERF_RECORD_COMM; size = strlen(event->comm.comm) + 1; @@ -138,8 +155,8 @@ static pid_t perf_event__prepare_comm(union perf_event *event, pid_t pid, (sizeof(event->comm.comm) - size) + machine->id_hdr_size); event->comm.tid = pid; -out: - return tgid; + + return 0; } static pid_t perf_event__synthesize_comm(struct perf_tool *tool, @@ -147,27 +164,27 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine) { - pid_t tgid = perf_event__prepare_comm(event, pid, machine); + pid_t tgid, ppid; - if (tgid == -1) - goto out; + if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) + return -1; if (process(tool, event, &synth_sample, machine) != 0) return -1; -out: return tgid; } static int perf_event__synthesize_fork(struct perf_tool *tool, - union perf_event *event, pid_t pid, - pid_t tgid, perf_event__handler_t process, + union perf_event *event, + pid_t pid, pid_t tgid, pid_t ppid, + perf_event__handler_t process, struct machine *machine) { memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - event->fork.ppid = tgid; - event->fork.ptid = tgid; + event->fork.ppid = ppid; + event->fork.ptid = ppid; event->fork.pid = tgid; event->fork.tid = pid; event->fork.header.type = PERF_RECORD_FORK; @@ -359,7 +376,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, char filename[PATH_MAX]; DIR *tasks; struct dirent dirent, *next; - pid_t tgid; + pid_t tgid, ppid; /* special case: only send one comm event using passed in pid */ if (!full) { @@ -394,12 +411,12 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (*end) continue; - tgid = perf_event__prepare_comm(comm_event, _pid, machine); - if (tgid == -1) + if (perf_event__prepare_comm(comm_event, _pid, machine, + &tgid, &ppid) != 0) return -1; if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - process, machine) < 0) + ppid, process, machine) < 0) return -1; /* * Send the prepared comm event -- cgit v1.1 From aae59fab978e143f24d22e52f075c4be3ee4e628 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 31 Mar 2015 09:53:50 -0300 Subject: perf session: Always initialize ordered_events Even when it is not used to actually reorder events, some of its fields are used, like session->ordered_events->tool, to shorten function signatures where tool, for instance, was being passed, as the tool is needed for the ordered_events code, we need it there and might as well use it for other perf_session needs. This fixes a problem where 'perf script' had some condition that made session->ordered_events not to be initialized even with its script->tool ordered_events related flags asking for it to be, which looks like another bug and needs to be investigated further. Always initializing session->ordered_events at least leaves the current assumptions in place, so do it now. Reported-by: David Ahern Reviewed-by: David Ahern Tested-by: David Ahern Cc: Adrian Hunter Cc: Borislav Petkov Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-b1xxk0rwkz2a0gip1uufmjqg@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index adf0740..89c6679 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -110,6 +110,8 @@ struct perf_session *perf_session__new(struct perf_data_file *file, session->repipe = repipe; machines__init(&session->machines); + ordered_events__init(&session->ordered_events, &session->machines, + session->evlist, tool, ordered_events__deliver_event); if (file) { if (perf_data_file__open(file)) @@ -139,9 +141,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; - } else { - ordered_events__init(&session->ordered_events, &session->machines, - session->evlist, tool, ordered_events__deliver_event); } return session; -- cgit v1.1 From 9870d7809575515e26194f4b3df1750872a6ee60 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 31 Mar 2015 12:48:16 -0300 Subject: perf ordered_samples: Remove references to perf_{evlist,tool} and machines As these can be obtained from the ordered_events pointer, via container_of, reducing the cross section of ordered_samples. These were added to ordered_samples in: commit b7b61cbebd789a3dbca522e3fdb727fe5c95593f Author: Arnaldo Carvalho de Melo Date: Tue Mar 3 11:58:45 2015 -0300 perf ordered_events: Shorten function signatures By keeping pointers to machines, evlist and tool in ordered_events. But that was more a transitional patch while moving stuff out from perf_session.c to ordered_events.c and possibly not even needed by then, as we could use the container_of() method and instead of having the nr_unordered_samples stats in events_stats, we can have it in ordered_samples. Based-on-a-patch-by: Jiri Olsa Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-4lk0t9js82g0tfc0x1onpkjt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.h | 1 - tools/perf/util/ordered-events.c | 21 ++++-------------- tools/perf/util/ordered-events.h | 14 +++--------- tools/perf/util/session.c | 47 +++++++++++++++++++++++++--------------- tools/perf/util/session.h | 1 + 5 files changed, 37 insertions(+), 47 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index c4ffe2b..09b9e8d 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -242,7 +242,6 @@ struct events_stats { u32 nr_invalid_chains; u32 nr_unknown_id; u32 nr_unprocessable_samples; - u32 nr_unordered_events; }; struct attr_event { diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 6002fa3..52be201 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -2,7 +2,6 @@ #include #include #include "ordered-events.h" -#include "evlist.h" #include "session.h" #include "asm/bug.h" #include "debug.h" @@ -167,7 +166,7 @@ int ordered_events__queue(struct ordered_events *oe, union perf_event *event, pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", oe->last_flush_type); - oe->evlist->stats.nr_unordered_events++; + oe->nr_unordered_events++; } oevent = ordered_events__new_event(oe, timestamp, event); @@ -187,7 +186,6 @@ static int __ordered_events__flush(struct ordered_events *oe) { struct list_head *head = &oe->events; struct ordered_event *tmp, *iter; - struct perf_sample sample; u64 limit = oe->next_flush; u64 last_ts = oe->last ? oe->last->timestamp : 0ULL; bool show_progress = limit == ULLONG_MAX; @@ -206,15 +204,9 @@ static int __ordered_events__flush(struct ordered_events *oe) if (iter->timestamp > limit) break; - - ret = perf_evlist__parse_sample(oe->evlist, iter->event, &sample); + ret = oe->deliver(oe, iter); if (ret) - pr_err("Can't parse sample, err = %d\n", ret); - else { - ret = oe->deliver(oe, iter, &sample); - if (ret) - return ret; - } + return ret; ordered_events__delete(oe, iter); oe->last_flush = iter->timestamp; @@ -292,18 +284,13 @@ int ordered_events__flush(struct ordered_events *oe, enum oe_flush how) return err; } -void ordered_events__init(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlist, struct perf_tool *tool, - ordered_events__deliver_t deliver) +void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver) { INIT_LIST_HEAD(&oe->events); INIT_LIST_HEAD(&oe->cache); INIT_LIST_HEAD(&oe->to_free); oe->max_alloc_size = (u64) -1; oe->cur_alloc_size = 0; - oe->evlist = evlist; - oe->machines = machines; - oe->tool = tool; oe->deliver = deliver; } diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index 173e13f..f403991 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -3,10 +3,7 @@ #include -struct perf_tool; -struct perf_evlist; struct perf_sample; -struct machines; struct ordered_event { u64 timestamp; @@ -25,8 +22,7 @@ enum oe_flush { struct ordered_events; typedef int (*ordered_events__deliver_t)(struct ordered_events *oe, - struct ordered_event *event, - struct perf_sample *sample); + struct ordered_event *event); struct ordered_events { u64 last_flush; @@ -39,13 +35,11 @@ struct ordered_events { struct list_head to_free; struct ordered_event *buffer; struct ordered_event *last; - struct machines *machines; - struct perf_evlist *evlist; - struct perf_tool *tool; ordered_events__deliver_t deliver; int buffer_idx; unsigned int nr_events; enum oe_flush last_flush_type; + u32 nr_unordered_events; bool copy_on_queue; }; @@ -53,9 +47,7 @@ int ordered_events__queue(struct ordered_events *oe, union perf_event *event, struct perf_sample *sample, u64 file_offset); void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); -void ordered_events__init(struct ordered_events *oe, struct machines *machines, - struct perf_evlist *evlsit, struct perf_tool *tool, - ordered_events__deliver_t deliver); +void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver); void ordered_events__free(struct ordered_events *oe); static inline diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 89c6679..dfacf1d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -93,11 +93,20 @@ static void perf_session__set_comm_exec(struct perf_session *session) } static int ordered_events__deliver_event(struct ordered_events *oe, - struct ordered_event *event, - struct perf_sample *sample) + struct ordered_event *event) { - return machines__deliver_event(oe->machines, oe->evlist, event->event, - sample, oe->tool, event->file_offset); + struct perf_sample sample; + struct perf_session *session = container_of(oe, struct perf_session, + ordered_events); + int ret = perf_evlist__parse_sample(session->evlist, event->event, &sample); + + if (ret) { + pr_err("Can't parse sample, err = %d\n", ret); + return ret; + } + + return machines__deliver_event(&session->machines, session->evlist, event->event, + &sample, session->tool, event->file_offset); } struct perf_session *perf_session__new(struct perf_data_file *file, @@ -109,9 +118,9 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out; session->repipe = repipe; + session->tool = tool; machines__init(&session->machines); - ordered_events__init(&session->ordered_events, &session->machines, - session->evlist, tool, ordered_events__deliver_event); + ordered_events__init(&session->ordered_events, ordered_events__deliver_event); if (file) { if (perf_data_file__open(file)) @@ -940,7 +949,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, u64 file_offset) { struct ordered_events *oe = &session->ordered_events; - struct perf_tool *tool = oe->tool; + struct perf_tool *tool = session->tool; int fd = perf_data_file__fd(session->file); int err; @@ -981,7 +990,7 @@ int perf_session__deliver_synth_event(struct perf_session *session, struct perf_sample *sample) { struct perf_evlist *evlist = session->evlist; - struct perf_tool *tool = session->ordered_events.tool; + struct perf_tool *tool = session->tool; events_stats__inc(&evlist->stats, event->header.type); @@ -1059,7 +1068,7 @@ static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, u64 file_offset) { struct perf_evlist *evlist = session->evlist; - struct perf_tool *tool = session->ordered_events.tool; + struct perf_tool *tool = session->tool; struct perf_sample sample; int ret; @@ -1116,10 +1125,12 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } -static void perf_tool__warn_about_errors(const struct perf_tool *tool, - const struct events_stats *stats) +static void perf_session__warn_about_errors(const struct perf_session *session) { - if (tool->lost == perf_event__process_lost && + const struct events_stats *stats = &session->evlist->stats; + const struct ordered_events *oe = &session->ordered_events; + + if (session->tool->lost == perf_event__process_lost && stats->nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", @@ -1155,8 +1166,8 @@ static void perf_tool__warn_about_errors(const struct perf_tool *tool, stats->nr_unprocessable_samples); } - if (stats->nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", stats->nr_unordered_events); + if (oe->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events); } volatile int session_done; @@ -1164,7 +1175,7 @@ volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; - struct perf_tool *tool = oe->tool; + struct perf_tool *tool = session->tool; int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; @@ -1247,7 +1258,7 @@ done: err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: free(buf); - perf_tool__warn_about_errors(tool, &session->evlist->stats); + perf_session__warn_about_errors(session); ordered_events__free(&session->ordered_events); return err; } @@ -1297,7 +1308,7 @@ static int __perf_session__process_events(struct perf_session *session, u64 file_size) { struct ordered_events *oe = &session->ordered_events; - struct perf_tool *tool = oe->tool; + struct perf_tool *tool = session->tool; int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; @@ -1393,7 +1404,7 @@ out: err = ordered_events__flush(oe, OE_FLUSH__FINAL); out_err: ui_progress__finish(); - perf_tool__warn_about_errors(tool, &session->evlist->stats); + perf_session__warn_about_errors(session); ordered_events__free(&session->ordered_events); session->one_mmap = false; return err; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 1310998..d5fa7b791 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -26,6 +26,7 @@ struct perf_session { u64 one_mmap_offset; struct ordered_events ordered_events; struct perf_data_file *file; + struct perf_tool *tool; }; #define PRINT_IP_OPT_IP (1<<0) -- cgit v1.1 From f9d5d549d2c2934be84b0bc7e5e034834459f591 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 1 Apr 2015 13:29:25 -0300 Subject: perf scripting: No need to pass thread twice to the scripting callbacks It is already in the addr_location, so remove the redundant 'thread' parameter from the callback signatures. Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1427906210-10519-3-git-send-email-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/scripting-engines/trace-event-perl.c | 5 ++--- tools/perf/util/scripting-engines/trace-event-python.c | 13 +++++-------- tools/perf/util/trace-event-scripting.c | 1 - tools/perf/util/trace-event.h | 3 +-- 4 files changed, 8 insertions(+), 14 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 8171fed..430b5d2 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -360,10 +360,9 @@ static void perl_process_event_generic(union perf_event *event, static void perl_process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, - struct addr_location *al __maybe_unused) + struct addr_location *al) { - perl_process_tracepoint(sample, evsel, thread); + perl_process_tracepoint(sample, evsel, al->thread); perl_process_event_generic(event, sample, evsel); } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 2ec5dfb..de8df1d 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -381,7 +381,6 @@ exit: static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, struct addr_location *al) { struct event_format *event = evsel->tp_format; @@ -395,7 +394,7 @@ static void python_process_tracepoint(struct perf_sample *sample, int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; - const char *comm = thread__comm_str(thread); + const char *comm = thread__comm_str(al->thread); t = PyTuple_New(MAX_FIELDS); if (!t) @@ -766,7 +765,6 @@ static int python_process_call_return(struct call_return *cr, void *data) static void python_process_general_event(struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, struct addr_location *al) { PyObject *handler, *t, *dict, *callchain, *dict_sample; @@ -816,7 +814,7 @@ static void python_process_general_event(struct perf_sample *sample, pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); pydict_set_item_string_decref(dict, "comm", - PyString_FromString(thread__comm_str(thread))); + PyString_FromString(thread__comm_str(al->thread))); if (al->map) { pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); @@ -843,22 +841,21 @@ exit: static void python_process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, struct addr_location *al) { struct tables *tables = &tables_global; switch (evsel->attr.type) { case PERF_TYPE_TRACEPOINT: - python_process_tracepoint(sample, evsel, thread, al); + python_process_tracepoint(sample, evsel, al); break; /* Reserve for future process_hw/sw/raw APIs */ default: if (tables->db_export_mode) db_export__sample(&tables->dbe, event, sample, evsel, - thread, al); + al->thread, al); else - python_process_general_event(sample, evsel, thread, al); + python_process_general_event(sample, evsel, al); } } diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 5c9bdd1..9df6105 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -43,7 +43,6 @@ static int stop_script_unsupported(void) static void process_event_unsupported(union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct thread *thread __maybe_unused, struct addr_location *al __maybe_unused) { } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 356629a..d5168f0 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -72,8 +72,7 @@ struct scripting_ops { void (*process_event) (union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, - struct addr_location *al); + struct addr_location *al); int (*generate_script) (struct pevent *pevent, const char *outfile); }; -- cgit v1.1 From 7327259d7ea96d04d02e7dbe51ee9201319dc204 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 2 Apr 2015 11:08:30 -0300 Subject: perf db-export: No need to pass thread twice to db_export__sample As it is available via another parameter, address_location->thread. Acked-by: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: lkml.kernel.org/r/551D08F8.3040706@intel.com Link: http://lkml.kernel.org/n/tip-6dbn0tcm9hyv92g7h3zj2dbt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/db-export.c | 3 ++- tools/perf/util/db-export.h | 2 +- tools/perf/util/scripting-engines/trace-event-python.c | 3 +-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index c81dae3..5499887 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -282,8 +282,9 @@ int db_export__branch_type(struct db_export *dbe, u32 branch_type, int db_export__sample(struct db_export *dbe, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, struct addr_location *al) + struct addr_location *al) { + struct thread* thread = al->thread; struct export_sample es = { .event = event, .sample = sample, diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h index adbd22d..b9faa13 100644 --- a/tools/perf/util/db-export.h +++ b/tools/perf/util/db-export.h @@ -97,7 +97,7 @@ int db_export__branch_type(struct db_export *dbe, u32 branch_type, const char *name); int db_export__sample(struct db_export *dbe, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread, struct addr_location *al); + struct addr_location *al); int db_export__branch_types(struct db_export *dbe); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index de8df1d..1d3cc1b 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -852,8 +852,7 @@ static void python_process_event(union perf_event *event, /* Reserve for future process_hw/sw/raw APIs */ default: if (tables->db_export_mode) - db_export__sample(&tables->dbe, event, sample, evsel, - al->thread, al); + db_export__sample(&tables->dbe, event, sample, evsel, al); else python_process_general_event(sample, evsel, al); } -- cgit v1.1 From b83e868d0a0350c107b98417b4dcc73834506f98 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 2 Apr 2015 11:16:05 -0300 Subject: perf db-export: No need to have ->thread twice in struct export_sample As it comes from address_location->thread, that is already stored as export_sample->al, where the thread can be obtained. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20150402141542.GA9630@kernel.org Link: http://lkml.kernel.org/n/tip-bzotbl4epoztw0jd6sm2stpf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/db-export.c | 1 - tools/perf/util/db-export.h | 1 - tools/perf/util/scripting-engines/trace-event-python.c | 2 +- 3 files changed, 1 insertion(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 5499887..bb39a3f 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -289,7 +289,6 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, .event = event, .sample = sample, .evsel = evsel, - .thread = thread, .al = al, }; struct thread *main_thread; diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h index b9faa13..25e22fd 100644 --- a/tools/perf/util/db-export.h +++ b/tools/perf/util/db-export.h @@ -34,7 +34,6 @@ struct export_sample { union perf_event *event; struct perf_sample *sample; struct perf_evsel *evsel; - struct thread *thread; struct addr_location *al; u64 db_id; u64 comm_db_id; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 1d3cc1b..5544b8c 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -679,7 +679,7 @@ static int python_export_sample(struct db_export *dbe, tuple_set_u64(t, 0, es->db_id); tuple_set_u64(t, 1, es->evsel->db_id); tuple_set_u64(t, 2, es->al->machine->db_id); - tuple_set_u64(t, 3, es->thread->db_id); + tuple_set_u64(t, 3, es->al->thread->db_id); tuple_set_u64(t, 4, es->comm_db_id); tuple_set_u64(t, 5, es->dso_db_id); tuple_set_u64(t, 6, es->sym_db_id); -- cgit v1.1 From c72738355b2ac79506fbfa10ffee8fe3a27e69da Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 2 Apr 2015 16:33:12 +0900 Subject: perf probe: Fix to track down unnamed union/structure members Fix 'perf probe' to track down unnamed union/structure members. perf probe did not track down the tree of unnamed union/structure members, since it just failed to find given "name" in a parent structure/union. To solve this issue, I've introduced 2 changes. - Fix die_find_member() to track down the type-DIE if it is unnamed, and if it contains the specified member, returns the unnamed member. (note that we don't return found member, since unnamed member has the offset in the parent structure) - Fix convert_variable_fields() to track down the unnamed union/ structure (one-by-one). With this patch, perf probe can access unnamed fields: ----- #./perf probe -nfx ./perf lock__delete ops 'locked_ops=ops->locked.ops' Added new event: probe_perf:lock__delete (on lock__delete in /home/mhiramat/ksrc/linux-3/tools/perf/perf with ops locked_ops=ops->locked.ops) You can now use it in all perf tools, such as: perf record -e probe_perf:lock__delete -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo Report-Link: https://lkml.org/lkml/2015/3/5/431 Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150402073312.14482.37942.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 14 ++++++++++---- tools/perf/util/probe-finder.c | 8 +++++++- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 780b2bc..c34e024 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -801,10 +801,16 @@ static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) { const char *name = data; - if ((dwarf_tag(die_mem) == DW_TAG_member) && - die_compare_name(die_mem, name)) - return DIE_FIND_CB_END; - + if (dwarf_tag(die_mem) == DW_TAG_member) { + if (die_compare_name(die_mem, name)) + return DIE_FIND_CB_END; + else if (!dwarf_diename(die_mem)) { /* Unnamed structure */ + Dwarf_Die type_die, tmp_die; + if (die_get_type(die_mem, &type_die) && + die_find_member(&type_die, name, &tmp_die)) + return DIE_FIND_CB_END; + } + } return DIE_FIND_CB_SIBLING; } diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 46f009a..7831e2d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -460,7 +460,8 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, " nor array.\n", varname); return -EINVAL; } - if (field->ref) { + /* While prcessing unnamed field, we don't care about this */ + if (field->ref && dwarf_diename(vr_die)) { pr_err("Semantic error: %s must be referred by '.'\n", field->name); return -EINVAL; @@ -491,6 +492,11 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } ref->offset += (long)offs; + /* If this member is unnamed, we need to reuse this field */ + if (!dwarf_diename(die_mem)) + return convert_variable_fields(die_mem, varname, field, + &ref, die_mem); + next: /* Converting next field */ if (field->next) -- cgit v1.1 From 9e3b6ec17374299516d83c2e36135b958a895aa3 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Thu, 2 Apr 2015 21:47:10 +0800 Subject: perf evlist: Support using -f to override perf.data file ownership Enable perf evlist to use perf.data when it is not owned by current user or root. Example: # perf record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 28260 Apr 2 10:18 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf evlist File perf.data not owned by current user or root (use -f to override) # perf evlist -f Error: unknown switch `f' usage: perf evlist [] -i, --input Input file name -F, --freq Show the sample frequency -v, --verbose Show all event attr details -g, --group Show event group information As shown above, the -f option does not work at all. After this patch: # perf evlist File perf.data not owned by current user or root (use -f to override) # perf evlist -f cycles As shown above, the -f option really works now. 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/1427982439-27388-2-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index dcf202a..c5a43d6 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -335,6 +335,7 @@ struct perf_attr_details { bool freq; bool verbose; bool event_group; + bool force; }; int perf_evsel__fprintf(struct perf_evsel *evsel, -- cgit v1.1 From 8cc5ec1f754355ed788838390e86389c9ffb7590 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Thu, 2 Apr 2015 21:47:13 +0800 Subject: perf kvm: Support using -f to override perf.data.guest file ownership Enable perf kvm to use perf.data.guest when it is not owned by current user or root. Example: # perf kvm stat record ls # chown Yunlong.Song:Yunlong.Song perf.data.guest # ls -al perf.data.guest -rw------- 1 Yunlong.Song Yunlong.Song 4128937 Apr 2 11:05 perf.data.guest # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf kvm stat report File perf.data.guest not owned by current user or root (use -f to override) Initializing perf session failed # perf kvm stat report -f Error: unknown switch `f' usage: perf kvm stat report [] --event event for reporting: vmexit, mmio (x86 only), ioport (x86 only) --vcpu vcpu id to report -k, --key key for sorting: sample(sort by samples number) time (sort by avg time) -p, --pid analyze events only for given process id(s) As shown above, the -f option does not work at all. After this patch: # perf kvm stat report File perf.data.guest not owned by current user or root (use -f to override) Initializing perf session failed # perf kvm stat report -f Analyze events for all VMs, all VCPUs: VM-EXIT Samples Samples% Time% Min Time Max Time Avg time Total Samples:0, Total events handled time:0.00us. As shown above, the -f option really works now. Since we have not launched any KVM related process, the result shows 0 sample here. 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/1427982439-27388-5-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/kvm-stat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index cf1d7913..ae825d4 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -99,6 +99,7 @@ struct perf_kvm_stat { int timerfd; unsigned int display_time; bool live; + bool force; }; struct kvm_reg_events_ops { -- cgit v1.1 From bd05954bfa17f03a7bd4454178ba09786b35e383 Mon Sep 17 00:00:00 2001 From: Yunlong Song Date: Thu, 2 Apr 2015 21:47:19 +0800 Subject: perf data: Support using -f to override perf.data file ownership for 'convert' Enable perf data convert to use perf.data when it is not owned by current user or root. Example: # perf record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 28260 Apr 2 17:35 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf data convert --to-ctf=./ctf-data/ File perf.data not owned by current user or root (use -f to override) # perf data convert --to-ctf=./ctf-data/ -f Error: unknown switch `f' usage: perf data convert [] -v, --verbose be more verbose -i, --input input file name --to-ctf ... Convert to CTF format After this patch: # perf data convert --to-ctf=./ctf-data/ File perf.data not owned by current user or root (use -f to override) # perf data convert --to-ctf=./ctf-data/ -f # ls ctf-data/ metadata perf_stream_0 As shown above, the -f option really works now. Signed-off-by: Yunlong Song Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1427982439-27388-11-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data-convert-bt.c | 3 ++- tools/perf/util/data-convert-bt.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index c6d6226..dd17c9a 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -791,12 +791,13 @@ err: return -1; } -int bt_convert__perf2ctf(const char *input, const char *path) +int bt_convert__perf2ctf(const char *input, const char *path, bool force) { struct perf_session *session; struct perf_data_file file = { .path = input, .mode = PERF_DATA_MODE_READ, + .force = force, }; struct convert c = { .tool = { diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h index dda30c5..4c20434 100644 --- a/tools/perf/util/data-convert-bt.h +++ b/tools/perf/util/data-convert-bt.h @@ -2,7 +2,7 @@ #define __DATA_CONVERT_BT_H #ifdef HAVE_LIBBABELTRACE_SUPPORT -int bt_convert__perf2ctf(const char *input_name, const char *to_ctf); +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, bool force); #endif /* HAVE_LIBBABELTRACE_SUPPORT */ #endif /* __DATA_CONVERT_BT_H */ -- cgit v1.1 From 8ea92ceb748535799e3e9f35afb85bdc23bf6d7c Mon Sep 17 00:00:00 2001 From: He Kuang Date: Tue, 7 Apr 2015 17:31:10 +0800 Subject: perf evlist: Fix inverted logic in perf_mmap__empty perf_evlist__mmap_consume() uses perf_mmap__empty() to judge whether perf_mmap is empty and can be released. But the result is inverted so fix it. Signed-off-by: He Kuang Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1428399071-7141-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 82bf224..76ef7ee 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -695,7 +695,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) static bool perf_mmap__empty(struct perf_mmap *md) { - return perf_mmap__read_head(md) != md->prev; + return perf_mmap__read_head(md) == md->prev; } static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx) -- cgit v1.1 From ba92732e9808df679ddf75c5ea1c0caae6d7dce2 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Tue, 7 Apr 2015 08:22:45 +0000 Subject: perf kmaps: Check kmaps to make code more robust This patch add checks in places where map__kmap is used to get kmaps from struct kmap. Error messages are added at map__kmap to warn invalid accessing of kmap (for the case of !map->dso->kernel, kmap(map) does not exists at all). Also, introduces map__kmaps() to warn uninitialized kmaps. Reviewed-by: Ingo Molnar Signed-off-by: Wang Nan Cc: pi3orama@163.com Cc: Jiri Olsa Cc: Namhyung Kim Cc: Zefan Li Link: http://lkml.kernel.org/r/1428394966-131044-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 5 ++++- tools/perf/util/map.c | 20 ++++++++++++++++++++ tools/perf/util/map.h | 6 ++---- tools/perf/util/probe-event.c | 2 ++ tools/perf/util/session.c | 3 +++ tools/perf/util/symbol-elf.c | 16 +++++++++++----- tools/perf/util/symbol.c | 34 ++++++++++++++++++++++++++++------ 7 files changed, 70 insertions(+), 16 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e45c8f3..9c380a2 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -679,6 +679,9 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) machine->vmlinux_maps[type]->unmap_ip = identity__map_ip; kmap = map__kmap(machine->vmlinux_maps[type]); + if (!kmap) + return -1; + kmap->kmaps = &machine->kmaps; map_groups__insert(&machine->kmaps, machine->vmlinux_maps[type]); @@ -700,7 +703,7 @@ void machine__destroy_kernel_maps(struct machine *machine) kmap = map__kmap(machine->vmlinux_maps[type]); map_groups__remove(&machine->kmaps, machine->vmlinux_maps[type]); - if (kmap->ref_reloc_sym) { + if (kmap && kmap->ref_reloc_sym) { /* * ref_reloc_sym is shared among all maps, so free just * on one of them. diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 62ca9f2..a14f08f 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -778,3 +778,23 @@ struct map *maps__next(struct map *map) return rb_entry(next, struct map, rb_node); return NULL; } + +struct kmap *map__kmap(struct map *map) +{ + if (!map->dso || !map->dso->kernel) { + pr_err("Internal error: map__kmap with a non-kernel map\n"); + return NULL; + } + return (struct kmap *)(map + 1); +} + +struct map_groups *map__kmaps(struct map *map) +{ + struct kmap *kmap = map__kmap(map); + + if (!kmap || !kmap->kmaps) { + pr_err("Internal error: map__kmaps with a non-kernel map\n"); + return NULL; + } + return kmap->kmaps; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0e42438..ec19c59 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -76,10 +76,8 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg) void map_groups__put(struct map_groups *mg); -static inline struct kmap *map__kmap(struct map *map) -{ - return (struct kmap *)(map + 1); -} +struct kmap *map__kmap(struct map *map); +struct map_groups *map__kmaps(struct map *map); static inline u64 map__map_ip(struct map *map, u64 ip) { diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8feac07..4fd49f0 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -135,6 +135,8 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) return NULL; kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]); + if (!kmap) + return NULL; return kmap->ref_reloc_sym; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index dfacf1d..0c74012 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1466,6 +1466,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, for (i = 0; i < MAP__NR_TYPES; ++i) { struct kmap *kmap = map__kmap(maps[i]); + + if (!kmap) + continue; kmap->ref_reloc_sym = ref; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 476268c..a7ab606 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -776,6 +776,7 @@ int dso__load_sym(struct dso *dso, struct map *map, symbol_filter_t filter, int kmodule) { struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; + struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = dso; Elf_Data *symstrs, *secstrs; @@ -791,6 +792,9 @@ int dso__load_sym(struct dso *dso, struct map *map, int nr = 0; bool remap_kernel = false, adjust_kernel_syms = false; + if (kmap && !kmaps) + return -1; + dso->symtab_type = syms_ss->type; dso->is_64_bit = syms_ss->is_64_bit; dso->rel = syms_ss->ehdr.e_type == ET_REL; @@ -958,8 +962,10 @@ int dso__load_sym(struct dso *dso, struct map *map, map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; /* Ensure maps are correctly ordered */ - map_groups__remove(kmap->kmaps, map); - map_groups__insert(kmap->kmaps, map); + if (kmaps) { + map_groups__remove(kmaps, map); + map_groups__insert(kmaps, map); + } } /* @@ -983,7 +989,7 @@ int dso__load_sym(struct dso *dso, struct map *map, snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); - curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name); + curr_map = map_groups__find_by_name(kmaps, map->type, dso_name); if (curr_map == NULL) { u64 start = sym.st_value; @@ -1013,7 +1019,7 @@ int dso__load_sym(struct dso *dso, struct map *map, curr_map->unmap_ip = identity__map_ip; } curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmap->kmaps, curr_map); + map_groups__insert(kmaps, curr_map); /* * The new DSO should go to the kernel DSOS */ @@ -1075,7 +1081,7 @@ new_symbol: * We need to fixup this here too because we create new * maps here, for things like vsyscall sections. */ - __map_groups__fixup_end(kmap->kmaps, map->type); + __map_groups__fixup_end(kmaps, map->type); } } err = nr; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index fddeb90..201f6c4c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -630,13 +630,16 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename, static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, symbol_filter_t filter) { - struct map_groups *kmaps = map__kmap(map)->kmaps; + struct map_groups *kmaps = map__kmaps(map); struct map *curr_map; struct symbol *pos; int count = 0, moved = 0; struct rb_root *root = &dso->symbols[map->type]; struct rb_node *next = rb_first(root); + if (!kmaps) + return -1; + while (next) { char *module; @@ -682,8 +685,8 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, symbol_filter_t filter) { - struct map_groups *kmaps = map__kmap(map)->kmaps; - struct machine *machine = kmaps->machine; + struct map_groups *kmaps = map__kmaps(map); + struct machine *machine; struct map *curr_map = map; struct symbol *pos; int count = 0, moved = 0; @@ -691,6 +694,11 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, struct rb_node *next = rb_first(root); int kernel_range = 0; + if (!kmaps) + return -1; + + machine = kmaps->machine; + while (next) { char *module; @@ -1025,9 +1033,12 @@ static bool filename_from_kallsyms_filename(char *filename, static int validate_kcore_modules(const char *kallsyms_filename, struct map *map) { - struct map_groups *kmaps = map__kmap(map)->kmaps; + struct map_groups *kmaps = map__kmaps(map); char modules_filename[PATH_MAX]; + if (!kmaps) + return -EINVAL; + if (!filename_from_kallsyms_filename(modules_filename, "modules", kallsyms_filename)) return -EINVAL; @@ -1043,6 +1054,9 @@ static int validate_kcore_addresses(const char *kallsyms_filename, { struct kmap *kmap = map__kmap(map); + if (!kmap) + return -EINVAL; + if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { u64 start; @@ -1081,8 +1095,8 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { - struct map_groups *kmaps = map__kmap(map)->kmaps; - struct machine *machine = kmaps->machine; + struct map_groups *kmaps = map__kmaps(map); + struct machine *machine; struct kcore_mapfn_data md; struct map *old_map, *new_map, *replacement_map = NULL; bool is_64_bit; @@ -1090,6 +1104,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map, char kcore_filename[PATH_MAX]; struct symbol *sym; + if (!kmaps) + return -EINVAL; + + machine = kmaps->machine; + /* This function requires that the map is the kernel map */ if (map != machine->vmlinux_maps[map->type]) return -EINVAL; @@ -1202,6 +1221,9 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) struct kmap *kmap = map__kmap(map); u64 addr; + if (!kmap) + return -1; + if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; -- cgit v1.1 From 814c8c38e13c7050259c72f89bb01f3fc903f642 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 31 Mar 2015 00:19:31 +0200 Subject: perf record: Add clockid parameter Teach perf-record about the new perf_event_attr::{use_clockid, clockid} fields. Add a simple parameter to set the clock (if any) to be used for the events to be recorded into the data file. Since we store the entire perf_event_attr in the EVENT_DESC section we also already store the used clockid in the data file. Signed-off-by: Peter Zijlstra (Intel) Acked-by: David Ahern Cc: "H. Peter Anvin" Cc: Adrian Hunter Cc: Andrew Morton Cc: Jiri Olsa Cc: John Stultz Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Yunlong Song Link: http://lkml.kernel.org/r/20150407154851.GR23123@twins.programming.kicks-ass.net [ Conditionally define CLOCK_BOOTTIME, at least rhel6 doesn't have it - dsahern Ditto for CLOCK_MONOTONIC_RAW, sles11sp2 doesn't have it - yunlong.song ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 59 ++++++++++++++++++++++++++++++++++++++++++++---- tools/perf/util/header.c | 3 +++ 2 files changed, 58 insertions(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 358e595..d190f99 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -32,8 +32,12 @@ static struct { bool exclude_guest; bool mmap2; bool cloexec; + bool clockid; + bool clockid_wrong; } perf_missing_features; +static clockid_t clockid; + static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) { return 0; @@ -761,6 +765,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->disabled = 0; attr->enable_on_exec = 0; } + + clockid = opts->clockid; + if (opts->use_clockid) { + attr->use_clockid = 1; + attr->clockid = opts->clockid; + } } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -1036,7 +1046,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_user, exclude_kernel); ret += PRINT_ATTR2(exclude_hv, exclude_idle); ret += PRINT_ATTR2(mmap, comm); - ret += PRINT_ATTR2(mmap2, comm_exec); ret += PRINT_ATTR2(freq, inherit_stat); ret += PRINT_ATTR2(enable_on_exec, task); ret += PRINT_ATTR2(watermark, precise_ip); @@ -1044,6 +1053,9 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_host, exclude_guest); ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, "excl.callchain_user", exclude_callchain_user); + ret += PRINT_ATTR2(mmap2, comm_exec); + ret += __PRINT_ATTR("%u",,use_clockid); + ret += PRINT_ATTR_U32(wakeup_events); ret += PRINT_ATTR_U32(wakeup_watermark); @@ -1055,6 +1067,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR_X64(branch_sample_type); ret += PRINT_ATTR_X64(sample_regs_user); ret += PRINT_ATTR_U32(sample_stack_user); + ret += PRINT_ATTR_U32(clockid); ret += PRINT_ATTR_X64(sample_regs_intr); ret += fprintf(fp, "%.60s\n", graph_dotted_line); @@ -1085,6 +1098,12 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } fallback_missing_features: + if (perf_missing_features.clockid_wrong) + evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */ + if (perf_missing_features.clockid) { + evsel->attr.use_clockid = 0; + evsel->attr.clockid = 0; + } if (perf_missing_features.cloexec) flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) @@ -1122,6 +1141,17 @@ retry_open: goto try_fallback; } set_rlimit = NO_CHANGE; + + /* + * If we succeeded but had to kill clockid, fail and + * have perf_evsel__open_strerror() print us a nice + * error. + */ + if (perf_missing_features.clockid || + perf_missing_features.clockid_wrong) { + err = -EINVAL; + goto out_close; + } } } @@ -1155,7 +1185,17 @@ try_fallback: if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { + /* + * Must probe features in the order they were added to the + * perf_event_attr interface. + */ + if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { + perf_missing_features.clockid_wrong = true; + goto fallback_missing_features; + } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { + perf_missing_features.clockid = true; + goto fallback_missing_features; + } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { perf_missing_features.cloexec = true; goto fallback_missing_features; } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { @@ -2063,9 +2103,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(exclude_hv); if_print(exclude_idle); if_print(mmap); - if_print(mmap2); if_print(comm); - if_print(comm_exec); if_print(freq); if_print(inherit_stat); if_print(enable_on_exec); @@ -2076,10 +2114,17 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(sample_id_all); if_print(exclude_host); if_print(exclude_guest); + if_print(mmap2); + if_print(comm_exec); + if_print(use_clockid); if_print(__reserved_1); if_print(wakeup_events); if_print(bp_type); if_print(branch_sample_type); + if_print(sample_regs_user); + if_print(sample_stack_user); + if_print(clockid); + if_print(sample_regs_intr); } out: fputc('\n', fp); @@ -2158,6 +2203,12 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "The PMU counters are busy/taken by another profiler.\n" "We found oprofile daemon running, please stop it and try again."); break; + case EINVAL: + if (perf_missing_features.clockid) + return scnprintf(msg, size, "clockid feature not supported."); + if (perf_missing_features.clockid_wrong) + return scnprintf(msg, size, "wrong clockid (%d).", clockid); + break; default: break; } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index fb43215..de5f466 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1098,6 +1098,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) } fprintf(fp, " }"); } + if (evsel->attr.use_clockid) + fprintf(fp, ", clockid = %d", evsel->attr.clockid); + fputc('\n', fp); } -- cgit v1.1 From 2c5e8c52c6354f77c4019357be8231bcc34456f8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 7 Apr 2015 11:09:54 +0200 Subject: perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) Acked-by: Adrian Hunter Acked-by: Ingo Molnar Acked-by: Jiri Olsa Cc: "H. Peter Anvin" Cc: Andrew Morton Cc: David Ahern Cc: John Stultz Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 288 +++++++++++++++++++++-------------------------- tools/perf/util/evsel.h | 6 + tools/perf/util/header.c | 29 ++--- 3 files changed, 141 insertions(+), 182 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d190f99..33e3fd8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1011,70 +1011,126 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) return fd; } -#define __PRINT_ATTR(fmt, cast, field) \ - fprintf(fp, " %-19s "fmt"\n", #field, cast attr->field) - -#define PRINT_ATTR_U32(field) __PRINT_ATTR("%u" , , field) -#define PRINT_ATTR_X32(field) __PRINT_ATTR("%#x", , field) -#define PRINT_ATTR_U64(field) __PRINT_ATTR("%" PRIu64, (uint64_t), field) -#define PRINT_ATTR_X64(field) __PRINT_ATTR("%#"PRIx64, (uint64_t), field) - -#define PRINT_ATTR2N(name1, field1, name2, field2) \ - fprintf(fp, " %-19s %u %-19s %u\n", \ - name1, attr->field1, name2, attr->field2) - -#define PRINT_ATTR2(field1, field2) \ - PRINT_ATTR2N(#field1, field1, #field2, field2) - -static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) -{ - size_t ret = 0; - - ret += fprintf(fp, "%.60s\n", graph_dotted_line); - ret += fprintf(fp, "perf_event_attr:\n"); - - ret += PRINT_ATTR_U32(type); - ret += PRINT_ATTR_U32(size); - ret += PRINT_ATTR_X64(config); - ret += PRINT_ATTR_U64(sample_period); - ret += PRINT_ATTR_U64(sample_freq); - ret += PRINT_ATTR_X64(sample_type); - ret += PRINT_ATTR_X64(read_format); - - ret += PRINT_ATTR2(disabled, inherit); - ret += PRINT_ATTR2(pinned, exclusive); - ret += PRINT_ATTR2(exclude_user, exclude_kernel); - ret += PRINT_ATTR2(exclude_hv, exclude_idle); - ret += PRINT_ATTR2(mmap, comm); - ret += PRINT_ATTR2(freq, inherit_stat); - ret += PRINT_ATTR2(enable_on_exec, task); - ret += PRINT_ATTR2(watermark, precise_ip); - ret += PRINT_ATTR2(mmap_data, sample_id_all); - ret += PRINT_ATTR2(exclude_host, exclude_guest); - ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, - "excl.callchain_user", exclude_callchain_user); - ret += PRINT_ATTR2(mmap2, comm_exec); - ret += __PRINT_ATTR("%u",,use_clockid); - - - ret += PRINT_ATTR_U32(wakeup_events); - ret += PRINT_ATTR_U32(wakeup_watermark); - ret += PRINT_ATTR_X32(bp_type); - ret += PRINT_ATTR_X64(bp_addr); - ret += PRINT_ATTR_X64(config1); - ret += PRINT_ATTR_U64(bp_len); - ret += PRINT_ATTR_X64(config2); - ret += PRINT_ATTR_X64(branch_sample_type); - ret += PRINT_ATTR_X64(sample_regs_user); - ret += PRINT_ATTR_U32(sample_stack_user); - ret += PRINT_ATTR_U32(clockid); - ret += PRINT_ATTR_X64(sample_regs_intr); - - ret += fprintf(fp, "%.60s\n", graph_dotted_line); +struct bit_names { + int bit; + const char *name; +}; + +static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) +{ + bool first_bit = true; + int i = 0; + + do { + if (value & bits[i].bit) { + buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); +} + +static void __p_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), bit_name(REGS_INTR), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_read_format(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +#define BUF_SIZE 1024 + +#define p_hex(val) snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val)) +#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) +#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) +#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) +#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) + +#define PRINT_ATTRn(_n, _f, _p) \ +do { \ + if (attr->_f) { \ + _p(attr->_f); \ + ret += attr__fprintf(fp, _n, buf, priv);\ + } \ +} while (0) + +#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv) +{ + char buf[BUF_SIZE]; + int ret = 0; + + PRINT_ATTRf(type, p_unsigned); + PRINT_ATTRf(size, p_unsigned); + PRINT_ATTRf(config, p_hex); + PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); + PRINT_ATTRf(sample_type, p_sample_type); + PRINT_ATTRf(read_format, p_read_format); + + PRINT_ATTRf(disabled, p_unsigned); + PRINT_ATTRf(inherit, p_unsigned); + PRINT_ATTRf(pinned, p_unsigned); + PRINT_ATTRf(exclusive, p_unsigned); + PRINT_ATTRf(exclude_user, p_unsigned); + PRINT_ATTRf(exclude_kernel, p_unsigned); + PRINT_ATTRf(exclude_hv, p_unsigned); + PRINT_ATTRf(exclude_idle, p_unsigned); + PRINT_ATTRf(mmap, p_unsigned); + PRINT_ATTRf(comm, p_unsigned); + PRINT_ATTRf(freq, p_unsigned); + PRINT_ATTRf(inherit_stat, p_unsigned); + PRINT_ATTRf(enable_on_exec, p_unsigned); + PRINT_ATTRf(task, p_unsigned); + PRINT_ATTRf(watermark, p_unsigned); + PRINT_ATTRf(precise_ip, p_unsigned); + PRINT_ATTRf(mmap_data, p_unsigned); + PRINT_ATTRf(sample_id_all, p_unsigned); + PRINT_ATTRf(exclude_host, p_unsigned); + PRINT_ATTRf(exclude_guest, p_unsigned); + PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); + PRINT_ATTRf(exclude_callchain_user, p_unsigned); + PRINT_ATTRf(mmap2, p_unsigned); + PRINT_ATTRf(comm_exec, p_unsigned); + PRINT_ATTRf(use_clockid, p_unsigned); + + PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); + PRINT_ATTRf(bp_type, p_unsigned); + PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); + PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); + PRINT_ATTRf(sample_regs_user, p_hex); + PRINT_ATTRf(sample_stack_user, p_unsigned); + PRINT_ATTRf(clockid, p_signed); + PRINT_ATTRf(sample_regs_intr, p_hex); return ret; } +static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __attribute__((unused))) +{ + return fprintf(fp, " %-32s %s\n", name, val); +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1114,8 +1170,12 @@ retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; - if (verbose >= 2) - perf_event_attr__fprintf(&evsel->attr, stderr); + if (verbose >= 2) { + fprintf(stderr, "%.60s\n", graph_dotted_line); + fprintf(stderr, "perf_event_attr:\n"); + perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL); + fprintf(stderr, "%.60s\n", graph_dotted_line); + } for (cpu = 0; cpu < cpus->nr; cpu++) { @@ -1996,62 +2056,9 @@ static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) return ret; } -static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value) -{ - if (value == 0) - return 0; - - return comma_fprintf(fp, first, " %s: %" PRIu64, field, value); -} - -#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field) - -struct bit_names { - int bit; - const char *name; -}; - -static int bits__fprintf(FILE *fp, const char *field, u64 value, - struct bit_names *bits, bool *first) +static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) { - int i = 0, printed = comma_fprintf(fp, first, " %s: ", field); - bool first_bit = true; - - do { - if (value & bits[i].bit) { - printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name); - first_bit = false; - } - } while (bits[++i].name != NULL); - - return printed; -} - -static int sample_type__fprintf(FILE *fp, bool *first, u64 value) -{ -#define bit_name(n) { PERF_SAMPLE_##n, #n } - struct bit_names bits[] = { - bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), - bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), - bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), - bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), - bit_name(IDENTIFIER), bit_name(REGS_INTR), - { .name = NULL, } - }; -#undef bit_name - return bits__fprintf(fp, "sample_type", value, bits, first); -} - -static int read_format__fprintf(FILE *fp, bool *first, u64 value) -{ -#define bit_name(n) { PERF_FORMAT_##n, #n } - struct bit_names bits[] = { - bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), - bit_name(ID), bit_name(GROUP), - { .name = NULL, } - }; -#undef bit_name - return bits__fprintf(fp, "read_format", value, bits, first); + return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); } int perf_evsel__fprintf(struct perf_evsel *evsel, @@ -2080,52 +2087,13 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - if (details->verbose || details->freq) { + if (details->verbose) { + printed += perf_event_attr__fprintf(fp, &evsel->attr, + __print_attr__fprintf, &first); + } else if (details->freq) { printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, (u64)evsel->attr.sample_freq); } - - if (details->verbose) { - if_print(type); - if_print(config); - if_print(config1); - if_print(config2); - if_print(size); - printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type); - if (evsel->attr.read_format) - printed += read_format__fprintf(fp, &first, evsel->attr.read_format); - if_print(disabled); - if_print(inherit); - if_print(pinned); - if_print(exclusive); - if_print(exclude_user); - if_print(exclude_kernel); - if_print(exclude_hv); - if_print(exclude_idle); - if_print(mmap); - if_print(comm); - if_print(freq); - if_print(inherit_stat); - if_print(enable_on_exec); - if_print(task); - if_print(watermark); - if_print(precise_ip); - if_print(mmap_data); - if_print(sample_id_all); - if_print(exclude_host); - if_print(exclude_guest); - if_print(mmap2); - if_print(comm_exec); - if_print(use_clockid); - if_print(__reserved_1); - if_print(wakeup_events); - if_print(bp_type); - if_print(branch_sample_type); - if_print(sample_regs_user); - if_print(sample_stack_user); - if_print(clockid); - if_print(sample_regs_intr); - } out: fputc('\n', fp); return ++printed; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index c5a43d6..e486151 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -360,4 +360,10 @@ static inline bool has_branch_callstack(struct perf_evsel *evsel) { return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } + +typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv); + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index de5f466..fff3b2a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1055,6 +1055,12 @@ error: goto out; } +static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __attribute__((unused))) +{ + return fprintf(fp, ", %s = %s", name, val); +} + static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) { struct perf_evsel *evsel, *events = read_event_desc(ph, fd); @@ -1069,26 +1075,6 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) for (evsel = events; evsel->attr.size; evsel++) { fprintf(fp, "# event : name = %s, ", evsel->name); - fprintf(fp, "type = %d, config = 0x%"PRIx64 - ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64, - evsel->attr.type, - (u64)evsel->attr.config, - (u64)evsel->attr.config1, - (u64)evsel->attr.config2); - - fprintf(fp, ", excl_usr = %d, excl_kern = %d", - evsel->attr.exclude_user, - evsel->attr.exclude_kernel); - - fprintf(fp, ", excl_host = %d, excl_guest = %d", - evsel->attr.exclude_host, - evsel->attr.exclude_guest); - - fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip); - - fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2); - fprintf(fp, ", attr_mmap = %d", evsel->attr.mmap); - fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data); if (evsel->ids) { fprintf(fp, ", id = {"); for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { @@ -1098,9 +1084,8 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) } fprintf(fp, " }"); } - if (evsel->attr.use_clockid) - fprintf(fp, ", clockid = %d", evsel->attr.clockid); + perf_event_attr__fprintf(fp, &evsel->attr, __desc_attr__fprintf, NULL); fputc('\n', fp); } -- cgit v1.1 From f6c15621f04b97ce882c66e5055f0ac325fb8eb8 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 8 Apr 2015 02:14:34 +0000 Subject: perf probe: Fix ARM 32 building error Commit 9b118acae310f57baee770b5db402500d8695e50 ("perf probe: Fix to handle aliased symbols in glibc") uses an absolute format '%lx' to print u64 argument, which causes compiling error on ARM 32. This patch replaces it with PRIx64. Signed-off-by: Wang Nan Acked-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1428459274-138470-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4fd49f0..b788517 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -322,7 +322,8 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, ret = -ENOENT; goto out; } - pr_debug("Symbol %s address found : %lx\n", pp->function, address); + pr_debug("Symbol %s address found : %" PRIx64 "\n", + pp->function, address); ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, result); -- cgit v1.1 From a1e12da4796a4ddd0e911687a290eb396d1c64bf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 7 Apr 2015 23:25:14 +0200 Subject: perf tools: Add 'I' event modifier for exclude_idle bit Adding 'I' event modifier to have complete set of modifiers for perf_event_attr:exclude_* bits. Any event specified with 'I' modifier will have the perf_event_attr:exclude_idle bit set. $ perf record -e cycles:I -vv ls 2>&1 | grep exclude_idle exclude_hv 0 exclude_idle 1 Adding automated tests. Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: William Cohen Link: http://lkml.kernel.org/r/1428441919-23099-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 8 +++++++- tools/perf/util/parse-events.l | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index fe07573..be06553 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -709,6 +709,7 @@ struct event_modifier { int eh; int eH; int eG; + int eI; int precise; int exclude_GH; int sample_read; @@ -723,6 +724,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int eh = evsel ? evsel->attr.exclude_hv : 0; int eH = evsel ? evsel->attr.exclude_host : 0; int eG = evsel ? evsel->attr.exclude_guest : 0; + int eI = evsel ? evsel->attr.exclude_idle : 0; int precise = evsel ? evsel->attr.precise_ip : 0; int sample_read = 0; int pinned = evsel ? evsel->attr.pinned : 0; @@ -753,6 +755,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, if (!exclude_GH) exclude_GH = eG = eH = 1; eH = 0; + } else if (*str == 'I') { + eI = 1; } else if (*str == 'p') { precise++; /* use of precise requires exclude_guest */ @@ -786,6 +790,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->eh = eh; mod->eH = eH; mod->eG = eG; + mod->eI = eI; mod->precise = precise; mod->exclude_GH = exclude_GH; mod->sample_read = sample_read; @@ -803,7 +808,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHpppSD") - 1)) + if (strlen(str) > (sizeof("ukhGHpppSDI") - 1)) return -1; while (*p) { @@ -839,6 +844,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->attr.precise_ip = mod.precise; evsel->attr.exclude_host = mod.eH; evsel->attr.exclude_guest = mod.eG; + evsel->attr.exclude_idle = mod.eI; evsel->exclude_GH = mod.exclude_GH; evsel->sample_read = mod.sample_read; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 94eacb6..8895cf3 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -101,7 +101,7 @@ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* /* If you add a modifier you need to update check_modifier() */ -modifier_event [ukhpGHSD]+ +modifier_event [ukhpGHSDI]+ modifier_bp [rwx]{1,3} %% -- cgit v1.1 From 7764a385f60bd200304a33124bdb4e684caeabdf Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 9 Apr 2015 12:48:27 -0400 Subject: perf tools: Fix synthesizing fork_event.ppid for non-main thread Commit ca6c41c59b9 sets the ppid based on what is read from the /proc/pid/status file when synthesizing fork events. This is correct thing to do for new processes but not threads of a process. Fix ppid for threads to be the main thread when synthesizing fork events (ie., assume main thread spawned all sub-threads in a process). Reported-by: Arnaldo Carvalho de Melo Signed-off-by: David Ahern Tested-by: Arnaldo Carvalho de Melo Acked-by: Don Zickus Link: http://lkml.kernel.org/r/1428598107-178999-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 5516236..9d09851 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -183,8 +183,18 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, { memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - event->fork.ppid = ppid; - event->fork.ptid = ppid; + /* + * for main thread set parent to ppid from status file. For other + * threads set parent pid to main thread. ie., assume main thread + * spawns all threads in a process + */ + if (tgid == pid) { + event->fork.ppid = ppid; + event->fork.ptid = ppid; + } else { + event->fork.ppid = tgid; + event->fork.ptid = tgid; + } event->fork.pid = tgid; event->fork.tid = pid; event->fork.header.type = PERF_RECORD_FORK; -- cgit v1.1 From d998b732599b304c3865e8e5c7ba6250faba6589 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 8 Apr 2015 11:57:03 -0300 Subject: perf tools: Fix error path to do closedir() when synthesizing threads When traversing /proc to synthesize the PERF_RECORD_FORK et al events we were bailing out on errors without calling closedir(), fix it. Reported-by: David Ahern Cc: Adrian Hunter Cc: Borislav Petkov Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-vxtp593rfztgbi8noy0m967p@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9d09851..ff866c4 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -387,6 +387,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, DIR *tasks; struct dirent dirent, *next; pid_t tgid, ppid; + int rc = 0; /* special case: only send one comm event using passed in pid */ if (!full) { @@ -414,38 +415,38 @@ static int __event__synthesize_thread(union perf_event *comm_event, while (!readdir_r(tasks, &dirent, &next) && next) { char *end; - int rc = 0; pid_t _pid; _pid = strtol(dirent.d_name, &end, 10); if (*end) continue; + rc = -1; if (perf_event__prepare_comm(comm_event, _pid, machine, &tgid, &ppid) != 0) - return -1; + break; if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, ppid, process, machine) < 0) - return -1; + break; /* * Send the prepared comm event */ if (process(tool, comm_event, &synth_sample, machine) != 0) - return -1; + break; + rc = 0; if (_pid == pid) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); + if (rc) + break; } - - if (rc) - return rc; } closedir(tasks); - return 0; + return rc; } int perf_event__synthesize_thread_map(struct perf_tool *tool, -- cgit v1.1 From 1060ab857f64f33a9445881fd31fa91470aeb622 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 9 Apr 2015 16:15:46 -0400 Subject: perf tools: Fix cross-endian analysis Trying to analyze a big endian data file on little endian system fails with the error: 0xa9b40 [0x70]: failed to process type: 9 The problem is that header parsing is not done correctly because the file attributes are not swapped. Make it so. With this patch able to analyze a sparc64 data file on x86_64. Signed-off-by: David Ahern Acked-by: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1428610546-178789-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index fff3b2a..918fd8a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2504,8 +2504,11 @@ int perf_session__read_header(struct perf_session *session) if (read_attr(fd, header, &f_attr) < 0) goto out_errno; - if (header->needs_swap) + if (header->needs_swap) { + f_attr.ids.size = bswap_64(f_attr.ids.size); + f_attr.ids.offset = bswap_64(f_attr.ids.offset); perf_event__attr_swap(&f_attr.attr); + } tmp = lseek(fd, 0, SEEK_CUR); evsel = perf_evsel__new(&f_attr.attr); -- cgit v1.1 From 5e78c69b72276853ac64070a010e6df64723dba9 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Fri, 10 Apr 2015 17:35:00 +0800 Subject: perf buildid-list: Fix segfault when show DSOs with hits commit: f3b623b8490a ("perf tools: Reference count struct thread") appends every thread->node to dead_threads in machine__remove_thread() and list_del_init() this node in thread__put(). perf_event__exit_del_thread() releases thread wihout using machine__remove_thread(), and causes a NULL pointer crash when list_del_init(&thread->node) is called. Fix this by using machine_remove_thread() instead of using thread__put() directly. This problem can be reproduced as following: $ perf record ls $ perf buildid-list --with-hits [ 3874.195070] perf[1018]: segfault at 0 ip 00000000004b0b15 sp 00007ffc35b44780 error 6 in perf[400000+166000] Segmentation fault After this patch: $ perf record ls $ perf buildid-list --with-hits bc23e7c3281e542650ba4324421d6acf78f4c23e /proc/kcore 643324cb0e969f30c56d660f167f84a150845511 [vdso] 0000000000000000000000000000000000000000 /bin/busybox ... Signed-off-by: He Kuang Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1428658500-6483-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 8 ++------ tools/perf/util/machine.c | 4 +--- tools/perf/util/machine.h | 1 + 3 files changed, 4 insertions(+), 9 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index f7fb258..61867df 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -59,12 +59,8 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, event->fork.ppid, event->fork.ptid); - if (thread) { - rb_erase(&thread->rb_node, &machine->threads); - if (machine->last_match == thread) - thread__zput(machine->last_match); - thread__put(thread); - } + if (thread) + machine__remove_thread(machine, thread); return 0; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9c380a2..527e032 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -14,8 +14,6 @@ #include "unwind.h" #include "linux/hash.h" -static void machine__remove_thread(struct machine *machine, struct thread *th); - static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -1256,7 +1254,7 @@ out_problem: return 0; } -static void machine__remove_thread(struct machine *machine, struct thread *th) +void machine__remove_thread(struct machine *machine, struct thread *th) { if (machine->last_match == th) thread__zput(machine->last_match); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index e2faf3b..6d64ced 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -120,6 +120,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); +void machine__remove_thread(struct machine *machine, struct thread *th); struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); -- cgit v1.1 From 7afb3fab390871b1d20b1dbb94e03b8a3861cb0d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 1 Apr 2015 19:25:39 +0900 Subject: perf probe: Support multiple probes on different binaries Support multiple probes on different binaries with just one command. In the result, this example sets up the probes on icmp_rcv in kernel, on main and set_target in perf, and on pcspkr_event in pcspker.ko driver. ----- # perf probe -a icmp_rcv -x ./perf -a main -a set_target \ -m /lib/modules/4.0.0-rc5+/kernel/drivers/input/misc/pcspkr.ko \ -a pcspkr_event Added new event: probe:icmp_rcv (on icmp_rcv) You can now use it in all perf tools, such as: perf record -e probe:icmp_rcv -aR sleep 1 Added new event: probe_perf:main (on main in /home/mhiramat/ksrc/linux-3/tools/perf/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:main -aR sleep 1 Added new event: probe_perf:set_target (on set_target in /home/mhiramat/ksrc/linux-3/tools/perf/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:set_target -aR sleep 1 Added new event: probe:pcspkr_event (on pcspkr_event in pcspkr) You can now use it in all perf tools, such as: perf record -e probe:pcspkr_event -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150401102539.17137.46454.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 5 +++-- tools/perf/util/probe-event.h | 6 +++--- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b788517..30545ce 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1906,6 +1906,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev) free(pev->event); free(pev->group); + free(pev->target); clear_perf_probe_point(&pev->point); for (i = 0; i < pev->nargs; i++) { @@ -2654,7 +2655,7 @@ struct __event_package { }; int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, - int max_tevs, const char *target, bool force_add) + int max_tevs, bool force_add) { int i, j, ret; struct __event_package *pkgs; @@ -2678,7 +2679,7 @@ 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, - target); + pkgs[i].pev->target); if (ret < 0) goto end; pkgs[i].ntevs = ret; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e01e994..d6b7834 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -73,7 +73,8 @@ struct perf_probe_event { char *group; /* Group name */ struct perf_probe_point point; /* Probe point */ int nargs; /* Number of arguments */ - bool uprobes; + bool uprobes; /* Uprobe event flag */ + char *target; /* Target binary */ struct perf_probe_arg *args; /* Arguments */ }; @@ -124,8 +125,7 @@ extern int line_range__init(struct line_range *lr); extern const char *kernel_get_module_path(const char *module); extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, - int max_probe_points, const char *module, - bool force_add); + int max_probe_points, bool force_add); extern int del_perf_probe_events(struct strlist *dellist); extern int show_perf_probe_events(void); extern int show_line_range(struct line_range *lr, const char *module, -- cgit v1.1 From 7b8283b56d9fb36106ff1c459dfd399a20bd374d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 7 Apr 2015 09:20:37 -0600 Subject: perf evlist: Fix type for references to data_head/tail The data_head and data_tail fields are defined as __u64 in linux/perf_event.h, but perf userspace uses int and unsigned int. Convert all references to u64 for consistency. Signed-off-by: David Ahern Acked-by: Peter Zijlstra Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1428420037-26599-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 6 +++--- tools/perf/util/evlist.h | 9 ++++----- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 76ef7ee..080be93 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -634,8 +634,8 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; - unsigned int head = perf_mmap__read_head(md); - unsigned int old = md->prev; + u64 head = perf_mmap__read_head(md); + u64 old = md->prev; unsigned char *data = md->base + page_size; union perf_event *event = NULL; @@ -716,7 +716,7 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) struct perf_mmap *md = &evlist->mmap[idx]; if (!evlist->overwrite) { - unsigned int old = md->prev; + u64 old = md->prev; perf_mmap__write_tail(md, old); } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index fb19c47..b5cce95 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -27,7 +27,7 @@ struct perf_mmap { void *base; int mask; int refcnt; - unsigned int prev; + u64 prev; char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); }; @@ -189,16 +189,15 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); -static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) +static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; - int head = ACCESS_ONCE(pc->data_head); + u64 head = ACCESS_ONCE(pc->data_head); rmb(); return head; } -static inline void perf_mmap__write_tail(struct perf_mmap *md, - unsigned long tail) +static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) { struct perf_event_mmap_page *pc = md->base; -- cgit v1.1