From f4be904d2fa7c65e230ed4b1008ebdf5f4053ac3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sun, 22 Sep 2013 13:22:09 +0300 Subject: perf machine: Use snprintf instead of sprintf To avoid buffer overruns. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1379845338-29637-2-git-send-email-adrian.hunter@intel.com [ Split from aa7fe3b ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 6188d2876a7..ddf917b787f 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -785,10 +785,10 @@ static int machine__create_modules(struct machine *machine) const char *modules; char path[PATH_MAX]; - if (machine__is_default_guest(machine)) + if (machine__is_default_guest(machine)) { modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", machine->root_dir); + } else { + snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir); modules = path; } -- cgit v1.2.3-70-g09d2 From 8fb598e5a3b0ac213012e8461a309843ba0f2e74 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 28 Sep 2013 13:13:00 -0600 Subject: perf trace: Fix comm resolution when reading events from file Task comm's are getting lost when processing events from a file. The problem is that the trace struct used by the live processing has its host machine and the perf-session used for file based processing has its host machine. Fix by having both references point to the same machine. Before: 0.030 ( 0.001 ms): :27743/27743 brk( ... 0.057 ( 0.004 ms): :27743/27743 mmap(len: 4096, prot: READ|WRITE, flags: ... 0.075 ( 0.006 ms): :27743/27743 access(filename: 0x7f3809fbce00, mode: R ... 0.091 ( 0.005 ms): :27743/27743 open(filename: 0x7f3809fba14c, flags: CLOEXEC ... ... After: 0.030 ( 0.001 ms): make/27743 brk( ... 0.057 ( 0.004 ms): make/27743 mmap(len: 4096, prot: READ|WRITE, flags: ... 0.075 ( 0.006 ms): make/27743 access(filename: 0x7f3809fbce00, mode: R ... 0.091 ( 0.005 ms): make/27743 open(filename: 0x7f3809fba14c, flags: CLOEXEC ... ... Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1380395584-9025-4-git-send-email-dsahern@gmail.com [ Moved creation of new host machine to a separate constructor: machine__new_host() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 25 +++++++++++++------------ tools/perf/util/machine.c | 17 +++++++++++++++++ tools/perf/util/machine.h | 1 + 3 files changed, 31 insertions(+), 12 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index fcc157fce6c..5776b5f829e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -906,7 +906,7 @@ struct trace { struct syscall *table; } syscalls; struct perf_record_opts opts; - struct machine host; + struct machine *host; u64 base_time; bool full_time; FILE *output; @@ -1083,16 +1083,17 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) if (err) return err; - machine__init(&trace->host, "", HOST_KERNEL_ID); - machine__create_kernel_maps(&trace->host); + trace->host = machine__new_host(); + if (trace->host == NULL) + return -ENOMEM; if (perf_target__has_task(&trace->opts.target)) { err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads, trace__tool_process, - &trace->host); + trace->host); } else { err = perf_event__synthesize_threads(&trace->tool, trace__tool_process, - &trace->host); + trace->host); } if (err) @@ -1304,8 +1305,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (sc->filtered) return 0; - thread = machine__findnew_thread(&trace->host, sample->pid, - sample->tid); + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) return -1; @@ -1357,8 +1357,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (sc->filtered) return 0; - thread = machine__findnew_thread(&trace->host, sample->pid, - sample->tid); + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) return -1; @@ -1414,7 +1413,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs { u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); double runtime_ms = (double)runtime / NSEC_PER_MSEC; - struct thread *thread = machine__findnew_thread(&trace->host, + struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); struct thread_trace *ttrace = thread__trace(thread, trace->output); @@ -1597,7 +1596,7 @@ again: trace->base_time = sample.time; if (type != PERF_RECORD_SAMPLE) { - trace__process_event(trace, &trace->host, event); + trace__process_event(trace, trace->host, event); continue; } @@ -1681,6 +1680,8 @@ static int trace__replay(struct trace *trace) if (session == NULL) return -ENOMEM; + trace->host = &session->machines.host; + err = perf_session__set_tracepoints_handlers(session, handlers); if (err) goto out; @@ -1728,7 +1729,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) size_t printed = trace__fprintf_threads_header(fp); struct rb_node *nd; - for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) { + for (nd = rb_first(&trace->host->threads); nd; nd = rb_next(nd)) { struct thread *thread = rb_entry(nd, struct thread, rb_node); struct thread_trace *ttrace = thread->priv; const char *color; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index ddf917b787f..fc14f9bf82c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -46,6 +46,23 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) return 0; } +struct machine *machine__new_host(void) +{ + struct machine *machine = malloc(sizeof(*machine)); + + if (machine != NULL) { + machine__init(machine, "", HOST_KERNEL_ID); + + if (machine__create_kernel_maps(machine) < 0) + goto out_delete; + } + + return machine; +out_delete: + free(machine); + return NULL; +} + static void dsos__delete(struct list_head *dsos) { struct dso *pos, *n; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 58a6be1fc73..5150d5e1db6 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -74,6 +74,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_symbol_filter(struct machines *machines, symbol_filter_t symbol_filter); +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); -- cgit v1.2.3-70-g09d2 From 35feee19f9fda7447f51073b5be3f6d082b508f5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 28 Sep 2013 13:12:58 -0600 Subject: perf machine: Add method to loop over threads and invoke handler Loop over all threads within a machine - including threads moved to the dead threads list -- and invoked a function. This allows commands to run some specific function on each thread (eg., dump statistics) yet hides how the threads are maintained within the machine. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1380395584-9025-2-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 23 +++++++++++++++++++++++ tools/perf/util/machine.h | 4 ++++ 2 files changed, 27 insertions(+) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index fc14f9bf82c..901397ae82b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1393,3 +1393,26 @@ int machine__resolve_callchain(struct machine *machine, sample); } + +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv) +{ + struct rb_node *nd; + struct thread *thread; + int rc = 0; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + thread = rb_entry(nd, struct thread, rb_node); + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + + list_for_each_entry(thread, &machine->dead_threads, node) { + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + return rc; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 5150d5e1db6..d44c09bdc45 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -166,4 +166,8 @@ void machines__destroy_kernel_maps(struct machines *machines); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv); + #endif /* __PERF_MACHINE_H */ -- cgit v1.2.3-70-g09d2 From 316d70d6dbde540b275289563cbddd9f0c903fc6 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 8 Oct 2013 11:45:48 +0300 Subject: perf symbols: Make a separate function to parse /proc/modules Make a separate function to parse /proc/modules so that it can be reused. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1381221956-16699-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 67 +++++++++++++---------------------------------- tools/perf/util/symbol.c | 58 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/symbol.h | 3 +++ 3 files changed, 79 insertions(+), 49 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 901397ae82b..6b861aefd99 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -793,12 +793,22 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); } -static int machine__create_modules(struct machine *machine) +static int machine__create_module(void *arg, const char *name, u64 start) { - char *line = NULL; - size_t n; - FILE *file; + struct machine *machine = arg; struct map *map; + + map = machine__new_module(machine, start, name); + if (map == NULL) + return -1; + + dso__kernel_module_get_build_id(map->dso, machine->root_dir); + + return 0; +} + +static int machine__create_modules(struct machine *machine) +{ const char *modules; char path[PATH_MAX]; @@ -812,56 +822,15 @@ static int machine__create_modules(struct machine *machine) if (symbol__restricted_filename(modules, "/proc/modules")) return -1; - file = fopen(modules, "r"); - if (file == NULL) + if (modules__parse(modules, machine, machine__create_module)) return -1; - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - goto out_failure; - - line[--line_len] = '\0'; /* \n */ - - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); - - sep = strchr(line, ' '); - if (sep == NULL) - continue; - - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(machine, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); - } + if (!machine__set_modules_path(machine)) + return 0; - free(line); - fclose(file); + pr_debug("Problems setting modules path maps, continuing anyway...\n"); - if (machine__set_modules_path(machine) < 0) { - pr_debug("Problems setting modules path maps, continuing anyway...\n"); - } return 0; - -out_delete_line: - free(line); -out_failure: - return -1; } int machine__create_kernel_maps(struct machine *machine) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 48c38791d61..5fd95135e83 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -500,6 +500,64 @@ out_failure: return -1; } +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)) +{ + char *line = NULL; + size_t n; + FILE *file; + int err = 0; + + file = fopen(filename, "r"); + if (file == NULL) + return -1; + + while (1) { + char name[PATH_MAX]; + u64 start; + char *sep; + ssize_t line_len; + + line_len = getline(&line, &n, file); + if (line_len < 0) { + if (feof(file)) + break; + err = -1; + goto out; + } + + if (!line) { + err = -1; + goto out; + } + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + scnprintf(name, sizeof(name), "[%s]", line); + + err = process_module(arg, name, start); + if (err) + break; + } +out: + free(line); + fclose(file); + return err; +} + struct process_kallsyms_args { struct map *map; struct dso *dso; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 9b8b213a62c..2d3eb43ab9f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -223,6 +223,9 @@ int sysfs__read_build_id(const char *filename, void *bf, size_t size); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); -- cgit v1.2.3-70-g09d2 From 91e95617429cb272fd908b1928a1915b37b9655f Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 18 Oct 2013 10:38:48 -0400 Subject: perf report: Add --max-stack option to limit callchain stack scan When callgraph data was included in the perf data file, it may take a long time to scan all those data and merge them together especially if the stored callchains are long and the perf data file itself is large, like a Gbyte or so. The callchain stack is currently limited to PERF_MAX_STACK_DEPTH (127). This is a large value. Usually the callgraph data that developers are most interested in are the first few levels, the rests are usually not looked at. This patch adds a new --max-stack option to perf-report to limit the depth of callchain stack data to look at to reduce the time it takes for perf-report to finish its processing. It trades the presence of trailing stack information with faster speed. The following table shows the elapsed time of doing perf-report on a perf.data file of size 985,531,828 bytes. --max_stack Elapsed Time Output data size ----------- ------------ ---------------- not set 88.0s 124,422,651 64 87.5s 116,303,213 32 87.2s 112,023,804 16 86.6s 94,326,380 8 59.9s 33,697,248 4 40.7s 10,116,637 -g none 27.1s 2,555,810 Signed-off-by: Waiman Long Acked-by: David Ahern Cc: Adrian Hunter Cc: Aswin Chandramouleeswaran Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Scott J Norton Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1382107129-2010-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 8 ++++++++ tools/perf/builtin-report.c | 22 +++++++++++++++++----- tools/perf/builtin-top.c | 3 ++- tools/perf/util/machine.c | 14 +++++++++----- tools/perf/util/machine.h | 3 ++- tools/perf/util/session.c | 3 ++- 6 files changed, 40 insertions(+), 13 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index be5ad87b6c3..10a27987125 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -141,6 +141,14 @@ OPTIONS Default: fractal,0.5,callee,function. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + + Default: 127 + -G:: --inverted:: alias for inverted caller based call graph. diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index fa68a36bc46..81addcabb35 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -49,6 +49,7 @@ struct perf_report { bool show_threads; bool inverted_callchain; bool mem_mode; + int max_stack; struct perf_read_values show_threads_values; const char *pretty_printing_style; const char *cpu_list; @@ -90,7 +91,8 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent, al); + sample, &parent, al, + rep->max_stack); if (err) return err; } @@ -181,7 +183,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent, al); + sample, &parent, al, + rep->max_stack); if (err) return err; } @@ -244,18 +247,21 @@ out: return err; } -static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, +static int perf_evsel__add_hist_entry(struct perf_tool *tool, + struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample, struct machine *machine) { + struct perf_report *rep = container_of(tool, struct perf_report, tool); struct symbol *parent = NULL; int err = 0; struct hist_entry *he; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent, al); + sample, &parent, al, + rep->max_stack); if (err) return err; } @@ -332,7 +338,8 @@ static int process_sample_event(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine); + ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample, + machine); if (ret < 0) pr_debug("problem incrementing symbol period, skipping event\n"); } @@ -772,6 +779,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_samples = true, .ordering_requires_timestamps = true, }, + .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", }; const struct option options[] = { @@ -812,6 +820,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order", "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). " "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt), + OPT_INTEGER(0, "max-stack", &report.max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('G', "inverted", &report.inverted_callchain, "alias for inverted call graph"), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d934f707ee7..112cb7d68e6 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -770,7 +770,8 @@ static void perf_event__process_sample(struct perf_tool *tool, sample->callchain) { err = machine__resolve_callchain(machine, evsel, al.thread, sample, - &parent, &al); + &parent, &al, + PERF_MAX_STACK_DEPTH); if (err) return; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 6b861aefd99..ea93425cce9 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1253,10 +1253,12 @@ static int machine__resolve_callchain_sample(struct machine *machine, struct thread *thread, struct ip_callchain *chain, struct symbol **parent, - struct addr_location *root_al) + struct addr_location *root_al, + int max_stack) { u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; + int chain_nr = min(max_stack, (int)chain->nr); + int i; int err; callchain_cursor_reset(&callchain_cursor); @@ -1266,7 +1268,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, return 0; } - for (i = 0; i < chain->nr; i++) { + for (i = 0; i < chain_nr; i++) { u64 ip; struct addr_location al; @@ -1338,12 +1340,14 @@ int machine__resolve_callchain(struct machine *machine, struct thread *thread, struct perf_sample *sample, struct symbol **parent, - struct addr_location *root_al) + struct addr_location *root_al, + int max_stack) { int ret; ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent, root_al); + sample->callchain, parent, + root_al, max_stack); if (ret) return ret; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index d44c09bdc45..4c1f5d567f5 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -92,7 +92,8 @@ int machine__resolve_callchain(struct machine *machine, struct thread *thread, struct perf_sample *sample, struct symbol **parent, - struct addr_location *root_al); + struct addr_location *root_al, + int max_stack); /* * Default guest kernel is defined by parameter --guestkallsyms diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 19fc71678c8..854c5aa4db0 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1512,7 +1512,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, if (symbol_conf.use_callchain && sample->callchain) { if (machine__resolve_callchain(machine, evsel, al.thread, - sample, NULL, NULL) != 0) { + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; -- cgit v1.2.3-70-g09d2 From 162f0befda3becc2cc9f44075fccc030e55baec1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Sep 2013 16:18:24 +0200 Subject: perf tools: Add time argument on COMM setting This way we can later delimit a lifecycle for the COMM and map a hist to a precise COMM:timeslice couple. PERF_RECORD_COMM and PERF_RECORD_FORK events that don't have PERF_SAMPLE_TIME samples can only send 0 value as a timestamp and thus should overwrite any previous COMM on a given thread because there is no sensible way to keep track of all the comms lifecycles in a thread without time informations. Signed-off-by: Frederic Weisbecker Tested-by: Jiri Olsa Cc: Jiri Olsa Cc: David Ahern Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-6tyow99vgmmtt9qwr2u2lqd7@git.kernel.org [ Made it cope with PERF_RECORD_MMAP2 ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 2 +- tools/perf/builtin-trace.c | 12 ++++++------ tools/perf/tests/code-reading.c | 2 +- tools/perf/tests/hists_link.c | 4 ++-- tools/perf/util/event.c | 28 ++++++++++++++-------------- tools/perf/util/machine.c | 39 ++++++++++++++++++++++----------------- tools/perf/util/machine.h | 21 ++++++++++++++------- tools/perf/util/session.c | 2 +- tools/perf/util/thread.c | 6 ++++-- tools/perf/util/thread.h | 4 ++-- 10 files changed, 67 insertions(+), 53 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a6ea956a533..21db76d71dd 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -856,7 +856,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) &sample, machine); } else if (event->header.type < PERF_RECORD_MAX) { hists__inc_nr_events(&evsel->hists, event->header.type); - machine__process_event(machine, event); + machine__process_event(machine, event, &sample); } else ++session->stats.nr_unknown_events; next_event: diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dc3da654ff1..95d639212d9 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1122,7 +1122,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre } static int trace__process_event(struct trace *trace, struct machine *machine, - union perf_event *event) + union perf_event *event, struct perf_sample *sample) { int ret = 0; @@ -1130,9 +1130,9 @@ static int trace__process_event(struct trace *trace, struct machine *machine, case PERF_RECORD_LOST: color_fprintf(trace->output, PERF_COLOR_RED, "LOST %" PRIu64 " events!\n", event->lost.lost); - ret = machine__process_lost_event(machine, event); + ret = machine__process_lost_event(machine, event, sample); default: - ret = machine__process_event(machine, event); + ret = machine__process_event(machine, event, sample); break; } @@ -1141,11 +1141,11 @@ static int trace__process_event(struct trace *trace, struct machine *machine, static int trace__tool_process(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { struct trace *trace = container_of(tool, struct trace, tool); - return trace__process_event(trace, machine, event); + return trace__process_event(trace, machine, event, sample); } static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) @@ -1751,7 +1751,7 @@ again: trace->base_time = sample.time; if (type != PERF_RECORD_SAMPLE) { - trace__process_event(trace, trace->host, event); + trace__process_event(trace, trace->host, event, &sample); continue; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index e3fedfa2906..49ccc3b2995 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -276,7 +276,7 @@ static int process_event(struct machine *machine, struct perf_evlist *evlist, return process_sample_event(machine, evlist, event, state); if (event->header.type < PERF_RECORD_MAX) - return machine__process_event(machine, event); + return machine__process_event(machine, event, NULL); return 0; } diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 4475b0ff76e..6c337e65354 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -93,7 +93,7 @@ static struct machine *setup_fake_machine(struct machines *machines) if (thread == NULL) goto out; - thread__set_comm(thread, fake_threads[i].comm); + thread__set_comm(thread, fake_threads[i].comm, 0); } for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { @@ -110,7 +110,7 @@ static struct machine *setup_fake_machine(struct machines *machines) strcpy(fake_mmap_event.mmap.filename, fake_mmap_info[i].filename); - machine__process_mmap_event(machine, &fake_mmap_event); + machine__process_mmap_event(machine, &fake_mmap_event, NULL); } for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 7a2842ed53f..c26b3539187 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -512,18 +512,18 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_comm_event(machine, event); + return machine__process_comm_event(machine, event, sample); } int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_lost_event(machine, event); + return machine__process_lost_event(machine, event, sample); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) @@ -546,18 +546,18 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_mmap_event(machine, event); + return machine__process_mmap_event(machine, event, sample); } int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_mmap2_event(machine, event); + return machine__process_mmap2_event(machine, event, sample); } size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) @@ -569,18 +569,18 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) int perf_event__process_fork(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_fork_event(machine, event); + return machine__process_fork_event(machine, event, sample); } int perf_event__process_exit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_exit_event(machine, event); + return machine__process_exit_event(machine, event, sample); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -611,10 +611,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) int perf_event__process(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_event(machine, event); + return machine__process_event(machine, event, sample); } void thread__find_addr_map(struct thread *self, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index ea93425cce9..ce034c183a7 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -40,7 +40,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) return -ENOMEM; snprintf(comm, sizeof(comm), "[guest/%d]", pid); - thread__set_comm(thread, comm); + thread__set_comm(thread, comm, 0); } return 0; @@ -331,7 +331,8 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid) return __machine__findnew_thread(machine, 0, tid, false); } -int machine__process_comm_event(struct machine *machine, union perf_event *event) +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { struct thread *thread = machine__findnew_thread(machine, event->comm.pid, @@ -340,7 +341,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event if (dump_trace) perf_event__fprintf_comm(event, stdout); - if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { + if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -349,7 +350,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event } int machine__process_lost_event(struct machine *machine __maybe_unused, - union perf_event *event) + union perf_event *event, struct perf_sample *sample __maybe_unused) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", event->lost.id, event->lost.lost); @@ -984,7 +985,8 @@ out_problem: } int machine__process_mmap2_event(struct machine *machine, - union perf_event *event) + union perf_event *event, + struct perf_sample *sample __maybe_unused) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread; @@ -1031,7 +1033,8 @@ out_problem: return 0; } -int machine__process_mmap_event(struct machine *machine, union perf_event *event) +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread; @@ -1088,7 +1091,8 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) list_add_tail(&th->node, &machine->dead_threads); } -int machine__process_fork_event(struct machine *machine, union perf_event *event) +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { struct thread *thread = machine__find_thread(machine, event->fork.tid); struct thread *parent = machine__findnew_thread(machine, @@ -1105,7 +1109,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event perf_event__fprintf_task(event, stdout); if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { + thread__fork(thread, parent, sample->time) < 0) { dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); return -1; } @@ -1113,8 +1117,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event return 0; } -int machine__process_exit_event(struct machine *machine __maybe_unused, - union perf_event *event) +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { struct thread *thread = machine__find_thread(machine, event->fork.tid); @@ -1127,23 +1131,24 @@ int machine__process_exit_event(struct machine *machine __maybe_unused, return 0; } -int machine__process_event(struct machine *machine, union perf_event *event) +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { int ret; switch (event->header.type) { case PERF_RECORD_COMM: - ret = machine__process_comm_event(machine, event); break; + ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: - ret = machine__process_mmap_event(machine, event); break; + ret = machine__process_mmap_event(machine, event, sample); break; case PERF_RECORD_MMAP2: - ret = machine__process_mmap2_event(machine, event); break; + ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: - ret = machine__process_fork_event(machine, event); break; + ret = machine__process_fork_event(machine, event, sample); break; case PERF_RECORD_EXIT: - ret = machine__process_exit_event(machine, event); break; + ret = machine__process_exit_event(machine, event, sample); break; case PERF_RECORD_LOST: - ret = machine__process_lost_event(machine, event); break; + ret = machine__process_lost_event(machine, event, sample); break; default: ret = -1; break; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 4c1f5d567f5..2389ba81faf 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -40,13 +40,20 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) struct thread *machine__find_thread(struct machine *machine, pid_t tid); -int machine__process_comm_event(struct machine *machine, union perf_event *event); -int machine__process_exit_event(struct machine *machine, union perf_event *event); -int machine__process_fork_event(struct machine *machine, union perf_event *event); -int machine__process_lost_event(struct machine *machine, union perf_event *event); -int machine__process_mmap_event(struct machine *machine, union perf_event *event); -int machine__process_mmap2_event(struct machine *machine, union perf_event *event); -int machine__process_event(struct machine *machine, union perf_event *event); +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_lost_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap2_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); typedef void (*machine__process_t)(struct machine *machine, void *data); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 4ba7b548e05..3c1b30103d5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1100,7 +1100,7 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se { struct thread *thread = perf_session__findnew(self, 0); - if (thread == NULL || thread__set_comm(thread, "swapper")) { + if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 56760079565..0ea73fe383f 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -31,7 +31,8 @@ void thread__delete(struct thread *thread) free(thread); } -int thread__set_comm(struct thread *thread, const char *comm) +int thread__set_comm(struct thread *thread, const char *comm, + u64 timestamp __maybe_unused) { int err; @@ -73,7 +74,8 @@ void thread__insert_map(struct thread *thread, struct map *map) map_groups__insert(&thread->mg, map); } -int thread__fork(struct thread *thread, struct thread *parent) +int thread__fork(struct thread *thread, struct thread *parent, + u64 timestamp __maybe_unused) { int i; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 6561ad21d9a..4e9724270a6 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -33,11 +33,11 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } -int thread__set_comm(struct thread *self, const char *comm); +int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp); int thread__comm_len(struct thread *self); const char *thread__comm_str(const struct thread *thread); void thread__insert_map(struct thread *self, struct map *map); -int thread__fork(struct thread *self, struct thread *parent); +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); static inline struct map *thread__find_map(struct thread *self, -- cgit v1.2.3-70-g09d2