From 4e319027a7aee58ce8d409f5597b418f08307841 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 11 Jun 2013 17:29:18 +0200 Subject: perf tools: Use default include path notation for libtraceevent headers Header files of libtraceevent or no longer local headers. Thus, use default path notation for them. Also removing extra traceevent include path and instead handle this similar to liblk. Signed-off-by: Robert Richter Signed-off-by: Robert Richter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Robert Richter Link: http://lkml.kernel.org/r/1370964558-8599-1-git-send-email-rric@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index cf1fe01b7e8..ad47fb9d020 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,4 +1,5 @@ #include +#include #include #include @@ -12,7 +13,6 @@ #include "sort.h" #include "util.h" #include "cpumap.h" -#include "event-parse.h" #include "perf_regs.h" #include "vdso.h" -- cgit v1.2.3-70-g09d2 From 47c3d1091cb68e727b840efd6fa3709d5b1ddfc2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 4 Jul 2013 16:20:21 +0300 Subject: perf tools: Fix missing tool parameter The 'inject' command expects to get a reference to 'struct perf_inject' from its 'tool' member. For that to work, 'tool' needs to be a parameter of all tool callbacks. Make it so. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1372944040-32690-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 26 +++++++++++--------------- tools/perf/util/header.c | 6 ++++-- tools/perf/util/header.h | 6 ++++-- tools/perf/util/session.c | 11 +++++++---- tools/perf/util/tool.h | 9 ++++----- 5 files changed, 30 insertions(+), 28 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index f299ddf2996..c943513d06b 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -73,22 +73,17 @@ static int perf_event__repipe_event_type_synth(struct perf_tool *tool, return perf_event__repipe_synth(tool, event); } -static int perf_event__repipe_tracing_data_synth(union perf_event *event, - struct perf_session *session - __maybe_unused) -{ - return perf_event__repipe_synth(NULL, event); -} - -static int perf_event__repipe_attr(union perf_event *event, - struct perf_evlist **pevlist __maybe_unused) +static int perf_event__repipe_attr(struct perf_tool *tool, + union perf_event *event, + struct perf_evlist **pevlist) { int ret; - ret = perf_event__process_attr(event, pevlist); + + ret = perf_event__process_attr(tool, event, pevlist); if (ret) return ret; - return perf_event__repipe_synth(NULL, event); + return perf_event__repipe_synth(tool, event); } static int perf_event__repipe(struct perf_tool *tool, @@ -147,13 +142,14 @@ static int perf_event__repipe_fork(struct perf_tool *tool, return err; } -static int perf_event__repipe_tracing_data(union perf_event *event, +static int perf_event__repipe_tracing_data(struct perf_tool *tool, + union perf_event *event, struct perf_session *session) { int err; - perf_event__repipe_synth(NULL, event); - err = perf_event__process_tracing_data(event, session); + perf_event__repipe_synth(tool, event); + err = perf_event__process_tracing_data(tool, event, session); return err; } @@ -407,7 +403,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .unthrottle = perf_event__repipe, .attr = perf_event__repipe_attr, .event_type = perf_event__repipe_event_type_synth, - .tracing_data = perf_event__repipe_tracing_data_synth, + .tracing_data = perf_event__repipe_op2_synth, .build_id = perf_event__repipe_op2_synth, }, .input_name = "-", diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a4dafbee251..d12d79cf8d3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2922,7 +2922,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, return err; } -int perf_event__process_attr(union perf_event *event, +int perf_event__process_attr(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_evlist **pevlist) { u32 i, ids, n_ids; @@ -3065,7 +3066,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, return aligned_size; } -int perf_event__process_tracing_data(union perf_event *event, +int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_session *session) { ssize_t size_read, padding, size = event->tracing_data.size; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 16a3e83c584..2d1ca7d3ca9 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -130,7 +130,8 @@ int perf_event__synthesize_attr(struct perf_tool *tool, int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process); -int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist); +int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, + struct perf_evlist **pevlist); int perf_event__synthesize_event_type(struct perf_tool *tool, u64 event_id, char *name, @@ -145,7 +146,8 @@ int perf_event__process_event_type(struct perf_tool *tool, int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process); -int perf_event__process_tracing_data(union perf_event *event, +int perf_event__process_tracing_data(struct perf_tool *tool, + union perf_event *event, struct perf_session *session); int perf_event__synthesize_build_id(struct perf_tool *tool, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ad47fb9d020..6b71b88f95f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -193,7 +193,9 @@ void perf_session__delete(struct perf_session *self) vdso__exit(); } -static int process_event_synth_tracing_data_stub(union perf_event *event +static int process_event_synth_tracing_data_stub(struct perf_tool *tool + __maybe_unused, + union perf_event *event __maybe_unused, struct perf_session *session __maybe_unused) @@ -202,7 +204,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event return 0; } -static int process_event_synth_attr_stub(union perf_event *event __maybe_unused, +static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_evlist **pevlist __maybe_unused) { @@ -921,7 +924,7 @@ static int perf_session__process_user_event(struct perf_session *session, union /* These events are processed right away */ switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - err = tool->attr(event, &session->evlist); + err = tool->attr(tool, event, &session->evlist); if (err == 0) perf_session__set_id_hdr_size(session); return err; @@ -930,7 +933,7 @@ static int perf_session__process_user_event(struct perf_session *session, union case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(session->fd, file_offset, SEEK_SET); - return tool->tracing_data(event, session); + return tool->tracing_data(tool, event, session); case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index b0e1aadba8d..88f8cbdb8a3 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -18,12 +18,11 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -typedef int (*event_attr_op)(union perf_event *event, +typedef int (*event_attr_op)(struct perf_tool *tool, + union perf_event *event, struct perf_evlist **pevlist); -typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event); -typedef int (*event_synth_op)(union perf_event *event, - struct perf_session *session); +typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event); typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); @@ -39,7 +38,7 @@ struct perf_tool { throttle, unthrottle; event_attr_op attr; - event_synth_op tracing_data; + event_op2 tracing_data; event_simple_op event_type; event_op2 finished_round, build_id; -- cgit v1.2.3-70-g09d2 From 27389d7823f573be8eaff32fb4abe564e181eb71 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 4 Jul 2013 16:20:27 +0300 Subject: perf tools: Validate perf event header size The 'size' variable includes the header so must be at least 'sizeof(struct perf_event_header)'. Error out immediately if that is not the case. Also don't byte-swap the header until it is actually "fetched" from the mmap region. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1372944040-32690-9-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 6b71b88f95f..951a1cfb317 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1094,8 +1094,10 @@ more: perf_event_header__bswap(&event->header); size = event->header.size; - if (size == 0) - size = 8; + if (size < sizeof(struct perf_event_header)) { + pr_err("bad event header size\n"); + goto out_err; + } if (size > cur_size) { void *new = realloc(buf, size); @@ -1164,8 +1166,12 @@ fetch_mmaped_event(struct perf_session *session, if (session->header.needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) + if (head + event->header.size > mmap_size) { + /* We're not fetching the event so swap back again */ + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); return NULL; + } return event; } @@ -1245,7 +1251,7 @@ more: size = event->header.size; - if (size == 0 || + if (size < sizeof(struct perf_event_header) || perf_session__process_event(session, event, tool, file_pos) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, -- cgit v1.2.3-70-g09d2 From b21484f1a1f300d422cfe5d4f8f50015e22cea24 Mon Sep 17 00:00:00 2001 From: Greg Price Date: Thu, 6 Dec 2012 21:48:05 -0800 Subject: perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price Tested-by: Jiri Olsa Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 5 +++++ tools/perf/Documentation/perf-top.txt | 5 +++++ tools/perf/builtin-report.c | 27 ++++++++++++++++++++++++--- tools/perf/builtin-top.c | 6 ++++-- tools/perf/util/machine.c | 24 +++++++++++++++--------- tools/perf/util/machine.h | 4 +++- tools/perf/util/session.c | 3 +-- tools/perf/util/sort.c | 2 ++ tools/perf/util/sort.h | 4 ++++ 9 files changed, 63 insertions(+), 17 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 66dab7410c1..747ff50284b 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -135,6 +135,11 @@ OPTIONS --inverted:: alias for inverted caller based call graph. +--ignore-callees=:: + Ignore callees of the function(s) matching the given regex. + This has the effect of collecting the callers of each such + function into one place in the call-graph tree. + --pretty=:: Pretty printing style. key: normal, raw diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 7fdd1909e37..58d6598a968 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -155,6 +155,11 @@ Default is to monitor all CPUS. Default: fractal,0.5,callee. +--ignore-callees=:: + Ignore callees of the function(s) matching the given regex. + This has the effect of collecting the callers of each such + function into one place in the call-graph tree. + --percent-limit:: Do not show entries which have an overhead under that percent. (Default: 0). diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ee2ca3eb22d..9a7e54d701c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -89,7 +89,7 @@ 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); + sample, &parent, al); if (err) return err; } @@ -180,7 +180,7 @@ 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); + sample, &parent, al); if (err) return err; } @@ -254,7 +254,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent); + sample, &parent, al); if (err) return err; } @@ -681,6 +681,24 @@ setup: return 0; } +int +report_parse_ignore_callees_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (arg) { + int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED); + if (err) { + char buf[BUFSIZ]; + regerror(err, &ignore_callees_regex, buf, sizeof(buf)); + pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf); + return -1; + } + have_ignore_callees = 1; + } + + return 0; +} + static int parse_branch_mode(const struct option *opt __maybe_unused, const char *str __maybe_unused, int unset) @@ -771,6 +789,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN('G', "inverted", &report.inverted_callchain, "alias for inverted call graph"), + OPT_CALLBACK(0, "ignore-callees", NULL, "regex", + "ignore callees of these functions in call graphs", + report_parse_ignore_callees_opt), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a237059f51c..bbf46357277 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -773,8 +773,7 @@ static void perf_event__process_sample(struct perf_tool *tool, sample->callchain) { err = machine__resolve_callchain(machine, evsel, al.thread, sample, - &parent); - + &parent, &al); if (err) return; } @@ -1109,6 +1108,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, "mode[,dump_size]", record_callchain_help, &parse_callchain_opt, "fp"), + OPT_CALLBACK(0, "ignore-callees", NULL, "regex", + "ignore callees of these functions in call graphs", + report_parse_ignore_callees_opt), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 5dd5026a82e..f9f9d6381b9 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1058,11 +1058,10 @@ int machine__process_event(struct machine *machine, union perf_event *event) return ret; } -static bool symbol__match_parent_regex(struct symbol *sym) +static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) + if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) return 1; - return 0; } @@ -1159,8 +1158,8 @@ struct branch_info *machine__resolve_bstack(struct machine *machine, static int machine__resolve_callchain_sample(struct machine *machine, struct thread *thread, struct ip_callchain *chain, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al) { u8 cpumode = PERF_RECORD_MISC_USER; unsigned int i; @@ -1211,8 +1210,15 @@ static int machine__resolve_callchain_sample(struct machine *machine, MAP__FUNCTION, ip, &al, NULL); if (al.sym != NULL) { if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) + symbol__match_regex(al.sym, &parent_regex)) *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } if (!symbol_conf.use_callchain) break; } @@ -1237,13 +1243,13 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al) { int ret; ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent); + sample->callchain, parent, root_al); if (ret) return ret; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index e49ba01b793..5bb6244194d 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -5,6 +5,7 @@ #include #include "map.h" +struct addr_location; struct branch_stack; struct perf_evsel; struct perf_sample; @@ -83,7 +84,8 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent); + struct symbol **parent, + struct addr_location *root_al); /* * Default guest kernel is defined by parameter --guestkallsyms diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 951a1cfb317..1eb58eedcac 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1406,9 +1406,8 @@ 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) != 0) { + sample, NULL, NULL) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 8deee19d2e7..cb2b108635e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -7,6 +7,8 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; +regex_t ignore_callees_regex; +int have_ignore_callees = 0; int sort__need_collapse = 0; int sort__has_parent = 0; int sort__has_sym = 0; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 45ac84c1e03..a4a6d0b1ea0 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -29,6 +29,8 @@ extern const char *sort_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; +extern regex_t ignore_callees_regex; +extern int have_ignore_callees; extern int sort__need_collapse; extern int sort__has_parent; extern int sort__has_sym; @@ -183,4 +185,6 @@ int setup_sorting(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); + #endif /* __PERF_SORT_H */ -- cgit v1.2.3-70-g09d2 From 6065210db932fd183cbc8bc77558fee275360e71 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 11 Jul 2013 17:28:33 +0200 Subject: perf tools: Remove event types framework completely Removing event types framework completely. The only remainder (apart from few comments) is following enum: enum perf_user_event_type { ... PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ ... } It's kept as deprecated, resulting in error when processed in perf_session__process_user_event function. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1373556513-3000-6-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 7 ---- tools/perf/builtin-record.c | 7 ---- tools/perf/builtin-report.c | 1 - tools/perf/builtin-script.c | 1 - tools/perf/util/event.h | 2 +- tools/perf/util/header.c | 90 --------------------------------------------- tools/perf/util/header.h | 13 ------- tools/perf/util/session.c | 11 ------ tools/perf/util/tool.h | 3 -- 9 files changed, 1 insertion(+), 134 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index ad1296c6f88..1d8de2e4a40 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -67,12 +67,6 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool, return perf_event__repipe_synth(tool, event); } -static int perf_event__repipe_event_type_synth(struct perf_tool *tool, - union perf_event *event) -{ - return perf_event__repipe_synth(tool, event); -} - static int perf_event__repipe_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist) @@ -402,7 +396,6 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .throttle = perf_event__repipe, .unthrottle = perf_event__repipe, .attr = perf_event__repipe_attr, - .event_type = perf_event__repipe_event_type_synth, .tracing_data = perf_event__repipe_op2_synth, .finished_round = perf_event__repipe_op2_synth, .build_id = perf_event__repipe_op2_synth, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 1f5243c1c47..a41ac41546c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -474,13 +474,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } - err = perf_event__synthesize_event_types(tool, process_synthesized_event, - machine); - if (err < 0) { - pr_err("Couldn't synthesize event_types.\n"); - goto out_delete_session; - } - if (have_tracepoints(&evsel_list->entries)) { /* * FIXME err <= 0 here actually means that diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 188c265751c..a34c587900c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -741,7 +741,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .lost = perf_event__process_lost, .read = process_read_event, .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .ordered_samples = true, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3de8979fe87..ecb697998d3 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -524,7 +524,6 @@ static struct perf_tool perf_script = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .ordered_samples = true, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 181389535c0..1ebb8fb0178 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -116,7 +116,7 @@ struct build_id_event { enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 88626678bfc..b28a65ecd61 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -25,41 +25,9 @@ static bool no_buildid_cache = false; -static int trace_event_count; -static struct perf_trace_event_type *trace_events; - static u32 header_argc; static const char **header_argv; -int perf_header__push_event(u64 id, const char *name) -{ - struct perf_trace_event_type *nevents; - - if (strlen(name) > MAX_EVENT_NAME) - pr_warning("Event %s will be truncated\n", name); - - nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events)); - if (nevents == NULL) - return -ENOMEM; - trace_events = nevents; - - memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type)); - trace_events[trace_event_count].event_id = id; - strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1); - trace_event_count++; - return 0; -} - -char *perf_header__find_event(u64 id) -{ - int i; - for (i = 0 ; i < trace_event_count; i++) { - if (trace_events[i].event_id == id) - return trace_events[i].name; - } - return NULL; -} - /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -2936,64 +2904,6 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, return 0; } -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t size = 0; - int err = 0; - - memset(&ev, 0, sizeof(ev)); - - ev.event_type.event_type.event_id = event_id; - memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME); - strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); - - ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(ev.event_type.event_type.name); - size = PERF_ALIGN(size, sizeof(u64)); - ev.event_type.header.size = sizeof(ev.event_type) - - (sizeof(ev.event_type.event_type.name) - size); - - err = process(tool, &ev, NULL, machine); - - return err; -} - -int perf_event__synthesize_event_types(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_trace_event_type *type; - int i, err = 0; - - for (i = 0; i < trace_event_count; i++) { - type = &trace_events[i]; - - err = perf_event__synthesize_event_type(tool, type->event_id, - type->name, process, - machine); - if (err) { - pr_debug("failed to create perf header event type\n"); - return err; - } - } - - return err; -} - -int perf_event__process_event_type(struct perf_tool *tool __maybe_unused, - union perf_event *event) -{ - if (perf_header__push_event(event->event_type.event_type.event_id, - event->event_type.event_type.name) < 0) - return -ENOMEM; - - return 0; -} - int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 298982fb195..669fda531da 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -102,9 +102,6 @@ int perf_session__write_header(struct perf_session *session, int fd, bool at_exit); int perf_header__write_pipe(int fd); -int perf_header__push_event(u64 id, const char *name); -char *perf_header__find_event(u64 id); - void perf_header__set_feat(struct perf_header *header, int feat); void perf_header__clear_feat(struct perf_header *header, int feat); bool perf_header__has_feat(const struct perf_header *header, int feat); @@ -132,16 +129,6 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist); -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_event_types(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); -int perf_event__process_event_type(struct perf_tool *tool, - union perf_event *event); - int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 1eb58eedcac..d0d9f946a1b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -241,13 +241,6 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_event_type_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct perf_session *session); @@ -274,8 +267,6 @@ static void perf_tool__fill_defaults(struct perf_tool *tool) tool->unthrottle = process_event_stub; if (tool->attr == NULL) tool->attr = process_event_synth_attr_stub; - if (tool->event_type == NULL) - tool->event_type = process_event_type_stub; if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) @@ -928,8 +919,6 @@ static int perf_session__process_user_event(struct perf_session *session, union if (err == 0) perf_session__set_id_hdr_size(session); return err; - case PERF_RECORD_HEADER_EVENT_TYPE: - return tool->event_type(tool, event); case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(session->fd, file_offset, SEEK_SET); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 88f8cbdb8a3..62b16b6165b 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -22,8 +22,6 @@ typedef int (*event_attr_op)(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist); -typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event); - typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); @@ -39,7 +37,6 @@ struct perf_tool { unthrottle; event_attr_op attr; event_op2 tracing_data; - event_simple_op event_type; event_op2 finished_round, build_id; bool ordered_samples; -- cgit v1.2.3-70-g09d2 From d4339569a6f8bb1e703337175dcd4fd4bcd5d891 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 17 Jul 2013 19:49:41 +0200 Subject: perf session: Use session->fd instead of passing fd as argument Using session->fd instead of passing fd as argument because it's always session->fd that's passed as fd argument. Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1374083403-14591-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 11 +++++------ tools/perf/util/header.h | 2 +- tools/perf/util/session.c | 4 ++-- 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b28a65ecd61..b3f253f2841 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2619,19 +2619,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, return 0; } -static int perf_header__read_pipe(struct perf_session *session, int fd) +static int perf_header__read_pipe(struct perf_session *session) { struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, fd, + if (perf_file_header__read_pipe(&f_header, header, session->fd, session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } - session->fd = fd; - return 0; } @@ -2725,20 +2723,21 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, return 0; } -int perf_session__read_header(struct perf_session *session, int fd) +int perf_session__read_header(struct perf_session *session) { struct perf_header *header = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; + int fd = session->fd; session->evlist = perf_evlist__new(); if (session->evlist == NULL) return -ENOMEM; if (session->fd_pipe) - return perf_header__read_pipe(session, fd); + return perf_header__read_pipe(session); if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 669fda531da..0bacb2d6eaf 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -96,7 +96,7 @@ struct perf_header { struct perf_evlist; struct perf_session; -int perf_session__read_header(struct perf_session *session, int fd); +int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, struct perf_evlist *evlist, int fd, bool at_exit); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d0d9f946a1b..272c9cf5712 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force) self->fd_pipe = true; self->fd = STDIN_FILENO; - if (perf_session__read_header(self, self->fd) < 0) + if (perf_session__read_header(self) < 0) pr_err("incompatible file format (rerun with -v to learn more)"); return 0; @@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force) goto out_close; } - if (perf_session__read_header(self, self->fd) < 0) { + if (perf_session__read_header(self) < 0) { pr_err("incompatible file format (rerun with -v to learn more)"); goto out_close; } -- cgit v1.2.3-70-g09d2 From 9ede473cc9f655f8a10cfc8ebbf04c48d84db7ee Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 17:38:13 +0200 Subject: perf tools: Add support for parsing PERF_SAMPLE_READ sample type Adding support to parse out the PERF_SAMPLE_READ sample bits. The code contains both single and group format specification. This code parse out and prepare PERF_SAMPLE_READ data into the perf_sample struct. It will be used for group leader sampling feature comming in shortly. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-0tgdoln5rwk3wocshb442cl3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.h | 18 ++++++++++++++++++ tools/perf/util/evlist.c | 26 ++++++++++++++++++++++++++ tools/perf/util/evlist.h | 2 ++ tools/perf/util/evsel.c | 30 ++++++++++++++++++++++++++++-- tools/perf/util/session.c | 38 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 112 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1ebb8fb0178..6119a649d86 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -80,6 +80,23 @@ struct stack_dump { char *data; }; +struct sample_read_value { + u64 value; + u64 id; +}; + +struct sample_read { + u64 time_enabled; + u64 time_running; + union { + struct { + u64 nr; + struct sample_read_value *values; + } group; + struct sample_read_value one; + }; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -97,6 +114,7 @@ struct perf_sample { struct branch_stack *branch_stack; struct regs_dump user_regs; struct stack_dump user_stack; + struct sample_read read; }; #define PERF_MEM_DATA_SRC_NONE \ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 0d3b7399625..df77a44fe27 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -676,6 +676,32 @@ u64 perf_evlist__sample_type(struct perf_evlist *evlist) return first->attr.sample_type; } +bool perf_evlist__valid_read_format(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + u64 read_format = first->attr.read_format; + u64 sample_type = first->attr.sample_type; + + list_for_each_entry_continue(pos, &evlist->entries, node) { + if (read_format != pos->attr.read_format) + return false; + } + + /* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */ + if ((sample_type & PERF_SAMPLE_READ) && + !(read_format & PERF_FORMAT_ID)) { + return false; + } + + return true; +} + +u64 perf_evlist__read_format(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + return first->attr.read_format; +} + u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) { struct perf_evsel *first = perf_evlist__first(evlist); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 0583d36252b..c7178b7b995 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -118,6 +118,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); +u64 perf_evlist__read_format(struct perf_evlist *evlist); u64 perf_evlist__sample_type(struct perf_evlist *evlist); bool perf_evlist__sample_id_all(struct perf_evlist *evlist); u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); @@ -127,6 +128,7 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); +bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8bed0c1a139..9ab8fff74e3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1096,8 +1096,34 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_READ) { - fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n"); - return -1; + u64 read_format = evsel->attr.read_format; + + if (read_format & PERF_FORMAT_GROUP) + data->read.group.nr = *array; + else + data->read.one.value = *array; + + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + data->read.time_enabled = *array; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + data->read.time_running = *array; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + data->read.group.values = (struct sample_read_value *) array; + array = (void *) array + data->read.group.nr * + sizeof(struct sample_read_value); + } else { + data->read.one.id = *array; + array++; + } } if (type & PERF_SAMPLE_CALLCHAIN) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 272c9cf5712..f082921a062 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -71,6 +71,11 @@ static int perf_session__open(struct perf_session *self, bool force) goto out_close; } + if (!perf_evlist__valid_read_format(self->evlist)) { + pr_err("non matching read_format"); + goto out_close; + } + self->size = input_stat.st_size; return 0; @@ -749,6 +754,36 @@ static void perf_session__print_tstamp(struct perf_session *session, printf("%" PRIu64 " ", sample->time); } +static void sample_read__printf(struct perf_sample *sample, u64 read_format) +{ + printf("... sample_read:\n"); + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("...... time enabled %016" PRIx64 "\n", + sample->read.time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("...... time running %016" PRIx64 "\n", + sample->read.time_running); + + if (read_format & PERF_FORMAT_GROUP) { + u64 i; + + printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); + + for (i = 0; i < sample->read.group.nr; i++) { + struct sample_read_value *value; + + value = &sample->read.group.values[i]; + printf("..... id %016" PRIx64 + ", value %016" PRIx64 "\n", + value->id, value->value); + } + } else + printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", + sample->read.one.id, sample->read.one.value); +} + static void dump_event(struct perf_session *session, union perf_event *event, u64 file_offset, struct perf_sample *sample) { @@ -798,6 +833,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + + if (sample_type & PERF_SAMPLE_READ) + sample_read__printf(sample, evsel->attr.read_format); } static struct machine * -- cgit v1.2.3-70-g09d2 From e4caec0d1af3d608d52e6b92d09fb862d7691d4b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2012 18:52:24 +0200 Subject: perf evsel: Add PERF_SAMPLE_READ sample related processing For sample with sample type PERF_SAMPLE_READ the period value is stored in the 'struct sample_read'. Moreover if the read format has PERF_FORMAT_GROUP, the 'struct sample_read' contains period values for all events in the group (for which the sample's event is a leader). We deliver separated samples for all the values contained within the 'struct sample_read'. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-6mdm5xkrm6kypouh1c33cyys@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.h | 3 ++ tools/perf/util/session.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 74 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3f156ccc1ac..6a2cf261f38 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -38,6 +38,9 @@ struct perf_sample_id { struct hlist_node node; u64 id; struct perf_evsel *evsel; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; }; /** struct perf_evsel - event selector diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f082921a062..9247d9c2f5e 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -860,6 +860,75 @@ static struct machine * return &session->machines.host; } +static int deliver_sample_value(struct perf_session *session, + 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; + + sid = perf_evlist__id2sid(session->evlist, v->id); + if (sid) { + sample->id = v->id; + sample->period = v->value - sid->period; + sid->period = v->value; + } + + if (!sid || sid->evsel == NULL) { + ++session->stats.nr_unknown_id; + return 0; + } + + return tool->sample(tool, event, sample, sid->evsel, machine); +} + +static int deliver_sample_group(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int ret = -EINVAL; + u64 i; + + for (i = 0; i < sample->read.group.nr; i++) { + ret = deliver_sample_value(session, tool, event, sample, + &sample->read.group.values[i], + machine); + if (ret) + break; + } + + return ret; +} + +static int +perf_session__deliver_sample(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + /* We know evsel != NULL. */ + u64 sample_type = evsel->attr.sample_type; + u64 read_format = evsel->attr.read_format; + + /* Standard sample delievery. */ + if (!(sample_type & PERF_SAMPLE_READ)) + return tool->sample(tool, event, sample, evsel, machine); + + /* 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, + machine); + else + return deliver_sample_value(session, tool, event, sample, + &sample->read.one, machine); +} + static int perf_session_deliver_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -902,7 +971,8 @@ static int perf_session_deliver_event(struct perf_session *session, ++session->stats.nr_unprocessable_samples; return 0; } - return tool->sample(tool, event, sample, evsel, machine); + return perf_session__deliver_sample(session, tool, event, + sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_COMM: -- cgit v1.2.3-70-g09d2 From 251f426fddd9217ce6e4478653d3ee33df518030 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 28 Jul 2013 09:14:34 -0600 Subject: perf evsel: Actually show symbol offset in stack trace when requested Symbol offset is one of the fields that can be requested in perf-script. Currently you do not get that data when requested. e.g., perf script -f comm,tid,pid,time,cpu,sym,symoff,ip ... gcc 6201/6201 [006] 762250.617897: ffffffff81090d95 update_curr ffffffff810911b8 dequeue_entity ffffffff81091825 dequeue_task_fair ffffffff81087163 dequeue_task ffffffff81087c03 deactivate_task ... With this patch you get the offset: ... gcc 6201/6201 [006] 762250.617897: ffffffff81090d95 update_curr+0x1c5 ffffffff810911b8 dequeue_entity+0x28 ffffffff81091825 dequeue_task_fair+0x45 ffffffff81087163 dequeue_task+0x93 ffffffff81087c03 deactivate_task+0x23 ... Signed-off-by: David Ahern Link: http://lkml.kernel.org/r/1375024474-45726-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 9247d9c2f5e..a0ce5a46abb 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1519,8 +1519,13 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, printf("\t%16" PRIx64, node->ip); if (print_sym) { printf(" "); - symbol__fprintf_symname(node->sym, stdout); + if (print_symoffset) { + al.addr = node->ip; + symbol__fprintf_symname_offs(node->sym, &al, stdout); + } else + symbol__fprintf_symname(node->sym, stdout); } + if (print_dso) { printf(" ("); map__fprintf_dsoname(node->map, stdout); -- cgit v1.2.3-70-g09d2 From 9c5014022f5d5b09abc8b713da81b3d2db319699 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 2 Aug 2013 14:05:41 -0600 Subject: perf session: Export a few functions for event processing Allows kvm live mode to reuse the event processing and ordered samples processing used by the perf-report path. v2: removed flush_sample_queue as noticed by Jiri Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Runzhen Wang Cc: Xiao Guangrong Link: http://lkml.kernel.org/r/1375473947-64285-4-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 12 ++++++------ tools/perf/util/session.h | 7 +++++++ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a0ce5a46abb..b5ebd4751a0 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -250,7 +250,7 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct perf_session *session); -static void perf_tool__fill_defaults(struct perf_tool *tool) +void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) tool->sample = process_event_sample_stub; @@ -495,7 +495,7 @@ static int perf_session_deliver_event(struct perf_session *session, u64 file_offset); static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) + struct perf_tool *tool) { struct ordered_samples *os = &s->ordered_samples; struct list_head *head = &os->samples; @@ -1049,10 +1049,10 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } -static int perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - u64 file_offset) +int perf_session__process_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) { struct perf_sample sample; int ret; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index ad8d3d4ef14..9818fc25a62 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -56,6 +56,13 @@ int __perf_session__process_events(struct perf_session *self, int perf_session__process_events(struct perf_session *self, struct perf_tool *tool); +int perf_session__process_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset); + +void perf_tool__fill_defaults(struct perf_tool *tool); + int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel, struct thread *thread, struct ip_callchain *chain, -- cgit v1.2.3-70-g09d2 From e30b88a77cc8ae2a1febf268c8443a6cdd696417 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Aug 2013 21:41:33 -0400 Subject: perf session: Export queue_event function Taking a lesson from perf-trace and bringing in control of event processing to perf-kvm-stat-live: parse the sample to get access the time leaving just the need to queue it to the ordered samples list. For that the queue_event function needs to be exported. Unexport perf_session__process_event. Signed-off-by: David Ahern Reviewed-by: Xiao Guangrong Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Runzhen Wang Cc: Xiao Guangrong Link: http://lkml.kernel.org/r/1375753297-69645-2-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 10 +++++----- tools/perf/util/session.h | 6 ++---- 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index b5ebd4751a0..dedaeb22b7b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -643,7 +643,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s) #define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) -static int perf_session_queue_event(struct perf_session *s, union perf_event *event, +int perf_session_queue_event(struct perf_session *s, union perf_event *event, struct perf_sample *sample, u64 file_offset) { struct ordered_samples *os = &s->ordered_samples; @@ -1049,10 +1049,10 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } -int perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - u64 file_offset) +static int perf_session__process_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) { struct perf_sample sample; int ret; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 9818fc25a62..8bed17e64a9 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -56,10 +56,8 @@ int __perf_session__process_events(struct perf_session *self, int perf_session__process_events(struct perf_session *self, struct perf_tool *tool); -int perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - 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); -- cgit v1.2.3-70-g09d2 From a6ffaf91302dc1689fc72da0068b87226747fbe0 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:51 -0400 Subject: perf tool: Simplify options to perf_evsel__print_ip Make print options based on flags. Simplifies addition of more print options which is the subject of upcoming patches. 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/1375930261-77273-10-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 27 +++++++++++++++++++++++---- tools/perf/util/session.c | 14 +++++++++++--- tools/perf/util/session.h | 7 ++++++- 3 files changed, 40 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index cd616ff5d22..ee5d6f8b741 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -66,6 +66,7 @@ struct output_option { static struct { bool user_set; bool wildcard_set; + unsigned int print_ip_opts; u64 fields; u64 invalid_fields; } output[PERF_TYPE_MAX] = { @@ -235,6 +236,7 @@ static int perf_session__check_output_opt(struct perf_session *session) { int j; struct perf_evsel *evsel; + struct perf_event_attr *attr; for (j = 0; j < PERF_TYPE_MAX; ++j) { evsel = perf_session__find_first_evtype(session, j); @@ -253,6 +255,24 @@ static int perf_session__check_output_opt(struct perf_session *session) if (evsel && output[j].fields && perf_evsel__check_attr(evsel, session)) return -1; + + if (evsel == NULL) + continue; + + attr = &evsel->attr; + + output[j].print_ip_opts = 0; + if (PRINT_FIELD(IP)) + output[j].print_ip_opts |= PRINT_IP_OPT_IP; + + if (PRINT_FIELD(SYM)) + output[j].print_ip_opts |= PRINT_IP_OPT_SYM; + + if (PRINT_FIELD(DSO)) + output[j].print_ip_opts |= PRINT_IP_OPT_DSO; + + if (PRINT_FIELD(SYMOFFSET)) + output[j].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET; } return 0; @@ -382,8 +402,7 @@ static void print_sample_bts(union perf_event *event, else printf("\n"); perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); + output[attr->type].print_ip_opts); } printf(" => "); @@ -423,9 +442,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample, printf(" "); else printf("\n"); + perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); + output[attr->type].print_ip_opts); } printf("\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index dedaeb22b7b..e5fd65802ed 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1489,10 +1489,14 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset) + unsigned int print_opts) { struct addr_location al; struct callchain_cursor_node *node; + int print_ip = print_opts & PRINT_IP_OPT_IP; + int print_sym = print_opts & PRINT_IP_OPT_SYM; + int print_dso = print_opts & PRINT_IP_OPT_DSO; + int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { @@ -1516,7 +1520,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, if (!node) break; - printf("\t%16" PRIx64, node->ip); + if (print_ip) + printf("%16" PRIx64, node->ip); + if (print_sym) { printf(" "); if (print_symoffset) { @@ -1537,7 +1543,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, } } else { - printf("%16" PRIx64, sample->ip); + if (print_ip) + printf("%16" PRIx64, sample->ip); + if (print_sym) { printf(" "); if (print_symoffset) diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 8bed17e64a9..69e554a29c1 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -41,6 +41,11 @@ struct perf_session { char filename[1]; }; +#define PRINT_IP_OPT_IP (1<<0) +#define PRINT_IP_OPT_SYM (1<<1) +#define PRINT_IP_OPT_DSO (1<<2) +#define PRINT_IP_OPT_SYMOFFSET (1<<3) + struct perf_tool; struct perf_session *perf_session__new(const char *filename, int mode, @@ -103,7 +108,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset); + unsigned int print_opts); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); -- cgit v1.2.3-70-g09d2 From b0b35f0179161a5e256eebffa274b0b6f023f451 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:52 -0400 Subject: perf evsel: Add option to print stack trace on single line Option is used by upcoming timehist command. 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/1375930261-77273-11-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 8 ++++++-- tools/perf/util/session.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e5fd65802ed..0d895e7040e 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1497,6 +1497,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, int print_sym = print_opts & PRINT_IP_OPT_SYM; int print_dso = print_opts & PRINT_IP_OPT_DSO; int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; + int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; + char s = print_oneline ? ' ' : '\t'; if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { @@ -1521,7 +1523,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, break; if (print_ip) - printf("%16" PRIx64, node->ip); + printf("%c%16" PRIx64, s, node->ip); if (print_sym) { printf(" "); @@ -1537,7 +1539,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, map__fprintf_dsoname(node->map, stdout); printf(")"); } - printf("\n"); + + if (!print_oneline) + printf("\n"); callchain_cursor_advance(&callchain_cursor); } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 69e554a29c1..7c00ccb1173 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -45,6 +45,7 @@ struct perf_session { #define PRINT_IP_OPT_SYM (1<<1) #define PRINT_IP_OPT_DSO (1<<2) #define PRINT_IP_OPT_SYMOFFSET (1<<3) +#define PRINT_IP_OPT_ONELINE (1<<4) struct perf_tool; -- cgit v1.2.3-70-g09d2 From 307cbb92aa2bdc9eed7c74409ff4d5fc9135b4e2 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:53 -0400 Subject: perf evsel: Add option to limit stack depth in callchain dumps Option is used by upcoming timehist command. 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/1375930261-77273-12-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 6 ++++-- tools/perf/util/session.c | 6 ++++-- tools/perf/util/session.h | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ee5d6f8b741..33b2d830eab 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -402,7 +402,8 @@ static void print_sample_bts(union perf_event *event, else printf("\n"); perf_evsel__print_ip(evsel, event, sample, machine, - output[attr->type].print_ip_opts); + output[attr->type].print_ip_opts, + PERF_MAX_STACK_DEPTH); } printf(" => "); @@ -444,7 +445,8 @@ static void process_event(union perf_event *event, struct perf_sample *sample, printf("\n"); perf_evsel__print_ip(evsel, event, sample, machine, - output[attr->type].print_ip_opts); + output[attr->type].print_ip_opts, + PERF_MAX_STACK_DEPTH); } printf("\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0d895e7040e..5a8996493d9 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1489,7 +1489,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - unsigned int print_opts) + unsigned int print_opts, unsigned int stack_depth) { struct addr_location al; struct callchain_cursor_node *node; @@ -1517,7 +1517,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, } callchain_cursor_commit(&callchain_cursor); - while (1) { + while (stack_depth) { node = callchain_cursor_current(&callchain_cursor); if (!node) break; @@ -1544,6 +1544,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, printf("\n"); callchain_cursor_advance(&callchain_cursor); + + stack_depth--; } } else { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 7c00ccb1173..3aa75fb2225 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -109,7 +109,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - unsigned int print_opts); + unsigned int print_opts, unsigned int stack_depth); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); -- cgit v1.2.3-70-g09d2 From 93ea01c29d4ed5a9fcf6d9a95bc584e54a420834 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:58 -0400 Subject: perf session: Change perf_session__has_traces to actually check for tracepoints Any event can have RAW data attribute set. The intent of the function is to determine if the session has tracepoints, so check for the type of each event explicitly. 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/1375930261-77273-17-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5a8996493d9..4d9028eef34 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1401,12 +1401,15 @@ int perf_session__process_events(struct perf_session *self, bool perf_session__has_traces(struct perf_session *session, const char *msg) { - if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) { - pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); - return false; + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + return true; } - return true; + pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); + return false; } int maps__set_kallsyms_ref_reloc_sym(struct map **maps, -- cgit v1.2.3-70-g09d2 From e44baa3ea1eaa09d7d247a9b245fcff06561bf96 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 8 Aug 2013 14:32:25 +0300 Subject: perf tools: Remove filter parameter of perf_event__preprocess_sample() Now that the symbol filter is recorded on the machine there is no need to pass it to perf_event__preprocess_sample(). So remove it. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1375961547-30267-7-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 3 +-- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-mem.c | 3 +-- tools/perf/builtin-report.c | 3 +-- tools/perf/builtin-script.c | 2 +- tools/perf/builtin-top.c | 3 +-- tools/perf/tests/hists_link.c | 4 ++-- tools/perf/util/event.c | 8 ++++---- tools/perf/util/event.h | 3 +-- tools/perf/util/session.c | 3 +-- 10 files changed, 14 insertions(+), 20 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 9754cb140a5..f988d380c52 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -90,8 +90,7 @@ static int process_sample_event(struct perf_tool *tool, struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool); struct addr_location al; - if (perf_event__preprocess_sample(event, machine, &al, sample, - machine->symbol_filter) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 93de3ac177c..f28799e94f2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -319,7 +319,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, { struct addr_location al; - if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index f96168c769c..706a1faa955 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -68,8 +68,7 @@ dump_raw_samples(struct perf_tool *tool, struct addr_location al; const char *fmt; - if (perf_event__preprocess_sample(event, machine, &al, sample, - NULL) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f06a5a228c7..958a56a0e39 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -304,8 +304,7 @@ static int process_sample_event(struct perf_tool *tool, struct addr_location al; int ret; - if (perf_event__preprocess_sample(event, machine, &al, sample, - machine->symbol_filter) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 33b2d830eab..a7d623f39c4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -520,7 +520,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return 0; } - if (perf_event__preprocess_sample(event, machine, &al, sample, 0) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_err("problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a63ade22cbc..e37521fc715 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -716,8 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) top->exact_samples++; - if (perf_event__preprocess_sample(event, machine, &al, sample, - machine->symbol_filter) < 0 || + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 || al.filtered) return; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 89085a9615e..50bfb01183e 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -220,7 +220,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) }; if (perf_event__preprocess_sample(&event, machine, &al, - &sample, 0) < 0) + &sample) < 0) goto out; he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); @@ -244,7 +244,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) }; if (perf_event__preprocess_sample(&event, machine, &al, - &sample, 0) < 0) + &sample) < 0) goto out; he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index cc7c0c9c9ea..f3cf771d362 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -683,8 +683,7 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine, int perf_event__preprocess_sample(const union perf_event *event, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter) + struct perf_sample *sample) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread = machine__findnew_thread(machine, event->ip.pid); @@ -709,7 +708,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine__create_kernel_maps(machine); thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, al, filter); + event->ip.ip, al, machine->symbol_filter); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : ""); @@ -727,7 +726,8 @@ int perf_event__preprocess_sample(const union perf_event *event, dso->long_name))))) goto out_filtered; - al->sym = map__find_symbol(al->map, al->addr, filter); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); } if (symbol_conf.sym_list && diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6119a649d86..15db071d96b 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -234,8 +234,7 @@ struct addr_location; int perf_event__preprocess_sample(const union perf_event *self, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter); + struct perf_sample *sample); const char *perf_event__name(unsigned int id); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 4d9028eef34..de16a773685 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1503,8 +1503,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; char s = print_oneline ? ' ' : '\t'; - if (perf_event__preprocess_sample(event, machine, &al, sample, - NULL) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { error("problem processing %d event, skipping it.\n", event->header.type); return; -- cgit v1.2.3-70-g09d2 From 314add6b1f045b59ca39683bd0cbc5310cd203f2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 27 Aug 2013 11:23:03 +0300 Subject: perf tools: change machine__findnew_thread() to set thread pid Add a new parameter for 'pid' to machine__findnew_thread(). Change callers to pass 'pid' when it is known. Note that callers sometimes want to find the main thread which has the memory maps. The main thread has tid == pid so the usage in that case is: machine__findnew_thread(machine, pid, pid) whereas the usage to find the specific thread is: machine__findnew_thread(machine, pid, tid) Signed-off-by: Adrian Hunter Acked-by: David Ahern Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1377591794-30553-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 2 +- tools/perf/builtin-kmem.c | 3 ++- tools/perf/builtin-kvm.c | 2 +- tools/perf/builtin-lock.c | 3 ++- tools/perf/builtin-sched.c | 20 +++++++++++--------- tools/perf/builtin-script.c | 3 ++- tools/perf/builtin-trace.c | 10 +++++++--- tools/perf/tests/code-reading.c | 4 ++-- tools/perf/tests/hists_link.c | 3 ++- tools/perf/util/build-id.c | 7 +++++-- tools/perf/util/event.c | 3 ++- tools/perf/util/machine.c | 22 +++++++++++++++------- tools/perf/util/machine.h | 3 ++- tools/perf/util/session.c | 2 +- 14 files changed, 55 insertions(+), 32 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 1d8de2e4a40..0d4ae1dd7b6 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -198,7 +198,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread = machine__findnew_thread(machine, event->ip.pid); + thread = machine__findnew_thread(machine, event->ip.pid, event->ip.pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", event->header.type); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b49f5c58e15..c32477837cb 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -305,7 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid, + event->ip.pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 6cd4de59be2..47b35407c2f 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -815,7 +815,7 @@ static int process_sample_event(struct perf_tool *tool, if (skip_sample(kvm, sample)) return 0; - thread = machine__findnew_thread(machine, sample->tid); + thread = machine__findnew_thread(machine, sample->pid, sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 76543a4a7a3..ee33ba2f05d 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -805,7 +805,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index f809cc7fb7d..d8c51b2f263 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -724,8 +724,10 @@ static int replay_fork_event(struct perf_sched *sched, { struct thread *child, *parent; - child = machine__findnew_thread(machine, event->fork.tid); - parent = machine__findnew_thread(machine, event->fork.ptid); + child = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ppid, + event->fork.ptid); if (child == NULL || parent == NULL) { pr_debug("thread does not exist on fork event: child %p, parent %p\n", @@ -934,8 +936,8 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { @@ -978,7 +980,7 @@ static int latency_runtime_event(struct perf_sched *sched, { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; int cpu = sample->cpu; @@ -1016,7 +1018,7 @@ static int latency_wakeup_event(struct perf_sched *sched, if (!success) return 0; - wakee = machine__findnew_thread(machine, pid); + wakee = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) @@ -1070,7 +1072,7 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, pid); + migrant = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) @@ -1289,8 +1291,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); sched->curr_thread[this_cpu] = sched_in; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 2ad9d5b6fb3..d82712f169b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -501,7 +501,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct machine *machine) { struct addr_location al; - struct thread *thread = machine__findnew_thread(machine, event->ip.tid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid, + event->ip.tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index b72afc73f9a..88387c56568 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -521,7 +521,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (sc->filtered) return 0; - thread = machine__findnew_thread(&trace->host, sample->tid); + thread = machine__findnew_thread(&trace->host, sample->pid, + sample->tid); ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) return -1; @@ -572,7 +573,8 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (sc->filtered) return 0; - thread = machine__findnew_thread(&trace->host, sample->tid); + thread = machine__findnew_thread(&trace->host, sample->pid, + sample->tid); ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) return -1; @@ -628,7 +630,9 @@ 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, sample->tid); + struct thread *thread = machine__findnew_thread(&trace->host, + sample->pid, + sample->tid); struct thread_trace *ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index df9afd9cab4..6fb781d5586 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -257,7 +257,7 @@ static int process_sample_event(struct machine *machine, return -1; } - thread = machine__findnew_thread(machine, sample.pid); + thread = machine__findnew_thread(machine, sample.pid, sample.pid); if (!thread) { pr_debug("machine__findnew_thread failed\n"); return -1; @@ -446,7 +446,7 @@ static int do_test_code_reading(bool try_kcore) goto out_err; } - thread = machine__findnew_thread(machine, pid); + thread = machine__findnew_thread(machine, pid, pid); if (!thread) { pr_debug("machine__findnew_thread failed\n"); goto out_err; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 50bfb01183e..87f9f7280c4 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -88,7 +88,8 @@ static struct machine *setup_fake_machine(struct machines *machines) for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { struct thread *thread; - thread = machine__findnew_thread(machine, fake_threads[i].pid); + thread = machine__findnew_thread(machine, fake_threads[i].pid, + fake_threads[i].pid); if (thread == NULL) goto out; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 5295625c0c0..0f9d27a6bc8 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -24,7 +24,8 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid, + event->ip.pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, __maybe_unused, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *thread = machine__findnew_thread(machine, + event->fork.pid, + event->fork.tid); dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, event->fork.ppid, event->fork.ptid); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 49713ae4655..61cecf9caff 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -686,7 +686,8 @@ int perf_event__preprocess_sample(const union perf_event *event, struct perf_sample *sample) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid, + event->ip.pid); if (thread == NULL) return -1; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 59486c18062..1dca61f0512 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -32,7 +32,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, + pid); char comm[64]; if (thread == NULL) @@ -302,9 +303,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, return th; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t tid) +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid) { - return __machine__findnew_thread(machine, 0, tid, true); + return __machine__findnew_thread(machine, pid, tid, true); } struct thread *machine__find_thread(struct machine *machine, pid_t tid) @@ -314,7 +316,9 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid) int machine__process_comm_event(struct machine *machine, union perf_event *event) { - struct thread *thread = machine__findnew_thread(machine, event->comm.tid); + struct thread *thread = machine__findnew_thread(machine, + event->comm.pid, + event->comm.tid); if (dump_trace) perf_event__fprintf_comm(event, stdout); @@ -1012,7 +1016,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event return 0; } - thread = machine__findnew_thread(machine, event->mmap.pid); + thread = machine__findnew_thread(machine, event->mmap.pid, + event->mmap.pid); if (thread == NULL) goto out_problem; @@ -1051,13 +1056,16 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) int machine__process_fork_event(struct machine *machine, union perf_event *event) { struct thread *thread = machine__find_thread(machine, event->fork.tid); - struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); + 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) machine__remove_thread(machine, thread); - thread = machine__findnew_thread(machine, event->fork.tid); + thread = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); if (dump_trace) perf_event__fprintf_task(event, stdout); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 603ffba999d..0df925ba6a4 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -106,7 +106,8 @@ static inline bool machine__is_host(struct machine *machine) return machine ? machine->pid == HOST_KERNEL_ID : false; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t tid); +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid); size_t machine__fprintf(struct machine *machine, FILE *fp); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index de16a773685..57b6f38f246 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1099,7 +1099,7 @@ void perf_event_header__bswap(struct perf_event_header *self) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, pid); + return machine__findnew_thread(&session->machines.host, 0, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *self) -- cgit v1.2.3-70-g09d2 From 07940293ba7a43070cdebda952b0e6025d80a383 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 27 Aug 2013 11:23:05 +0300 Subject: perf callchain: Remove unnecessary validation Now that the sample parsing correctly checks data sizes there is no reason for it to be done again for callchains. Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1377591794-30553-4-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 8 -------- tools/perf/util/callchain.h | 5 ----- tools/perf/util/session.c | 20 -------------------- 3 files changed, 33 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 4fee33b229b..482f68081cd 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -21,14 +21,6 @@ __thread struct callchain_cursor callchain_cursor; -bool ip_callchain__valid(struct ip_callchain *chain, - const union perf_event *event) -{ - unsigned int chain_size = event->header.size; - chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event; - return chain->nr * sizeof(u64) <= chain_size; -} - #define chain_for_each_child(child, parent) \ list_for_each_entry(child, &parent->children, siblings) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 812d5a0ff2b..2b585bc308c 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -109,11 +109,6 @@ int callchain_append(struct callchain_root *root, int callchain_merge(struct callchain_cursor *cursor, struct callchain_root *dst, struct callchain_root *src); -struct ip_callchain; -union perf_event; - -bool ip_callchain__valid(struct ip_callchain *chain, - const union perf_event *event); /* * Initialize a cursor before adding entries inside, but keep * the previously allocated entries as a cache. diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 57b6f38f246..07590c3c68b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -997,22 +997,6 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__preprocess_sample(struct perf_session *session, - union perf_event *event, struct perf_sample *sample) -{ - if (event->header.type != PERF_RECORD_SAMPLE || - !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN)) - return 0; - - if (!ip_callchain__valid(sample->callchain, event)) { - pr_debug("call-chain problem with event, skipping it.\n"); - ++session->stats.nr_invalid_chains; - session->stats.total_invalid_chains += sample->period; - return -EINVAL; - } - return 0; -} - static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) { @@ -1075,10 +1059,6 @@ static int perf_session__process_event(struct perf_session *session, if (ret) return ret; - /* Preprocess sample records - precheck callchains */ - if (perf_session__preprocess_sample(session, event, &sample)) - return 0; - if (tool->ordered_samples) { ret = perf_session_queue_event(session, event, &sample, file_offset); -- cgit v1.2.3-70-g09d2 From ef89325f773bc9f2f4e6019bd7f3d968ba85df9a Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 27 Aug 2013 11:23:06 +0300 Subject: perf tools: Remove references to struct ip_event The ip_event struct assumes fixed positions for ip, pid and tid. That is no longer true with the addition of PERF_SAMPLE_IDENTIFIER. The information is anyway in struct sample, so use that instead. Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1377591794-30553-5-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 4 ++-- tools/perf/builtin-kmem.c | 4 ++-- tools/perf/builtin-mem.c | 2 +- tools/perf/builtin-script.c | 4 ++-- tools/perf/builtin-top.c | 11 ++++++----- tools/perf/tests/hists_link.c | 20 ++++++++------------ tools/perf/util/build-id.c | 8 ++++---- tools/perf/util/event.c | 6 +++--- tools/perf/util/event.h | 11 ----------- tools/perf/util/evsel.c | 4 ++-- tools/perf/util/session.c | 8 +++++--- 11 files changed, 35 insertions(+), 47 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0d4ae1dd7b6..ffacd464f9f 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -198,7 +198,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread = machine__findnew_thread(machine, event->ip.pid, event->ip.pid); + thread = machine__findnew_thread(machine, sample->pid, sample->pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", event->header.type); @@ -206,7 +206,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, } thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + sample->ip, &al); if (al.map != NULL) { if (!al.map->dso->hit) { diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c32477837cb..c2dff9cb1f2 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -305,8 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->ip.pid, - event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 706a1faa955..791b432df84 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -94,7 +94,7 @@ dump_raw_samples(struct perf_tool *tool, symbol_conf.field_sep, sample->tid, symbol_conf.field_sep, - event->ip.ip, + sample->ip, symbol_conf.field_sep, sample->addr, symbol_conf.field_sep, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d82712f169b..93a34cef967 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -501,8 +501,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct machine *machine) { struct addr_location al; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid, - event->ip.tid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e37521fc715..212214162bb 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -689,7 +689,7 @@ static void perf_event__process_sample(struct perf_tool *tool, { struct perf_top *top = container_of(tool, struct perf_top, tool); struct symbol *parent = NULL; - u64 ip = event->ip.ip; + u64 ip = sample->ip; struct addr_location al; int err; @@ -699,10 +699,10 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!seen) seen = intlist__new(NULL); - if (!intlist__has_entry(seen, event->ip.pid)) { + if (!intlist__has_entry(seen, sample->pid)) { pr_err("Can't find guest [%d]'s kernel information\n", - event->ip.pid); - intlist__add(seen, event->ip.pid); + sample->pid); + intlist__add(seen, sample->pid); } return; } @@ -836,7 +836,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) break; case PERF_RECORD_MISC_GUEST_KERNEL: ++top->guest_kernel_samples; - machine = perf_session__find_machine(session, event->ip.pid); + machine = perf_session__find_machine(session, + sample.pid); break; case PERF_RECORD_MISC_GUEST_USER: ++top->guest_us_samples; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 87f9f7280c4..4228ffc0d96 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -211,15 +211,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) list_for_each_entry(evsel, &evlist->entries, node) { for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) { const union perf_event event = { - .ip = { - .header = { - .misc = PERF_RECORD_MISC_USER, - }, - .pid = fake_common_samples[k].pid, - .ip = fake_common_samples[k].ip, + .header = { + .misc = PERF_RECORD_MISC_USER, }, }; + sample.pid = fake_common_samples[k].pid; + sample.ip = fake_common_samples[k].ip; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) goto out; @@ -235,15 +233,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) { const union perf_event event = { - .ip = { - .header = { - .misc = PERF_RECORD_MISC_USER, - }, - .pid = fake_samples[i][k].pid, - .ip = fake_samples[i][k].ip, + .header = { + .misc = PERF_RECORD_MISC_USER, }, }; + sample.pid = fake_samples[i][k].pid; + sample.ip = fake_samples[i][k].ip; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) goto out; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0f9d27a6bc8..fb584092eb8 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -18,14 +18,14 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct perf_evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid, - event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -34,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, } thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 61cecf9caff..8d51f21107a 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -686,8 +686,8 @@ int perf_event__preprocess_sample(const union perf_event *event, struct perf_sample *sample) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid, - event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) return -1; @@ -709,7 +709,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine__create_kernel_maps(machine); thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, al); + sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : ""); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 15db071d96b..19d911c011c 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -8,16 +8,6 @@ #include "map.h" #include "build-id.h" -/* - * PERF_SAMPLE_IP | PERF_SAMPLE_TID | * - */ -struct ip_event { - struct perf_event_header header; - u64 ip; - u32 pid, tid; - unsigned char __more_data[]; -}; - struct mmap_event { struct perf_event_header header; u32 pid, tid; @@ -166,7 +156,6 @@ struct tracing_data_event { union perf_event { struct perf_event_header header; - struct ip_event ip; struct mmap_event mmap; struct comm_event comm; struct fork_event fork; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9a5fb23ff8e..7e328c47f3b 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1185,7 +1185,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, return -EFAULT; if (type & PERF_SAMPLE_IP) { - data->ip = event->ip.ip; + data->ip = *array; array++; } @@ -1397,7 +1397,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array = event->sample.array; if (type & PERF_SAMPLE_IP) { - event->ip.ip = sample->ip; + *array = sample->ip; array++; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 07590c3c68b..c3ac483be48 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -840,7 +840,8 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, static struct machine * perf_session__find_machine_for_cpumode(struct perf_session *session, - union perf_event *event) + union perf_event *event, + struct perf_sample *sample) { const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; @@ -852,7 +853,7 @@ static struct machine * if (event->header.type == PERF_RECORD_MMAP) pid = event->mmap.pid; else - pid = event->ip.pid; + pid = sample->pid; return perf_session__findnew_machine(session, pid); } @@ -958,7 +959,8 @@ static int perf_session_deliver_event(struct perf_session *session, hists__inc_nr_events(&evsel->hists, event->header.type); } - machine = perf_session__find_machine_for_cpumode(session, event); + machine = perf_session__find_machine_for_cpumode(session, event, + sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: -- cgit v1.2.3-70-g09d2 From 75562573bab35b129cfd342fc2bcf89da84a6644 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 27 Aug 2013 11:23:09 +0300 Subject: perf tools: Add support for PERF_SAMPLE_IDENTIFIER Enable parsing of samples with sample format bit PERF_SAMPLE_IDENTIFIER. In addition, if the kernel supports it, prefer it to selecting PERF_SAMPLE_ID thereby allowing non-matching sample types. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1377591794-30553-8-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 2 +- tools/perf/tests/mmap-basic.c | 2 +- tools/perf/util/event.h | 3 +- tools/perf/util/evlist.c | 111 +++++++++++++++++++++++++++++++++++++++--- tools/perf/util/evlist.h | 8 ++- tools/perf/util/evsel.c | 101 ++++++++++++++++++++++++++++++++++++-- tools/perf/util/evsel.h | 14 +++++- tools/perf/util/record.c | 89 +++++++++++++++++++++++++++++++-- tools/perf/util/session.c | 2 +- 9 files changed, 310 insertions(+), 22 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 958a56a0e39..9725aa37541 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -365,7 +365,7 @@ static int process_read_event(struct perf_tool *tool, static int perf_report__setup_sample_type(struct perf_report *rep) { struct perf_session *self = rep->session; - u64 sample_type = perf_evlist__sample_type(self->evlist); + u64 sample_type = perf_evlist__combined_sample_type(self->evlist); if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 5b1b5aba722..c4185b9aeb8 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -72,7 +72,7 @@ int test__basic_mmap(void) } evsels[i]->attr.wakeup_events = 1; - perf_evsel__set_sample_id(evsels[i]); + perf_evsel__set_sample_id(evsels[i], false); perf_evlist__add(evlist, evsels[i]); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 19d911c011c..491333910cf 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -53,7 +53,8 @@ struct read_event { (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \ - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \ + PERF_SAMPLE_IDENTIFIER) struct sample_event { struct perf_event_header header; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9d682e5f718..6a629af5137 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -49,6 +49,21 @@ struct perf_evlist *perf_evlist__new(void) return evlist; } +/** + * perf_evlist__set_id_pos - set the positions of event ids. + * @evlist: selected event list + * + * Events with compatible sample types all have the same id_pos + * and is_pos. For convenience, put a copy on evlist. + */ +void perf_evlist__set_id_pos(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + + evlist->id_pos = first->id_pos; + evlist->is_pos = first->is_pos; +} + static void perf_evlist__purge(struct perf_evlist *evlist) { struct perf_evsel *pos, *n; @@ -79,15 +94,20 @@ void perf_evlist__delete(struct perf_evlist *evlist) void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { list_add_tail(&entry->node, &evlist->entries); - ++evlist->nr_entries; + if (!evlist->nr_entries++) + perf_evlist__set_id_pos(evlist); } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, int nr_entries) { + bool set_id_pos = !evlist->nr_entries; + list_splice_tail(list, &evlist->entries); evlist->nr_entries += nr_entries; + if (set_id_pos) + perf_evlist__set_id_pos(evlist); } void __perf_evlist__set_leader(struct list_head *list) @@ -349,6 +369,55 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } +static int perf_evlist__event2id(struct perf_evlist *evlist, + union perf_event *event, u64 *id) +{ + const u64 *array = event->sample.array; + ssize_t n; + + n = (event->header.size - sizeof(event->header)) >> 3; + + if (event->header.type == PERF_RECORD_SAMPLE) { + if (evlist->id_pos >= n) + return -1; + *id = array[evlist->id_pos]; + } else { + if (evlist->is_pos > n) + return -1; + n -= evlist->is_pos; + *id = array[n]; + } + return 0; +} + +static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, + union perf_event *event) +{ + struct hlist_head *head; + struct perf_sample_id *sid; + int hash; + u64 id; + + if (evlist->nr_entries == 1) + return perf_evlist__first(evlist); + + if (perf_evlist__event2id(evlist, event, &id)) + return NULL; + + /* Synthesized events have an id of zero */ + if (!id) + return perf_evlist__first(evlist); + + hash = hash_64(id, PERF_EVLIST__HLIST_BITS); + head = &evlist->heads[hash]; + + hlist_for_each_entry(sid, head, node) { + if (sid->id == id) + return sid->evsel; + } + return NULL; +} + union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; @@ -659,20 +728,40 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + struct perf_evsel *pos; - list_for_each_entry_continue(pos, &evlist->entries, node) { - if (first->attr.sample_type != pos->attr.sample_type) + if (evlist->nr_entries == 1) + return true; + + if (evlist->id_pos < 0 || evlist->is_pos < 0) + return false; + + list_for_each_entry(pos, &evlist->entries, node) { + if (pos->id_pos != evlist->id_pos || + pos->is_pos != evlist->is_pos) return false; } return true; } -u64 perf_evlist__sample_type(struct perf_evlist *evlist) +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.sample_type; + struct perf_evsel *evsel; + + if (evlist->combined_sample_type) + return evlist->combined_sample_type; + + list_for_each_entry(evsel, &evlist->entries, node) + evlist->combined_sample_type |= evsel->attr.sample_type; + + return evlist->combined_sample_type; +} + +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) +{ + evlist->combined_sample_type = 0; + return __perf_evlist__combined_sample_type(evlist); } bool perf_evlist__valid_read_format(struct perf_evlist *evlist) @@ -727,6 +816,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) if (sample_type & PERF_SAMPLE_CPU) size += sizeof(data->cpu) * 2; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + size += sizeof(data->id); out: return size; } @@ -885,7 +977,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + + if (!evsel) + return -EFAULT; return perf_evsel__parse_sample(evsel, event, sample); } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 327ababa67b..ab95d727363 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -32,6 +32,9 @@ struct perf_evlist { int nr_fds; int nr_mmaps; int mmap_len; + int id_pos; + int is_pos; + u64 combined_sample_type; struct { int cork_fd; pid_t pid; @@ -85,6 +88,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); +void perf_evlist__set_id_pos(struct perf_evlist *evlist); +bool perf_can_sample_identifier(void); void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts); @@ -121,7 +126,8 @@ void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); u64 perf_evlist__read_format(struct perf_evlist *evlist); -u64 perf_evlist__sample_type(struct perf_evlist *evlist); +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist); +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist); bool perf_evlist__sample_id_all(struct perf_evlist *evlist); u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 7e328c47f3b..db4e431cb6c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -31,7 +31,7 @@ static struct { #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -static int __perf_evsel__sample_size(u64 sample_type) +int __perf_evsel__sample_size(u64 sample_type) { u64 mask = sample_type & PERF_SAMPLE_MASK; int size = 0; @@ -47,6 +47,72 @@ static int __perf_evsel__sample_size(u64 sample_type) return size; } +/** + * __perf_evsel__calc_id_pos - calculate id_pos. + * @sample_type: sample type + * + * This function returns the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct + * sample_event. + */ +static int __perf_evsel__calc_id_pos(u64 sample_type) +{ + int idx = 0; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 0; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_IP) + idx += 1; + + if (sample_type & PERF_SAMPLE_TID) + idx += 1; + + if (sample_type & PERF_SAMPLE_TIME) + idx += 1; + + if (sample_type & PERF_SAMPLE_ADDR) + idx += 1; + + return idx; +} + +/** + * __perf_evsel__calc_is_pos - calculate is_pos. + * @sample_type: sample type + * + * This function returns the position (counting backwards) of the event id + * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if + * sample_id_all is used there is an id sample appended to non-sample events. + */ +static int __perf_evsel__calc_is_pos(u64 sample_type) +{ + int idx = 1; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 1; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_CPU) + idx += 1; + + if (sample_type & PERF_SAMPLE_STREAM_ID) + idx += 1; + + return idx; +} + +void perf_evsel__calc_id_pos(struct perf_evsel *evsel) +{ + evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type); + evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); +} + void hists__init(struct hists *hists) { memset(hists, 0, sizeof(*hists)); @@ -63,6 +129,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, if (!(evsel->attr.sample_type & bit)) { evsel->attr.sample_type |= bit; evsel->sample_size += sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } @@ -72,12 +139,19 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, if (evsel->attr.sample_type & bit) { evsel->attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } -void perf_evsel__set_sample_id(struct perf_evsel *evsel) +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool can_sample_identifier) { - perf_evsel__set_sample_bit(evsel, ID); + if (can_sample_identifier) { + perf_evsel__reset_sample_bit(evsel, ID); + perf_evsel__set_sample_bit(evsel, IDENTIFIER); + } else { + perf_evsel__set_sample_bit(evsel, ID); + } evsel->attr.read_format |= PERF_FORMAT_ID; } @@ -90,6 +164,7 @@ void perf_evsel__init(struct perf_evsel *evsel, INIT_LIST_HEAD(&evsel->node); hists__init(&evsel->hists); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); + perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) @@ -509,7 +584,7 @@ void perf_evsel__config(struct perf_evsel *evsel, * We need ID even in case of single event, because * PERF_SAMPLE_READ process ID specific data. */ - perf_evsel__set_sample_id(evsel); + perf_evsel__set_sample_id(evsel, false); /* * Apply group format only if we belong to group @@ -1088,6 +1163,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, array += ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1; + if (type & PERF_SAMPLE_IDENTIFIER) { + sample->id = *array; + array--; + } + if (type & PERF_SAMPLE_CPU) { u.val64 = *array; if (swapped) { @@ -1184,6 +1264,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (evsel->sample_size + sizeof(event->header) > event->header.size) return -EFAULT; + data->id = -1ULL; + if (type & PERF_SAMPLE_IDENTIFIER) { + data->id = *array; + array++; + } + if (type & PERF_SAMPLE_IP) { data->ip = *array; array++; @@ -1214,7 +1300,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } - data->id = -1ULL; if (type & PERF_SAMPLE_ID) { data->id = *array; array++; @@ -1396,6 +1481,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array = event->sample.array; + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + if (type & PERF_SAMPLE_IP) { *array = sample->ip; array++; @@ -1584,6 +1674,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value) 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), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 532a5f925da..4a7bdc713ba 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -48,6 +48,12 @@ struct perf_sample_id { * @name - Can be set to retain the original event name passed by the user, * so that when showing results in tools such as 'perf stat', we * show the name used, not some alias. + * @id_pos: the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of + * struct sample_event + * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all + * is used there is an id sample appended to non-sample events */ struct perf_evsel { struct list_head node; @@ -74,6 +80,8 @@ struct perf_evsel { } handler; struct cpu_map *cpus; unsigned int sample_size; + int id_pos; + int is_pos; bool supported; bool needs_swap; /* parse modifier helper */ @@ -104,6 +112,9 @@ void perf_evsel__delete(struct perf_evsel *evsel); void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts); +int __perf_evsel__sample_size(u64 sample_type); +void perf_evsel__calc_id_pos(struct perf_evsel *evsel); + bool perf_evsel__is_cache_op_valid(u8 type, u8 op); #define PERF_EVSEL__MAX_ALIASES 8 @@ -142,7 +153,8 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, #define perf_evsel__reset_sample_bit(evsel, bit) \ __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) -void perf_evsel__set_sample_id(struct perf_evsel *evsel); +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool use_sample_identifier); int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 9b5ef793313..18d73aa2f0f 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -1,11 +1,83 @@ #include "evlist.h" #include "evsel.h" #include "cpumap.h" +#include "parse-events.h" + +typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); + +static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + int err = -EAGAIN, fd; + + evlist = perf_evlist__new(); + if (!evlist) + return -ENOMEM; + + if (parse_events(evlist, str)) + goto out_delete; + + evsel = perf_evlist__first(evlist); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) + goto out_delete; + close(fd); + + fn(evsel); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) { + if (errno == EINVAL) + err = -EINVAL; + goto out_delete; + } + close(fd); + err = 0; + +out_delete: + perf_evlist__delete(evlist); + return err; +} + +static bool perf_probe_api(setup_probe_fn_t fn) +{ + const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL}; + struct cpu_map *cpus; + int cpu, ret, i = 0; + + cpus = cpu_map__new(NULL); + if (!cpus) + return false; + cpu = cpus->map[0]; + cpu_map__delete(cpus); + + do { + ret = perf_do_probe_api(fn, cpu, try[i++]); + if (!ret) + return true; + } while (ret == -EAGAIN && try[i]); + + return false; +} + +static void perf_probe_sample_identifier(struct perf_evsel *evsel) +{ + evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; +} + +bool perf_can_sample_identifier(void) +{ + return perf_probe_api(perf_probe_sample_identifier); +} void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts) { struct perf_evsel *evsel; + bool use_sample_identifier = false; + /* * Set the evsel leader links before we configure attributes, * since some might depend on this info. @@ -16,10 +88,21 @@ void perf_evlist__config(struct perf_evlist *evlist, if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - list_for_each_entry(evsel, &evlist->entries, node) { + list_for_each_entry(evsel, &evlist->entries, node) perf_evsel__config(evsel, opts); - if (evlist->nr_entries > 1) - perf_evsel__set_sample_id(evsel); + if (evlist->nr_entries > 1) { + struct perf_evsel *first = perf_evlist__first(evlist); + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->attr.sample_type == first->attr.sample_type) + continue; + use_sample_identifier = perf_can_sample_identifier(); + break; + } + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__set_sample_id(evsel, use_sample_identifier); } + + perf_evlist__set_id_pos(evlist); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c3ac483be48..07642a7b934 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -739,7 +739,7 @@ static void perf_session__print_tstamp(struct perf_session *session, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = perf_evlist__sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); if (event->header.type != PERF_RECORD_SAMPLE && !perf_evlist__sample_id_all(session->evlist)) { -- cgit v1.2.3-70-g09d2 From 0b8c25d949e010274c6697c570b772797ebc7c27 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 28 Jul 2013 09:48:32 -0600 Subject: perf tools: Fix symbol offset computation for some dsos For some dsos (e.g., libc, libpthread, kernel modules) the symbol offset is huge. e.g., qemu-kvm 17238/17242 [007] 762235.640311: ffffffff816288a1 __schedule+0x451 ([kernel.kallsyms]) ffffffff81629609 schedule+0x29 ([kernel.kallsyms]) ffffffffa00a6ded kvm_vcpu_block+0xffffffffa00a106d (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffffa00bae6b kvm_arch_vcpu_ioctl_run+0xffffffffa00a118b (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffffa00a4d7a kvm_vcpu_ioctl+0xffffffffa00a141a (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffff811a7bdb do_vfs_ioctl+0x8b ([kernel.kallsyms]) ffffffff811a80c1 sys_ioctl+0x91 ([kernel.kallsyms]) ffffffff81633182 system_call+0x72 ([kernel.kallsyms]) 7f882a97af27 __GI___ioctl+0x7f882a891007 (/lib64/libc-2.14.90.so) 100000002 [unknown] ([unknown]) It seems to be maps with a non-0 start. Taking that into account the offsets are correct: qemu-kvm 17238/17242 [007] 762235.640311: ffffffff816288a1 __schedule+0x451 ([kernel.kallsyms]) ffffffff81629609 schedule+0x29 ([kernel.kallsyms]) ffffffffa00a6ded kvm_vcpu_block+0x6d (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffffa00bae6b kvm_arch_vcpu_ioctl_run+0x18b (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffffa00a4d7a kvm_vcpu_ioctl+0x41a (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko) ffffffff811a7bdb do_vfs_ioctl+0x8b ([kernel.kallsyms]) ffffffff811a80c1 sys_ioctl+0x91 ([kernel.kallsyms]) ffffffff81633182 system_call+0x72 ([kernel.kallsyms]) 7f882a97af27 __GI___ioctl+0x7 (/lib64/libc-2.14.90.so) 100000002 [unknown] ([unknown]) Signed-off-by: David Ahern Link: http://lkml.kernel.org/r/1375026512-45826-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 1 + tools/perf/util/symbol.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 07642a7b934..1fc0c628683 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1513,6 +1513,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, printf(" "); if (print_symoffset) { al.addr = node->ip; + al.map = node->map; symbol__fprintf_symname_offs(node->sym, &al, stdout); } else symbol__fprintf_symname(node->sym, stdout); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 77f3b95bb46..7eb0362f4ff 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -259,7 +259,10 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym, if (sym && sym->name) { length = fprintf(fp, "%s", sym->name); if (al) { - offset = al->addr - sym->start; + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; length += fprintf(fp, "+0x%lx", offset); } return length; -- cgit v1.2.3-70-g09d2