From 6490dda55dcabbd5cf408387f932c9343a22c872 Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Sun, 15 Sep 2024 10:34:29 +0900 Subject: libperf: Explicitly specify install-html dependencies install_doc of tools/lib/perf/Makefile invokes install-man, install-html, and install-examples of tools/lib/perf/Documentation/Makefile at once. This invocation succeeds when make runs in serial but can fail when make runs in parallel because while install-man of tools/lib/perf/Documentation/Makefile depends on all, install-html depends on nothing and can run ahead of all. Explicitly specify the dependencies of install-html to ensure that they are resolved before install-html. Signed-off-by: Akihiko Odaki Link: https://lore.kernel.org/r/20240915-perf-v1-1-cbfd9cd1d482@daynix.com Signed-off-by: Namhyung Kim --- tools/lib/perf/Documentation/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib') diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile index 972754082a85..573ca5b27556 100644 --- a/tools/lib/perf/Documentation/Makefile +++ b/tools/lib/perf/Documentation/Makefile @@ -121,7 +121,7 @@ install-man: all $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \ $(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir); -install-html: +install-html: $(MAN_HTML) $(call QUIET_INSTALL, html) \ $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \ $(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \ -- cgit v1.2.3 From 80c281fca252827facd05875b8d9d36d7aad0f8d Mon Sep 17 00:00:00 2001 From: Ben Gainey Date: Tue, 1 Oct 2024 13:15:04 +0100 Subject: tools/perf: Correctly calculate sample period for inherited SAMPLE_READ values Sample period calculation in deliver_sample_value is updated to calculate the per-thread period delta for events that are inherit + PERF_SAMPLE_READ. When the sampling event has this configuration, the read_format.id is used with the tid from the sample to lookup the storage of the previously accumulated counter total before calculating the delta. All existing valid configurations where read_format.value represents some global value continue to use just the read_format.id to locate the storage of the previously accumulated total. perf_sample_id is modified to support tracking per-thread values, along with the existing global per-id values. In the per-thread case, values are stored in a hash by tid within the perf_sample_id, and are dynamically allocated as the number is not known ahead of time. Signed-off-by: Ben Gainey Cc: james.clark@arm.com Link: https://lore.kernel.org/r/20241001121505.1009685-2-ben.gainey@arm.com Signed-off-by: Namhyung Kim --- tools/lib/perf/evsel.c | 48 +++++++++++++++++++++++++ tools/lib/perf/include/internal/evsel.h | 63 +++++++++++++++++++++++++++++++-- tools/perf/util/session.c | 28 ++++++++++----- 3 files changed, 128 insertions(+), 11 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index c07160953224..c475319e2e41 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { INIT_LIST_HEAD(&evsel->node); + INIT_LIST_HEAD(&evsel->per_stream_periods); evsel->attr = *attr; evsel->idx = idx; evsel->leader = evsel; @@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) void perf_evsel__free_id(struct perf_evsel *evsel) { + struct perf_sample_id_period *pos, *n; + xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; zfree(&evsel->id); evsel->ids = 0; + + perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) { + list_del_init(&pos->node); + free(pos); + } +} + +bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel) +{ + return (evsel->attr.sample_type & PERF_SAMPLE_READ) && + (evsel->attr.sample_type & PERF_SAMPLE_TID) && + evsel->attr.inherit; +} + +u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, bool per_thread) +{ + struct hlist_head *head; + struct perf_sample_id_period *res; + int hash; + + if (!per_thread) + return &sid->period; + + hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS); + head = &sid->periods[hash]; + + hlist_for_each_entry(res, head, hnode) + if (res->tid == tid) + return &res->period; + + if (sid->evsel == NULL) + return NULL; + + res = zalloc(sizeof(struct perf_sample_id_period)); + if (res == NULL) + return NULL; + + INIT_LIST_HEAD(&res->node); + res->tid = tid; + + list_add_tail(&res->node, &sid->evsel->per_stream_periods); + hlist_add_head(&res->hnode, &sid->periods[hash]); + + return &res->period; } void perf_counts_values__scale(struct perf_counts_values *count, diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index 5cd220a61962..ea78defa77d0 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -11,6 +11,32 @@ struct perf_thread_map; struct xyarray; +/** + * The per-thread accumulated period storage node. + */ +struct perf_sample_id_period { + struct list_head node; + struct hlist_node hnode; + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; + /* The TID that the values belongs to */ + u32 tid; +}; + +/** + * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the + * per_stream_periods + * @evlist:perf_evsel instance to iterate + * @item: struct perf_sample_id_period iterator + * @tmp: struct perf_sample_id_period temp iterator + */ +#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \ + list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node) + + +#define PERF_SAMPLE_ID__HLIST_BITS 4 +#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS) + /* * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are * more than one entry in the evlist. @@ -34,8 +60,32 @@ struct perf_sample_id { pid_t machine_pid; struct perf_cpu vcpu; - /* Holds total ID period value for PERF_SAMPLE_READ processing. */ - u64 period; + /* + * Per-thread, and global event counts are mutually exclusive: + * Whilst it is possible to combine events into a group with differing + * values of PERF_SAMPLE_READ, it is not valid to have inconsistent + * values for `inherit`. Therefore it is not possible to have a + * situation where a per-thread event is sampled as a global event; + * all !inherit groups are global, and all groups where the sampling + * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event + * that is part of such a group that is inherit but not PERF_SAMPLE_READ + * will be read as per-thread. If such an event can also trigger a + * sample (such as with sample_period > 0) then it will not cause + * `read_format` to be included in its PERF_RECORD_SAMPLE, and + * therefore will not expose the per-thread group members as global. + */ + union { + /* + * Holds total ID period value for PERF_SAMPLE_READ processing + * (when period is not per-thread). + */ + u64 period; + /* + * Holds total ID period value for PERF_SAMPLE_READ processing + * (when period is per-thread). + */ + struct hlist_head periods[PERF_SAMPLE_ID__HLIST_SIZE]; + }; }; struct perf_evsel { @@ -58,6 +108,10 @@ struct perf_evsel { u32 ids; struct perf_evsel *leader; + /* For events where the read_format value is per-thread rather than + * global, stores the per-thread cumulative period */ + struct list_head per_stream_periods; + /* parse modifier helper */ int nr_members; /* @@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__free_id(struct perf_evsel *evsel); +bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel); + +u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, + bool per_thread); + #endif /* __LIBPERF_INTERNAL_EVSEL_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index dbaf07bf6c5f..507e6cba9545 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1171,18 +1171,24 @@ static int deliver_sample_value(struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, - struct machine *machine) + struct machine *machine, + bool per_thread) { struct perf_sample_id *sid = evlist__id2sid(evlist, v->id); struct evsel *evsel; + u64 *storage = NULL; if (sid) { + storage = perf_sample_id__get_period_storage(sid, sample->tid, per_thread); + } + + if (storage) { sample->id = v->id; - sample->period = v->value - sid->period; - sid->period = v->value; + sample->period = v->value - *storage; + *storage = v->value; } - if (!sid || sid->evsel == NULL) { + if (!storage || sid->evsel == NULL) { ++evlist->stats.nr_unknown_id; return 0; } @@ -1203,17 +1209,19 @@ static int deliver_sample_group(struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct machine *machine, - u64 read_format) + u64 read_format, + bool per_thread) { int ret = -EINVAL; struct sample_read_value *v = sample->read.group.values; if (tool->dont_split_sample_group) - return deliver_sample_value(evlist, tool, event, sample, v, machine); + return deliver_sample_value(evlist, tool, event, sample, v, machine, + per_thread); sample_read_group__for_each(v, sample->read.group.nr, read_format) { ret = deliver_sample_value(evlist, tool, event, sample, v, - machine); + machine, per_thread); if (ret) break; } @@ -1228,6 +1236,7 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool /* We know evsel != NULL. */ u64 sample_type = evsel->core.attr.sample_type; u64 read_format = evsel->core.attr.read_format; + bool per_thread = perf_evsel__attr_has_per_thread_sample_period(&evsel->core); /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) @@ -1236,10 +1245,11 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) return deliver_sample_group(evlist, tool, event, sample, - machine, read_format); + machine, read_format, per_thread); else return deliver_sample_value(evlist, tool, event, sample, - &sample->read.one, machine); + &sample->read.one, machine, + per_thread); } static int machines__deliver_event(struct machines *machines, -- cgit v1.2.3 From 5ce42b5de461c3154f61a023b191dd6b77ee66c0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 25 Oct 2024 12:21:00 -0700 Subject: tools subcmd: Add non-waitpid check_if_command_finished() Using waitpid can cause stdout/stderr of the child process to be lost. Use Linux's /prod//status file to determine if the process has reached the zombie state. Use the 'status' file rather than 'stat' to avoid issues around skipping the process name. Tested-by: James Clark Signed-off-by: Ian Rogers Cc: Colin Ian King Cc: Howard Chu Cc: Weilin Wang Cc: Ilya Leoshkevich Cc: Thomas Richter Cc: Andi Kleen Cc: Dapeng Mi Cc: Athira Jajeev Cc: Michael Petlan Cc: Veronika Molnarova Link: https://lore.kernel.org/r/20241025192109.132482-2-irogers@google.com Signed-off-by: Namhyung Kim --- tools/lib/subcmd/run-command.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c index 4e3a557a2f37..0a764c25c384 100644 --- a/tools/lib/subcmd/run-command.c +++ b/tools/lib/subcmd/run-command.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -217,8 +218,40 @@ static int wait_or_whine(struct child_process *cmd, bool block) int check_if_command_finished(struct child_process *cmd) { +#ifdef __linux__ + char filename[FILENAME_MAX + 12]; + char status_line[256]; + FILE *status_file; + + /* + * Check by reading /proc//status as calling waitpid causes + * stdout/stderr to be closed and data lost. + */ + sprintf(filename, "/proc/%d/status", cmd->pid); + status_file = fopen(filename, "r"); + if (status_file == NULL) { + /* Open failed assume finish_command was called. */ + return true; + } + while (fgets(status_line, sizeof(status_line), status_file) != NULL) { + char *p; + + if (strncmp(status_line, "State:", 6)) + continue; + + fclose(status_file); + p = status_line + 6; + while (isspace(*p)) + p++; + return *p == 'Z' ? 1 : 0; + } + /* Read failed assume finish_command was called. */ + fclose(status_file); + return 1; +#else wait_or_whine(cmd, /*block=*/false); return cmd->finished; +#endif } int finish_command(struct child_process *cmd) -- cgit v1.2.3 From f4db95b68ae68ebaf91d35cc0487ac1cbd04261e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 8 Nov 2024 16:37:53 -0800 Subject: tools api io: Ensure line_len_out is always initialized Ensure initialization to avoid compiler warnings about potential use of uninitialized variables. Signed-off-by: Ian Rogers Cc: Ravi Bangoria Cc: Yoshihiro Furudera Cc: Howard Chu Cc: Ze Gao Cc: Changbin Du Cc: Junhao He Cc: Weilin Wang Cc: James Clark Cc: Oliver Upton Cc: Athira Jajeev Link: https://lore.kernel.org/r/20241109003759.473460-2-irogers@google.com Signed-off-by: Namhyung Kim --- tools/lib/api/io.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/lib') diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h index d3eb04d1bc89..1731996b2c32 100644 --- a/tools/lib/api/io.h +++ b/tools/lib/api/io.h @@ -189,6 +189,7 @@ static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_ err_out: free(line); *line_out = NULL; + *line_len_out = 0; return -ENOMEM; } -- cgit v1.2.3 From 31bedc1fb1d93250ae1900ee92ccd56689956d22 Mon Sep 17 00:00:00 2001 From: Luo Yifan Date: Mon, 11 Nov 2024 17:17:01 +0800 Subject: libsubcmd: Move va_end() before exit This patch makes a minor adjustment by moving the va_end call before exit. Since the exit() function terminates the program, any code after exit(128) (i.e., va_end(params)) is unreachable and thus not executed. Placing va_end before exit ensures that the va_list is properly cleaned up. Signed-off-by: Luo Yifan Cc: Josh Poimboeuf Link: https://lore.kernel.org/r/20241111091701.275496-1-luoyifan@cmss.chinamobile.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/subcmd/subcmd-util.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib') diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index dfac76e35ac7..c742b08815dc 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -20,8 +20,8 @@ static __noreturn inline void die(const char *err, ...) va_start(params, err); report(" Fatal: ", err, params); - exit(128); va_end(params); + exit(128); } #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) -- cgit v1.2.3