struct perf_record_header_feature;
struct perf_record_compressed;
struct perf_record_compressed2;
+ struct perf_record_schedstat_cpu;
+ struct perf_record_schedstat_domain;
--
DESCRIPTION
cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ)
HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h
+HDRS += schedstat-v15.h
INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h
INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf
struct perf_record_bpf_metadata_entry entries[];
};
+struct perf_record_schedstat_cpu_v15 {
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver) _type _name
+#include "schedstat-v15.h"
+#undef CPU_FIELD
+};
+
+struct perf_record_schedstat_cpu {
+ struct perf_event_header header;
+ __u64 timestamp;
+ __u32 cpu;
+ __u16 version;
+ /* Padding */
+ char __pad[2];
+ union {
+ struct perf_record_schedstat_cpu_v15 v15;
+ };
+};
+
+struct perf_record_schedstat_domain_v15 {
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver) _type _name
+#include "schedstat-v15.h"
+#undef DOMAIN_FIELD
+};
+
+#define DOMAIN_NAME_LEN 16
+
+struct perf_record_schedstat_domain {
+ struct perf_event_header header;
+ __u64 timestamp;
+ __u32 cpu;
+ __u16 version;
+ __u16 domain;
+ union {
+ struct perf_record_schedstat_domain_v15 v15;
+ };
+};
+
enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_USER_TYPE_START = 64,
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_FINISHED_INIT = 82,
PERF_RECORD_COMPRESSED2 = 83,
PERF_RECORD_BPF_METADATA = 84,
+ PERF_RECORD_SCHEDSTAT_CPU = 85,
+ PERF_RECORD_SCHEDSTAT_DOMAIN = 86,
PERF_RECORD_HEADER_MAX
};
struct perf_record_compressed pack;
struct perf_record_compressed2 pack2;
struct perf_record_bpf_metadata bpf_metadata;
+ struct perf_record_schedstat_cpu schedstat_cpu;
+ struct perf_record_schedstat_domain schedstat_domain;
};
#endif /* __LIBPERF_EVENT_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CPU_FIELD
+CPU_FIELD(__u32, yld_count, "sched_yield() count",
+ "%11u", false, yld_count, v15);
+CPU_FIELD(__u32, array_exp, "Legacy counter can be ignored",
+ "%11u", false, array_exp, v15);
+CPU_FIELD(__u32, sched_count, "schedule() called",
+ "%11u", false, sched_count, v15);
+CPU_FIELD(__u32, sched_goidle, "schedule() left the processor idle",
+ "%11u", true, sched_count, v15);
+CPU_FIELD(__u32, ttwu_count, "try_to_wake_up() was called",
+ "%11u", false, ttwu_count, v15);
+CPU_FIELD(__u32, ttwu_local, "try_to_wake_up() was called to wake up the local cpu",
+ "%11u", true, ttwu_count, v15);
+CPU_FIELD(__u64, rq_cpu_time, "total runtime by tasks on this processor (in jiffies)",
+ "%11llu", false, rq_cpu_time, v15);
+CPU_FIELD(__u64, run_delay, "total waittime by tasks on this processor (in jiffies)",
+ "%11llu", true, rq_cpu_time, v15);
+CPU_FIELD(__u64, pcount, "total timeslices run on this cpu",
+ "%11llu", false, pcount, v15);
+#endif
+
+#ifdef DOMAIN_FIELD
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category idle> ");
+#endif
+DOMAIN_FIELD(__u32, idle_lb_count,
+ "load_balance() count on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_balanced,
+ "load_balance() found balanced on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_failed,
+ "load_balance() move task failed on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_imbalance,
+ "imbalance sum on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_gained,
+ "pull_task() count on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_hot_gained,
+ "pull_task() when target task was cache-hot on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_nobusyq,
+ "load_balance() failed to find busier queue on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_nobusyg,
+ "load_balance() failed to find busier group on cpu idle", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(idle_lb_success_count, "load_balance() success count on cpu idle", "%11u",
+ idle_lb_count, idle_lb_balanced, idle_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(idle_lb_avg_pulled,
+ "avg task pulled per successful lb attempt (cpu idle)", "%11.2Lf",
+ idle_lb_count, idle_lb_balanced, idle_lb_failed, idle_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category busy> ");
+#endif
+DOMAIN_FIELD(__u32, busy_lb_count,
+ "load_balance() count on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_balanced,
+ "load_balance() found balanced on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_failed,
+ "load_balance() move task failed on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_imbalance,
+ "imbalance sum on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_gained,
+ "pull_task() count on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_hot_gained,
+ "pull_task() when target task was cache-hot on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_nobusyq,
+ "load_balance() failed to find busier queue on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_nobusyg,
+ "load_balance() failed to find busier group on cpu busy", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(busy_lb_success_count, "load_balance() success count on cpu busy", "%11u",
+ busy_lb_count, busy_lb_balanced, busy_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(busy_lb_avg_pulled,
+ "avg task pulled per successful lb attempt (cpu busy)", "%11.2Lf",
+ busy_lb_count, busy_lb_balanced, busy_lb_failed, busy_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category newidle> ");
+#endif
+DOMAIN_FIELD(__u32, newidle_lb_count,
+ "load_balance() count on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_balanced,
+ "load_balance() found balanced on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_failed,
+ "load_balance() move task failed on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance,
+ "imbalance sum on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_gained,
+ "pull_task() count on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_hot_gained,
+ "pull_task() when target task was cache-hot on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyq,
+ "load_balance() failed to find busier queue on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyg,
+ "load_balance() failed to find busier group on cpu newly idle", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(newidle_lb_success_count,
+ "load_balance() success count on cpu newly idle", "%11u",
+ newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(newidle_lb_avg_pulled,
+ "avg task pulled per successful lb attempt (cpu newly idle)", "%11.2Lf",
+ newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, newidle_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category active_load_balance()> ");
+#endif
+DOMAIN_FIELD(__u32, alb_count,
+ "active_load_balance() count", "%11u", false, v15);
+DOMAIN_FIELD(__u32, alb_failed,
+ "active_load_balance() move task failed", "%11u", false, v15);
+DOMAIN_FIELD(__u32, alb_pushed,
+ "active_load_balance() successfully moved a task", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_exec()> ");
+#endif
+DOMAIN_FIELD(__u32, sbe_count,
+ "sbe_count is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbe_balanced,
+ "sbe_balanced is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbe_pushed,
+ "sbe_pushed is not used", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_fork()> ");
+#endif
+DOMAIN_FIELD(__u32, sbf_count,
+ "sbf_count is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbf_balanced,
+ "sbf_balanced is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbf_pushed,
+ "sbf_pushed is not used", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Wakeup Info> ");
+#endif
+DOMAIN_FIELD(__u32, ttwu_wake_remote,
+ "try_to_wake_up() awoke a task that last ran on a diff cpu", "%11u", false, v15);
+DOMAIN_FIELD(__u32, ttwu_move_affine,
+ "try_to_wake_up() moved task because cache-cold on own cpu", "%11u", false, v15);
+DOMAIN_FIELD(__u32, ttwu_move_balance,
+ "try_to_wake_up() started passive balancing", "%11u", false, v15);
+#endif /* DOMAIN_FIELD */
inject.tool.compressed = perf_event__repipe_op4_synth;
inject.tool.auxtrace = perf_event__repipe_auxtrace;
inject.tool.bpf_metadata = perf_event__repipe_op2_synth;
+ inject.tool.schedstat_cpu = perf_event__repipe_op2_synth;
+ inject.tool.schedstat_domain = perf_event__repipe_op2_synth;
inject.tool.dont_split_sample_group = true;
inject.tool.merge_deferred_callchains = false;
inject.session = __perf_session__new(&data, &inject.tool,
#include "util/debug.h"
#include "util/event.h"
#include "util/util.h"
+#include "util/synthetic-events.h"
+#include "util/target.h"
#include <linux/kernel.h>
#include <linux/log2.h>
#define MAX_PRIO 140
static const char *cpu_list;
+static struct perf_cpu_map *user_requested_cpus;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
struct sched_atom;
volatile bool thread_funcs_exit;
const char *prio_str;
DECLARE_BITMAP(prio_bitmap, MAX_PRIO);
+
+ struct perf_session *session;
+ struct perf_data *data;
};
/* per thread run time data */
sort_dimension__add("pid", &sched->cmp_pid);
}
+static int process_synthesized_schedstat_event(const struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+ struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+
+ if (perf_data__write(sched->data, event, event->header.size) <= 0) {
+ pr_err("failed to write perf data, error: %m\n");
+ return -1;
+ }
+
+ sched->session->header.data_size += event->header.size;
+ return 0;
+}
+
+static void sighandler(int sig __maybe_unused)
+{
+}
+
+static int enable_sched_schedstats(int *reset)
+{
+ char path[PATH_MAX];
+ FILE *fp;
+ char ch;
+
+ snprintf(path, PATH_MAX, "%s/sys/kernel/sched_schedstats", procfs__mountpoint());
+ fp = fopen(path, "w+");
+ if (!fp) {
+ pr_err("Failed to open %s\n", path);
+ return -1;
+ }
+
+ ch = getc(fp);
+ if (ch == '0') {
+ *reset = 1;
+ rewind(fp);
+ putc('1', fp);
+ fclose(fp);
+ }
+ return 0;
+}
+
+static int disable_sched_schedstat(void)
+{
+ char path[PATH_MAX];
+ FILE *fp;
+
+ snprintf(path, PATH_MAX, "%s/sys/kernel/sched_schedstats", procfs__mountpoint());
+ fp = fopen(path, "w");
+ if (!fp) {
+ pr_err("Failed to open %s\n", path);
+ return -1;
+ }
+
+ putc('0', fp);
+ fclose(fp);
+ return 0;
+}
+
+/* perf.data or any other output file name used by stats subcommand (only). */
+const char *output_name;
+
+static int perf_sched__schedstat_record(struct perf_sched *sched,
+ int argc, const char **argv)
+{
+ struct perf_session *session;
+ struct target target = {};
+ struct evlist *evlist;
+ int reset = 0;
+ int err = 0;
+ int fd;
+ struct perf_data data = {
+ .path = output_name,
+ .mode = PERF_DATA_MODE_WRITE,
+ };
+
+ signal(SIGINT, sighandler);
+ signal(SIGCHLD, sighandler);
+ signal(SIGTERM, sighandler);
+
+ evlist = evlist__new();
+ if (!evlist)
+ return -ENOMEM;
+
+ session = perf_session__new(&data, &sched->tool);
+ if (IS_ERR(session)) {
+ pr_err("Perf session creation failed.\n");
+ evlist__delete(evlist);
+ return PTR_ERR(session);
+ }
+
+ session->evlist = evlist;
+
+ sched->session = session;
+ sched->data = &data;
+
+ fd = perf_data__fd(&data);
+
+ /*
+ * Capture all important metadata about the system. Although they are
+ * not used by `perf sched stats` tool directly, they provide useful
+ * information about profiled environment.
+ */
+ perf_header__set_feat(&session->header, HEADER_HOSTNAME);
+ perf_header__set_feat(&session->header, HEADER_OSRELEASE);
+ perf_header__set_feat(&session->header, HEADER_VERSION);
+ perf_header__set_feat(&session->header, HEADER_ARCH);
+ perf_header__set_feat(&session->header, HEADER_NRCPUS);
+ perf_header__set_feat(&session->header, HEADER_CPUDESC);
+ perf_header__set_feat(&session->header, HEADER_CPUID);
+ perf_header__set_feat(&session->header, HEADER_TOTAL_MEM);
+ perf_header__set_feat(&session->header, HEADER_CMDLINE);
+ perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
+ perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
+ perf_header__set_feat(&session->header, HEADER_CACHE);
+ perf_header__set_feat(&session->header, HEADER_MEM_TOPOLOGY);
+ perf_header__set_feat(&session->header, HEADER_HYBRID_TOPOLOGY);
+ perf_header__set_feat(&session->header, HEADER_CPU_DOMAIN_INFO);
+
+ err = perf_session__write_header(session, evlist, fd, false);
+ if (err < 0)
+ goto out;
+
+ /*
+ * `perf sched stats` does not support workload profiling (-p pid)
+ * since /proc/schedstat file contains cpu specific data only. Hence, a
+ * profile target is either set of cpus or systemwide, never a process.
+ * Note that, although `-- <workload>` is supported, profile data are
+ * still cpu/systemwide.
+ */
+ if (cpu_list)
+ target.cpu_list = cpu_list;
+ else
+ target.system_wide = true;
+
+ if (argc) {
+ err = evlist__prepare_workload(evlist, &target, argv, false, NULL);
+ if (err)
+ goto out;
+ }
+
+ err = evlist__create_maps(evlist, &target);
+ if (err < 0)
+ goto out;
+
+ user_requested_cpus = evlist->core.user_requested_cpus;
+
+ err = perf_event__synthesize_schedstat(&(sched->tool),
+ process_synthesized_schedstat_event,
+ user_requested_cpus);
+ if (err < 0)
+ goto out;
+
+ err = enable_sched_schedstats(&reset);
+ if (err < 0)
+ goto out;
+
+ if (argc)
+ evlist__start_workload(evlist);
+
+ /* wait for signal */
+ pause();
+
+ if (reset) {
+ err = disable_sched_schedstat();
+ if (err < 0)
+ goto out;
+ }
+
+ err = perf_event__synthesize_schedstat(&(sched->tool),
+ process_synthesized_schedstat_event,
+ user_requested_cpus);
+ if (err < 0)
+ goto out;
+
+ err = perf_session__write_header(session, evlist, fd, true);
+
+out:
+ if (!err)
+ fprintf(stderr, "[ perf sched stats: Wrote samples to %s ]\n", data.path);
+ else
+ fprintf(stderr, "[ perf sched stats: Failed !! ]\n");
+
+ evlist__delete(evlist);
+ close(fd);
+ return err;
+}
+
static bool schedstat_events_exposed(void)
{
/*
OPT_BOOLEAN('P', "pre-migrations", &sched.pre_migrations, "Show pre-migration wait time"),
OPT_PARENT(sched_options)
};
+ const struct option stats_options[] = {
+ OPT_STRING('o', "output", &output_name, "file",
+ "`stats record` with output filename"),
+ OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+ OPT_END()
+ };
const char * const latency_usage[] = {
"perf sched latency [<options>]",
"perf sched timehist [<options>]",
NULL
};
+ const char *stats_usage[] = {
+ "perf sched stats {record} [<options>]",
+ NULL
+ };
const char *const sched_subcommands[] = { "record", "latency", "map",
"replay", "script",
- "timehist", NULL };
+ "timehist", "stats", NULL };
const char *sched_usage[] = {
NULL,
NULL
ret = symbol__validate_sym_arguments();
if (!ret)
ret = perf_sched__timehist(&sched);
+ } else if (!strcmp(argv[0], "stats")) {
+ const char *const stats_subcommands[] = {"record", NULL};
+
+ argc = parse_options_subcommand(argc, argv, stats_options,
+ stats_subcommands,
+ stats_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ if (argv[0] && !strcmp(argv[0], "record")) {
+ if (argc)
+ argc = parse_options(argc, argv, stats_options,
+ stats_usage, 0);
+ return perf_sched__schedstat_record(&sched, argc, argv);
+ }
+ usage_with_options(stats_usage, stats_options);
} else {
usage_with_options(sched_usage, sched_options);
}
[PERF_RECORD_FINISHED_INIT] = "FINISHED_INIT",
[PERF_RECORD_COMPRESSED2] = "COMPRESSED2",
[PERF_RECORD_BPF_METADATA] = "BPF_METADATA",
+ [PERF_RECORD_SCHEDSTAT_CPU] = "SCHEDSTAT_CPU",
+ [PERF_RECORD_SCHEDSTAT_DOMAIN] = "SCHEDSTAT_DOMAIN",
};
const char *perf_event__name(unsigned int id)
return ret;
}
+size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp)
+{
+ struct perf_record_schedstat_cpu *cs = &event->schedstat_cpu;
+ size_t size = fprintf(fp, "\ncpu%u ", cs->cpu);
+ __u16 version = cs->version;
+
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver) \
+ size += fprintf(fp, "%" PRIu64 " ", (uint64_t)cs->_ver._name)
+
+ if (version == 15) {
+#include <perf/schedstat-v15.h>
+ return size;
+ }
+#undef CPU_FIELD
+
+ return fprintf(fp, "Unsupported /proc/schedstat version %d.\n",
+ event->schedstat_cpu.version);
+}
+
+size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp)
+{
+ struct perf_record_schedstat_domain *ds = &event->schedstat_domain;
+ __u16 version = ds->version;
+ size_t size = fprintf(fp, "\ndomain%u ", ds->domain);
+
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver) \
+ size += fprintf(fp, "%" PRIu64 " ", (uint64_t)ds->_ver._name)
+
+ if (version == 15) {
+#include <perf/schedstat-v15.h>
+ return size;
+ }
+#undef DOMAIN_FIELD
+
+ return fprintf(fp, "Unsupported /proc/schedstat version %d.\n",
+ event->schedstat_domain.version);
+}
+
size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_bpf_metadata(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine,FILE *fp);
+size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp);
int kallsyms__get_function_start(const char *kallsyms_filename,
}
}
+static void
+perf_event__schedstat_cpu_swap(union perf_event *event __maybe_unused,
+ bool sample_id_all __maybe_unused)
+{
+ /* FIXME */
+}
+
+static void
+perf_event__schedstat_domain_swap(union perf_event *event __maybe_unused,
+ bool sample_id_all __maybe_unused)
+{
+ /* FIXME */
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
[PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap,
[PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap,
[PERF_RECORD_TIME_CONV] = perf_event__time_conv_swap,
+ [PERF_RECORD_SCHEDSTAT_CPU] = perf_event__schedstat_cpu_swap,
+ [PERF_RECORD_SCHEDSTAT_DOMAIN] = perf_event__schedstat_domain_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
case PERF_RECORD_BPF_METADATA:
err = tool->bpf_metadata(tool, session, event);
break;
+ case PERF_RECORD_SCHEDSTAT_CPU:
+ err = tool->schedstat_cpu(tool, session, event);
+ break;
+ case PERF_RECORD_SCHEDSTAT_DOMAIN:
+ err = tool->schedstat_domain(tool, session, event);
+ break;
default:
err = -EINVAL;
break;
return ret;
}
+
+static union perf_event *__synthesize_schedstat_cpu(struct io *io, __u16 version,
+ __u64 *cpu, __u64 timestamp)
+{
+ struct perf_record_schedstat_cpu *cs;
+ union perf_event *event;
+ size_t size;
+ char ch;
+
+ size = sizeof(*cs);
+ size = PERF_ALIGN(size, sizeof(u64));
+ event = zalloc(size);
+
+ if (!event)
+ return NULL;
+
+ cs = &event->schedstat_cpu;
+ cs->header.type = PERF_RECORD_SCHEDSTAT_CPU;
+ cs->header.size = size;
+ cs->timestamp = timestamp;
+
+ if (io__get_char(io) != 'p' || io__get_char(io) != 'u')
+ goto out_cpu;
+
+ if (io__get_dec(io, (__u64 *)cpu) != ' ')
+ goto out_cpu;
+
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver) \
+ do { \
+ __u64 _tmp; \
+ ch = io__get_dec(io, &_tmp); \
+ if (ch != ' ' && ch != '\n') \
+ goto out_cpu; \
+ cs->_ver._name = _tmp; \
+ } while (0)
+
+ if (version == 15) {
+#include <perf/schedstat-v15.h>
+ }
+#undef CPU_FIELD
+
+ cs->cpu = *cpu;
+ cs->version = version;
+
+ return event;
+out_cpu:
+ free(event);
+ return NULL;
+}
+
+static union perf_event *__synthesize_schedstat_domain(struct io *io, __u16 version,
+ __u64 cpu, __u64 timestamp)
+{
+ struct perf_record_schedstat_domain *ds;
+ union perf_event *event = NULL;
+ __u64 d_num;
+ size_t size;
+ char ch;
+
+ if (io__get_char(io) != 'o' || io__get_char(io) != 'm' || io__get_char(io) != 'a' ||
+ io__get_char(io) != 'i' || io__get_char(io) != 'n')
+ return NULL;
+
+ ch = io__get_dec(io, &d_num);
+
+ /* Skip cpumask as it can be extracted from perf header */
+ while (io__get_char(io) != ' ')
+ continue;
+
+ size = sizeof(*ds);
+ size = PERF_ALIGN(size, sizeof(u64));
+ event = zalloc(size);
+
+ ds = &event->schedstat_domain;
+ ds->header.type = PERF_RECORD_SCHEDSTAT_DOMAIN;
+ ds->header.size = size;
+ ds->version = version;
+ ds->timestamp = timestamp;
+ ds->domain = d_num;
+
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver) \
+ do { \
+ __u64 _tmp; \
+ ch = io__get_dec(io, &_tmp); \
+ if (ch != ' ' && ch != '\n') \
+ goto out_domain; \
+ ds->_ver._name = _tmp; \
+ } while (0)
+
+ if (version == 15) {
+#include <perf/schedstat-v15.h>
+ }
+#undef DOMAIN_FIELD
+
+ ds->cpu = cpu;
+ goto out;
+
+out_domain:
+ free(event);
+ event = NULL;
+out:
+ return event;
+}
+
+int perf_event__synthesize_schedstat(const struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct perf_cpu_map *user_requested_cpus)
+{
+ char *line = NULL, path[PATH_MAX];
+ union perf_event *event = NULL;
+ size_t line_len = 0;
+ char bf[BUFSIZ];
+ __u64 timestamp;
+ __u64 cpu = -1;
+ __u16 version;
+ struct io io;
+ int ret = -1;
+ char ch;
+
+ snprintf(path, PATH_MAX, "%s/schedstat", procfs__mountpoint());
+ io.fd = open(path, O_RDONLY, 0);
+ if (io.fd < 0) {
+ pr_err("Failed to open %s. Possibly CONFIG_SCHEDSTAT is disabled.\n", path);
+ return -1;
+ }
+ io__init(&io, io.fd, bf, sizeof(bf));
+
+ if (io__getline(&io, &line, &line_len) < 0 || !line_len)
+ goto out;
+
+ if (!strcmp(line, "version 15\n")) {
+ version = 15;
+ } else {
+ pr_err("Unsupported %s version: %s", path, line + 8);
+ goto out_free_line;
+ }
+
+ if (io__getline(&io, &line, &line_len) < 0 || !line_len)
+ goto out_free_line;
+ timestamp = atol(line + 10);
+
+ /*
+ * FIXME: Can be optimized a bit by not synthesizing domain samples
+ * for filtered out cpus.
+ */
+ for (ch = io__get_char(&io); !io.eof; ch = io__get_char(&io)) {
+ struct perf_cpu this_cpu;
+
+ if (ch == 'c') {
+ event = __synthesize_schedstat_cpu(&io, version,
+ &cpu, timestamp);
+ } else if (ch == 'd') {
+ event = __synthesize_schedstat_domain(&io, version,
+ cpu, timestamp);
+ }
+ if (!event)
+ goto out_free_line;
+
+ this_cpu.cpu = cpu;
+
+ if (user_requested_cpus && !perf_cpu_map__has(user_requested_cpus, this_cpu))
+ continue;
+
+ if (process(tool, event, NULL, NULL) < 0) {
+ free(event);
+ goto out_free_line;
+ }
+
+ free(event);
+ }
+
+ ret = 0;
+
+out_free_line:
+ free(line);
+out:
+ close(io.fd);
+ return ret;
+}
struct perf_data *data,
perf_event__handler_t process);
+int perf_event__synthesize_schedstat(const struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct perf_cpu_map *user_requested_cpu);
#endif // __PERF_SYNTHETIC_EVENTS_H
{
if (dump_trace)
perf_event__fprintf_bpf_metadata(event, stdout);
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+static int process_schedstat_cpu_stub(const struct perf_tool *tool __maybe_unused,
+ struct perf_session *perf_session __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_schedstat_cpu(event, stdout);
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+static int process_schedstat_domain_stub(const struct perf_tool *tool __maybe_unused,
+ struct perf_session *perf_session __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_schedstat_domain(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
#endif
tool->finished_init = process_event_op2_stub;
tool->bpf_metadata = perf_event__process_bpf_metadata_stub;
+ tool->schedstat_cpu = process_schedstat_cpu_stub;
+ tool->schedstat_domain = process_schedstat_domain_stub;
}
bool perf_tool__compressed_is_stub(const struct perf_tool *tool)
stat_round,
feature,
finished_init,
- bpf_metadata;
+ bpf_metadata,
+ schedstat_cpu,
+ schedstat_domain;
event_op4 compressed;
event_op3 auxtrace;
bool ordered_events;
projects / thirdparty / linux.git / commitdiff
