mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-08-26 19:00:25 +00:00
Code Issues Releases Wiki Activity

perf/core improvement.

Browse source 
User visible:
 
 - Generate perf.data files from 'perf stat', to tap into the scripting
   capabilities perf has instead of defining a 'perf stat' specific scripting
   support to calculate event ratios, etc. Simple example:
 
   $ perf stat record -e cycles usleep 1
 
    Performance counter stats for 'usleep 1':
 
          1,134,996      cycles
 
        0.000670644 seconds time elapsed
 
   $ perf stat report
 
    Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':
 
          1,134,996      cycles
 
        0.000670644 seconds time elapsed
 
   $
 
   It generates PERF_RECORD_ userspace records to store the details:
 
   $ perf report -D | grep PERF_RECORD
   0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
   0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
   0x12a [0x40]: PERF_RECORD_STAT_CONFIG
   0x16a [0x30]: PERF_RECORD_STAT
   -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
   0x1da [0x18]: PERF_RECORD_STAT_ROUND
   [acme@ssdandy linux]$
 
   An effort was made to make perf.data files generated like this to not
   generate cryptic messages when processed by older tools.
 
   The 'perf script' bits need rebasing, will go up later.
 
 Jiri's cover letter for this series:
 
 The initial attempt defined its own formula lang and allowed triggering user's
 script on the end of the stat command:
 
   http://marc.info/?l=linux-kernel&m=136742146322273&w=2
 
 This patchset abandons the idea of new formula language and rather adds support
 to:
 
   - store stat data into perf.data file
   - add python support to process stat events
 
 Basically it allows to store stat data into perf.data and post process it with
 python scripts in a similar way we do for sampling data.
 
 The stat data are stored in new stat, stat-round, stat-config user events.
   stat        - stored for each read syscall of the counter
   stat round  - stored for each interval or end of the command invocation
   stat config - stores all the config information needed to process data
                 so report tool could restore the same output as record
 
 The python script can now define 'stat__<eventname>_<modifier>' functions
 to get stat events data and 'stat__interval' to get stat-round data.
 
 See CPI script example in scripts/python/stat-cpi.py.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJWcxCQAAoJENZQFvNTUqpAp/QQAJcu8R5MBLBiktaaJLEKawcZ
 cVh5OslEVL7oIaGYZOWtqLE2sRJiY/GdLlkxaVKhkxU7Zebbgy6G97N9zfAAzJd4
 zecKZ1GhHuGgncSflS9uzF2yTr8glZRTYTBgdqSzriUzvuicm/BRmwWRgfPPVVL6
 t/6foo+1HlKG0hpTek19uQZJtR0MgQyQ/HeYmPu8aQTYGrBzvb1iv5l4xW3L8zZV
 6z4VtoeymrC/U+O/lC4CJRQpl1nmTch+Zzm83NEyAD76N7Qy5ur2iwfYP80tJkYB
 9k7LTAiuWZnapRPY9SxsItqF/NHWUIDdQyg7AVu+mDqFzdqrOxxj+qLMNOiKlX0G
 zgIQqL6pQnEsYs2bo7RaRat/LeVl4wARfY1zHkvXoXI45e1Q+wOPB3br9Sl6m82M
 tuyNlgawhEGRTi4gsOmt+CmKRFr+Sa/QDDY1vIzIRUh6hAdb+WQtDBg8ZQR4+UjN
 6j/f6zZ5Ez0qh5sAPmlpyuD9Q2FHezgSoS5EAltrDDjd+qTZhFvX5E4cNGVBcLez
 pq2LbRmf0ZrXPpLLTTTLIjey6UF5dU3b94iQMUcHo2EpfluKhvhuNN4uLrufKlr0
 wZL6lyeNFw4hf0KU1DUki2/DBeNEA3nlQuhV6hJSGQ+C4r7Xh2NPD3xSGv9saRQh
 zJ3QwTM1XEqLF2JaaWth
 =qwUx
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-3' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull new perf tool feature from Arnaldo Carvalho de Melo:

" User visible changes:

  - Generate perf.data files from 'perf stat', to tap into the scripting
    capabilities perf has instead of defining a 'perf stat' specific scripting
    support to calculate event ratios, etc. Simple example:

    $ perf stat record -e cycles usleep 1

     Performance counter stats for 'usleep 1':

           1,134,996      cycles

         0.000670644 seconds time elapsed

    $ perf stat report

     Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

           1,134,996      cycles

         0.000670644 seconds time elapsed

    $

    It generates PERF_RECORD_ userspace records to store the details:

    $ perf report -D | grep PERF_RECORD
    0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
    0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
    0x12a [0x40]: PERF_RECORD_STAT_CONFIG
    0x16a [0x30]: PERF_RECORD_STAT
    -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
    0x1da [0x18]: PERF_RECORD_STAT_ROUND
    [acme@ssdandy linux]$

    An effort was made to make perf.data files generated like this to not
    generate cryptic messages when processed by older tools.

    The 'perf script' bits need rebasing, will go up later.

  Jiri's cover letter for this series:

  The initial attempt defined its own formula lang and allowed triggering user's
  script on the end of the stat command:

    http://marc.info/?l=linux-kernel&m=136742146322273&w=2

  This patchset abandons the idea of new formula language and rather adds support
  to:

    - store stat data into perf.data file
    - add python support to process stat events

  Basically it allows to store stat data into perf.data and post process it with
  python scripts in a similar way we do for sampling data.

  The stat data are stored in new stat, stat-round, stat-config user events.
    stat        - stored for each read syscall of the counter
    stat round  - stored for each interval or end of the command invocation
    stat config - stores all the config information needed to process data
                  so report tool could restore the same output as record

  The python script can now define 'stat__<eventname>_<modifier>' functions
  to get stat events data and 'stat__interval' to get stat-round data.

  See CPI script example in scripts/python/stat-cpi.py."

Also a few other changes:

User visible changes:

  - Make command line options always available, even when they
    depend on some feature being enabled, warning the user about
    use of such options (Wang Nan)

  - Support --vmlinux in perf record, useful, so far, for eBPF,
    where we will set up events that will be used in the record
    session (He Kuang)

  - Automatically disable collecting branch flags and cycles with
    --call-graph lbr. This allows avoiding a bunch of extra MSR
    reads in the PMI on Skylake.  (Andi Kleen)

Infrastructure changes:

  - Dump the stack when a 'perf test -v ' entry segfaults, so far we
    would have to run it under gdb with 'set follow-fork-mode child'
    set to get a proper backtrace (Arnaldo Carvalho de Melo)

  - Initialize the refcnt in 'struct thread' to 1 and fixup its
    users accordingly, so that we try to have the same refcount
    model accross the perf codebase (Arnaldo Carvalho de Melo)

  - More prep work for moving the subcmd infrastructure out of
    tools/perf/ and into tools/lib/subcmd/ to be used by other
    tools/ living utilities (Josh Poimboeuf)

  - Fix 'perf test' hist testcases when kptr_restrict is on (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar 2015-12-18 09:46:17 +01:00
commit d64fe8e6b3
24 changed files with 2054 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
tools/perf/Documentation/perf-stat.txt
View file

@ -10,6 +10,8 @@ SYNOPSIS
[verse]
'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>]
'perf stat' report [-i file]
DESCRIPTION
-----------
@ -22,6 +24,11 @@ OPTIONS
<command>...::
Any command you can specify in a shell.
record::
See STAT RECORD.
report::
See STAT REPORT.
-e::
--event=::
@ -159,6 +166,33 @@ filter out the startup phase of the program, which is often very different.
Print statistics of transactional execution if supported.
STAT RECORD
-----------
Stores stat data into perf data file.
-o file::
--output file::
Output file name.
STAT REPORT
-----------
Reads and reports stat data from perf data file.
-i file::
--input file::
Input file name.
--per-socket::
Aggregate counts per processor socket for system-wide mode measurements.
--per-core::
Aggregate counts per physical processor for system-wide mode measurements.
-A::
--no-aggr::
Do not aggregate counts across all monitored CPUs.
EXAMPLES
--------

2
tools/perf/builtin-record.c
View file

@ -452,6 +452,8 @@ static void record__init_features(struct record *rec)
if (!rec->opts.full_auxtrace)
perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
perf_header__clear_feat(&session->header, HEADER_STAT);
}
static volatile int workload_exec_errno;

614
tools/perf/builtin-stat.c
View file

@ -59,6 +59,9 @@
#include "util/thread.h"
#include "util/thread_map.h"
#include "util/counts.h"
#include "util/session.h"
#include "util/tool.h"
#include "asm/bug.h"
#include <stdlib.h>
#include <sys/prctl.h>
@ -126,6 +129,21 @@ static bool append_file;
static const char *output_name;
static int output_fd;
struct perf_stat {
bool record;
struct perf_data_file file;
struct perf_session *session;
u64 bytes_written;
struct perf_tool tool;
bool maps_allocated;
struct cpu_map *cpus;
struct thread_map *threads;
enum aggr_mode aggr_mode;
};
static struct perf_stat perf_stat;
#define STAT_RECORD perf_stat.record
static volatile int done = 0;
static struct perf_stat_config stat_config = {
@ -166,7 +184,11 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
* like tracepoints. Clear it up for counting.
*/
attr->sample_period = 0;
attr->sample_type = 0;
/*
* But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
* while avoiding that older tools show confusing messages.
*/
attr->sample_type = PERF_SAMPLE_IDENTIFIER;
/*
* Disabling all counters initially, they will be enabled
@ -202,6 +224,42 @@ static inline int nsec_counter(struct perf_evsel *evsel)
return 0;
}
static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
pr_err("failed to write perf data, error: %m\n");
return -1;
}
perf_stat.bytes_written += event->header.size;
return 0;
}
static int write_stat_round_event(u64 tm, u64 type)
{
return perf_event__synthesize_stat_round(NULL, tm, type,
process_synthesized_event,
NULL);
}
#define WRITE_STAT_ROUND_EVENT(time, interval) \
write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)
#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
static int
perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
struct perf_counts_values *count)
{
struct perf_sample_id *sid = SID(counter, cpu, thread);
return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
process_synthesized_event, NULL);
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
@ -225,6 +283,13 @@ static int read_counter(struct perf_evsel *counter)
count = perf_counts(counter->counts, cpu, thread);
if (perf_evsel__read(counter, cpu, thread, count))
return -1;
if (STAT_RECORD) {
if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
pr_err("failed to write stat event\n");
return -1;
}
}
}
}
@ -258,6 +323,11 @@ static void process_interval(void)
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
if (STAT_RECORD) {
if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL))
pr_err("failed to write stat round event\n");
}
print_counters(&rs, 0, NULL);
}
@ -288,6 +358,135 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
workload_exec_errno = info->si_value.sival_int;
}
static bool has_unit(struct perf_evsel *counter)
{
return counter->unit && *counter->unit;
}
static bool has_scale(struct perf_evsel *counter)
{
return counter->scale != 1;
}
static int perf_stat_synthesize_config(bool is_pipe)
{
struct perf_evsel *counter;
int err;
if (is_pipe) {
err = perf_event__synthesize_attrs(NULL, perf_stat.session,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
return err;
}
}
/*
* Synthesize other events stuff not carried within
* attr event - unit, scale, name
*/
evlist__for_each(evsel_list, counter) {
if (!counter->supported)
continue;
/*
* Synthesize unit and scale only if it's defined.
*/
if (has_unit(counter)) {
err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize evsel unit.\n");
return err;
}
}
if (has_scale(counter)) {
err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize evsel scale.\n");
return err;
}
}
if (counter->own_cpus) {
err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize evsel scale.\n");
return err;
}
}
/*
* Name is needed only for pipe output,
* perf.data carries event names.
*/
if (is_pipe) {
err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize evsel name.\n");
return err;
}
}
}
err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
process_synthesized_event,
NULL);
if (err < 0) {
pr_err("Couldn't synthesize thread map.\n");
return err;
}
err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
process_synthesized_event, NULL);
if (err < 0) {
pr_err("Couldn't synthesize thread map.\n");
return err;
}
err = perf_event__synthesize_stat_config(NULL, &stat_config,
process_synthesized_event, NULL);
if (err < 0) {
pr_err("Couldn't synthesize config.\n");
return err;
}
return 0;
}
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
static int __store_counter_ids(struct perf_evsel *counter,
struct cpu_map *cpus,
struct thread_map *threads)
{
int cpu, thread;
for (cpu = 0; cpu < cpus->nr; cpu++) {
for (thread = 0; thread < threads->nr; thread++) {
int fd = FD(counter, cpu, thread);
if (perf_evlist__id_add_fd(evsel_list, counter,
cpu, thread, fd) < 0)
return -1;
}
}
return 0;
}
static int store_counter_ids(struct perf_evsel *counter)
{
struct cpu_map *cpus = counter->cpus;
struct thread_map *threads = counter->threads;
if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
return -ENOMEM;
return __store_counter_ids(counter, cpus, threads);
}
static int __run_perf_stat(int argc, const char **argv)
{
int interval = stat_config.interval;
@ -298,6 +497,7 @@ static int __run_perf_stat(int argc, const char **argv)
size_t l;
int status = 0;
const bool forks = (argc > 0);
bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
if (interval) {
ts.tv_sec = interval / 1000;
@ -308,7 +508,7 @@ static int __run_perf_stat(int argc, const char **argv)
}
if (forks) {
if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
workload_exec_failed_signal) < 0) {
perror("failed to prepare workload");
return -1;
@ -352,6 +552,9 @@ static int __run_perf_stat(int argc, const char **argv)
l = strlen(counter->unit);
if (l > unit_width)
unit_width = l;
if (STAT_RECORD && store_counter_ids(counter))
return -1;
}
if (perf_evlist__apply_filters(evsel_list, &counter)) {
@ -361,6 +564,24 @@ static int __run_perf_stat(int argc, const char **argv)
return -1;
}
if (STAT_RECORD) {
int err, fd = perf_data_file__fd(&perf_stat.file);
if (is_pipe) {
err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
} else {
err = perf_session__write_header(perf_stat.session, evsel_list,
fd, false);
}
if (err < 0)
return err;
err = perf_stat_synthesize_config(is_pipe);
if (err < 0)
return err;
}
/*
* Enable counters and exec the command:
*/
@ -827,8 +1048,8 @@ static void print_header(int argc, const char **argv)
else if (target.cpu_list)
fprintf(output, "\'CPU(s) %s", target.cpu_list);
else if (!target__has_task(&target)) {
fprintf(output, "\'%s", argv[0]);
for (i = 1; i < argc; i++)
fprintf(output, "\'%s", argv ? argv[0] : "pipe");
for (i = 1; argv && (i < argc); i++)
fprintf(output, " %s", argv[i]);
} else if (target.pid)
fprintf(output, "process id \'%s", target.pid);
@ -864,6 +1085,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
struct perf_evsel *counter;
char buf[64], *prefix = NULL;
/* Do not print anything if we record to the pipe. */
if (STAT_RECORD && perf_stat.file.is_pipe)
return;
if (interval)
print_interval(prefix = buf, ts);
else
@ -1102,6 +1327,101 @@ static void perf_stat__exit_aggr_mode(void)
cpus_aggr_map = NULL;
}
static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
{
int cpu;
if (idx > map->nr)
return -1;
cpu = map->map[idx];
if (cpu >= env->nr_cpus_online)
return -1;
return cpu;
}
static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
{
struct perf_env *env = data;
int cpu = perf_env__get_cpu(env, map, idx);
return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
}
static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
{
struct perf_env *env = data;
int core = -1, cpu = perf_env__get_cpu(env, map, idx);
if (cpu != -1) {
int socket_id = env->cpu[cpu].socket_id;
/*
* Encode socket in upper 16 bits
* core_id is relative to socket, and
* we need a global id. So we combine
* socket + core id.
*/
core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
}
return core;
}
static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus,
struct cpu_map **sockp)
{
return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
}
static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
struct cpu_map **corep)
{
return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
}
static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
{
return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
}
static int perf_stat__get_core_file(struct cpu_map *map, int idx)
{
return perf_env__get_core(map, idx, &perf_stat.session->header.env);
}
static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
{
struct perf_env *env = &st->session->header.env;
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
perror("cannot build socket map");
return -1;
}
aggr_get_id = perf_stat__get_socket_file;
break;
case AGGR_CORE:
if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
perror("cannot build core map");
return -1;
}
aggr_get_id = perf_stat__get_core_file;
break;
case AGGR_NONE:
case AGGR_GLOBAL:
case AGGR_THREAD:
case AGGR_UNSET:
default:
break;
}
return 0;
}
/*
* Add default attributes, if there were no attributes specified or
* if -d/--detailed, -d -d or -d -d -d is used:
@ -1261,6 +1581,225 @@ static int add_default_attributes(void)
return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
}
static const char * const recort_usage[] = {
"perf stat record [<options>]",
NULL,
};
static void init_features(struct perf_session *session)
{
int feat;
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
perf_header__set_feat(&session->header, feat);
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static int __cmd_record(int argc, const char **argv)
{
struct perf_session *session;
struct perf_data_file *file = &perf_stat.file;
argc = parse_options(argc, argv, stat_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (output_name)
file->path = output_name;
if (run_count != 1 || forever) {
pr_err("Cannot use -r option with perf stat record.\n");
return -1;
}
session = perf_session__new(file, false, NULL);
if (session == NULL) {
pr_err("Perf session creation failed.\n");
return -1;
}
init_features(session);
session->evlist = evsel_list;
perf_stat.session = session;
perf_stat.record = true;
return argc;
}
static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session)
{
struct stat_round_event *round = &event->stat_round;
struct perf_evsel *counter;
struct timespec tsh, *ts = NULL;
const char **argv = session->header.env.cmdline_argv;
int argc = session->header.env.nr_cmdline;
evlist__for_each(evsel_list, counter)
perf_stat_process_counter(&stat_config, counter);
if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
update_stats(&walltime_nsecs_stats, round->time);
if (stat_config.interval && round->time) {
tsh.tv_sec = round->time / NSECS_PER_SEC;
tsh.tv_nsec = round->time % NSECS_PER_SEC;
ts = &tsh;
}
print_counters(ts, argc, argv);
return 0;
}
static
int process_stat_config_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session __maybe_unused)
{
struct perf_stat *st = container_of(tool, struct perf_stat, tool);
perf_event__read_stat_config(&stat_config, &event->stat_config);
if (cpu_map__empty(st->cpus)) {
if (st->aggr_mode != AGGR_UNSET)
pr_warning("warning: processing task data, aggregation mode not set\n");
return 0;
}
if (st->aggr_mode != AGGR_UNSET)
stat_config.aggr_mode = st->aggr_mode;
if (perf_stat.file.is_pipe)
perf_stat_init_aggr_mode();
else
perf_stat_init_aggr_mode_file(st);
return 0;
}
static int set_maps(struct perf_stat *st)
{
if (!st->cpus || !st->threads)
return 0;
if (WARN_ONCE(st->maps_allocated, "stats double allocation\n"))
return -EINVAL;
perf_evlist__set_maps(evsel_list, st->cpus, st->threads);
if (perf_evlist__alloc_stats(evsel_list, true))
return -ENOMEM;
st->maps_allocated = true;
return 0;
}
static
int process_thread_map_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session __maybe_unused)
{
struct perf_stat *st = container_of(tool, struct perf_stat, tool);
if (st->threads) {
pr_warning("Extra thread map event, ignoring.\n");
return 0;
}
st->threads = thread_map__new_event(&event->thread_map);
if (!st->threads)
return -ENOMEM;
return set_maps(st);
}
static
int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session __maybe_unused)
{
struct perf_stat *st = container_of(tool, struct perf_stat, tool);
struct cpu_map *cpus;
if (st->cpus) {
pr_warning("Extra cpu map event, ignoring.\n");
return 0;
}
cpus = cpu_map__new_data(&event->cpu_map.data);
if (!cpus)
return -ENOMEM;
st->cpus = cpus;
return set_maps(st);
}
static const char * const report_usage[] = {
"perf stat report [<options>]",
NULL,
};
static struct perf_stat perf_stat = {
.tool = {
.attr = perf_event__process_attr,
.event_update = perf_event__process_event_update,
.thread_map = process_thread_map_event,
.cpu_map = process_cpu_map_event,
.stat_config = process_stat_config_event,
.stat = perf_event__process_stat_event,
.stat_round = process_stat_round_event,
},
.aggr_mode = AGGR_UNSET,
};
static int __cmd_report(int argc, const char **argv)
{
struct perf_session *session;
const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
"disable CPU count aggregation", AGGR_NONE),
OPT_END()
};
struct stat st;
int ret;
argc = parse_options(argc, argv, options, report_usage, 0);
if (!input_name || !strlen(input_name)) {
if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
input_name = "-";
else
input_name = "perf.data";
}
perf_stat.file.path = input_name;
perf_stat.file.mode = PERF_DATA_MODE_READ;
session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
if (session == NULL)
return -1;
perf_stat.session = session;
stat_config.output = stderr;
evsel_list = session->evlist;
ret = perf_session__process_events(session);
if (ret)
return ret;
perf_session__delete(session);
return 0;
}
int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char * const stat_usage[] = {
@ -1271,6 +1810,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
const char *mode;
FILE *output = stderr;
unsigned int interval;
const char * const stat_subcommands[] = { "record", "report" };
setlocale(LC_ALL, "");
@ -1278,12 +1818,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
if (evsel_list == NULL)
return -ENOMEM;
argc = parse_options(argc, argv, stat_options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
(const char **) stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (csv_sep) {
csv_output = true;
if (!strcmp(csv_sep, "\\t"))
csv_sep = "\t";
} else
csv_sep = DEFAULT_SEPARATOR;
if (argc && !strncmp(argv[0], "rec", 3)) {
argc = __cmd_record(argc, argv);
if (argc < 0)
return -1;
} else if (argc && !strncmp(argv[0], "rep", 3))
return __cmd_report(argc, argv);
interval = stat_config.interval;
if (output_name && strcmp(output_name, "-"))
/*
* For record command the -o is already taken care of.
*/
if (!STAT_RECORD && output_name && strcmp(output_name, "-"))
output = NULL;
if (output_name && output_fd) {
@ -1321,13 +1879,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
stat_config.output = output;
if (csv_sep) {
csv_output = true;
if (!strcmp(csv_sep, "\\t"))
csv_sep = "\t";
} else
csv_sep = DEFAULT_SEPARATOR;
/*
* let the spreadsheet do the pretty-printing
*/
@ -1450,6 +2001,41 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
if (!forever && status != -1 && !interval)
print_counters(NULL, argc, argv);
if (STAT_RECORD) {
/*
* We synthesize the kernel mmap record just so that older tools
* don't emit warnings about not being able to resolve symbols
* due to /proc/sys/kernel/kptr_restrict settings and instear provide
* a saner message about no samples being in the perf.data file.
*
* This also serves to suppress a warning about f_header.data.size == 0
* in header.c at the moment 'perf stat record' gets introduced, which
* is not really needed once we start adding the stat specific PERF_RECORD_
* records, but the need to suppress the kptr_restrict messages in older
* tools remain -acme
*/
int fd = perf_data_file__fd(&perf_stat.file);
int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
process_synthesized_event,
&perf_stat.session->machines.host);
if (err) {
pr_warning("Couldn't synthesize the kernel mmap record, harmless, "
"older tools may produce warnings about this file\n.");
}
if (!interval) {
if (WRITE_STAT_ROUND_EVENT(walltime_nsecs_stats.max, FINAL))
pr_err("failed to write stat round event\n");
}
if (!perf_stat.file.is_pipe) {
perf_stat.session->header.data_size += perf_stat.bytes_written;
perf_session__write_header(perf_stat.session, evsel_list, fd, true);
}
perf_session__delete(perf_stat.session);
}
perf_stat__exit_aggr_mode();
perf_evlist__free_stats(evsel_list);
out:

3
tools/perf/tests/Build
View file

@ -34,6 +34,9 @@ perf-y += thread-map.o
perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
perf-y += bpf.o
perf-y += topology.o
perf-y += cpumap.o
perf-y += stat.o
perf-y += event_update.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)

24
tools/perf/tests/builtin-test.c
View file

@ -179,6 +179,30 @@ static struct test generic_tests[] = {
.get_desc = test__bpf_subtest_get_desc,
},
},
{
.desc = "Test thread map synthesize",
.func = test__thread_map_synthesize,
},
{
.desc = "Test cpu map synthesize",
.func = test__cpu_map_synthesize,
},
{
.desc = "Test stat config synthesize",
.func = test__synthesize_stat_config,
},
{
.desc = "Test stat synthesize",
.func = test__synthesize_stat,
},
{
.desc = "Test stat round synthesize",
.func = test__synthesize_stat_round,
},
{
.desc = "Test attr update synthesize",
.func = test__event_update,
},
{
.func = NULL,
},

88
tools/perf/tests/cpumap.c Normal file
View file

@ -0,0 +1,88 @@
#include "tests.h"
#include "cpumap.h"
static int process_event_mask(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct cpu_map_event *map_event = &event->cpu_map;
struct cpu_map_mask *mask;
struct cpu_map_data *data;
struct cpu_map *map;
int i;
data = &map_event->data;
TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
mask = (struct cpu_map_mask *)data->data;
TEST_ASSERT_VAL("wrong nr", mask->nr == 1);
for (i = 0; i < 20; i++) {
TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
}
map = cpu_map__new_data(data);
TEST_ASSERT_VAL("wrong nr", map->nr == 20);
for (i = 0; i < 20; i++) {
TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
}
cpu_map__put(map);
return 0;
}
static int process_event_cpus(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct cpu_map_event *map_event = &event->cpu_map;
struct cpu_map_entries *cpus;
struct cpu_map_data *data;
struct cpu_map *map;
data = &map_event->data;
TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
cpus = (struct cpu_map_entries *)data->data;
TEST_ASSERT_VAL("wrong nr", cpus->nr == 2);
TEST_ASSERT_VAL("wrong cpu", cpus->cpu[0] == 1);
TEST_ASSERT_VAL("wrong cpu", cpus->cpu[1] == 256);
map = cpu_map__new_data(data);
TEST_ASSERT_VAL("wrong nr", map->nr == 2);
TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
cpu_map__put(map);
return 0;
}
int test__cpu_map_synthesize(int subtest __maybe_unused)
{
struct cpu_map *cpus;
/* This one is better stores in mask. */
cpus = cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19");
TEST_ASSERT_VAL("failed to synthesize map",
!perf_event__synthesize_cpu_map(NULL, cpus, process_event_mask, NULL));
cpu_map__put(cpus);
/* This one is better stores in cpu values. */
cpus = cpu_map__new("1,256");
TEST_ASSERT_VAL("failed to synthesize map",
!perf_event__synthesize_cpu_map(NULL, cpus, process_event_cpus, NULL));
cpu_map__put(cpus);
return 0;
}

117
tools/perf/tests/event_update.c Normal file
View file

@ -0,0 +1,117 @@
#include <linux/compiler.h>
#include "evlist.h"
#include "evsel.h"
#include "machine.h"
#include "tests.h"
#include "debug.h"
static int process_event_unit(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct event_update_event *ev = (struct event_update_event *) event;
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__UNIT);
TEST_ASSERT_VAL("wrong unit", !strcmp(ev->data, "KRAVA"));
return 0;
}
static int process_event_scale(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct event_update_event *ev = (struct event_update_event *) event;
struct event_update_event_scale *ev_data;
ev_data = (struct event_update_event_scale *) ev->data;
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE);
TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123);
return 0;
}
struct event_name {
struct perf_tool tool;
const char *name;
};
static int process_event_name(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct event_name *tmp = container_of(tool, struct event_name, tool);
struct event_update_event *ev = (struct event_update_event*) event;
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__NAME);
TEST_ASSERT_VAL("wrong name", !strcmp(ev->data, tmp->name));
return 0;
}
static int process_event_cpus(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct event_update_event *ev = (struct event_update_event*) event;
struct event_update_event_cpus *ev_data;
struct cpu_map *map;
ev_data = (struct event_update_event_cpus*) ev->data;
map = cpu_map__new_data(&ev_data->cpus);
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
cpu_map__put(map);
return 0;
}
int test__event_update(int subtest __maybe_unused)
{
struct perf_evlist *evlist;
struct perf_evsel *evsel;
struct event_name tmp;
evlist = perf_evlist__new_default();
TEST_ASSERT_VAL("failed to get evlist", evlist);
evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("failed to allos ids",
!perf_evsel__alloc_id(evsel, 1, 1));
perf_evlist__id_add(evlist, evsel, 0, 0, 123);
evsel->unit = strdup("KRAVA");
TEST_ASSERT_VAL("failed to synthesize attr update unit",
!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
evsel->scale = 0.123;
TEST_ASSERT_VAL("failed to synthesize attr update scale",
!perf_event__synthesize_event_update_scale(NULL, evsel, process_event_scale));
tmp.name = perf_evsel__name(evsel);
TEST_ASSERT_VAL("failed to synthesize attr update name",
!perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name));
evsel->own_cpus = cpu_map__new("1,2,3");
TEST_ASSERT_VAL("failed to synthesize attr update cpus",
!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
cpu_map__put(evsel->own_cpus);
return 0;
}

111
tools/perf/tests/stat.c Normal file
View file

@ -0,0 +1,111 @@
#include <linux/compiler.h>
#include "event.h"
#include "tests.h"
#include "stat.h"
#include "counts.h"
#include "debug.h"
static bool has_term(struct stat_config_event *config,
u64 tag, u64 val)
{
unsigned i;
for (i = 0; i < config->nr; i++) {
if ((config->data[i].tag == tag) &&
(config->data[i].val == val))
return true;
}
return false;
}
static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct stat_config_event *config = &event->stat_config;
struct perf_stat_config stat_config;
#define HAS(term, val) \
has_term(config, PERF_STAT_CONFIG_TERM__##term, val)
TEST_ASSERT_VAL("wrong nr", config->nr == PERF_STAT_CONFIG_TERM__MAX);
TEST_ASSERT_VAL("wrong aggr_mode", HAS(AGGR_MODE, AGGR_CORE));
TEST_ASSERT_VAL("wrong scale", HAS(SCALE, 1));
TEST_ASSERT_VAL("wrong interval", HAS(INTERVAL, 1));
#undef HAS
perf_event__read_stat_config(&stat_config, config);
TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE);
TEST_ASSERT_VAL("wrong scale", stat_config.scale == 1);
TEST_ASSERT_VAL("wrong interval", stat_config.interval == 1);
return 0;
}
int test__synthesize_stat_config(int subtest __maybe_unused)
{
struct perf_stat_config stat_config = {
.aggr_mode = AGGR_CORE,
.scale = 1,
.interval = 1,
};
TEST_ASSERT_VAL("failed to synthesize stat_config",
!perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL));
return 0;
}
static int process_stat_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct stat_event *st = &event->stat;
TEST_ASSERT_VAL("wrong cpu", st->cpu == 1);
TEST_ASSERT_VAL("wrong thread", st->thread == 2);
TEST_ASSERT_VAL("wrong id", st->id == 3);
TEST_ASSERT_VAL("wrong val", st->val == 100);
TEST_ASSERT_VAL("wrong run", st->ena == 200);
TEST_ASSERT_VAL("wrong ena", st->run == 300);
return 0;
}
int test__synthesize_stat(int subtest __maybe_unused)
{
struct perf_counts_values count;
count.val = 100;
count.ena = 200;
count.run = 300;
TEST_ASSERT_VAL("failed to synthesize stat_config",
!perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
return 0;
}
static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct stat_round_event *stat_round = &event->stat_round;
TEST_ASSERT_VAL("wrong time", stat_round->time == 0xdeadbeef);
TEST_ASSERT_VAL("wrong type", stat_round->type == PERF_STAT_ROUND_TYPE__INTERVAL);
return 0;
}
int test__synthesize_stat_round(int subtest __maybe_unused)
{
TEST_ASSERT_VAL("failed to synthesize stat_config",
!perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
process_stat_round_event, NULL));
return 0;
}

6
tools/perf/tests/tests.h
View file

@ -79,6 +79,12 @@ int test__bpf(int subtest);
const char *test__bpf_subtest_get_desc(int subtest);
int test__bpf_subtest_get_nr(void);
int test_session_topology(int subtest);
int test__thread_map_synthesize(int subtest);
int test__cpu_map_synthesize(int subtest);
int test__synthesize_stat_config(int subtest);
int test__synthesize_stat(int subtest);
int test__synthesize_stat_round(int subtest);
int test__event_update(int subtest);
#if defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT

43
tools/perf/tests/thread-map.c
View file

@ -40,3 +40,46 @@ int test__thread_map(int subtest __maybe_unused)
thread_map__put(map);
return 0;
}
static int process_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct thread_map_event *map = &event->thread_map;
struct thread_map *threads;
TEST_ASSERT_VAL("wrong nr", map->nr == 1);
TEST_ASSERT_VAL("wrong pid", map->entries[0].pid == (u64) getpid());
TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf"));
threads = thread_map__new_event(&event->thread_map);
TEST_ASSERT_VAL("failed to alloc map", threads);
TEST_ASSERT_VAL("wrong nr", threads->nr == 1);
TEST_ASSERT_VAL("wrong pid",
thread_map__pid(threads, 0) == getpid());
TEST_ASSERT_VAL("wrong comm",
thread_map__comm(threads, 0) &&
!strcmp(thread_map__comm(threads, 0), "perf"));
TEST_ASSERT_VAL("wrong refcnt",
atomic_read(&threads->refcnt) == 1);
thread_map__put(threads);
return 0;
}
int test__thread_map_synthesize(int subtest __maybe_unused)
{
struct thread_map *threads;
/* test map on current pid */
threads = thread_map__new_by_pid(getpid());
TEST_ASSERT_VAL("failed to alloc map", threads);
thread_map__read_comms(threads);
TEST_ASSERT_VAL("failed to synthesize map",
!perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
return 0;
}

42
tools/perf/util/cpumap.c
View file

@ -5,6 +5,7 @@
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <linux/bitmap.h>
#include "asm/bug.h"
static struct cpu_map *cpu_map__default_new(void)
@ -179,6 +180,47 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
return cpus;
}
static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
{
struct cpu_map *map;
map = cpu_map__empty_new(cpus->nr);
if (map) {
unsigned i;
for (i = 0; i < cpus->nr; i++)
map->map[i] = (int)cpus->cpu[i];
}
return map;
}
static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask)
{
struct cpu_map *map;
int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
nr = bitmap_weight(mask->mask, nbits);
map = cpu_map__empty_new(nr);
if (map) {
int cpu, i = 0;
for_each_set_bit(cpu, mask->mask, nbits)
map->map[i++] = cpu;
}
return map;
}
struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
{
if (data->type == PERF_CPU_MAP__CPUS)
return cpu_map__from_entries((struct cpu_map_entries *)data->data);
else
return cpu_map__from_mask((struct cpu_map_mask *)data->data);
}
size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
{
int i;

1
tools/perf/util/cpumap.h
View file

@ -17,6 +17,7 @@ struct cpu_map {
struct cpu_map *cpu_map__new(const char *cpu_list);
struct cpu_map *cpu_map__empty_new(int nr);
struct cpu_map *cpu_map__dummy_new(void);
struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
struct cpu_map *cpu_map__read(FILE *file);
size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
int cpu_map__get_socket_id(int cpu);

308
tools/perf/util/event.c
View file

@ -10,6 +10,8 @@
#include "thread.h"
#include "thread_map.h"
#include "symbol/kallsyms.h"
#include "asm/bug.h"
#include "stat.h"
static const char *perf_event__names[] = {
[0] = "TOTAL",
@ -37,6 +39,12 @@ static const char *perf_event__names[] = {
[PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
[PERF_RECORD_AUXTRACE] = "AUXTRACE",
[PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
[PERF_RECORD_THREAD_MAP] = "THREAD_MAP",
[PERF_RECORD_CPU_MAP] = "CPU_MAP",
[PERF_RECORD_STAT_CONFIG] = "STAT_CONFIG",
[PERF_RECORD_STAT] = "STAT",
[PERF_RECORD_STAT_ROUND] = "STAT_ROUND",
[PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE",
};
const char *perf_event__name(unsigned int id)
@ -699,6 +707,274 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
return err;
}
int perf_event__synthesize_thread_map2(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
struct machine *machine)
{
union perf_event *event;
int i, err, size;
size = sizeof(event->thread_map);
size += threads->nr * sizeof(event->thread_map.entries[0]);
event = zalloc(size);
if (!event)
return -ENOMEM;
event->header.type = PERF_RECORD_THREAD_MAP;
event->header.size = size;
event->thread_map.nr = threads->nr;
for (i = 0; i < threads->nr; i++) {
struct thread_map_event_entry *entry = &event->thread_map.entries[i];
char *comm = thread_map__comm(threads, i);
if (!comm)
comm = (char *) "";
entry->pid = thread_map__pid(threads, i);
strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
}
err = process(tool, event, NULL, machine);
free(event);
return err;
}
static void synthesize_cpus(struct cpu_map_entries *cpus,
struct cpu_map *map)
{
int i;
cpus->nr = map->nr;
for (i = 0; i < map->nr; i++)
cpus->cpu[i] = map->map[i];
}
static void synthesize_mask(struct cpu_map_mask *mask,
struct cpu_map *map, int max)
{
int i;
mask->nr = BITS_TO_LONGS(max);
mask->long_size = sizeof(long);
for (i = 0; i < map->nr; i++)
set_bit(map->map[i], mask->mask);
}
static size_t cpus_size(struct cpu_map *map)
{
return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
}
static size_t mask_size(struct cpu_map *map, int *max)
{
int i;
*max = 0;
for (i = 0; i < map->nr; i++) {
/* bit possition of the cpu is + 1 */
int bit = map->map[i] + 1;
if (bit > *max)
*max = bit;
}
return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
}
void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
{
size_t size_cpus, size_mask;
bool is_dummy = cpu_map__empty(map);
/*
* Both array and mask data have variable size based
* on the number of cpus and their actual values.
* The size of the 'struct cpu_map_data' is:
*
* array = size of 'struct cpu_map_entries' +
* number of cpus * sizeof(u64)
*
* mask = size of 'struct cpu_map_mask' +
* maximum cpu bit converted to size of longs
*
* and finaly + the size of 'struct cpu_map_data'.
*/
size_cpus = cpus_size(map);
size_mask = mask_size(map, max);
if (is_dummy || (size_cpus < size_mask)) {
*size += size_cpus;
*type = PERF_CPU_MAP__CPUS;
} else {
*size += size_mask;
*type = PERF_CPU_MAP__MASK;
}
*size += sizeof(struct cpu_map_data);
return zalloc(*size);
}
void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
u16 type, int max)
{
data->type = type;
switch (type) {
case PERF_CPU_MAP__CPUS:
synthesize_cpus((struct cpu_map_entries *) data->data, map);
break;
case PERF_CPU_MAP__MASK:
synthesize_mask((struct cpu_map_mask *) data->data, map, max);
default:
break;
};
}
static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
{
size_t size = sizeof(struct cpu_map_event);
struct cpu_map_event *event;
int max;
u16 type;
event = cpu_map_data__alloc(map, &size, &type, &max);
if (!event)
return NULL;
event->header.type = PERF_RECORD_CPU_MAP;
event->header.size = size;
event->data.type = type;
cpu_map_data__synthesize(&event->data, map, type, max);
return event;
}
int perf_event__synthesize_cpu_map(struct perf_tool *tool,
struct cpu_map *map,
perf_event__handler_t process,
struct machine *machine)
{
struct cpu_map_event *event;
int err;
event = cpu_map_event__new(map);
if (!event)
return -ENOMEM;
err = process(tool, (union perf_event *) event, NULL, machine);
free(event);
return err;
}
int perf_event__synthesize_stat_config(struct perf_tool *tool,
struct perf_stat_config *config,
perf_event__handler_t process,
struct machine *machine)
{
struct stat_config_event *event;
int size, i = 0, err;
size = sizeof(*event);
size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
event = zalloc(size);
if (!event)
return -ENOMEM;
event->header.type = PERF_RECORD_STAT_CONFIG;
event->header.size = size;
event->nr = PERF_STAT_CONFIG_TERM__MAX;
#define ADD(__term, __val) \
event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \
event->data[i].val = __val; \
i++;
ADD(AGGR_MODE, config->aggr_mode)
ADD(INTERVAL, config->interval)
ADD(SCALE, config->scale)
WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
"stat config terms unbalanced\n");
#undef ADD
err = process(tool, (union perf_event *) event, NULL, machine);
free(event);
return err;
}
int perf_event__synthesize_stat(struct perf_tool *tool,
u32 cpu, u32 thread, u64 id,
struct perf_counts_values *count,
perf_event__handler_t process,
struct machine *machine)
{
struct stat_event event;
event.header.type = PERF_RECORD_STAT;
event.header.size = sizeof(event);
event.header.misc = 0;
event.id = id;
event.cpu = cpu;
event.thread = thread;
event.val = count->val;
event.ena = count->ena;
event.run = count->run;
return process(tool, (union perf_event *) &event, NULL, machine);
}
int perf_event__synthesize_stat_round(struct perf_tool *tool,
u64 evtime, u64 type,
perf_event__handler_t process,
struct machine *machine)
{
struct stat_round_event event;
event.header.type = PERF_RECORD_STAT_ROUND;
event.header.size = sizeof(event);
event.header.misc = 0;
event.time = evtime;
event.type = type;
return process(tool, (union perf_event *) &event, NULL, machine);
}
void perf_event__read_stat_config(struct perf_stat_config *config,
struct stat_config_event *event)
{
unsigned i;
for (i = 0; i < event->nr; i++) {
switch (event->data[i].tag) {
#define CASE(__term, __val) \
case PERF_STAT_CONFIG_TERM__##__term: \
config->__val = event->data[i].val; \
break;
CASE(AGGR_MODE, aggr_mode)
CASE(SCALE, scale)
CASE(INTERVAL, interval)
#undef CASE
default:
pr_warning("unknown stat config term %" PRIu64 "\n",
event->data[i].tag);
}
}
}
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
{
const char *s;
@ -783,6 +1059,38 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
event->mmap2.filename);
}
size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
{
struct thread_map *threads = thread_map__new_event(&event->thread_map);
size_t ret;
ret = fprintf(fp, " nr: ");
if (threads)
ret += thread_map__fprintf(threads, fp);
else
ret += fprintf(fp, "failed to get threads from event\n");
thread_map__put(threads);
return ret;
}
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
{
struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
size_t ret;
ret = fprintf(fp, " nr: ");
if (cpus)
ret += cpu_map__fprintf(cpus, fp);
else
ret += fprintf(fp, "failed to get cpumap from event\n");
cpu_map__put(cpus);
return ret;
}
int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,

150
tools/perf/util/event.h
View file

@ -226,6 +226,12 @@ enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_AUXTRACE_INFO = 70,
PERF_RECORD_AUXTRACE = 71,
PERF_RECORD_AUXTRACE_ERROR = 72,
PERF_RECORD_THREAD_MAP = 73,
PERF_RECORD_CPU_MAP = 74,
PERF_RECORD_STAT_CONFIG = 75,
PERF_RECORD_STAT = 76,
PERF_RECORD_STAT_ROUND = 77,
PERF_RECORD_EVENT_UPDATE = 78,
PERF_RECORD_HEADER_MAX
};
@ -270,12 +276,61 @@ struct events_stats {
u32 nr_proc_map_timeout;
};
enum {
PERF_CPU_MAP__CPUS = 0,
PERF_CPU_MAP__MASK = 1,
};
struct cpu_map_entries {
u16 nr;
u16 cpu[];
};
struct cpu_map_mask {
u16 nr;
u16 long_size;
unsigned long mask[];
};
struct cpu_map_data {
u16 type;
char data[];
};
struct cpu_map_event {
struct perf_event_header header;
struct cpu_map_data data;
};
struct attr_event {
struct perf_event_header header;
struct perf_event_attr attr;
u64 id[];
};
enum {
PERF_EVENT_UPDATE__UNIT = 0,
PERF_EVENT_UPDATE__SCALE = 1,
PERF_EVENT_UPDATE__NAME = 2,
PERF_EVENT_UPDATE__CPUS = 3,
};
struct event_update_event_cpus {
struct cpu_map_data cpus;
};
struct event_update_event_scale {
double scale;
};
struct event_update_event {
struct perf_event_header header;
u64 type;
u64 id;
char data[];
};
#define MAX_EVENT_NAME 64
struct perf_trace_event_type {
@ -356,6 +411,63 @@ struct context_switch_event {
u32 next_prev_tid;
};
struct thread_map_event_entry {
u64 pid;
char comm[16];
};
struct thread_map_event {
struct perf_event_header header;
u64 nr;
struct thread_map_event_entry entries[];
};
enum {
PERF_STAT_CONFIG_TERM__AGGR_MODE = 0,
PERF_STAT_CONFIG_TERM__INTERVAL = 1,
PERF_STAT_CONFIG_TERM__SCALE = 2,
PERF_STAT_CONFIG_TERM__MAX = 3,
};
struct stat_config_event_entry {
u64 tag;
u64 val;
};
struct stat_config_event {
struct perf_event_header header;
u64 nr;
struct stat_config_event_entry data[];
};
struct stat_event {
struct perf_event_header header;
u64 id;
u32 cpu;
u32 thread;
union {
struct {
u64 val;
u64 ena;
u64 run;
};
u64 values[3];
};
};
enum {
PERF_STAT_ROUND_TYPE__INTERVAL = 0,
PERF_STAT_ROUND_TYPE__FINAL = 1,
};
struct stat_round_event {
struct perf_event_header header;
u64 type;
u64 time;
};
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
@ -368,6 +480,7 @@ union perf_event {
struct throttle_event throttle;
struct sample_event sample;
struct attr_event attr;
struct event_update_event event_update;
struct event_type_event event_type;
struct tracing_data_event tracing_data;
struct build_id_event build_id;
@ -378,12 +491,20 @@ union perf_event {
struct aux_event aux;
struct itrace_start_event itrace_start;
struct context_switch_event context_switch;
struct thread_map_event thread_map;
struct cpu_map_event cpu_map;
struct stat_config_event stat_config;
struct stat_event stat;
struct stat_round_event stat_round;
};
void perf_event__print_totals(void);
struct perf_tool;
struct thread_map;
struct cpu_map;
struct perf_stat_config;
struct perf_counts_values;
typedef int (*perf_event__handler_t)(struct perf_tool *tool,
union perf_event *event,
@ -395,6 +516,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine, bool mmap_data,
unsigned int proc_map_timeout);
int perf_event__synthesize_thread_map2(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_cpu_map(struct perf_tool *tool,
struct cpu_map *cpus,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine, bool mmap_data,
@ -402,7 +531,21 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_stat_config(struct perf_tool *tool,
struct perf_stat_config *config,
perf_event__handler_t process,
struct machine *machine);
void perf_event__read_stat_config(struct perf_stat_config *config,
struct stat_config_event *event);
int perf_event__synthesize_stat(struct perf_tool *tool,
u32 cpu, u32 thread, u64 id,
struct perf_counts_values *count,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_stat_round(struct perf_tool *tool,
u64 time, u64 type,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_modules(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);
@ -499,9 +642,14 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
const char *symbol_name);
void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max);
void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
u16 type, int max);
#endif /* __PERF_RECORD_H */

6
tools/perf/util/evlist.c
View file

@ -534,9 +534,9 @@ void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
evsel->id[evsel->ids++] = id;
}
static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
struct perf_evsel *evsel,
int cpu, int thread, int fd)
int perf_evlist__id_add_fd(struct perf_evlist *evlist,
struct perf_evsel *evsel,
int cpu, int thread, int fd)
{
u64 read_data[4] = { 0, };
int id_idx = 1; /* The first entry is the counter value */

3
tools/perf/util/evlist.h
View file

@ -97,6 +97,9 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
int perf_evlist__id_add_fd(struct perf_evlist *evlist,
struct perf_evsel *evsel,
int cpu, int thread, int fd);
int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);

205
tools/perf/util/header.c
View file

@ -868,6 +868,13 @@ static int write_auxtrace(int fd, struct perf_header *h,
return err;
}
static int write_stat(int fd __maybe_unused,
struct perf_header *h __maybe_unused,
struct perf_evlist *evlist __maybe_unused)
{
return 0;
}
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@ -1159,6 +1166,12 @@ static void print_auxtrace(struct perf_header *ph __maybe_unused,
fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
}
static void print_stat(struct perf_header *ph __maybe_unused,
int fd __maybe_unused, FILE *fp)
{
fprintf(fp, "# contains stat data\n");
}
static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
@ -1948,6 +1961,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
FEAT_OPP(HEADER_AUXTRACE, auxtrace),
FEAT_OPA(HEADER_STAT, stat),
};
struct header_print_data {
@ -2686,6 +2700,152 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
return err;
}
static struct event_update_event *
event_update_event__new(size_t size, u64 type, u64 id)
{
struct event_update_event *ev;
size += sizeof(*ev);
size = PERF_ALIGN(size, sizeof(u64));
ev = zalloc(size);
if (ev) {
ev->header.type = PERF_RECORD_EVENT_UPDATE;
ev->header.size = (u16)size;
ev->type = type;
ev->id = id;
}
return ev;
}
int
perf_event__synthesize_event_update_unit(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process)
{
struct event_update_event *ev;
size_t size = strlen(evsel->unit);
int err;
ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
if (ev == NULL)
return -ENOMEM;
strncpy(ev->data, evsel->unit, size);
err = process(tool, (union perf_event *)ev, NULL, NULL);
free(ev);
return err;
}
int
perf_event__synthesize_event_update_scale(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process)
{
struct event_update_event *ev;
struct event_update_event_scale *ev_data;
int err;
ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
if (ev == NULL)
return -ENOMEM;
ev_data = (struct event_update_event_scale *) ev->data;
ev_data->scale = evsel->scale;
err = process(tool, (union perf_event*) ev, NULL, NULL);
free(ev);
return err;
}
int
perf_event__synthesize_event_update_name(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process)
{
struct event_update_event *ev;
size_t len = strlen(evsel->name);
int err;
ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
if (ev == NULL)
return -ENOMEM;
strncpy(ev->data, evsel->name, len);
err = process(tool, (union perf_event*) ev, NULL, NULL);
free(ev);
return err;
}
int
perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process)
{
size_t size = sizeof(struct event_update_event);
struct event_update_event *ev;
int max, err;
u16 type;
if (!evsel->own_cpus)
return 0;
ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max);
if (!ev)
return -ENOMEM;
ev->header.type = PERF_RECORD_EVENT_UPDATE;
ev->header.size = (u16)size;
ev->type = PERF_EVENT_UPDATE__CPUS;
ev->id = evsel->id[0];
cpu_map_data__synthesize((struct cpu_map_data *) ev->data,
evsel->own_cpus,
type, max);
err = process(tool, (union perf_event*) ev, NULL, NULL);
free(ev);
return err;
}
size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
{
struct event_update_event *ev = &event->event_update;
struct event_update_event_scale *ev_scale;
struct event_update_event_cpus *ev_cpus;
struct cpu_map *map;
size_t ret;
ret = fprintf(fp, "\n... id: %" PRIu64 "\n", ev->id);
switch (ev->type) {
case PERF_EVENT_UPDATE__SCALE:
ev_scale = (struct event_update_event_scale *) ev->data;
ret += fprintf(fp, "... scale: %f\n", ev_scale->scale);
break;
case PERF_EVENT_UPDATE__UNIT:
ret += fprintf(fp, "... unit: %s\n", ev->data);
break;
case PERF_EVENT_UPDATE__NAME:
ret += fprintf(fp, "... name: %s\n", ev->data);
break;
case PERF_EVENT_UPDATE__CPUS:
ev_cpus = (struct event_update_event_cpus *) ev->data;
ret += fprintf(fp, "... ");
map = cpu_map__new_data(&ev_cpus->cpus);
if (map)
ret += cpu_map__fprintf(map, fp);
else
ret += fprintf(fp, "failed to get cpus\n");
break;
default:
ret += fprintf(fp, "... unknown type\n");
break;
}
return ret;
}
int perf_event__synthesize_attrs(struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process)
@ -2745,6 +2905,51 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
return 0;
}
int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_evlist **pevlist)
{
struct event_update_event *ev = &event->event_update;
struct event_update_event_scale *ev_scale;
struct event_update_event_cpus *ev_cpus;
struct perf_evlist *evlist;
struct perf_evsel *evsel;
struct cpu_map *map;
if (!pevlist || *pevlist == NULL)
return -EINVAL;
evlist = *pevlist;
evsel = perf_evlist__id2evsel(evlist, ev->id);
if (evsel == NULL)
return -EINVAL;
switch (ev->type) {
case PERF_EVENT_UPDATE__UNIT:
evsel->unit = strdup(ev->data);
break;
case PERF_EVENT_UPDATE__NAME:
evsel->name = strdup(ev->data);
break;
case PERF_EVENT_UPDATE__SCALE:
ev_scale = (struct event_update_event_scale *) ev->data;
evsel->scale = ev_scale->scale;
case PERF_EVENT_UPDATE__CPUS:
ev_cpus = (struct event_update_event_cpus *) ev->data;
map = cpu_map__new_data(&ev_cpus->cpus);
if (map)
evsel->own_cpus = map;
else
pr_err("failed to get event_update cpus\n");
default:
break;
}
return 0;
}
int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
struct perf_evlist *evlist,
perf_event__handler_t process)

17
tools/perf/util/header.h
View file

@ -31,6 +31,7 @@ enum {
HEADER_PMU_MAPPINGS,
HEADER_GROUP_DESC,
HEADER_AUXTRACE,
HEADER_STAT,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
@ -105,8 +106,24 @@ 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__synthesize_event_update_unit(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process);
int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process);
int perf_event__synthesize_event_update_name(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process);
int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
struct perf_evsel *evsel,
perf_event__handler_t process);
int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
struct perf_evlist **pevlist);
int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_evlist **pevlist);
size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
int perf_event__synthesize_tracing_data(struct perf_tool *tool,
int fd, struct perf_evlist *evlist,

189
tools/perf/util/session.c
View file

@ -17,6 +17,7 @@
#include "asm/bug.h"
#include "auxtrace.h"
#include "thread-stack.h"
#include "stat.h"
static int perf_session__deliver_event(struct perf_session *session,
union perf_event *event,
@ -36,6 +37,9 @@ static int perf_session__open(struct perf_session *session)
if (perf_data_file__is_pipe(file))
return 0;
if (perf_header__has_feat(&session->header, HEADER_STAT))
return 0;
if (!perf_evlist__valid_sample_type(session->evlist)) {
pr_err("non matching sample_type\n");
return -1;
@ -205,6 +209,18 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
return 0;
}
static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_evlist **pevlist
__maybe_unused)
{
if (dump_trace)
perf_event__fprintf_event_update(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_sample *sample __maybe_unused,
@ -296,6 +312,67 @@ int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
return 0;
}
static
int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_session *session __maybe_unused)
{
if (dump_trace)
perf_event__fprintf_thread_map(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
static
int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_session *session __maybe_unused)
{
if (dump_trace)
perf_event__fprintf_cpu_map(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
static
int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_session *session __maybe_unused)
{
if (dump_trace)
perf_event__fprintf_stat_config(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
static int process_stat_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_session *perf_session
__maybe_unused)
{
if (dump_trace)
perf_event__fprintf_stat(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
struct perf_session *perf_session
__maybe_unused)
{
if (dump_trace)
perf_event__fprintf_stat_round(event, stdout);
dump_printf(": unhandled!\n");
return 0;
}
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
@ -328,6 +405,8 @@ 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_update == NULL)
tool->event_update = process_event_synth_event_update_stub;
if (tool->tracing_data == NULL)
tool->tracing_data = process_event_synth_tracing_data_stub;
if (tool->build_id == NULL)
@ -346,6 +425,16 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
tool->auxtrace = process_event_auxtrace_stub;
if (tool->auxtrace_error == NULL)
tool->auxtrace_error = process_event_auxtrace_error_stub;
if (tool->thread_map == NULL)
tool->thread_map = process_event_thread_map_stub;
if (tool->cpu_map == NULL)
tool->cpu_map = process_event_cpu_map_stub;
if (tool->stat_config == NULL)
tool->stat_config = process_event_stat_config_stub;
if (tool->stat == NULL)
tool->stat = process_stat_stub;
if (tool->stat_round == NULL)
tool->stat_round = process_stat_round_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
@ -569,6 +658,13 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
mem_bswap_64(event->attr.id, size);
}
static void perf_event__event_update_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
event->event_update.type = bswap_64(event->event_update.type);
event->event_update.id = bswap_64(event->event_update.id);
}
static void perf_event__event_type_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
@ -616,6 +712,81 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip);
}
static void perf_event__thread_map_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
unsigned i;
event->thread_map.nr = bswap_64(event->thread_map.nr);
for (i = 0; i < event->thread_map.nr; i++)
event->thread_map.entries[i].pid = bswap_64(event->thread_map.entries[i].pid);
}
static void perf_event__cpu_map_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
struct cpu_map_data *data = &event->cpu_map.data;
struct cpu_map_entries *cpus;
struct cpu_map_mask *mask;
unsigned i;
data->type = bswap_64(data->type);
switch (data->type) {
case PERF_CPU_MAP__CPUS:
cpus = (struct cpu_map_entries *)data->data;
cpus->nr = bswap_16(cpus->nr);
for (i = 0; i < cpus->nr; i++)
cpus->cpu[i] = bswap_16(cpus->cpu[i]);
break;
case PERF_CPU_MAP__MASK:
mask = (struct cpu_map_mask *) data->data;
mask->nr = bswap_16(mask->nr);
mask->long_size = bswap_16(mask->long_size);
switch (mask->long_size) {
case 4: mem_bswap_32(&mask->mask, mask->nr); break;
case 8: mem_bswap_64(&mask->mask, mask->nr); break;
default:
pr_err("cpu_map swap: unsupported long size\n");
}
default:
break;
}
}
static void perf_event__stat_config_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
u64 size;
size = event->stat_config.nr * sizeof(event->stat_config.data[0]);
size += 1; /* nr item itself */
mem_bswap_64(&event->stat_config.nr, size);
}
static void perf_event__stat_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
event->stat.id = bswap_64(event->stat.id);
event->stat.thread = bswap_32(event->stat.thread);
event->stat.cpu = bswap_32(event->stat.cpu);
event->stat.val = bswap_64(event->stat.val);
event->stat.ena = bswap_64(event->stat.ena);
event->stat.run = bswap_64(event->stat.run);
}
static void perf_event__stat_round_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
event->stat_round.type = bswap_64(event->stat_round.type);
event->stat_round.time = bswap_64(event->stat_round.time);
}
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
@ -643,6 +814,12 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
[PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
[PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap,
[PERF_RECORD_THREAD_MAP] = perf_event__thread_map_swap,
[PERF_RECORD_CPU_MAP] = perf_event__cpu_map_swap,
[PERF_RECORD_STAT_CONFIG] = perf_event__stat_config_swap,
[PERF_RECORD_STAT] = perf_event__stat_swap,
[PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap,
[PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@ -1154,6 +1331,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
perf_session__set_comm_exec(session);
}
return err;
case PERF_RECORD_EVENT_UPDATE:
return tool->event_update(tool, event, &session->evlist);
case PERF_RECORD_HEADER_EVENT_TYPE:
/*
* Depreceated, but we need to handle it for sake
@ -1179,6 +1358,16 @@ static s64 perf_session__process_user_event(struct perf_session *session,
case PERF_RECORD_AUXTRACE_ERROR:
perf_session__auxtrace_error_inc(session, event);
return tool->auxtrace_error(tool, event, session);
case PERF_RECORD_THREAD_MAP:
return tool->thread_map(tool, event, session);
case PERF_RECORD_CPU_MAP:
return tool->cpu_map(tool, event, session);
case PERF_RECORD_STAT_CONFIG:
return tool->stat_config(tool, event, session);
case PERF_RECORD_STAT:
return tool->stat(tool, event, session);
case PERF_RECORD_STAT_ROUND:
return tool->stat_round(tool, event, session);
default:
return -EINVAL;
}

62
tools/perf/util/stat.c
View file

@ -341,3 +341,65 @@ int perf_stat_process_counter(struct perf_stat_config *config,
return 0;
}
int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session)
{
struct perf_counts_values count;
struct stat_event *st = &event->stat;
struct perf_evsel *counter;
count.val = st->val;
count.ena = st->ena;
count.run = st->run;
counter = perf_evlist__id2evsel(session->evlist, st->id);
if (!counter) {
pr_err("Failed to resolve counter for stat event.\n");
return -EINVAL;
}
*perf_counts(counter->counts, st->cpu, st->thread) = count;
counter->supported = true;
return 0;
}
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
{
struct stat_event *st = (struct stat_event *) event;
size_t ret;
ret = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
st->id, st->cpu, st->thread);
ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
st->val, st->ena, st->run);
return ret;
}
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
{
struct stat_round_event *rd = (struct stat_round_event *)event;
size_t ret;
ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
return ret;
}
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
{
struct perf_stat_config sc;
size_t ret;
perf_event__read_stat_config(&sc, &event->stat_config);
ret = fprintf(fp, "\n");
ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
ret += fprintf(fp, "... scale %d\n", sc.scale);
ret += fprintf(fp, "... interval %u\n", sc.interval);
return ret;
}

10
tools/perf/util/stat.h
View file

@ -90,4 +90,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist);
int perf_stat_process_counter(struct perf_stat_config *config,
struct perf_evsel *counter);
struct perf_tool;
union perf_event;
struct perf_session;
int perf_event__process_stat_event(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session);
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
#endif

27
tools/perf/util/thread_map.c
View file

@ -13,6 +13,7 @@
#include "thread_map.h"
#include "util.h"
#include "debug.h"
#include "event.h"
/* Skip "." and ".." directories */
static int filter(const struct dirent *dir)
@ -409,3 +410,29 @@ void thread_map__read_comms(struct thread_map *threads)
for (i = 0; i < threads->nr; ++i)
comm_init(threads, i);
}
static void thread_map__copy_event(struct thread_map *threads,
struct thread_map_event *event)
{
unsigned i;
threads->nr = (int) event->nr;
for (i = 0; i < event->nr; i++) {
thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
threads->map[i].comm = strndup(event->entries[i].comm, 16);
}
atomic_set(&threads->refcnt, 1);
}
struct thread_map *thread_map__new_event(struct thread_map_event *event)
{
struct thread_map *threads;
threads = thread_map__alloc(event->nr);
if (threads)
thread_map__copy_event(threads, event);
return threads;
}

3
tools/perf/util/thread_map.h
View file

@ -16,11 +16,14 @@ struct thread_map {
struct thread_map_data map[];
};
struct thread_map_event;
struct thread_map *thread_map__new_dummy(void);
struct thread_map *thread_map__new_by_pid(pid_t pid);
struct thread_map *thread_map__new_by_tid(pid_t tid);
struct thread_map *thread_map__new_by_uid(uid_t uid);
struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
struct thread_map *thread_map__new_event(struct thread_map_event *event);
struct thread_map *thread_map__get(struct thread_map *map);
void thread_map__put(struct thread_map *map);

8
tools/perf/util/tool.h
View file

@ -50,12 +50,18 @@ struct perf_tool {
throttle,
unthrottle;
event_attr_op attr;
event_attr_op event_update;
event_op2 tracing_data;
event_oe finished_round;
event_op2 build_id,
id_index,
auxtrace_info,
auxtrace_error;
auxtrace_error,
thread_map,
cpu_map,
stat_config,
stat,
stat_round;
event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;