2009-06-03 04:59:57 +08:00
|
|
|
/*
|
2009-06-03 05:37:05 +08:00
|
|
|
* builtin-record.c
|
|
|
|
*
|
|
|
|
* Builtin record command: Record the profile of a workload
|
|
|
|
* (or a CPU, or a PID) into the perf.data output file - for
|
|
|
|
* later analysis via perf report.
|
2009-06-03 04:59:57 +08:00
|
|
|
*/
|
2010-02-03 11:53:14 +08:00
|
|
|
#define _FILE_OFFSET_BITS 64
|
|
|
|
|
2009-05-27 15:10:38 +08:00
|
|
|
#include "builtin.h"
|
2009-06-03 05:37:05 +08:00
|
|
|
|
|
|
|
#include "perf.h"
|
|
|
|
|
2010-02-04 02:52:05 +08:00
|
|
|
#include "util/build-id.h"
|
2009-05-02 00:29:57 +08:00
|
|
|
#include "util/util.h"
|
2009-05-26 15:17:18 +08:00
|
|
|
#include "util/parse-options.h"
|
2009-05-26 17:10:09 +08:00
|
|
|
#include "util/parse-events.h"
|
2009-05-02 00:29:57 +08:00
|
|
|
|
2009-06-25 23:05:54 +08:00
|
|
|
#include "util/header.h"
|
2009-08-12 17:07:25 +08:00
|
|
|
#include "util/event.h"
|
2011-01-12 06:56:53 +08:00
|
|
|
#include "util/evlist.h"
|
2011-01-04 02:39:04 +08:00
|
|
|
#include "util/evsel.h"
|
2009-08-17 04:05:48 +08:00
|
|
|
#include "util/debug.h"
|
2009-12-12 07:24:02 +08:00
|
|
|
#include "util/session.h"
|
2011-11-28 18:30:20 +08:00
|
|
|
#include "util/tool.h"
|
perf symbols: Use the buildids if present
With this change 'perf record' will intercept PERF_RECORD_MMAP
calls, creating a linked list of DSOs, then when the session
finishes, it will traverse this list and read the buildids,
stashing them at the end of the file and will set up a new
feature bit in the header bitmask.
'perf report' will then notice this feature and populate the
'dsos' list and set the build ids.
When reading the symtabs it will refuse to load from a file that
doesn't have the same build id. This improves the
reliability of the profiler output, as symbols and profiling
data is more guaranteed to match.
Example:
[root@doppio ~]# perf report | head
/home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols
# Samples: 2621434559
#
# Overhead Command Shared Object Symbol
# ........ ............... ............................. ......
#
7.91% init [kernel] [k] read_hpet
7.64% init [kernel] [k] mwait_idle_with_hints
7.60% swapper [kernel] [k] read_hpet
7.60% swapper [kernel] [k] mwait_idle_with_hints
3.65% init [kernel] [k] 0xffffffffa02339d9
[root@doppio ~]#
In this case the 'perf' binary was an older one, vanished,
so its symbols probably wouldn't match or would cause subtly
different (and misleading) output.
Next patches will support the kernel as well, reading the build
id notes for it and the modules from /sys.
Another patch should also introduce a new plumbing command:
'perf list-buildids'
that will then be used in porcelain that is distro specific to
fetch -debuginfo packages where such buildids are present. This
will in turn allow for one to run 'perf record' in one machine
and 'perf report' in another.
Future work on having the buildid sent directly from the kernel
in the PERF_RECORD_MMAP event is needed to close races, as the
DSO can be changed during a 'perf record' session, but this
patch at least helps with non-corner cases and current/older
kernels.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: K. Prasad <prasad@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roland McGrath <roland@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
|
|
|
#include "util/symbol.h"
|
perf tools: Fix sparse CPU numbering related bugs
At present, the perf subcommands that do system-wide monitoring
(perf stat, perf record and perf top) don't work properly unless
the online cpus are numbered 0, 1, ..., N-1. These tools ask
for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN)
and then try to create events for cpus 0, 1, ..., N-1.
This creates problems for systems where the online cpus are
numbered sparsely. For example, a POWER6 system in
single-threaded mode (i.e. only running 1 hardware thread per
core) will have only even-numbered cpus online.
This fixes the problem by reading the /sys/devices/system/cpu/online
file to find out which cpus are online. The code that does that is in
tools/perf/util/cpumap.[ch], and consists of a read_cpu_map()
function that sets up a cpumap[] array and returns the number of
online cpus. If /sys/devices/system/cpu/online can't be read or
can't be parsed successfully, it falls back to using sysconf to
ask how many cpus are online and sets up an identity map in cpumap[].
The perf record, perf stat and perf top code then calls
read_cpu_map() in the system-wide monitoring case (instead of
sysconf) and uses cpumap[] to get the cpu numbers to pass to
perf_event_open.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 17:36:09 +08:00
|
|
|
#include "util/cpumap.h"
|
2011-01-19 01:15:24 +08:00
|
|
|
#include "util/thread_map.h"
|
2009-06-25 23:05:54 +08:00
|
|
|
|
2009-06-02 21:52:24 +08:00
|
|
|
#include <unistd.h>
|
2009-04-08 21:01:31 +08:00
|
|
|
#include <sched.h>
|
2010-05-19 05:29:23 +08:00
|
|
|
#include <sys/mman.h>
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2010-04-15 01:42:07 +08:00
|
|
|
enum write_mode_t {
|
|
|
|
WRITE_FORCE,
|
|
|
|
WRITE_APPEND
|
|
|
|
};
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_record {
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool tool;
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_record_opts opts;
|
|
|
|
u64 bytes_written;
|
|
|
|
const char *output_name;
|
|
|
|
struct perf_evlist *evlist;
|
|
|
|
struct perf_session *session;
|
|
|
|
const char *progname;
|
2012-01-20 00:08:15 +08:00
|
|
|
const char *uid_str;
|
2011-11-25 18:19:45 +08:00
|
|
|
int output;
|
|
|
|
unsigned int page_size;
|
|
|
|
int realtime_prio;
|
|
|
|
enum write_mode_t write_mode;
|
|
|
|
bool no_buildid;
|
|
|
|
bool no_buildid_cache;
|
|
|
|
bool force;
|
|
|
|
bool file_new;
|
|
|
|
bool append_file;
|
|
|
|
long samples;
|
|
|
|
off_t post_processing_offset;
|
2011-11-09 00:41:57 +08:00
|
|
|
};
|
2009-06-06 15:58:57 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void advance_output(struct perf_record *rec, size_t size)
|
2010-04-02 12:59:21 +08:00
|
|
|
{
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->bytes_written += size;
|
2010-04-02 12:59:21 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void write_output(struct perf_record *rec, void *buf, size_t size)
|
2009-06-19 05:22:55 +08:00
|
|
|
{
|
|
|
|
while (size) {
|
2011-11-25 18:19:45 +08:00
|
|
|
int ret = write(rec->output, buf, size);
|
2009-06-19 05:22:55 +08:00
|
|
|
|
|
|
|
if (ret < 0)
|
|
|
|
die("failed to write");
|
|
|
|
|
|
|
|
size -= ret;
|
|
|
|
buf += ret;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->bytes_written += ret;
|
2009-06-19 05:22:55 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
static int process_synthesized_event(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2011-01-29 23:02:00 +08:00
|
|
|
struct perf_sample *sample __used,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine __used)
|
2009-10-27 05:23:18 +08:00
|
|
|
{
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_record *rec = container_of(tool, struct perf_record, tool);
|
2011-11-25 18:19:45 +08:00
|
|
|
write_output(rec, event, event->header.size);
|
2009-10-27 05:23:18 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void perf_record__mmap_read(struct perf_record *rec,
|
|
|
|
struct perf_mmap *md)
|
2009-04-08 21:01:31 +08:00
|
|
|
{
|
2011-01-13 03:07:28 +08:00
|
|
|
unsigned int head = perf_mmap__read_head(md);
|
2009-04-08 21:01:31 +08:00
|
|
|
unsigned int old = md->prev;
|
2011-11-25 18:19:45 +08:00
|
|
|
unsigned char *data = md->base + rec->page_size;
|
2009-04-08 21:01:31 +08:00
|
|
|
unsigned long size;
|
|
|
|
void *buf;
|
|
|
|
|
2011-01-29 00:49:19 +08:00
|
|
|
if (old == head)
|
|
|
|
return;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->samples++;
|
2009-04-08 21:01:31 +08:00
|
|
|
|
|
|
|
size = head - old;
|
|
|
|
|
|
|
|
if ((old & md->mask) + size != (head & md->mask)) {
|
|
|
|
buf = &data[old & md->mask];
|
|
|
|
size = md->mask + 1 - (old & md->mask);
|
|
|
|
old += size;
|
2009-06-04 01:27:19 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
write_output(rec, buf, size);
|
2009-04-08 21:01:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
buf = &data[old & md->mask];
|
|
|
|
size = head - old;
|
|
|
|
old += size;
|
2009-06-04 01:27:19 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
write_output(rec, buf, size);
|
2009-04-08 21:01:31 +08:00
|
|
|
|
|
|
|
md->prev = old;
|
2011-01-13 03:11:53 +08:00
|
|
|
perf_mmap__write_tail(md, old);
|
2009-04-08 21:01:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static volatile int done = 0;
|
2009-06-10 21:55:59 +08:00
|
|
|
static volatile int signr = -1;
|
2011-09-16 05:31:40 +08:00
|
|
|
static volatile int child_finished = 0;
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2009-05-05 23:50:27 +08:00
|
|
|
static void sig_handler(int sig)
|
2009-04-08 21:01:31 +08:00
|
|
|
{
|
2011-09-16 05:31:40 +08:00
|
|
|
if (sig == SIGCHLD)
|
|
|
|
child_finished = 1;
|
|
|
|
|
2009-05-05 23:50:27 +08:00
|
|
|
done = 1;
|
2009-06-10 21:55:59 +08:00
|
|
|
signr = sig;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void perf_record__sig_exit(int exit_status __used, void *arg)
|
2009-06-10 21:55:59 +08:00
|
|
|
{
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_record *rec = arg;
|
2011-09-16 05:31:40 +08:00
|
|
|
int status;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->evlist->workload.pid > 0) {
|
2011-09-16 05:31:40 +08:00
|
|
|
if (!child_finished)
|
2011-11-25 18:19:45 +08:00
|
|
|
kill(rec->evlist->workload.pid, SIGTERM);
|
2011-09-16 05:31:40 +08:00
|
|
|
|
|
|
|
wait(&status);
|
|
|
|
if (WIFSIGNALED(status))
|
2011-11-25 18:19:45 +08:00
|
|
|
psignal(WTERMSIG(status), rec->progname);
|
2011-09-16 05:31:40 +08:00
|
|
|
}
|
2009-10-04 08:35:01 +08:00
|
|
|
|
2010-12-07 01:13:38 +08:00
|
|
|
if (signr == -1 || signr == SIGUSR1)
|
2009-06-10 21:55:59 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
signal(signr, SIG_DFL);
|
|
|
|
kill(getpid(), signr);
|
2009-04-08 21:01:31 +08:00
|
|
|
}
|
|
|
|
|
2011-03-10 22:15:54 +08:00
|
|
|
static bool perf_evlist__equal(struct perf_evlist *evlist,
|
|
|
|
struct perf_evlist *other)
|
|
|
|
{
|
|
|
|
struct perf_evsel *pos, *pair;
|
|
|
|
|
|
|
|
if (evlist->nr_entries != other->nr_entries)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
pair = list_entry(other->entries.next, struct perf_evsel, node);
|
|
|
|
|
|
|
|
list_for_each_entry(pos, &evlist->entries, node) {
|
|
|
|
if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
|
|
|
|
return false;
|
|
|
|
pair = list_entry(pair->node.next, struct perf_evsel, node);
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void perf_record__open(struct perf_record *rec)
|
2011-01-13 00:28:51 +08:00
|
|
|
{
|
2011-10-25 20:42:19 +08:00
|
|
|
struct perf_evsel *pos, *first;
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_evlist *evlist = rec->evlist;
|
|
|
|
struct perf_session *session = rec->session;
|
|
|
|
struct perf_record_opts *opts = &rec->opts;
|
2011-01-13 00:28:51 +08:00
|
|
|
|
2011-10-25 20:42:19 +08:00
|
|
|
first = list_entry(evlist->entries.next, struct perf_evsel, node);
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_evlist__config_attrs(evlist, opts);
|
2011-11-09 00:41:57 +08:00
|
|
|
|
2011-01-13 00:28:51 +08:00
|
|
|
list_for_each_entry(pos, &evlist->entries, node) {
|
|
|
|
struct perf_event_attr *attr = &pos->attr;
|
2011-10-25 20:42:19 +08:00
|
|
|
struct xyarray *group_fd = NULL;
|
2011-01-13 00:28:51 +08:00
|
|
|
/*
|
|
|
|
* Check if parse_single_tracepoint_event has already asked for
|
|
|
|
* PERF_SAMPLE_TIME.
|
|
|
|
*
|
|
|
|
* XXX this is kludgy but short term fix for problems introduced by
|
|
|
|
* eac23d1c that broke 'perf script' by having different sample_types
|
|
|
|
* when using multiple tracepoint events when we use a perf binary
|
|
|
|
* that tries to use sample_id_all on an older kernel.
|
|
|
|
*
|
|
|
|
* We need to move counter creation to perf_session, support
|
|
|
|
* different sample_types, etc.
|
|
|
|
*/
|
|
|
|
bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
|
2010-03-18 22:36:05 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (opts->group && pos != first)
|
2011-10-25 20:42:19 +08:00
|
|
|
group_fd = first->fd;
|
2012-02-15 00:05:30 +08:00
|
|
|
fallback_missing_features:
|
|
|
|
if (opts->exclude_guest_missing)
|
|
|
|
attr->exclude_guest = attr->exclude_host = 0;
|
2011-01-13 00:28:51 +08:00
|
|
|
retry_sample_id:
|
2012-02-15 00:18:57 +08:00
|
|
|
attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
|
2011-01-13 00:28:51 +08:00
|
|
|
try_again:
|
2011-11-12 01:12:56 +08:00
|
|
|
if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
|
2011-11-25 18:19:45 +08:00
|
|
|
opts->group, group_fd) < 0) {
|
2010-03-18 22:36:05 +08:00
|
|
|
int err = errno;
|
|
|
|
|
2011-03-28 20:50:11 +08:00
|
|
|
if (err == EPERM || err == EACCES) {
|
2011-10-26 18:02:55 +08:00
|
|
|
ui__error_paranoid();
|
2011-03-28 20:50:11 +08:00
|
|
|
exit(EXIT_FAILURE);
|
2011-11-25 18:19:45 +08:00
|
|
|
} else if (err == ENODEV && opts->cpu_list) {
|
2010-03-18 22:36:05 +08:00
|
|
|
die("No such device - did you specify"
|
|
|
|
" an out-of-range profile CPU?\n");
|
2012-02-15 00:05:30 +08:00
|
|
|
} else if (err == EINVAL) {
|
|
|
|
if (!opts->exclude_guest_missing &&
|
|
|
|
(attr->exclude_guest || attr->exclude_host)) {
|
|
|
|
pr_debug("Old kernel, cannot exclude "
|
|
|
|
"guest or host samples.\n");
|
|
|
|
opts->exclude_guest_missing = true;
|
|
|
|
goto fallback_missing_features;
|
2012-02-15 00:18:57 +08:00
|
|
|
} else if (!opts->sample_id_all_missing) {
|
2012-02-15 00:05:30 +08:00
|
|
|
/*
|
|
|
|
* Old kernel, no attr->sample_id_type_all field
|
|
|
|
*/
|
2012-02-15 00:18:57 +08:00
|
|
|
opts->sample_id_all_missing = true;
|
2012-02-15 00:05:30 +08:00
|
|
|
if (!opts->sample_time && !opts->raw_samples && !time_needed)
|
|
|
|
attr->sample_type &= ~PERF_SAMPLE_TIME;
|
|
|
|
|
|
|
|
goto retry_sample_id;
|
|
|
|
}
|
2010-03-18 22:36:05 +08:00
|
|
|
}
|
2009-06-07 23:39:02 +08:00
|
|
|
|
2010-03-18 22:36:05 +08:00
|
|
|
/*
|
|
|
|
* If it's cycles then fall back to hrtimer
|
|
|
|
* based cpu-clock-tick sw counter, which
|
|
|
|
* is always available even if no PMU support:
|
|
|
|
*/
|
|
|
|
if (attr->type == PERF_TYPE_HARDWARE
|
|
|
|
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
|
|
|
|
|
|
|
|
if (verbose)
|
2011-03-26 03:11:11 +08:00
|
|
|
ui__warning("The cycles event is not supported, "
|
|
|
|
"trying to fall back to cpu-clock-ticks\n");
|
2010-03-18 22:36:05 +08:00
|
|
|
attr->type = PERF_TYPE_SOFTWARE;
|
|
|
|
attr->config = PERF_COUNT_SW_CPU_CLOCK;
|
|
|
|
goto try_again;
|
|
|
|
}
|
2011-03-26 03:11:11 +08:00
|
|
|
|
|
|
|
if (err == ENOENT) {
|
|
|
|
ui__warning("The %s event is not supported.\n",
|
|
|
|
event_name(pos));
|
|
|
|
exit(EXIT_FAILURE);
|
|
|
|
}
|
|
|
|
|
2010-03-18 22:36:05 +08:00
|
|
|
printf("\n");
|
2010-11-20 09:37:24 +08:00
|
|
|
error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n",
|
2011-01-13 00:28:51 +08:00
|
|
|
err, strerror(err));
|
2009-11-16 13:25:53 +08:00
|
|
|
|
|
|
|
#if defined(__i386__) || defined(__x86_64__)
|
2010-03-18 22:36:05 +08:00
|
|
|
if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
|
|
|
|
die("No hardware sampling interrupt available."
|
|
|
|
" No APIC? If so then you can boot the kernel"
|
|
|
|
" with the \"lapic\" boot parameter to"
|
|
|
|
" force-enable it.\n");
|
2009-11-16 13:25:53 +08:00
|
|
|
#endif
|
|
|
|
|
2010-03-18 22:36:05 +08:00
|
|
|
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
|
2009-10-15 11:22:07 +08:00
|
|
|
}
|
|
|
|
}
|
2010-12-25 22:12:25 +08:00
|
|
|
|
2011-02-26 11:51:54 +08:00
|
|
|
if (perf_evlist__set_filters(evlist)) {
|
|
|
|
error("failed to set filter with %d (%s)\n", errno,
|
|
|
|
strerror(errno));
|
|
|
|
exit(-1);
|
|
|
|
}
|
|
|
|
|
2011-12-19 21:39:31 +08:00
|
|
|
if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
|
|
|
|
if (errno == EPERM)
|
|
|
|
die("Permission error mapping pages.\n"
|
|
|
|
"Consider increasing "
|
|
|
|
"/proc/sys/kernel/perf_event_mlock_kb,\n"
|
|
|
|
"or try again with a smaller value of -m/--mmap_pages.\n"
|
|
|
|
"(current value: %d)\n", opts->mmap_pages);
|
2011-12-19 21:39:32 +08:00
|
|
|
else if (!is_power_of_2(opts->mmap_pages))
|
|
|
|
die("--mmap_pages/-m value must be a power of two.");
|
|
|
|
|
2011-01-15 01:50:51 +08:00
|
|
|
die("failed to mmap with %d (%s)\n", errno, strerror(errno));
|
2011-12-19 21:39:31 +08:00
|
|
|
}
|
2011-01-15 01:50:51 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->file_new)
|
2011-03-10 22:15:54 +08:00
|
|
|
session->evlist = evlist;
|
|
|
|
else {
|
|
|
|
if (!perf_evlist__equal(session->evlist, evlist)) {
|
|
|
|
fprintf(stderr, "incompatible append\n");
|
|
|
|
exit(-1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
perf_session__update_sample_type(session);
|
2009-05-05 23:50:27 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static int process_buildids(struct perf_record *rec)
|
2010-02-04 02:52:05 +08:00
|
|
|
{
|
2011-11-25 18:19:45 +08:00
|
|
|
u64 size = lseek(rec->output, 0, SEEK_CUR);
|
2010-02-04 02:52:05 +08:00
|
|
|
|
2010-03-12 02:53:11 +08:00
|
|
|
if (size == 0)
|
|
|
|
return 0;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->session->fd = rec->output;
|
|
|
|
return __perf_session__process_events(rec->session, rec->post_processing_offset,
|
|
|
|
size - rec->post_processing_offset,
|
2010-02-04 02:52:05 +08:00
|
|
|
size, &build_id__mark_dso_hit_ops);
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void perf_record__exit(int status __used, void *arg)
|
2009-06-19 05:22:55 +08:00
|
|
|
{
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_record *rec = arg;
|
|
|
|
|
|
|
|
if (!rec->opts.pipe_output) {
|
|
|
|
rec->session->header.data_size += rec->bytes_written;
|
|
|
|
|
|
|
|
if (!rec->no_buildid)
|
|
|
|
process_buildids(rec);
|
|
|
|
perf_session__write_header(rec->session, rec->evlist,
|
|
|
|
rec->output, true);
|
|
|
|
perf_session__delete(rec->session);
|
|
|
|
perf_evlist__delete(rec->evlist);
|
2010-07-31 05:31:28 +08:00
|
|
|
symbol__exit();
|
2010-04-02 12:59:22 +08:00
|
|
|
}
|
2009-06-19 05:22:55 +08:00
|
|
|
}
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
|
2010-04-19 13:32:50 +08:00
|
|
|
{
|
|
|
|
int err;
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool *tool = data;
|
2010-04-19 13:32:50 +08:00
|
|
|
|
2010-04-28 08:17:50 +08:00
|
|
|
if (machine__is_host(machine))
|
2010-04-19 13:32:50 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
*As for guest kernel when processing subcommand record&report,
|
|
|
|
*we arrange module mmap prior to guest kernel mmap and trigger
|
|
|
|
*a preload dso because default guest module symbols are loaded
|
|
|
|
*from guest kallsyms instead of /lib/modules/XXX/XXX. This
|
|
|
|
*method is used to avoid symbol missing when the first addr is
|
|
|
|
*in module instead of in guest kernel.
|
|
|
|
*/
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_modules(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine);
|
2010-04-19 13:32:50 +08:00
|
|
|
if (err < 0)
|
|
|
|
pr_err("Couldn't record guest kernel [%d]'s reference"
|
2010-04-28 08:17:50 +08:00
|
|
|
" relocation symbol.\n", machine->pid);
|
2010-04-19 13:32:50 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
|
|
|
|
* have no _text sometimes.
|
|
|
|
*/
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine, "_text");
|
2010-04-19 13:32:50 +08:00
|
|
|
if (err < 0)
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine, "_stext");
|
2010-04-19 13:32:50 +08:00
|
|
|
if (err < 0)
|
|
|
|
pr_err("Couldn't record guest kernel [%d]'s reference"
|
2010-04-28 08:17:50 +08:00
|
|
|
" relocation symbol.\n", machine->pid);
|
2010-04-19 13:32:50 +08:00
|
|
|
}
|
|
|
|
|
2010-05-03 04:05:29 +08:00
|
|
|
static struct perf_event_header finished_round_event = {
|
|
|
|
.size = sizeof(struct perf_event_header),
|
|
|
|
.type = PERF_RECORD_FINISHED_ROUND,
|
|
|
|
};
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static void perf_record__mmap_read_all(struct perf_record *rec)
|
2010-05-03 04:05:29 +08:00
|
|
|
{
|
2010-05-20 20:45:26 +08:00
|
|
|
int i;
|
2010-05-03 04:05:29 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
|
|
|
|
if (rec->evlist->mmap[i].base)
|
|
|
|
perf_record__mmap_read(rec, &rec->evlist->mmap[i]);
|
2010-05-03 04:05:29 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (perf_header__has_feat(&rec->session->header, HEADER_TRACE_INFO))
|
|
|
|
write_output(rec, &finished_round_event, sizeof(finished_round_event));
|
2010-05-03 04:05:29 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
|
2009-05-05 23:50:27 +08:00
|
|
|
{
|
2009-06-03 04:59:57 +08:00
|
|
|
struct stat st;
|
|
|
|
int flags;
|
2011-12-16 00:32:40 +08:00
|
|
|
int err, output, feat;
|
2009-09-18 01:59:05 +08:00
|
|
|
unsigned long waking = 0;
|
2010-03-18 22:36:04 +08:00
|
|
|
const bool forks = argc > 0;
|
2010-04-28 08:17:50 +08:00
|
|
|
struct machine *machine;
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool *tool = &rec->tool;
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_record_opts *opts = &rec->opts;
|
|
|
|
struct perf_evlist *evsel_list = rec->evlist;
|
|
|
|
const char *output_name = rec->output_name;
|
|
|
|
struct perf_session *session;
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->progname = argv[0];
|
2011-09-16 05:31:40 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->page_size = sysconf(_SC_PAGE_SIZE);
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
on_exit(perf_record__sig_exit, rec);
|
2009-06-19 05:22:55 +08:00
|
|
|
signal(SIGCHLD, sig_handler);
|
|
|
|
signal(SIGINT, sig_handler);
|
2010-12-07 01:13:38 +08:00
|
|
|
signal(SIGUSR1, sig_handler);
|
2009-06-19 05:22:55 +08:00
|
|
|
|
2011-01-17 00:14:45 +08:00
|
|
|
if (!output_name) {
|
|
|
|
if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
|
2011-11-25 18:19:45 +08:00
|
|
|
opts->pipe_output = true;
|
2011-01-17 00:14:45 +08:00
|
|
|
else
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->output_name = output_name = "perf.data";
|
2011-01-17 00:14:45 +08:00
|
|
|
}
|
|
|
|
if (output_name) {
|
|
|
|
if (!strcmp(output_name, "-"))
|
2011-11-25 18:19:45 +08:00
|
|
|
opts->pipe_output = true;
|
2011-01-17 00:14:45 +08:00
|
|
|
else if (!stat(output_name, &st) && st.st_size) {
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->write_mode == WRITE_FORCE) {
|
2011-01-17 00:14:45 +08:00
|
|
|
char oldname[PATH_MAX];
|
|
|
|
snprintf(oldname, sizeof(oldname), "%s.old",
|
|
|
|
output_name);
|
|
|
|
unlink(oldname);
|
|
|
|
rename(output_name, oldname);
|
|
|
|
}
|
2011-11-25 18:19:45 +08:00
|
|
|
} else if (rec->write_mode == WRITE_APPEND) {
|
|
|
|
rec->write_mode = WRITE_FORCE;
|
2009-08-07 20:16:01 +08:00
|
|
|
}
|
2009-06-02 21:52:24 +08:00
|
|
|
}
|
|
|
|
|
2010-02-04 16:46:42 +08:00
|
|
|
flags = O_CREAT|O_RDWR;
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->write_mode == WRITE_APPEND)
|
|
|
|
rec->file_new = 0;
|
2009-06-03 04:59:57 +08:00
|
|
|
else
|
|
|
|
flags |= O_TRUNC;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (opts->pipe_output)
|
2010-04-02 12:59:16 +08:00
|
|
|
output = STDOUT_FILENO;
|
|
|
|
else
|
|
|
|
output = open(output_name, flags, S_IRUSR | S_IWUSR);
|
2009-04-08 21:01:31 +08:00
|
|
|
if (output < 0) {
|
|
|
|
perror("failed to create output file");
|
|
|
|
exit(-1);
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->output = output;
|
|
|
|
|
2010-04-15 01:42:07 +08:00
|
|
|
session = perf_session__new(output_name, O_WRONLY,
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->write_mode == WRITE_FORCE, false, NULL);
|
2009-12-12 07:24:02 +08:00
|
|
|
if (session == NULL) {
|
2009-11-17 11:18:11 +08:00
|
|
|
pr_err("Not enough memory for reading perf file header\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->session = session;
|
|
|
|
|
2011-12-16 00:32:40 +08:00
|
|
|
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
|
|
|
|
perf_header__set_feat(&session->header, feat);
|
|
|
|
|
|
|
|
if (rec->no_buildid)
|
|
|
|
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
|
|
|
|
|
|
|
|
if (!have_tracepoints(&evsel_list->entries))
|
|
|
|
perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
|
2010-11-27 05:39:15 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (!rec->file_new) {
|
2011-03-10 22:15:54 +08:00
|
|
|
err = perf_session__read_header(session, output);
|
2009-11-20 00:55:55 +08:00
|
|
|
if (err < 0)
|
2010-07-30 01:08:55 +08:00
|
|
|
goto out_delete_session;
|
2009-11-20 00:55:55 +08:00
|
|
|
}
|
|
|
|
|
2009-12-28 07:36:57 +08:00
|
|
|
if (forks) {
|
2011-11-25 18:19:45 +08:00
|
|
|
err = perf_evlist__prepare_workload(evsel_list, opts, argv);
|
2011-11-09 18:47:15 +08:00
|
|
|
if (err < 0) {
|
|
|
|
pr_err("Couldn't run the workload!\n");
|
|
|
|
goto out_delete_session;
|
2009-12-17 00:55:55 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_record__open(rec);
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2011-02-17 22:18:42 +08:00
|
|
|
/*
|
2011-11-25 18:19:45 +08:00
|
|
|
* perf_session__delete(session) will be called at perf_record__exit()
|
2011-02-17 22:18:42 +08:00
|
|
|
*/
|
2011-11-25 18:19:45 +08:00
|
|
|
on_exit(perf_record__exit, rec);
|
2011-02-17 22:18:42 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (opts->pipe_output) {
|
2010-04-02 12:59:16 +08:00
|
|
|
err = perf_header__write_pipe(output);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
2011-11-25 18:19:45 +08:00
|
|
|
} else if (rec->file_new) {
|
2011-03-10 22:15:54 +08:00
|
|
|
err = perf_session__write_header(session, evsel_list,
|
|
|
|
output, false);
|
2009-11-20 00:55:56 +08:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
2010-01-06 02:50:31 +08:00
|
|
|
}
|
|
|
|
|
2012-02-07 06:27:52 +08:00
|
|
|
if (!rec->no_buildid
|
2011-12-07 17:02:55 +08:00
|
|
|
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
|
2012-02-07 06:27:52 +08:00
|
|
|
pr_err("Couldn't generate buildids. "
|
2011-12-07 17:02:55 +08:00
|
|
|
"Use --no-buildid to profile anyway.\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
|
2010-02-04 02:52:05 +08:00
|
|
|
|
2011-11-28 17:56:39 +08:00
|
|
|
machine = perf_session__find_host_machine(session);
|
|
|
|
if (!machine) {
|
|
|
|
pr_err("Couldn't find native kernel information.\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (opts->pipe_output) {
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_attrs(tool, session,
|
2011-11-25 18:19:45 +08:00
|
|
|
process_synthesized_event);
|
2010-04-02 12:59:19 +08:00
|
|
|
if (err < 0) {
|
|
|
|
pr_err("Couldn't synthesize attrs.\n");
|
|
|
|
return err;
|
|
|
|
}
|
2010-04-02 12:59:20 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_event_types(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine);
|
2010-04-02 12:59:20 +08:00
|
|
|
if (err < 0) {
|
|
|
|
pr_err("Couldn't synthesize event_types.\n");
|
|
|
|
return err;
|
|
|
|
}
|
2010-04-02 12:59:21 +08:00
|
|
|
|
2011-01-12 06:56:53 +08:00
|
|
|
if (have_tracepoints(&evsel_list->entries)) {
|
2010-05-03 13:14:48 +08:00
|
|
|
/*
|
|
|
|
* FIXME err <= 0 here actually means that
|
|
|
|
* there were no tracepoints so its not really
|
|
|
|
* an error, just that we don't need to
|
|
|
|
* synthesize anything. We really have to
|
|
|
|
* return this more properly and also
|
|
|
|
* propagate errors that now are calling die()
|
|
|
|
*/
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
|
2011-11-28 17:56:39 +08:00
|
|
|
process_synthesized_event);
|
2010-05-03 13:14:48 +08:00
|
|
|
if (err <= 0) {
|
|
|
|
pr_err("Couldn't record tracing data.\n");
|
|
|
|
return err;
|
|
|
|
}
|
2011-11-25 18:19:45 +08:00
|
|
|
advance_output(rec, err);
|
2010-05-03 13:14:48 +08:00
|
|
|
}
|
2010-04-02 12:59:19 +08:00
|
|
|
}
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine, "_text");
|
2010-03-31 05:27:39 +08:00
|
|
|
if (err < 0)
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine, "_stext");
|
2010-11-23 00:01:55 +08:00
|
|
|
if (err < 0)
|
|
|
|
pr_err("Couldn't record kernel reference relocation symbol\n"
|
|
|
|
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
|
|
|
|
"Check /proc/kallsyms permission or run as root.\n");
|
perf tools: Encode kernel module mappings in perf.data
We were always looking at the running machine /proc/modules,
even when processing a perf.data file, which only makes sense
when we're doing 'perf record' and 'perf report' on the same
machine, and in close sucession, or if we don't use modules at
all, right Peter? ;-)
Now, at 'perf record' time we read /proc/modules, find the long
path for modules, and put them as PERF_MMAP events, just like we
did to encode the reloc reference symbol for vmlinux. Talking
about that now it is encoded in .pgoff, so that we can use
.{start,len} to store the address boundaries for the kernel so
that when we reconstruct the kmaps tree we can do lookups right
away, without having to fixup the end of the kernel maps like we
did in the past (and now only in perf record).
One more step in the 'perf archive' direction when we'll finally
be able to collect data in one machine and analyse in another.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1263396139-4798-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 23:22:17 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
err = perf_event__synthesize_modules(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine);
|
2010-11-23 00:01:55 +08:00
|
|
|
if (err < 0)
|
|
|
|
pr_err("Couldn't record kernel module information.\n"
|
|
|
|
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
|
|
|
|
"Check /proc/modules permission or run as root.\n");
|
|
|
|
|
2010-04-19 13:32:50 +08:00
|
|
|
if (perf_guest)
|
2011-11-28 18:30:20 +08:00
|
|
|
perf_session__process_machines(session, tool,
|
2011-01-30 00:01:45 +08:00
|
|
|
perf_event__synthesize_guest_os);
|
2009-06-25 23:05:54 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (!opts->system_wide)
|
2011-11-28 18:30:20 +08:00
|
|
|
perf_event__synthesize_thread_map(tool, evsel_list->threads,
|
2011-02-11 21:45:54 +08:00
|
|
|
process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine);
|
2009-10-27 05:23:18 +08:00
|
|
|
else
|
2011-11-28 18:30:20 +08:00
|
|
|
perf_event__synthesize_threads(tool, process_synthesized_event,
|
2011-11-28 17:56:39 +08:00
|
|
|
machine);
|
2009-06-25 23:05:54 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->realtime_prio) {
|
2009-04-08 21:01:31 +08:00
|
|
|
struct sched_param param;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
param.sched_priority = rec->realtime_prio;
|
2009-04-08 21:01:31 +08:00
|
|
|
if (sched_setscheduler(0, SCHED_FIFO, ¶m)) {
|
2009-10-22 03:34:06 +08:00
|
|
|
pr_err("Could not set realtime priority.\n");
|
2009-04-08 21:01:31 +08:00
|
|
|
exit(-1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-08-26 00:17:55 +08:00
|
|
|
perf_evlist__enable(evsel_list);
|
|
|
|
|
2009-12-17 00:55:55 +08:00
|
|
|
/*
|
|
|
|
* Let the child rip
|
|
|
|
*/
|
2009-12-28 07:36:57 +08:00
|
|
|
if (forks)
|
2011-11-09 18:47:15 +08:00
|
|
|
perf_evlist__start_workload(evsel_list);
|
2009-12-17 00:55:55 +08:00
|
|
|
|
2009-06-25 03:12:48 +08:00
|
|
|
for (;;) {
|
2011-11-25 18:19:45 +08:00
|
|
|
int hits = rec->samples;
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_record__mmap_read_all(rec);
|
2009-04-08 21:01:31 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (hits == rec->samples) {
|
2009-06-25 03:12:48 +08:00
|
|
|
if (done)
|
|
|
|
break;
|
2011-01-12 08:30:02 +08:00
|
|
|
err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
|
2009-09-18 01:59:05 +08:00
|
|
|
waking++;
|
|
|
|
}
|
|
|
|
|
2011-07-25 22:06:19 +08:00
|
|
|
if (done)
|
|
|
|
perf_evlist__disable(evsel_list);
|
2009-04-08 21:01:31 +08:00
|
|
|
}
|
|
|
|
|
2010-12-07 01:13:38 +08:00
|
|
|
if (quiet || signr == SIGUSR1)
|
2010-10-27 01:20:09 +08:00
|
|
|
return 0;
|
|
|
|
|
2009-09-18 01:59:05 +08:00
|
|
|
fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
|
|
|
|
|
2009-06-04 01:27:19 +08:00
|
|
|
/*
|
|
|
|
* Approximate RIP event size: 24 bytes.
|
|
|
|
*/
|
|
|
|
fprintf(stderr,
|
2011-01-23 06:37:02 +08:00
|
|
|
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
|
2011-11-25 18:19:45 +08:00
|
|
|
(double)rec->bytes_written / 1024.0 / 1024.0,
|
2009-06-04 01:27:19 +08:00
|
|
|
output_name,
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->bytes_written / 24);
|
2009-06-03 05:43:11 +08:00
|
|
|
|
2009-04-08 21:01:31 +08:00
|
|
|
return 0;
|
2010-07-30 01:08:55 +08:00
|
|
|
|
|
|
|
out_delete_session:
|
|
|
|
perf_session__delete(session);
|
|
|
|
return err;
|
2009-04-08 21:01:31 +08:00
|
|
|
}
|
2009-05-26 15:17:18 +08:00
|
|
|
|
|
|
|
static const char * const record_usage[] = {
|
2009-05-28 22:25:34 +08:00
|
|
|
"perf record [<options>] [<command>]",
|
|
|
|
"perf record [<options>] -- <command> [<options>]",
|
2009-05-26 15:17:18 +08:00
|
|
|
NULL
|
|
|
|
};
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
/*
|
|
|
|
* XXX Ideally would be local to cmd_record() and passed to a perf_record__new
|
|
|
|
* because we need to have access to it in perf_record__exit, that is called
|
|
|
|
* after cmd_record() exits, but since record_options need to be accessible to
|
|
|
|
* builtin-script, leave it here.
|
|
|
|
*
|
|
|
|
* At least we don't ouch it in all the other functions here directly.
|
|
|
|
*
|
|
|
|
* Just say no to tons of global variables, sigh.
|
|
|
|
*/
|
|
|
|
static struct perf_record record = {
|
|
|
|
.opts = {
|
|
|
|
.mmap_pages = UINT_MAX,
|
|
|
|
.user_freq = UINT_MAX,
|
|
|
|
.user_interval = ULLONG_MAX,
|
|
|
|
.freq = 1000,
|
|
|
|
},
|
|
|
|
.write_mode = WRITE_FORCE,
|
|
|
|
.file_new = true,
|
|
|
|
};
|
2010-04-15 01:42:07 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
/*
|
|
|
|
* XXX Will stay a global variable till we fix builtin-script.c to stop messing
|
|
|
|
* with it and switch to use the library functions in perf_evlist that came
|
|
|
|
* from builtin-record.c, i.e. use perf_record_opts,
|
|
|
|
* perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
|
|
|
|
* using pipes, etc.
|
|
|
|
*/
|
2010-11-10 22:11:30 +08:00
|
|
|
const struct option record_options[] = {
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_CALLBACK('e', "event", &record.evlist, "event",
|
2009-06-06 18:24:17 +08:00
|
|
|
"event selector. use 'perf list' to list available events",
|
2011-07-14 17:25:32 +08:00
|
|
|
parse_events_option),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_CALLBACK(0, "filter", &record.evlist, "filter",
|
2009-10-15 11:22:07 +08:00
|
|
|
"event filter", parse_filter),
|
2012-02-09 00:32:52 +08:00
|
|
|
OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
|
2010-03-18 22:36:05 +08:00
|
|
|
"record events on existing process id"),
|
2012-02-09 00:32:52 +08:00
|
|
|
OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
|
2010-03-18 22:36:05 +08:00
|
|
|
"record events on existing thread id"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_INTEGER('r', "realtime", &record.realtime_prio,
|
2009-05-26 15:17:18 +08:00
|
|
|
"collect data with this RT SCHED_FIFO priority"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('D', "no-delay", &record.opts.no_delay,
|
perf record: Add "nodelay" mode, disabled by default
Sometimes there is a need to use perf in "live-log" mode. The problem
is, for seldom events, actual info output is largely delayed because
perf-record reads sample data in whole pages.
So for such scenarious, add flag for perf-record to go in "nodelay"
mode. To track e.g. what's going on in icmp_rcv while ping is running
Use it with something like this:
(1) $ perf probe -L icmp_rcv | grep -U8 '^ *43\>'
goto error;
}
38 if (!pskb_pull(skb, sizeof(*icmph)))
goto error;
icmph = icmp_hdr(skb);
43 ICMPMSGIN_INC_STATS_BH(net, icmph->type);
/*
* 18 is the highest 'known' ICMP type. Anything else is a mystery
*
* RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
* discarded.
*/
50 if (icmph->type > NR_ICMP_TYPES)
goto error;
$ perf probe icmp_rcv:43 'type=icmph->type'
(2) $ cat trace-icmp.py
[...]
def trace_begin():
print "in trace_begin"
def trace_end():
print "in trace_end"
def probe__icmp_rcv(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
__probe_ip, type):
print_header(event_name, common_cpu, common_secs, common_nsecs,
common_pid, common_comm)
print "__probe_ip=%u, type=%u\n" % \
(__probe_ip, type),
[...]
(3) $ perf record -a -D -e probe:icmp_rcv -o - | \
perf script -i - -s trace-icmp.py
Thanks to Peter Zijlstra for pointing how to do it.
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>, Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <20110112140613.GA11698@tugrik.mns.mnsspb.ru>
Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-12 22:59:36 +08:00
|
|
|
"collect data without buffering"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
|
2009-08-13 16:27:19 +08:00
|
|
|
"collect raw sample records from all opened counters"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('a', "all-cpus", &record.opts.system_wide,
|
2009-05-26 15:17:18 +08:00
|
|
|
"system-wide collection from all CPUs"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('A', "append", &record.append_file,
|
2009-06-03 04:59:57 +08:00
|
|
|
"append to the output file to do incremental profiling"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_STRING('C', "cpu", &record.opts.cpu_list, "cpu",
|
2010-05-28 18:00:01 +08:00
|
|
|
"list of cpus to monitor"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('f', "force", &record.force,
|
2010-04-15 01:42:07 +08:00
|
|
|
"overwrite existing data file (deprecated)"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
|
|
|
|
OPT_STRING('o', "output", &record.output_name, "file",
|
2009-06-03 04:59:57 +08:00
|
|
|
"output file name"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
|
2010-05-12 16:40:01 +08:00
|
|
|
"child tasks do not inherit counters"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
|
|
|
|
OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages,
|
2011-11-09 19:16:26 +08:00
|
|
|
"number of mmap data pages"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN(0, "group", &record.opts.group,
|
2011-08-17 18:42:07 +08:00
|
|
|
"put the counters into a counter group"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('g', "call-graph", &record.opts.call_graph,
|
2009-06-14 21:04:15 +08:00
|
|
|
"do call-graph (stack chain/backtrace) recording"),
|
2010-04-13 16:37:33 +08:00
|
|
|
OPT_INCR('v', "verbose", &verbose,
|
2009-06-07 23:39:02 +08:00
|
|
|
"be more verbose (show counter open errors, etc)"),
|
2010-10-27 01:20:09 +08:00
|
|
|
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
|
2009-06-25 03:12:48 +08:00
|
|
|
"per thread counts"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('d', "data", &record.opts.sample_address,
|
2009-07-16 21:44:29 +08:00
|
|
|
"Sample addresses"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
|
2011-12-20 22:32:45 +08:00
|
|
|
OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
|
2009-06-25 03:12:48 +08:00
|
|
|
"don't sample"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
|
2010-06-17 17:39:01 +08:00
|
|
|
"do not update the buildid cache"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
|
2010-11-27 05:39:15 +08:00
|
|
|
"do not collect buildids in perf.data"),
|
2011-11-25 18:19:45 +08:00
|
|
|
OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
"monitor event in cgroup name only",
|
|
|
|
parse_cgroups),
|
2012-01-20 00:08:15 +08:00
|
|
|
OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
|
2009-05-26 15:17:18 +08:00
|
|
|
OPT_END()
|
|
|
|
};
|
|
|
|
|
2009-07-01 18:37:06 +08:00
|
|
|
int cmd_record(int argc, const char **argv, const char *prefix __used)
|
2009-05-26 15:17:18 +08:00
|
|
|
{
|
2011-01-04 02:39:04 +08:00
|
|
|
int err = -ENOMEM;
|
|
|
|
struct perf_evsel *pos;
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_evlist *evsel_list;
|
|
|
|
struct perf_record *rec = &record;
|
2009-05-26 15:17:18 +08:00
|
|
|
|
perf tools: Make perf.data more self-descriptive (v8)
The goal of this patch is to include more information about the host
environment into the perf.data so it is more self-descriptive. Overtime,
profiles are captured on various machines and it becomes hard to track
what was recorded, on what machine and when.
This patch provides a way to solve this by extending the perf.data file
with basic information about the host machine. To add those extensions,
we leverage the feature bits capabilities of the perf.data format. The
change is backward compatible with existing perf.data files.
We define the following useful new extensions:
- HEADER_HOSTNAME: the hostname
- HEADER_OSRELEASE: the kernel release number
- HEADER_ARCH: the hw architecture
- HEADER_CPUDESC: generic CPU description
- HEADER_NRCPUS: number of online/avail cpus
- HEADER_CMDLINE: perf command line
- HEADER_VERSION: perf version
- HEADER_TOPOLOGY: cpu topology
- HEADER_EVENT_DESC: full event description (attrs)
- HEADER_CPUID: easy-to-parse low level CPU identication
The small granularity for the entries is to make it easier to extend
without breaking backward compatiblity. Many entries are provided as
ASCII strings.
Perf report/script have been modified to print the basic information as
easy-to-parse ASCII strings. Extended information about CPU and NUMA
topology may be requested with the -I option.
Thanks to David Ahern for reviewing and testing the many versions of
this patch.
$ perf report --stdio
# ========
# captured on : Mon Sep 26 15:22:14 2011
# hostname : quad
# os release : 3.1.0-rc4-tip
# perf version : 3.1.0-rc4
# arch : x86_64
# nrcpus online : 4
# nrcpus avail : 4
# cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
# cpuid : GenuineIntel,6,15,11
# total memory : 8105360 kB
# cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
# event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
# HEADER_CPU_TOPOLOGY info available, use -I to display
# HEADER_NUMA_TOPOLOGY info available, use -I to display
# ========
#
...
$ perf report --stdio -I
# ========
# captured on : Mon Sep 26 15:22:14 2011
# hostname : quad
# os release : 3.1.0-rc4-tip
# perf version : 3.1.0-rc4
# arch : x86_64
# nrcpus online : 4
# nrcpus avail : 4
# cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
# cpuid : GenuineIntel,6,15,11
# total memory : 8105360 kB
# cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
# event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
# sibling cores : 0-3
# sibling threads : 0
# sibling threads : 1
# sibling threads : 2
# sibling threads : 3
# node0 meminfo : total = 8320608 kB, free = 7571024 kB
# node0 cpu list : 0-3
# ========
#
...
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20110930134040.GA5575@quad
Signed-off-by: Stephane Eranian <eranian@google.com>
[ committer notes: Use --show-info in the tools as was in the docs, rename
perf_header_fprintf_info to perf_file_section__fprintf_info, fixup
conflict with f69b64f7 "perf: Support setting the disassembler style" ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-30 21:40:40 +08:00
|
|
|
perf_header__set_cmdline(argc, argv);
|
|
|
|
|
2011-01-30 21:59:43 +08:00
|
|
|
evsel_list = perf_evlist__new(NULL, NULL);
|
2011-01-12 06:56:53 +08:00
|
|
|
if (evsel_list == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->evlist = evsel_list;
|
|
|
|
|
2010-11-10 22:11:30 +08:00
|
|
|
argc = parse_options(argc, argv, record_options, record_usage,
|
2009-12-16 06:04:40 +08:00
|
|
|
PARSE_OPT_STOP_AT_NON_OPTION);
|
2012-02-09 00:32:52 +08:00
|
|
|
if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
|
2012-01-20 00:08:15 +08:00
|
|
|
!rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
|
2010-11-10 22:11:30 +08:00
|
|
|
usage_with_options(record_usage, record_options);
|
2009-05-26 15:17:18 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->force && rec->append_file) {
|
2010-04-15 01:42:07 +08:00
|
|
|
fprintf(stderr, "Can't overwrite and append at the same time."
|
|
|
|
" You need to choose between -f and -A");
|
2010-11-10 22:11:30 +08:00
|
|
|
usage_with_options(record_usage, record_options);
|
2011-11-25 18:19:45 +08:00
|
|
|
} else if (rec->append_file) {
|
|
|
|
rec->write_mode = WRITE_APPEND;
|
2010-04-15 01:42:07 +08:00
|
|
|
} else {
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->write_mode = WRITE_FORCE;
|
2010-04-15 01:42:07 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (nr_cgroups && !rec->opts.system_wide) {
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
fprintf(stderr, "cgroup monitoring only available in"
|
|
|
|
" system-wide mode\n");
|
|
|
|
usage_with_options(record_usage, record_options);
|
|
|
|
}
|
|
|
|
|
2009-12-16 06:04:40 +08:00
|
|
|
symbol__init();
|
2010-11-27 05:39:15 +08:00
|
|
|
|
perf symbols: Handle /proc/sys/kernel/kptr_restrict
Perf uses /proc/modules to figure out where kernel modules are loaded.
With the advent of kptr_restrict, non root users get zeroes for all module
start addresses.
So check if kptr_restrict is non zero and don't generate the syntethic
PERF_RECORD_MMAP events for them.
Warn the user about it in perf record and in perf report.
In perf report the reference relocation symbol being zero means that
kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't
use it to fixup symbol addresses when using a valid kallsyms (in the buildid
cache) or vmlinux (in the vmlinux path) build-id located automatically or
specified by the user.
Provide an explanation about it in 'perf report' if kernel samples were taken,
checking if a suitable vmlinux or kallsyms was found/specified.
Restricted /proc/kallsyms don't go to the buildid cache anymore.
Example:
[acme@emilia ~]$ perf record -F 100000 sleep 1
WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check
/proc/sys/kernel/kptr_restrict.
Samples in kernel functions may not be resolved if a suitable vmlinux file is
not found in the buildid cache or in the vmlinux path.
Samples in kernel modules won't be resolved at all.
If some relocation was applied (e.g. kexec) symbols may be misresolved even
with a suitable vmlinux or kallsyms file.
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ]
[acme@emilia ~]$
[acme@emilia ~]$ perf report --stdio
Kernel address maps (/proc/{kallsyms,modules}) were restricted,
check /proc/sys/kernel/kptr_restrict before running 'perf record'.
If some relocation was applied (e.g. kexec) symbols may be misresolved.
Samples in kernel modules can't be resolved as well.
# Events: 13 cycles
#
# Overhead Command Shared Object Symbol
# ........ ....... ................. .....................
#
20.24% sleep [kernel.kallsyms] [k] page_fault
20.04% sleep [kernel.kallsyms] [k] filemap_fault
19.78% sleep [kernel.kallsyms] [k] __lru_cache_add
19.69% sleep ld-2.12.so [.] memcpy
14.71% sleep [kernel.kallsyms] [k] dput
4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers
0.73% sleep [kernel.kallsyms] [k] perf_event_comm
0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe
#
# (For a higher level overview, try: perf report --sort comm,dso)
#
[acme@emilia ~]$
This is because it found a suitable vmlinux (build-id checked) in
/lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long
file name).
If we remove that file from the vmlinux path:
[root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \
/lib/modules/2.6.39-rc7+/build/vmlinux.OFF
[acme@emilia ~]$ perf report --stdio
[kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562
not found, continuing without symbols
Kernel address maps (/proc/{kallsyms,modules}) were restricted, check
/proc/sys/kernel/kptr_restrict before running 'perf record'.
As no suitable kallsyms nor vmlinux was found, kernel samples can't be
resolved.
Samples in kernel modules can't be resolved as well.
# Events: 13 cycles
#
# Overhead Command Shared Object Symbol
# ........ ....... ................. ......
#
80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a
19.69% sleep ld-2.12.so [.] memcpy
#
# (For a higher level overview, try: perf report --sort comm,dso)
#
[acme@emilia ~]$
Reported-by: Stephane Eranian <eranian@google.com>
Suggested-by: David Miller <davem@davemloft.net>
Cc: Dave Jones <davej@redhat.com>
Cc: David Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Kees Cook <kees.cook@canonical.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 20:53:51 +08:00
|
|
|
if (symbol_conf.kptr_restrict)
|
2011-05-27 22:00:41 +08:00
|
|
|
pr_warning(
|
|
|
|
"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
|
|
|
|
"check /proc/sys/kernel/kptr_restrict.\n\n"
|
|
|
|
"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
|
|
|
|
"file is not found in the buildid cache or in the vmlinux path.\n\n"
|
|
|
|
"Samples in kernel modules won't be resolved at all.\n\n"
|
|
|
|
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
|
|
|
|
"even with a suitable vmlinux or kallsyms file.\n\n");
|
perf symbols: Handle /proc/sys/kernel/kptr_restrict
Perf uses /proc/modules to figure out where kernel modules are loaded.
With the advent of kptr_restrict, non root users get zeroes for all module
start addresses.
So check if kptr_restrict is non zero and don't generate the syntethic
PERF_RECORD_MMAP events for them.
Warn the user about it in perf record and in perf report.
In perf report the reference relocation symbol being zero means that
kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't
use it to fixup symbol addresses when using a valid kallsyms (in the buildid
cache) or vmlinux (in the vmlinux path) build-id located automatically or
specified by the user.
Provide an explanation about it in 'perf report' if kernel samples were taken,
checking if a suitable vmlinux or kallsyms was found/specified.
Restricted /proc/kallsyms don't go to the buildid cache anymore.
Example:
[acme@emilia ~]$ perf record -F 100000 sleep 1
WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check
/proc/sys/kernel/kptr_restrict.
Samples in kernel functions may not be resolved if a suitable vmlinux file is
not found in the buildid cache or in the vmlinux path.
Samples in kernel modules won't be resolved at all.
If some relocation was applied (e.g. kexec) symbols may be misresolved even
with a suitable vmlinux or kallsyms file.
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ]
[acme@emilia ~]$
[acme@emilia ~]$ perf report --stdio
Kernel address maps (/proc/{kallsyms,modules}) were restricted,
check /proc/sys/kernel/kptr_restrict before running 'perf record'.
If some relocation was applied (e.g. kexec) symbols may be misresolved.
Samples in kernel modules can't be resolved as well.
# Events: 13 cycles
#
# Overhead Command Shared Object Symbol
# ........ ....... ................. .....................
#
20.24% sleep [kernel.kallsyms] [k] page_fault
20.04% sleep [kernel.kallsyms] [k] filemap_fault
19.78% sleep [kernel.kallsyms] [k] __lru_cache_add
19.69% sleep ld-2.12.so [.] memcpy
14.71% sleep [kernel.kallsyms] [k] dput
4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers
0.73% sleep [kernel.kallsyms] [k] perf_event_comm
0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe
#
# (For a higher level overview, try: perf report --sort comm,dso)
#
[acme@emilia ~]$
This is because it found a suitable vmlinux (build-id checked) in
/lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long
file name).
If we remove that file from the vmlinux path:
[root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \
/lib/modules/2.6.39-rc7+/build/vmlinux.OFF
[acme@emilia ~]$ perf report --stdio
[kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562
not found, continuing without symbols
Kernel address maps (/proc/{kallsyms,modules}) were restricted, check
/proc/sys/kernel/kptr_restrict before running 'perf record'.
As no suitable kallsyms nor vmlinux was found, kernel samples can't be
resolved.
Samples in kernel modules can't be resolved as well.
# Events: 13 cycles
#
# Overhead Command Shared Object Symbol
# ........ ....... ................. ......
#
80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a
19.69% sleep ld-2.12.so [.] memcpy
#
# (For a higher level overview, try: perf report --sort comm,dso)
#
[acme@emilia ~]$
Reported-by: Stephane Eranian <eranian@google.com>
Suggested-by: David Miller <davem@davemloft.net>
Cc: Dave Jones <davej@redhat.com>
Cc: David Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Kees Cook <kees.cook@canonical.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 20:53:51 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->no_buildid_cache || rec->no_buildid)
|
2010-06-17 17:39:01 +08:00
|
|
|
disable_buildid_cache();
|
2009-12-16 06:04:40 +08:00
|
|
|
|
2011-01-12 06:56:53 +08:00
|
|
|
if (evsel_list->nr_entries == 0 &&
|
|
|
|
perf_evlist__add_default(evsel_list) < 0) {
|
2011-01-04 02:39:04 +08:00
|
|
|
pr_err("Not enough memory for event selector list\n");
|
|
|
|
goto out_symbol_exit;
|
2009-06-12 05:11:50 +08:00
|
|
|
}
|
2009-05-26 15:17:18 +08:00
|
|
|
|
2012-01-20 00:08:15 +08:00
|
|
|
rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid,
|
|
|
|
rec->opts.target_pid);
|
|
|
|
if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1)
|
|
|
|
goto out_free_fd;
|
|
|
|
|
2012-02-09 00:32:52 +08:00
|
|
|
if (rec->opts.target_pid)
|
2011-11-25 18:19:45 +08:00
|
|
|
rec->opts.target_tid = rec->opts.target_pid;
|
2010-03-18 22:36:05 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
|
2012-01-20 00:08:15 +08:00
|
|
|
rec->opts.target_tid, rec->opts.uid,
|
|
|
|
rec->opts.cpu_list) < 0)
|
2011-01-13 00:28:51 +08:00
|
|
|
usage_with_options(record_usage, record_options);
|
2011-01-04 02:39:04 +08:00
|
|
|
|
2011-01-12 06:56:53 +08:00
|
|
|
list_for_each_entry(pos, &evsel_list->entries, node) {
|
2011-01-18 04:28:13 +08:00
|
|
|
if (perf_header__push_event(pos->attr.config, event_name(pos)))
|
|
|
|
goto out_free_fd;
|
2010-03-18 22:36:05 +08:00
|
|
|
}
|
2011-01-12 08:30:02 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->opts.user_interval != ULLONG_MAX)
|
|
|
|
rec->opts.default_interval = rec->opts.user_interval;
|
|
|
|
if (rec->opts.user_freq != UINT_MAX)
|
|
|
|
rec->opts.freq = rec->opts.user_freq;
|
2010-04-15 04:09:02 +08:00
|
|
|
|
2009-10-12 13:56:03 +08:00
|
|
|
/*
|
|
|
|
* User specified count overrides default frequency.
|
|
|
|
*/
|
2011-11-25 18:19:45 +08:00
|
|
|
if (rec->opts.default_interval)
|
|
|
|
rec->opts.freq = 0;
|
|
|
|
else if (rec->opts.freq) {
|
|
|
|
rec->opts.default_interval = rec->opts.freq;
|
2009-10-12 13:56:03 +08:00
|
|
|
} else {
|
|
|
|
fprintf(stderr, "frequency and count are zero, aborting\n");
|
2010-07-30 01:08:55 +08:00
|
|
|
err = -EINVAL;
|
2011-01-12 08:30:02 +08:00
|
|
|
goto out_free_fd;
|
2009-10-12 13:56:03 +08:00
|
|
|
}
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
err = __cmd_record(&record, argc, argv);
|
2010-07-30 01:08:55 +08:00
|
|
|
out_free_fd:
|
2011-01-30 21:59:43 +08:00
|
|
|
perf_evlist__delete_maps(evsel_list);
|
2010-07-31 05:31:28 +08:00
|
|
|
out_symbol_exit:
|
|
|
|
symbol__exit();
|
2010-07-30 01:08:55 +08:00
|
|
|
return err;
|
2009-05-26 15:17:18 +08:00
|
|
|
}
|