OpenCloudOS-Kernel/tools/perf/builtin-record.c

834 lines
23 KiB
C
Raw Normal View History

/*
* 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.
*/
#define _FILE_OFFSET_BITS 64
#include "builtin.h"
#include "perf.h"
#include "util/build-id.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/header.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
#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"
#include "util/thread_map.h"
#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
};
struct perf_record {
struct perf_tool tool;
struct perf_record_opts opts;
u64 bytes_written;
const char *output_name;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
const char *uid_str;
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;
};
static void advance_output(struct perf_record *rec, size_t size)
{
rec->bytes_written += size;
}
static void write_output(struct perf_record *rec, void *buf, size_t size)
{
while (size) {
int ret = write(rec->output, buf, size);
if (ret < 0)
die("failed to write");
size -= ret;
buf += ret;
rec->bytes_written += ret;
}
}
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __used,
struct machine *machine __used)
{
struct perf_record *rec = container_of(tool, struct perf_record, tool);
write_output(rec, event, event->header.size);
return 0;
}
static void perf_record__mmap_read(struct perf_record *rec,
struct perf_mmap *md)
{
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + rec->page_size;
unsigned long size;
void *buf;
if (old == head)
return;
rec->samples++;
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;
write_output(rec, buf, size);
}
buf = &data[old & md->mask];
size = head - old;
old += size;
write_output(rec, buf, size);
md->prev = old;
perf_mmap__write_tail(md, old);
}
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
child_finished = 1;
done = 1;
signr = sig;
}
static void perf_record__sig_exit(int exit_status __used, void *arg)
{
struct perf_record *rec = arg;
int status;
if (rec->evlist->workload.pid > 0) {
if (!child_finished)
kill(rec->evlist->workload.pid, SIGTERM);
wait(&status);
if (WIFSIGNALED(status))
psignal(WTERMSIG(status), rec->progname);
}
if (signr == -1 || signr == SIGUSR1)
return;
signal(signr, SIG_DFL);
kill(getpid(), signr);
}
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;
}
static void perf_record__open(struct perf_record *rec)
{
struct perf_evsel *pos, *first;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
struct perf_record_opts *opts = &rec->opts;
first = list_entry(evlist->entries.next, struct perf_evsel, node);
perf_evlist__config_attrs(evlist, opts);
list_for_each_entry(pos, &evlist->entries, node) {
struct perf_event_attr *attr = &pos->attr;
struct xyarray *group_fd = NULL;
/*
* 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;
if (opts->group && pos != first)
group_fd = first->fd;
fallback_missing_features:
if (opts->exclude_guest_missing)
attr->exclude_guest = attr->exclude_host = 0;
retry_sample_id:
attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
try_again:
if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
opts->group, group_fd) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
ui__error_paranoid();
exit(EXIT_FAILURE);
} else if (err == ENODEV && opts->cpu_list) {
die("No such device - did you specify"
" an out-of-range profile CPU?\n");
} 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;
} else if (!opts->sample_id_all_missing) {
/*
* Old kernel, no attr->sample_id_type_all field
*/
opts->sample_id_all_missing = true;
if (!opts->sample_time && !opts->raw_samples && !time_needed)
attr->sample_type &= ~PERF_SAMPLE_TIME;
goto retry_sample_id;
}
}
/*
* 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)
ui__warning("The cycles event is not supported, "
"trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
if (err == ENOENT) {
ui__warning("The %s event is not supported.\n",
event_name(pos));
exit(EXIT_FAILURE);
}
printf("\n");
error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n",
err, strerror(err));
#if defined(__i386__) || defined(__x86_64__)
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");
#endif
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
}
}
if (perf_evlist__set_filters(evlist)) {
error("failed to set filter with %d (%s)\n", errno,
strerror(errno));
exit(-1);
}
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);
else if (!is_power_of_2(opts->mmap_pages))
die("--mmap_pages/-m value must be a power of two.");
die("failed to mmap with %d (%s)\n", errno, strerror(errno));
}
if (rec->file_new)
session->evlist = evlist;
else {
if (!perf_evlist__equal(session->evlist, evlist)) {
fprintf(stderr, "incompatible append\n");
exit(-1);
}
}
perf_session__update_sample_type(session);
}
static int process_buildids(struct perf_record *rec)
{
u64 size = lseek(rec->output, 0, SEEK_CUR);
if (size == 0)
return 0;
rec->session->fd = rec->output;
return __perf_session__process_events(rec->session, rec->post_processing_offset,
size - rec->post_processing_offset,
size, &build_id__mark_dso_hit_ops);
}
static void perf_record__exit(int status __used, void *arg)
{
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);
symbol__exit();
}
}
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
int err;
struct perf_tool *tool = data;
if (machine__is_host(machine))
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.
*/
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
/*
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
* have no _text sometimes.
*/
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_text");
if (err < 0)
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_stext");
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
}
static struct perf_event_header finished_round_event = {
.size = sizeof(struct perf_event_header),
.type = PERF_RECORD_FINISHED_ROUND,
};
static void perf_record__mmap_read_all(struct perf_record *rec)
{
int i;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
if (rec->evlist->mmap[i].base)
perf_record__mmap_read(rec, &rec->evlist->mmap[i]);
}
if (perf_header__has_feat(&rec->session->header, HEADER_TRACE_INFO))
write_output(rec, &finished_round_event, sizeof(finished_round_event));
}
static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
{
struct stat st;
int flags;
int err, output, feat;
unsigned long waking = 0;
const bool forks = argc > 0;
struct machine *machine;
struct perf_tool *tool = &rec->tool;
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;
rec->progname = argv[0];
rec->page_size = sysconf(_SC_PAGE_SIZE);
on_exit(perf_record__sig_exit, rec);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
if (!output_name) {
if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
opts->pipe_output = true;
else
rec->output_name = output_name = "perf.data";
}
if (output_name) {
if (!strcmp(output_name, "-"))
opts->pipe_output = true;
else if (!stat(output_name, &st) && st.st_size) {
if (rec->write_mode == WRITE_FORCE) {
char oldname[PATH_MAX];
snprintf(oldname, sizeof(oldname), "%s.old",
output_name);
unlink(oldname);
rename(output_name, oldname);
}
} else if (rec->write_mode == WRITE_APPEND) {
rec->write_mode = WRITE_FORCE;
}
}
flags = O_CREAT|O_RDWR;
if (rec->write_mode == WRITE_APPEND)
rec->file_new = 0;
else
flags |= O_TRUNC;
if (opts->pipe_output)
output = STDOUT_FILENO;
else
output = open(output_name, flags, S_IRUSR | S_IWUSR);
if (output < 0) {
perror("failed to create output file");
exit(-1);
}
rec->output = output;
session = perf_session__new(output_name, O_WRONLY,
rec->write_mode == WRITE_FORCE, false, NULL);
if (session == NULL) {
pr_err("Not enough memory for reading perf file header\n");
return -1;
}
rec->session = session;
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);
if (!rec->file_new) {
err = perf_session__read_header(session, output);
if (err < 0)
goto out_delete_session;
}
if (forks) {
err = perf_evlist__prepare_workload(evsel_list, opts, argv);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
goto out_delete_session;
}
}
perf_record__open(rec);
/*
* perf_session__delete(session) will be called at perf_record__exit()
*/
on_exit(perf_record__exit, rec);
if (opts->pipe_output) {
err = perf_header__write_pipe(output);
if (err < 0)
return err;
} else if (rec->file_new) {
err = perf_session__write_header(session, evsel_list,
output, false);
if (err < 0)
return err;
perf tools: Handle relocatable kernels DSOs don't have this problem because the kernel emits a PERF_MMAP for each new executable mapping it performs on monitored threads. To fix the kernel case we simulate the same behaviour, by having 'perf record' to synthesize a PERF_MMAP for the kernel, encoded like this: [root@doppio ~]# perf record -a -f sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.344 MB perf.data (~15038 samples) ] [root@doppio ~]# perf report -D | head -10 0xd0 [0x40]: event: 1 . . ... raw event: size 64 bytes . 0000: 01 00 00 00 00 00 40 00 00 00 00 00 00 00 00 00 ......@........ . 0010: 00 00 00 81 ff ff ff ff 00 00 00 00 00 00 00 00 ............... . 0020: 00 00 00 00 00 00 00 00 5b 6b 65 72 6e 65 6c 2e ........ [kernel . 0030: 6b 61 6c 6c 73 79 6d 73 2e 5f 74 65 78 74 5d 00 kallsyms._text] . 0xd0 [0x40]: PERF_RECORD_MMAP 0/0: [0xffffffff81000000((nil)) @ (nil)]: [kernel.kallsyms._text] I.e. we identify such event as having: .pid = 0 .filename = [kernel.kallsyms.REFNAME] .start = REFNAME addr in /proc/kallsyms at 'perf record' time and use now a hardcoded value of '.text' for REFNAME. Then, later, in 'perf report', if there are any kernel hits and thus we need to resolve kernel symbols, we search for REFNAME and if its address changed, relocation happened and we thus must change the kernel mapping routines to one that uses .pgoff as the relocation to apply. This way we use the same mechanism used for the other DSOs and don't have to do a two pass in all the kernel symbols. Reported-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> LKML-Reference: <1262717431-1246-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 02:50:31 +08:00
}
if (!rec->no_buildid
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
pr_err("Couldn't generate buildids. "
"Use --no-buildid to profile anyway.\n");
return -1;
}
rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
machine = perf_session__find_host_machine(session);
if (!machine) {
pr_err("Couldn't find native kernel information.\n");
return -1;
}
if (opts->pipe_output) {
err = perf_event__synthesize_attrs(tool, session,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
return err;
}
err = perf_event__synthesize_event_types(tool, process_synthesized_event,
machine);
if (err < 0) {
pr_err("Couldn't synthesize event_types.\n");
return err;
}
if (have_tracepoints(&evsel_list->entries)) {
/*
* 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()
*/
err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
return err;
}
advance_output(rec, err);
}
}
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_text");
if (err < 0)
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_stext");
perf record: Handle restrictive permissions in /proc/{kallsyms,modules} The 59365d1 commit, even being reverted by 33e0d57, showed a non robust behavior in 'perf record': it really should just warn the user that some functionality will not be available. The new behavior then becomes: [acme@felicio linux]$ ls -la /proc/{kallsyms,modules} -r-------- 1 root root 0 Nov 22 12:19 /proc/kallsyms -r-------- 1 root root 0 Nov 22 12:19 /proc/modules [acme@felicio linux]$ perf record ls -R > /dev/null Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.004 MB perf.data (~161 samples) ] [acme@felicio linux]$ perf report --stdio [kernel.kallsyms] with build id 77b05e00e64e4de1c9347d83879779b540d69f00 not found, continuing without symbols # Events: 98 cycles # # Overhead Command Shared Object Symbol # ........ ....... ............... .................... # 48.26% ls [kernel] [k] ffffffff8102b92b 22.49% ls libc-2.12.90.so [.] __strlen_sse2 8.35% ls libc-2.12.90.so [.] __GI___strcoll_l 8.17% ls ls [.] 11580 3.35% ls libc-2.12.90.so [.] _IO_new_file_xsputn 3.33% ls libc-2.12.90.so [.] _int_malloc 1.88% ls libc-2.12.90.so [.] _int_free 0.84% ls libc-2.12.90.so [.] malloc_consolidate 0.84% ls libc-2.12.90.so [.] __readdir64 0.83% ls ls [.] strlen@plt 0.83% ls libc-2.12.90.so [.] __GI_fwrite_unlocked 0.83% ls libc-2.12.90.so [.] __memcpy_sse2 # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@felicio linux]$ It still has the build-ids for DSOs in the maps with hits: [acme@felicio linux]$ perf buildid-list 77b05e00e64e4de1c9347d83879779b540d69f00 [kernel.kallsyms] 09c4a431a4a8b648fcfc2c2bdda70f56050ddff1 /bin/ls af75ea9ad951d25e0f038901a11b3846dccb29a4 /lib64/libc-2.12.90.so [acme@felicio linux]$ That can be used in another machine to resolve kernel symbols. Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jesper Juhl <jj@chaosbits.net> Cc: Marcus Meissner <meissner@suse.de> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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");
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
perf record: Handle restrictive permissions in /proc/{kallsyms,modules} The 59365d1 commit, even being reverted by 33e0d57, showed a non robust behavior in 'perf record': it really should just warn the user that some functionality will not be available. The new behavior then becomes: [acme@felicio linux]$ ls -la /proc/{kallsyms,modules} -r-------- 1 root root 0 Nov 22 12:19 /proc/kallsyms -r-------- 1 root root 0 Nov 22 12:19 /proc/modules [acme@felicio linux]$ perf record ls -R > /dev/null Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.004 MB perf.data (~161 samples) ] [acme@felicio linux]$ perf report --stdio [kernel.kallsyms] with build id 77b05e00e64e4de1c9347d83879779b540d69f00 not found, continuing without symbols # Events: 98 cycles # # Overhead Command Shared Object Symbol # ........ ....... ............... .................... # 48.26% ls [kernel] [k] ffffffff8102b92b 22.49% ls libc-2.12.90.so [.] __strlen_sse2 8.35% ls libc-2.12.90.so [.] __GI___strcoll_l 8.17% ls ls [.] 11580 3.35% ls libc-2.12.90.so [.] _IO_new_file_xsputn 3.33% ls libc-2.12.90.so [.] _int_malloc 1.88% ls libc-2.12.90.so [.] _int_free 0.84% ls libc-2.12.90.so [.] malloc_consolidate 0.84% ls libc-2.12.90.so [.] __readdir64 0.83% ls ls [.] strlen@plt 0.83% ls libc-2.12.90.so [.] __GI_fwrite_unlocked 0.83% ls libc-2.12.90.so [.] __memcpy_sse2 # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@felicio linux]$ It still has the build-ids for DSOs in the maps with hits: [acme@felicio linux]$ perf buildid-list 77b05e00e64e4de1c9347d83879779b540d69f00 [kernel.kallsyms] 09c4a431a4a8b648fcfc2c2bdda70f56050ddff1 /bin/ls af75ea9ad951d25e0f038901a11b3846dccb29a4 /lib64/libc-2.12.90.so [acme@felicio linux]$ That can be used in another machine to resolve kernel symbols. Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jesper Juhl <jj@chaosbits.net> Cc: Marcus Meissner <meissner@suse.de> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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");
if (perf_guest)
perf_session__process_machines(session, tool,
perf_event__synthesize_guest_os);
if (!opts->system_wide)
perf_event__synthesize_thread_map(tool, evsel_list->threads,
process_synthesized_event,
machine);
else
perf_event__synthesize_threads(tool, process_synthesized_event,
machine);
if (rec->realtime_prio) {
struct sched_param param;
param.sched_priority = rec->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, &param)) {
pr_err("Could not set realtime priority.\n");
exit(-1);
}
}
perf_evlist__enable(evsel_list);
/*
* Let the child rip
*/
if (forks)
perf_evlist__start_workload(evsel_list);
for (;;) {
int hits = rec->samples;
perf_record__mmap_read_all(rec);
if (hits == rec->samples) {
if (done)
break;
err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
waking++;
}
if (done)
perf_evlist__disable(evsel_list);
}
if (quiet || signr == SIGUSR1)
return 0;
fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
/*
* Approximate RIP event size: 24 bytes.
*/
fprintf(stderr,
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
(double)rec->bytes_written / 1024.0 / 1024.0,
output_name,
rec->bytes_written / 24);
return 0;
out_delete_session:
perf_session__delete(session);
return err;
}
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
NULL
};
/*
* 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,
};
/*
* 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.
*/
const struct option record_options[] = {
OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK(0, "filter", &record.evlist, "filter",
"event filter", parse_filter),
OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
"record events on existing process id"),
OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
"record events on existing thread id"),
OPT_INTEGER('r', "realtime", &record.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
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"),
OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
"collect raw sample records from all opened counters"),
OPT_BOOLEAN('a', "all-cpus", &record.opts.system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('A', "append", &record.append_file,
"append to the output file to do incremental profiling"),
OPT_STRING('C', "cpu", &record.opts.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_BOOLEAN('f', "force", &record.force,
"overwrite existing data file (deprecated)"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
OPT_STRING('o', "output", &record.output_name, "file",
"output file name"),
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages,
"number of mmap data pages"),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_BOOLEAN('g', "call-graph", &record.opts.call_graph,
"do call-graph (stack chain/backtrace) recording"),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
OPT_BOOLEAN('d', "data", &record.opts.sample_address,
"Sample addresses"),
OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
"don't sample"),
OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
"do not update the buildid cache"),
OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
"do not collect buildids in perf.data"),
OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
"monitor event in cgroup name only",
parse_cgroups),
OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
OPT_END()
};
int cmd_record(int argc, const char **argv, const char *prefix __used)
{
int err = -ENOMEM;
struct perf_evsel *pos;
struct perf_evlist *evsel_list;
struct perf_record *rec = &record;
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);
evsel_list = perf_evlist__new(NULL, NULL);
if (evsel_list == NULL)
return -ENOMEM;
rec->evlist = evsel_list;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
!rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
usage_with_options(record_usage, record_options);
if (rec->force && rec->append_file) {
fprintf(stderr, "Can't overwrite and append at the same time."
" You need to choose between -f and -A");
usage_with_options(record_usage, record_options);
} else if (rec->append_file) {
rec->write_mode = WRITE_APPEND;
} else {
rec->write_mode = WRITE_FORCE;
}
if (nr_cgroups && !rec->opts.system_wide) {
fprintf(stderr, "cgroup monitoring only available in"
" system-wide mode\n");
usage_with_options(record_usage, record_options);
}
symbol__init();
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)
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
if (rec->no_buildid_cache || rec->no_buildid)
disable_buildid_cache();
if (evsel_list->nr_entries == 0 &&
perf_evlist__add_default(evsel_list) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out_symbol_exit;
}
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;
if (rec->opts.target_pid)
rec->opts.target_tid = rec->opts.target_pid;
if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
rec->opts.target_tid, rec->opts.uid,
rec->opts.cpu_list) < 0)
usage_with_options(record_usage, record_options);
list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_header__push_event(pos->attr.config, event_name(pos)))
goto out_free_fd;
}
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;
/*
* User specified count overrides default frequency.
*/
if (rec->opts.default_interval)
rec->opts.freq = 0;
else if (rec->opts.freq) {
rec->opts.default_interval = rec->opts.freq;
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
err = -EINVAL;
goto out_free_fd;
}
err = __cmd_record(&record, argc, argv);
out_free_fd:
perf_evlist__delete_maps(evsel_list);
out_symbol_exit:
symbol__exit();
return err;
}